Change search
Refine search result
12345 1 - 50 of 242
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Mahmud, Tanjim
    et al.
    Department of Computer Science and Engineering, Rangamati Science and Technology University, Rangamati, 4500, Bangladesh.
    Barua, Koushick
    Department of Computer Science and Engineering, Rangamati Science and Technology University, Rangamati, 4500, Bangladesh.
    Habiba, Sultana Umme
    Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh.
    Sharmen, Nahed
    Department of Obstetrics and Gynecology, Chattogram Maa-O-Shishu Hospital Medical College, Chittagong, 4100, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong 4331, Bangladesh.
    Andersson, Karl
    Pervasive and Mobile Computing Laboratory, Luleå University of Technology, Luleå, 97187, Sweden.
    An Explainable AI Paradigm for Alzheimer’s Diagnosis Using Deep Transfer Learning2024In: Diagnostics, ISSN 2075-4418, Vol. 14, no 3, article id 345Article in journal (Refereed)
    Abstract [en]

    Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of individuals worldwide, causing severe cognitive decline and memory impairment. The early and accurate diagnosis of AD is crucial for effective intervention and disease management. In recent years, deep learning techniques have shown promising results in medical image analysis, including AD diagnosis from neuroimaging data. However, the lack of interpretability in deep learning models hinders their adoption in clinical settings, where explainability is essential for gaining trust and acceptance from healthcare professionals. In this study, we propose an explainable AI (XAI)-based approach for the diagnosis of Alzheimer’s disease, leveraging the power of deep transfer learning and ensemble modeling. The proposed framework aims to enhance the interpretability of deep learning models by incorporating XAI techniques, allowing clinicians to understand the decision-making process and providing valuable insights into disease diagnosis. By leveraging popular pre-trained convolutional neural networks (CNNs) such as VGG16, VGG19, DenseNet169, and DenseNet201, we conducted extensive experiments to evaluate their individual performances on a comprehensive dataset. The proposed ensembles, Ensemble-1 (VGG16 and VGG19) and Ensemble-2 (DenseNet169 and DenseNet201), demonstrated superior accuracy, precision, recall, and F1 scores compared to individual models, reaching up to 95%. In order to enhance interpretability and transparency in Alzheimer’s diagnosis, we introduced a novel model achieving an impressive accuracy of 96%. This model incorporates explainable AI techniques, including saliency maps and grad-CAM (gradient-weighted class activation mapping). The integration of these techniques not only contributes to the model’s exceptional accuracy but also provides clinicians and researchers with visual insights into the neural regions influencing the diagnosis. Our findings showcase the potential of combining deep transfer learning with explainable AI in the realm of Alzheimer’s disease diagnosis, paving the way for more interpretable and clinically relevant AI models in healthcare.

    Download full text (pdf)
    fulltext
  • 2.
    Hossain, Mohammad Shahadat
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Ahmed, Mumtahina
    Port City International University, Dhaka, Bangladesh.
    Raihan, S. M. Shafkat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Sharma, Angel
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Belief Rule Based Expert System to Diagnose Schizophrenia Using Whole Blood DNA Methylation Data2023In: Machine Intelligence and Emerging Technologies - First International Conference, MIET 2022, Proceedings, part 2 / [ed] Md. Shahriare Satu; Mohammad Ali Moni; M. Shamim Kaiser; Mohammad Shamsul Arefin; Mohammad Shamsul Arefin, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 271-282Conference paper (Refereed)
    Abstract [en]

    Schizophrenia is a severe neurological disease where a patient’s perceptions of reality are disrupted. Its symptoms include hallucinations, delusions, and profoundly strange thinking and behavior, which make the patient’s daily functions difficult. Despite identifying genetic variations linked to Schizophrenia, causative genes involved in pathogenesis and expression regulations remain unknown. There is no particular way in life sciences for diagnosing Schizophrenia. Commonly used machine learning and deep learning are data-oriented. They lack the ability to deal with uncertainty in data. Belief Rule Based Expert System (BRBES) methodology addresses various categories of uncertainty in data with evidential reasoning. Previous researches showed the association of DNA methylation (DNAm) with risk of Schizophrenia. Whole blood DNAm data, hence, is useful for smart diagnosis of Scizophrenia. However, to our knowledge, no previous studies have investigated the performance of BRBES to diagnose Schizophrenia. Therefore, in this study, we explore BRBES’ performance in diagnosing Schizophrenia using whole blood DNAm data. BRBES was optimized by gradient-free algorithms due to the limitations of gradient-based optimization. Classification thresholds were optimized to yield better results. Finally, we compared performance to two machine learning models after 5-fold cross-validation where our model achieved the highest average sensitivity (76.8%) among the three.

  • 3.
    Banna, Md. Hasan Al
    et al.
    Department of Computer Science and Engineering, Bangladesh University of Professionals, Dhaka 1216, Bangladesh.
    Ghosh, Tapotosh
    Department of Computer Science and Engineering, United International University, Dhaka 1209, Bangladesh.
    Nahian, Md. Jaber AL
    Department of Information and Communication Technology, Bangladesh University of Professionals, Dhaka 1212, Bangladesh.
    Kaiser, M. Shamim
    Institute of Information Technology, Jahangirnagar University, Savar, Dhaka 1342, Bangladesh.
    Mahmud, Mufti
    Department of Computer Science and Medical Technology Innovation Facility, Nottingham Trent University, Clifton, NG11 8NS Nottingham, U.K..
    Taher, Kazi Abu
    Department of Information and Communication Technology, Bangladesh University of Professionals, Dhaka 1212, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Hybrid Deep Learning Model to Predict the Impact of COVID-19 on Mental Health from Social Media Big Data2023In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 77009-77022Article in journal (Refereed)
    Abstract [en]

    The novel coronavirus disease (COVID-19) pandemic is provoking a prevalent consequence on mental health because of less interaction among people, economic collapse, negativity, fear of losing jobs, and death of the near and dear ones. To express their mental state, people often are using social media as one of the preferred means. Due to reduced outdoor activities, people are spending more time on social media than usual and expressing their emotion of anxiety, fear, and depression. On a daily basis, about 2.5 quintillion bytes of data are generated on social media. Analyzing this big data can become an excellent means to evaluate the effect of COVID-19 on mental health. In this work, we have analyzed data from Twitter microblog (tweets) to find out the effect of COVID-19 on people’s mental health with a special focus on depression. We propose a novel pipeline, based on recurrent neural network (in the form of long short-term memory or LSTM) and convolutional neural network, capable of identifying depressive tweets with an accuracy of 99.42%. Preprocessed using various natural language processing techniques, the aim was to find out depressive emotion from these tweets. Analyzing over 571 thousand tweets posted between October 2019 and May 2020 by 482 users, a significant rise in depressing tweets was observed between February and May of 2020, which indicates as an impact of the long ongoing COVID-19 pandemic situation.

    Download full text (pdf)
    fulltext
  • 4.
    Nahar, Lutfun
    et al.
    International Islamic University, Chittagong, Bangladesh.
    Basnin, Nanziba
    International Islamic University, Chittagong, Bangladesh.
    Hoque, Sirazum Nadia
    International Islamic University, Chittagong, Bangladesh.
    Tasnim, Farzana
    International Islamic University, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Hybrid Deep Learning System to Detect Face-Mask and Monitor Social Distance2023In: Applied Intelligence and Informatics: Second International Conference, AII 2022, Reggio Calabria, Italy, September 1–3, 2022, Proceedings, Springer Nature, 2023, p. 308-319Conference paper (Refereed)
  • 5.
    Tarek, Iftakher Hasan Mohammad
    et al.
    International Islamic University Chittagong, Chittagong, 4318, Bangladesh.
    Munna, Fahad Uddin
    International Islamic University Chittagong, Chittagong, 4318, Bangladesh.
    Mojumder, A. T. M. Tanbin Hossain
    International Islamic University Chittagong, Chittagong, 4318, Bangladesh.
    Rahman, Mohammed Mahmudur
    International Islamic University Chittagong, Chittagong, 4318, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Hybrid Hotel Recommendation Using Collaborative, Content Based and Knowledge Based Approach2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 1049-1057Chapter in book (Refereed)
    Abstract [en]

    Everybody plans vacations, and the first step in that process is to book a hotel. With the hospitality sector being so competitive, it’s critical to maintain best practices and stay on top of client demands and wants. They want individualized experiences, one-of-a-kind amenities, and a general sense of well-being on all levels. A consumer of a hotel recommendation system frequently encounters challenges in obtaining and fulfilling his or her wishes. Content-based filtering and collaborative filtering are two well-known strategies for creating a recommender system. Content-based filtering does not use human opinions to produce predictions, whereas collaborative filtering does, resulting in more accurate predictions. Collaborative filtering, on the other hand, cannot forecast objects that have never been rated by anyone. Both approaches can be merged with a hybrid methodology to cover the disadvantages of each approach while gaining the benefits of the other. This research employed Item-Item collaborative filtering (CF) and content-based filtering (CB) to calculate hotel similarity in our suggested method. It uses cosine similarity to calculate user similarity. For content-based filtering, natural language processing (NLP) is also employed. Our model employs a knowledge-based approach for Cold-User scenarios. Precision, recall and f1 used to evaluate the recommendation system.

  • 6.
    Karim, Sara
    et al.
    Department of Computer Science and Engineering, International Islamic University Chittagong, Chittagong, Bangladesh.
    Patwary, Muhammed J. A.
    Department of Computer Science and Engineering, International Islamic University Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Novel Fuzzy Semi-supervised Learning Approach for the Classification of Colorectal Cancer (FSSL-CRCC)2023In: Applied Intelligence and Informatics: Second International Conference, AII 2022, Reggio Calabria, Italy, September 1–3, 2022, Proceedings, Springer Nature, 2023, p. 174-185Conference paper (Refereed)
  • 7.
    Nath, Tanuja
    et al.
    University of Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Transfer Learning Approach to Detect Face Mask in COVID-19 Pandemic2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 948-957Chapter in book (Refereed)
    Abstract [en]

    COVID-19 is tumultuous creating our life so unpredictable. There has no solution of this contagious disease rather than vaccination and prevention. The first and foremost preventative step is using face masks. Face mask can hindrance its droplet from one to another. So this paper has focused the detection of facial mask from image processing using Transfer Learning. For this purpose, total 1376 images have been collected where 690 images of with mask and 686 images of without a mask. Here transfer learning is chosen for the reason of its capability to produce best accurate regardless the limited size of the image dataset. Here, multifarious transfer learning models have been trained to find out the best fitting model. Finally, We have found the VGG16 model with the best accuracy where training accuracy is 98.25% and testing accuracy is 96.38%.

  • 8.
    Monrat, Ahmed Afif
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Schelén, Olov
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Addressing the Performance of Blockchain by Discussing Sharding Techniques2023In: Proceedings of 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), IEEE, 2023Conference paper (Refereed)
    Abstract [en]

    Blockchain technology is extensively used for cryptocurrencies and is considered for industrial applications due to features like decentralization, anonymity, and a tamper-proof history of transactions. However, the well-known blockchain trilemma of being unable to simultaneously meet the properties of decentralization, security, and scalability (DSS) negatively impacts widespread acceptance. Numerous solutions have been put forward in response to this challenge, aiming to increase performance and scalability while retaining the decentralized and trustless aspects. They range from introducing off-chain technologies to changing consensus algorithms and on-chain data structures. One of the most effective methods to accomplish horizontal scalability along with the growing network size could be sharding, which involves dividing the network of nodes into numerous shards or channels. The overhead of repetitive communication, storage, and processing at each node is decreased by this technique. This paper explores various sharding approaches to solve performance issues regarding blockchain. We review recent sharding technologies, including Polkadot, Ethereum Casper, and Cardano Hydra. We discuss the performance challenges of blockchains and provide essential insights into the tradeoffs.

  • 9.
    Sultana, Zinnia
    et al.
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Nahar, Lutfun
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Tasnim, Farzana
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An Encoding and Decoding Technique to Compress Huffman Tree Size in an Efficient Manner2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 863-873Chapter in book (Refereed)
    Abstract [en]

    Now a days transfer of gigantic amount of information in an accurate format is a big problem. Storage is needed to store all this information is limited to be calculated before sending data over the internet. The intercommunication path which is also determinate with limited and restricted communication lines. This restriction driven to necessity of data compression. To compress data effectively a most widely popular used compression technique is Huffman. By minimizing the memory space for Huffman tree it will be more feasible. Our paper focused on minimizing the size of Huffman tree for encoding and decoding and also proposed an efficient method for storing Huffman tree. For this purpose we also design an encoding algorithm as well as a decoding algorithm.This method works more efficiently among all present techniques in where total memory needs to represent the tree structure for Huffman tree are 10.75n−3 bits for worst case and in best case it is 9n bits.

  • 10.
    Sultana, Zinnia
    et al.
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Nahar, Lutfun
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Sultana, Sharmin
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Tasnim, Farzana
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An IoT Prototype for Monitoring Covid19 Patients Using Real Time Data from Wearable Sensor Through Android App2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 330-340Chapter in book (Refereed)
    Abstract [en]

    In the age of modern technology peoples are still facing a great challenges to manage and monitor the infected patients of COVID-19. Many systems have been implemented to track the location of infected person to reduce the spread of diseases. In today’s world IoT with the health care system plays an important role specially in this COVID situation. In this research an IoT based monitoring system is designed to monitor and measure different signs of COVID-19 using wearable device. It also sends notification to the proper authority by monitoring the activity of infected patient. To determine the condition of patient, sensor data are analyzed which is passed from edge node, as body sensor are connected to IoT cloud via edge node. Three layered architecture is implemented in our proposed design, wearable sensor layer, Peripheral Interface (API) layer and Android web layer. Different layer have different work, at first health symptom is determined by analyzing data from IoT sensor layer. In next layer information is stored in the cloud database to take immediate actions. Finally android application layer is used to send notifications and alerts for the infected patient. To predict the health condition and alarming the situation both API and mobile application communicate with each other. The designed system has simple structure and helps the authority to find the infected person.

  • 11.
    Monrat, Ahmed Afif
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Schelén, Olov
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Applicability Analysis of Blockchain Technology2023In: 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), IEEE, 2023Conference paper (Refereed)
    Abstract [en]

    Blockchain technology has been generating great interest by a variety of industry sectors. Realizing the strength of blockchain technology beyond its successful application in the cryptocurrency arena, researchers have been evaluating and using blockchain for applications such as supply chain management, the energy industry, health sectors, and much more. Some of the features include smart contracts, decentralization, consensus, immutable distributed ledgers, cryptographic hashing, and digital signatures. There are multiple types of blockchain and different consensus models. However, it is often a significant undertaking to determine if an application requires a blockchain. What kind of blockchain and consensus model is best suited for a given scenario? This paper addresses this challenge by evaluating different blockchain solutions along with the consensus models to determine the applicability for different use cases. We propose a guideline and applicability analysis framework (AAF) to determine whether an application needs a blockchain solution or not. The AAF is divided into 6 domains, 11 subdomains, and 45 controls. It is designed to ingest detailed user requirements to perform a weighted evaluation that is built on mathematical constructs to determine the scenario in which a blockchain-based solution is appropriate. Moreover, this article also includes an example of evaluating applicability through AAF with the help of a use-case scenario.

  • 12.
    Mahamud, Faisal
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Neloy, Md. Arif Istiak
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Barua, Parthiba
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Das, Mithun
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hoassain, Md. Sazzad
    University of Liberal Arts Bangladesh, Dhaka, 1209, Bangladesh.
    Bell Pepper Leaf Disease Classification Using Convolutional Neural Network2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 75-86Chapter in book (Refereed)
    Abstract [en]

    In today’s agriculture, leaf disease is a major issue. It hinders the natural growth of plants. Stifles a country’s economic development. It will lower the quality of agricultural products. Leaf disease can develop as a result of bacterial, fungal, or other causes. Finding and detecting sick plants in the open eye takes a long time. As a result, automatically detecting and resolving plant disease is critical. Pepper Bacterial spot disease is generally caused by Xanthomonas campestris which reduces pepper production and quality. In this paper, we used the plant village dataset. The dataset contains 2080 image data of bacterial spotted pepper bell leaf and 1,881 healthy bell pepper leaf. We will study pepper belt bacterial spot disease. Using Conventional Neural Network(CNN), our suggested method will detect bell pepper bacterial spot plant disease. We’ll classify each plant image and look for illnesses. Our proposed CNN system has an accuracy rate of testing is 96.88% the accuracy rate of training and validation is 99.44% and 97.34% respectively.

  • 13.
    Habiba, Sultana Umme
    et al.
    Green University of Bangladesh, Dhaka, Bangladesh; Khulna University of Engineering and Technology, Khulna, Bangladesh.
    Islam, Md. Khairul
    Khulna University of Engineering and Technology, Khulna, Bangladesh.
    Nahar, Lutfun
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Tasnim, Farzana
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Brain-DeepNet: A Deep Learning Based Classifier for Brain Tumor Detection and Classification2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 550-560Chapter in book (Refereed)
    Abstract [en]

    Brain tumor is one of the most hazardous disease that leads a man to gradual death. To ensure proper and effective treatment, this is very important to detect the brain tumor and predict this as cancerous or non-cancerous. Radiologists have shown interest to detect brain tumor and its category analyzing the MRI (Magnetic Resonance Image) of brain. This detection and classification task seems to be challenging because of different size, location and behavior of brain tumors. Deep learning based classifiers extract features from MRI and helps to diagnose brain tumor with the help of computer aided diagnosis system. In this paper, we have experimented this classification task on a publicly available dataset using transfer learning approach in InceptionV3 and DenseNet201 model. Data augmentation technique is performed to enrich the dataset for achieving a good classification result an to avoid over fitting.“Brain-DeepNet” a deep convolutional neural network has been proposed where six convolution layers are densely connected and extract features from dense layers. These dense layers extract features and all features are passed to a fully connected layer. Dense network extract features more efficiently from brain MRI. This work is experimented on MRI as MRI provides more details of cell structure and functions. Our proposed model has shown approximately 96.3% classification accuracy to differentiate among the three types of brain tumors most commonly encountered Glioma, meningioma, and pituitary. This model outperforms the classification performance in comparison with the pretrained models.

  • 14.
    Sumi, Tahmina Akter
    et al.
    University of Chittagong, Chittagong, Bangladesh.
    Basnin, Nanziba
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Hossain, Md. Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hoassain, Md. Sazzad
    University of Liberal Arts Bangladesh, Dhaka, 1209, Bangladesh.
    Classifying Humerus Fracture Using X-Ray Images2023In: The Fourth Industrial Revolution and Beyond - Select Proceedings of IC4IR+ / [ed] Md. Sazzad Hossain; Satya Prasad Majumder; Nazmul Siddique; Md. Shahadat Hossain, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 527-538Conference paper (Refereed)
    Abstract [en]

    Bone is the most important part of our body which holds the whole structure of human body. The long bone situated in the upper arm of human body between the shoulder and elbow junction is known as “Humerus”. Humerus works as a structural support of the muscles and arms in the upper body which helps in the movement of the hand and elbow. Therefore, any fracture in humerus disrupts our daily lives. The manual fracture detection process where the doctors detect the fracture by analyzing X-ray images is quite time consuming and also error prone. Therefore, we have introduced an automated system to diagnose humerus fracture in an efficient way. In this study, we have focused on deep learning algorithm for fracture detection. In this purpose at first, 1266 X-ray images of humerus bone including fractured and non-fractured have been collected from a publicly available dataset called “MURA”. As a deep learning model has been used here, data augmentation has been applied to increase the dataset for reducing over-fitting problem. Finally, all the images are passed through CNN model to train the images and classify the fractured and non-fractured bone. Moreover, different pretrained model has also been applied in our dataset to find out the best accuracy. After implementation, it is observed that our model shows the best accuracy which is 80% training accuracy and 78% testing accuracy comparing with other models.

  • 15.
    Ahmed, Faisal
    et al.
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Hasan, Mohammad
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Comparative Performance of Tree Based Machine Learning Classifiers in Product Backorder Prediction2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 572-584Chapter in book (Refereed)
    Abstract [en]

    Early prediction of whether a product will go to backorder or not is necessary for optimal management of inventory that can reduce the losses in sales, establish a good relationship between the supplier and customer and maximize the revenues. In this study, we have investigated the performance and effectiveness of tree based machine learning algorithms to predict the backorder of a product. The research methodology consists of preprocessing of data, feature selection using statistical hypothesis test, imbalanced learning using the random undersampling method and performance evaluating and comparing of four tree based machine learning algorithms including decision tree, random forest, adaptive boosting and gradient boosting in terms of accuracy, precision, recall, f1-score, area under the receiver operating characteristic curve and area under the precision and recall curve. Three main findings of this study are (1) random forest model without feature selection and with random undersampling method achieved the highest performance in terms of all performance measure metrics, (2) feature selection cannot contribute to the performance enhancement of the tree based classifiers, and (3) random undersampling method significantly improves performance of tree based classifiers in product backorder prediction.

  • 16.
    Shafiq, Shakila
    et al.
    Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, Bangladesh.
    Ahmed, Sabbir
    Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, Bangladesh.
    Kaiser, M Shamim
    Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, Bangladesh.
    Mahmud, Mufti
    Department of Computer Science, Nottingham Trent University, Nottingham, U.K..
    Hossain, Md. Shahadat
    Department of Computer Science and Engineering, University of Chittagong, University-4331, Chattogram, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Comprehensive Analysis of Nature-Inspired Algorithms for Parkinson’s Disease Diagnosis2023In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 1629-1653Article in journal (Refereed)
    Abstract [en]

    Parkinson’s disease (PD) is a prominent neurodegenerative disease that damages the neurons of the substantia nigra, causing irreversible impairments leading to involuntary movements. As this disease disrupts patients’ daily activities in a mature stage, early detection of the disease is crucial. Several methods based on nature-inspired (NI) algorithms have been proposed for PD detection and patient management. As there are several NI algorithms for feature selection, a mapping with an individual machine learning (ML) classifier is necessary to obtain optimal performance of the detection pipeline. To fill this gap, in this work, 13 NI algorithms and 11 ML classifiers were selected, and critical comparisons were performed regarding their combined performance in detecting PD. Each NI algorithm was employed to select an optimal feature set which was then classified by the 11 ML classifiers keeping the same parameters. This generated 143 NI-ML pairs, which were carefully compared to find the best-performing pairs considering several assessment criteria such as accuracy, cross-validation mean score, precision, recall and F1-score. The results of the extensive comparative analysis allowed the ranking of the algorithms in the 50th, 75th and 95th percentile to identify the best-performing pairs. The analyses revealed that 12 NI-ML models obtained a testing accuracy of over 91%, which is above the 95th percentile value. The Flower Pollination Algorithm and Extreme Gradient Boost Algorithm pair obtained the highest testing accuracy of 93%. This study revealed the remarkable performance of the boosting algorithms promoting explainable machine learning in PD detection.

  • 17.
    Mahmud, Tanjim
    et al.
    Rangamati Science and Technology University, Bangladesh.
    Ara, Israt
    Rangamati Science and Technology University, Bangladesh.
    Chakma, Rishita
    Rangamati Science and Technology University, Bangladesh.
    Barua, Koushick
    Rangamati Science and Technology University, Bangladesh.
    Islam, Dilshad
    Chattogram Veterinary and Animal Sciences University, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Bangladesh.
    Barua, Anik
    Rangamati Science and Technology University, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Design and Implementation of an Ultrasonic Sensor-Based Obstacle Avoidance System for Arduino Robots2023In: 2023 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD 2023): Conference Proceedings / [ed] Mustafa Kamal; Kazi Abu Taher; Saiful Islam; Mohammed Nasir Uddin, IEEE, 2023, p. 264-268Conference paper (Refereed)
  • 18.
    Mahmud, Tanjim
    et al.
    Dept. of CSE, Rangamati Science and Technology University, Bangladesh.
    Barua, Anik
    Dept. of CSE, Rangamati Science and Technology University, Bangladesh.
    Islam, Dilshad
    Dept. of Physical and Mathematical Sciences Chattogram Veterinary and Animal Sciences University, Bangladesh.
    Hossain, Mohammad Shahadat
    Dept. of CSE, University of Chittagong Bangladesh.
    Chakma, Rishita
    Dept. of CSE Rangamati Science and Technology University, Bangladesh.
    Barua, Koushick
    Dept. of CSE Rangamati Science and Technology University, Bangladesh.
    Monju, Mahabuba
    Dept. of CSE Rangamati Science and Technology University, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Ensemble Deep Learning Approach for ECG-Based Cardiac Disease Detection: Signal and Image Analysis2023In: 2023 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD 2023): Conference Proceedings / [ed] Mustafa Kamal; Kazi Abu Taher; Saiful Islam; Mohammed Nasir Uddin, IEEE, 2023, p. 70-74Conference paper (Refereed)
  • 19.
    Mahmud, Tanjim
    et al.
    Rangamati Science and Technology University, 4500, Rangamati, Bangladesh.
    Barua, Koushick
    Rangamati Science and Technology University, 4500, Rangamati, Bangladesh.
    Barua, Anik
    Rangamati Science and Technology University, 4500, Rangamati, Bangladesh.
    Das, Sudhakar
    Rangamati Science and Technology University, 4500, Rangamati, Bangladesh.
    Basnin, Nanziba
    Leeds Beckette University, Leeds, UK.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Kaiser, M. Shamim
    Institute of Information Technology, Jahangirnagar University, Dhaka, Bangladesh.
    Sharmen, Nahed
    Chattogram Maa-O-Shishu Hospital Medical College, Chittagong, Bangladesh.
    Exploring Deep Transfer Learning Ensemble for Improved Diagnosis and Classification of Alzheimer’s Disease2023In: BI 2023: Brain Informatics, Proceedings / [ed] Yu Zhang, Hongzhi Kuai & Emily P. Stephen, Springer, 2023, p. 109-120Conference paper (Refereed)
    Abstract [en]

    Alzheimer’s disease (AD) is a progressive and irreversible neurological disorder that affects millions of people worldwide. Early detection and accurate diagnosis of AD are crucial for effective treatment and management of the disease. In this paper, we propose a transfer learning-based approach for the diagnosis of AD using magnetic resonance imaging (MRI) data. Our approach involves extracting relevant features from the MRI data using transfer learning by alter the weights and then using these features to train pre-trained models and combined ensemble classifier. We evaluated our approach on a dataset of MRI scans from patients with AD and healthy controls, achieving an accuracy of 95% for combined ensemble models. Our results demonstrate the potential of transfer learning-based approaches for the early and accurate diagnosis of AD, which could lead to improved patient outcomes and more effective management of the disease.

  • 20.
    Farshid, Mohammad
    et al.
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Aziz, Atia Binti
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Basnin, Nanziba
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Akhter, Mohoshena
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    IoMT-based Android Application for Monitoring COVID-19 Patients Using Real-Time Data2023In: Proceedings of the Fourth International Conference on Trends in Computational and Cognitive Engineering - TCCE 2022 / [ed] M. Shamim Kaiser; Sajjad Waheed; Anirban Bandyopadhyay; Mufti Mahmud; Kanad Ray, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 145-157Conference paper (Refereed)
    Abstract [en]

    Surviving three years of the pandemic since December 2019, monitoring COVID-19 patients in a projected way is still challenging. Even after testing negative for coronavirus, people face a lot of post-covid stresses and symptoms. Scarcity of hospital beds, shortage of medical equipment like oxygen, ventilation, etc. have made the situation worse as people failed to receive proper treatment. In this regard, this work proposes an IoMT-based wearable checking device for assessing COVID-19-identified imperative signals. Furthermore, by continuously monitoring data, the device promptly warns concerned clinical personnel about any breach of isolation for possibly contaminated patients. The data from the body-wearable sensor is processed and broken down by an edge node in the IoMT cloud to characterize the condition of health. A puttable IoMT sensor layer, a cloud layer with Application Peripheral Interface (API), and an Android-based cell prototype are part of the proposed system. Each layer has its own function; for example, the data from the IoMT sensor layer is used to characterize the wellness of the side effects. The Android portable application layer is in charge of informing and cautioning possibly infected patient family members, the nearest hospital, and the patient’s signed doctor about the potential contamination. Two APIs and a variety of applications are synchronized in the integrated system to predict and disrupt the situation. In a word, the target is to monitor this data and send it to the cloud through the IoMT gateway and monitor these parameters using the Android app. The doctor and the patient’s relative could also observe the monitor system through the app using the device id from this app. Because there are fewer available beds in hospitals, more people are dying as a result of inadequate care.

  • 21.
    Sultana, Zinnia
    et al.
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Nahar, Lutfun
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Tasnim, Farzana
    International Islamic University Chittagong, Sonaichhari, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Lossy Compression Effect on Color and Texture Based Image Retrieval Performance2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 1159-1167Chapter in book (Refereed)
    Abstract [en]

    Image retrieval and compression are rigorous research field to solve the problem of storage and management of digital image. Several digital compression techniques are available for digital compression such as lossy and lossless compression methods. JPEG, an international organization issues an effective digital image compression standard. CBIR system have been proposed to reduce the storage of digital multimedia collections. Content Based Indexing and Retrieval method provides some advantages in compression of digital image. However, lossy compression technique reduce the visual appearance of images and also the values of real pixels have been altered. There is a filtering effect on pictorial qualities due to data loss. This purpose of this research is find an efficient retrieval and compression technique of image based on color and texture. This experiment investigates the compression effects on image retrieval using color and texture features and presents retrieval results of a Content Based Image Retrieval (CBIR) system. By using some performance metrics the system’s output can be evaluated. Each one is evaluated by different measurement. In this experiment only Two performance metric has been used namely F1 measure and Average Normalized Modified Retrieval Rank (ANMRR). Here four visual descriptors are used and measure performance individually. Two of the color feature and other two is texture features. The system is tested with two different image database color and gray images with visual feature vectors.

  • 22.
    Ahmed, Faisal
    et al.
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Naim Uddin Rahi, Mohammad
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Uddin, Raihan
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Sen, Anik
    Department of Computer Science and Engineering, Premier University, Chattogram, Bangladesh.
    Shahadat Hossain, Mohammad
    University of Chittagong, Chattogram, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Machine Learning-Based Tomato Leaf Disease Diagnosis Using Radiomics Features2023In: Proceedings of the Fourth International Conference on Trends in Computational and Cognitive Engineering - TCCE 2022 / [ed] M. Shamim Kaiser; Sajjad Waheed; Anirban Bandyopadhyay; Mufti Mahmud; Kanad Ray, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 25-35Conference paper (Refereed)
    Abstract [en]

    Tomato leaves can be infected with various infectious viruses and fungal diseases that drastically reduce tomato production and incur a great economic loss. Therefore, tomato leaf disease detection and identification are crucial for maintaining the global demand for tomatoes for a large population. This paper proposes a machine learning-based technique to identify diseases on tomato leaves and classify them into three diseases (Septoria, Yellow Curl Leaf, and Late Blight) and one healthy class. The proposed method extracts radiomics-based features from tomato leaf images and identifies the disease with a gradient boosting classifier. The dataset used in this study consists of 4000 tomato leaf disease images collected from the Plant Village dataset. The experimental results demonstrate the effectiveness and applicability of our proposed method for tomato leaf disease detection and classification.

  • 23.
    Al Arafat, Md. Mahedi
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Hossain, Delowar
    Cumming School of Medicine, University of Calgary, Calgary, AB, T2N 1N4, Canada.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Neural Network-Based Obstacle and Pothole Avoiding Robot2023In: Proceedings of the Fourth International Conference on Trends in Computational and Cognitive Engineering - TCCE 2022 / [ed] M. Shamim Kaiser; Sajjad Waheed; Anirban Bandyopadhyay; Mufti Mahmud; Kanad Ray, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 173-184Conference paper (Refereed)
    Abstract [en]

    The main challenge of any mobile robot is to detect and avoid obstacles and potholes. This paper presents the development and implementation of a novel mobile robot. An Arduino Uno is used as the processing unit of the robot. A Sharp distance measurement sensor and Ultrasonic sensors are used for taking inputs from the environment. The robot trains a neural network based on a feedforward backpropagation algorithm to detect and avoid obstacles and potholes. For that purpose, we have used a truth table. Our experimental results show that our developed system can ideally detect and avoid obstacles and potholes and navigate environments.

  • 24.
    Mahmud, Tanjim
    et al.
    Rangamati Science and Technology University, Rangamati, Bangladesh; Kitami Institute of Technology, Kitami, Japan.
    Das, Sudhakar
    Rangamati Science and Technology University, Rangamati, Bangladesh.
    Ptaszynski, Michal
    Kitami Institute of Technology, Kitami, Japan.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Barua, Koushick
    Rangamati Science and Technology University, Rangamati, Bangladesh.
    Reason Based Machine Learning Approach to Detect Bangla Abusive Social Media Comments2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 489-498Chapter in book (Refereed)
    Abstract [en]

    For the study issue of abusive language detection, English is the most commonly employed language. There are just a few works accessible in low-resource languages such as Bangla. People use these sorts of statements on many social media sites. As a result, detection of this type of language is a demand of time. Our goal is to identify this abusive Bangla language in a novel approach. There are some works that use Bengali corpus and transliterated Bengali corpus to detect abusive language. However, in this research, we utilized annotated translated Bengali corpora, and we added a formal justification in each remark for being classified as abusive or non abusive language. For evaluations, we employed a variety of machine learning classifiers where logistic regression achieves 97% accuracy.

  • 25.
    Neloy, Md. Arif Istiak
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Mahamud, Faisal
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Tomato Leaf Disease Classification Using Transfer Learning Method2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 231-241Chapter in book (Refereed)
    Abstract [en]

    Human civilization is completely reliant on plants to provide our dietary needs. Despite having a population of over seven billion people that is rapidly expanding, our cultivable land has declined rather than increased. Plants, on the other hand, are susceptible to a variety of illnesses. Leaf disease, which comprises leaf spots, bacterial spots, black spots, and other conditions, is one of them. Bacteria and fungi are the most common causes of these disorders. This has an evident negative effect on the plant in the long run. As a result, it should be recognized early in order to save the crop’s productivity. We choose to focus on tomato leaf disease especially in our study report. Where we have used transfer learning technology to detect early blight, late blight, bacterial spots, and a few other diseases in tomato leaves images. Inception-V3 model has been deployed to have the best predictive outcome from the dataset which includes ten sets of tomato leaf images. The training and testing accuracy of transfer learning based inception-V3 model is 99.58% and 97.19% respectively. We also compare our model with other three transfer learning model which are VGG19, MobileNet and ResNet50.

  • 26.
    Mahamud, Faisal
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Emon, Al Shareya
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Imam, Md. Hasan
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University, Chittagong, 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Transfer Learning Based Method for Classification of Schizophrenia Using MobileNet2023In: Intelligent Computing & Optimization: Proceedings of the 5th International Conference on Intelligent Computing and Optimization 2022 (ICO2022) / [ed] Pandian Vasant; Gerhard-Wilhelm Weber; José Antonio Marmolejo-Saucedo; Elias Munapo; J. Joshua Thomas, Springer, 2023, 1, p. 210-220Chapter in book (Refereed)
    Abstract [en]

    Schizophrenia is a serious mental disorder which makes a patient abnormal than other patient thinks he is not there and everyone is for his enemy. As a result, it is so much important to detect the disease at an early stage. If we can detect the disease at an early stage, we can make the patient’s life normal. CNN (Convolutional Neural Network) -based technique for classification of the disease is used many times. In our research, we are using two class one is normal class, another is Schizophrenia class which is used transfer learning approach for classifying Schizophrenia disease from brain MRI data. In our presented method, our technique, which is based on transfer learning theory, uses a pre-trained MobileNet method to identify brain MRI images by extracting features using the sigmoid classifier method with a mean classification accuracy of 93.95%. Our proposed method exceeds all previous strategies. We utilize the Kaggle dataset to evaluate our technique. One of the important performance indicators used in this study is precision, recall, and F-score. Our classification method got accuracy of 90.62%.

  • 27.
    Barman, Sourav
    et al.
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Biswas, Md Raju
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Marjan, Sultana
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Transfer Learning Based Skin Cancer Classification Using GoogLeNet2023In: Machine Intelligence and Emerging Technologies - First International Conference, MIET 2022, Proceedings, part 1 / [ed] Md. Shahriare Satu; Mohammad Ali Moni; M. Shamim Kaiser; Mohammad Shamsul Arefin; Mohammad Shamsul Arefin, Springer Science and Business Media Deutschland GmbH , 2023, Vol. 1, p. 238-252Conference paper (Refereed)
    Abstract [en]

    Skin cancer has been one of the top three cancers that can be fatal when caused by broken DNA. Damaged DNA causes cells to expand uncontrollably, and the rate of growth is currently increasing rapidly. Some studies have been conducted on the computerized detection of malignancy in skin lesion images. However, due to some problematic aspects such as light reflections from the skin surface, differences in color lighting, and varying forms and sizes of the lesions, analyzing these images is extremely difficult. As a result, evidence-based automatic skin cancer detection can help pathologists improve their accuracy and competency in the early stages of the disease. In this paper, we present a transfer ring strategy based on a convolutional neural network (CNN) model for accurately classifying various types of skin lesions. Preprocessing normalizes the input photos for accurate classification; data augmentation increases the amount of images, which enhances classification rate accuracy. The performance of the GoogLeNet transfer learning model is compared to that of other transfer learning models such as Xpection, InceptionResNetVe, and DenseNet, among others. The model was tested on the ISIC dataset, and we ended up with the highest training and testing accuracy of 91.16% and 89.93%, respectively. When compared to existing transfer learning models, the final results of our proposed GoogLeNet transfer learning model characterize it as more dependable and resilient.

  • 28.
    Umme Habiba, Sultana
    et al.
    Khulna University of Engineering & Technology, Khulna, Bangladesh.
    Debnath, Tanoy
    Department of Computer Science and Engineering, Green University of Bangladesh, Dhaka, Bangladesh.
    Islam, Md. Khairul
    Khulna University of Engineering & Technology, Khulna, Bangladesh.
    Nahar, Lutfun
    Department of Computer Science and Engineering, International Islamic University Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Basnin, Nanziba
    Leeds Beckett University, Leeds, UK.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Transfer Learning-Assisted DementiaNet: A Four Layer Deep CNN for Accurate Alzheimer’s Disease Detection from MRI Images2023In: BI 2023: Brain Informatics, Proceedings / [ed] Yu Zhang, Hongzhi Kuai & Emily P. Stephen, Springer, 2023, p. 383-394Conference paper (Refereed)
    Abstract [en]

    Alzheimer’s disease is the most common type of dementia and the sixth highest cause of mortality among people over 65. Also, according to statistics, the number of deaths from Alzheimer’s disease has increased dramatically. As a result, early detection of Alzheimer’s disease can improve patient survival chances. Machine learning methods using magnetic resonance imaging have been utilized in the diagnosis of Alzheimer’s disease to help clinicians and speed up the procedure. This research mainly focuses on Alzheimer’s disease detection to overcome previous limitations. We use a publicly available dataset which contains 6400 MRI images. In order to train our dataset, we employ our suggested model, “DementiaNet”, using “EfficientNet” as a feature extractor and a Deep CNN as a classifier. In order to capture all the features, this framework uses a small number of convolutional layers, which improves the effectiveness of feature learning and results in a more accurate and reliable output. In addition, to address the issue of data imbalance, we apply data augmentation to enhance the size of the minority class by considering four stages of dementia. Also, in this study, we take advantage of the transfer learning approach with the attachment of “EfficientNet”, which allows our model to easily solve the overfitting problem and also extract all the features in a effective way. Finally, we compare our proposed models with those reported in the literature. Our experimental results indicate that our “DementiaNet” model achieve an overall classification accuracy of 97% to detect Alzheimer from brain MRI images, exceeding all other state-of-the-art models.

  • 29.
    Jamil, Mohammad Newaj
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Workload Orchestration in Multi-access Edge Computing Using Belief Rule-Based Approach2023In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 118002-118023Article in journal (Refereed)
    Abstract [en]

    Multi-access Edge Computing (MEC) is a standard network architecture for edge computing, which is proposed to handle enormous computation demands from emerging resource-intensive and latency-sensitive applications and services as well as accommodate Quality of Service (QoS) requirements for ever-growing users through computation offloading. Since the demand of end-users is unknown in a rapidly changing dynamic environment, processing offloaded tasks in a non-optimal server can deteriorate QoS due to high latency and increasing task failures. In order to deal with such a challenge in MEC, a two-stage Belief Rule-Based (BRB) workload orchestrator is proposed to distribute the workload of end-users to optimum computing units, support strict QoS requirements, ensure efficient utilization of computational resources, minimize task failures, and reduce the overall service time. The proposed BRB workload orchestrator decides the optimal execution location for each offloaded task from User Equipment (UE) within the overall MEC architecture based on network conditions, computational resources, and task requirements. EdgeCloudSim simulator is used to conduct comprehensive simulation experiments for evaluating the performance of the proposed BRB orchestrator in contrast to four workload orchestration approaches from the literature with different types of applications. Based on the simulation experiments, the proposed workload orchestrator outperforms state-of-the-art workload orchestration approaches and ensures efficient utilization of computational resources while minimizing task failures and reducing the overall service time.

    Download full text (pdf)
    fulltext
  • 30.
    Raihan, S. M. Shafkat
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Ahmed, Mumtahina
    Port City International University, Chittagong, Bangladesh.
    Sharma, Angel
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, 4331, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Belief Rule Based Expert System to Diagnose Alzheimer’s Disease Using Whole Blood Gene Expression Data2022In: Brain Informatics: 15th International Conference, BI 2022, Padua, Italy, July 15–17, 2022, Proceedings / [ed] Mufti Mahmud, Jing He, Stefano Vassanelli, André van Zundert, Ning Zhong, Springer, 2022, p. 301-315Conference paper (Refereed)
    Abstract [en]

    Alzheimer’s disease (AD) is a degenerative neurological disease that is the most common cause of dementia. It is also the fifth-greatest reason for death in adults aged 65 and over. However, there is no accurate way of diagnosing neurological Alzheimer’s disorders in medical research. Blood gene expression analysis offers a realistic option for identifying those at risk of AD. Blood gene expression patterns have previously proved beneficial in diagnosing several brain disorders, despite the blood-brain barrier’s restricted permeability. The most extensively used statistical machine learning and deep learning algorithms are data-driven and do not address data uncertainty. Belief Rule-Based Expert System (BRBES) is an approach that can identify various forms of uncertainty in data and reason using evidential reasoning. No previous research studies have examined BRBES’ performance in diagnosing AD. As a result, this study aims to identify how effective BRBES is at diagnosing Alzheimer’s disease from blood gene expression data. We used a gradient-free technique to optimize the BRBES because prior research had shown the limits of gradient-based optimization. We have also attempted to address the class imbalance problem using BRBES’ consequent utility parameters. Finally, after 5-fold cross-validation, we compared our model to three classic ML models, finding that our model had a greater specificity than the other three models across all folds. The average specificity of our models for all folds was 32%

  • 31.
    Shafkat Raihan, S.M.
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hossain, M. S.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A BRBES to Support Diagnosis of COVID-19 Using Clinical and CT Scan Data2022In: Proceedings of the International Conference on Big Data, IoT, and Machine Learning / [ed] Mohammad Shamsul Arefin; M. Shamim Kaiser; Anirban Bandyopadhyay; Md. Atiqur Rahman Ahad; Kanad Ray, Springer, 2022, Vol. 95, p. 483-496Conference paper (Refereed)
    Abstract [en]

    In the prevailing COVID-19 pandemic, accurate diagnosis plays a vital role in preventing the mass transmission of the SARS-CoV-2 virus. Especially patients with pneumonia need correct diagnosis for proper treatment of their respiratory distress. However, the current standard diagnosis method, RT-PCR testing has a significant false negative and false positive rate. As alternatives, diagnosis methods based on artificial intelligence can be applied for faster and more accurate diagnosis. Currently, various machine learning and deep learning techniques are being researched on to develop better COVID-19 diagnosis system. However, these approaches do not consider the uncertainty in data. Deep learning approaches use backpropagation. It is an unexplainable black box approach and is prone to problems like catastrophic forgetting. This article applies a belief rule-based expert system (BRBES) for diagnosis of COVID-19 on hematological data and CT scan data of lung tissue infection of adult pneumonia patients. The system is optimized with nature-inspired optimization algorithm—BRBES-based adaptive differential evolution (BRBaDE). This model has been evaluated on a real-world dataset of COVID-19 patients published in a previous work. Also, performance of the BRBaDE has been compared with BRBES optimized with genetic algorithm and MATLAB’s fmincon function where BRBaDE outperformed genetic algorithm and fmincon and showed best accuracy of 73.91%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

  • 32.
    Ahmed, Tawsin Uddin
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Hossain, Sazzad
    Department of Computer Science and Engineering, University of Liberal Arts Bangladesh, Dhaka, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Deep Learning Approach with Data Augmentation to Recognize Facial Expressions in Real Time2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 487-500Conference paper (Refereed)
    Abstract [en]

    The enormous use of facial expression recognition in various sectors of computer science elevates the interest of researchers to research this topic. Computer vision coupled with deep learning approach formulates a way to solve several real-world problems. For instance, in robotics, to carry out as well as to strengthen the communication between expert systems and human or even between expert agents, it is one of the requirements to analyze information from visual content. Facial expression recognition is one of the trending topics in the area of computer vision. In our previous work, a facial expression recognition system is delivered which can classify an image into seven universal facial expressions—angry, disgust, fear, happy, neutral, sad, and surprise. This is the extension of our previous research in which a real-time facial expression recognition system is proposed that can recognize a total of ten facial expressions including the previous seven facial expressions and additional three facial expressions—mockery, think, and wink from video streaming data. After model training, the proposed model has been able to gain high validation accuracy on a combined facial expression dataset. Moreover, the real-time validation of the proposed model is also promising.

  • 33.
    Nahar, Lutfun
    et al.
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Das, Promi
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Alam, Tanzeem
    International Islamic University Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Deep Learning-Based Ophthalmologic Approach for Retinal Fundus Image Analysis to Detect Glaucoma2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 519-532Conference paper (Refereed)
  • 34.
    Nahar, Nazmun
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Ara, Ferdous
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Junjun, Jubair Ahmed
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Hybrid CNN-LSTM-Based Emotional Status Determination using Physiological Signals2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 149-161Conference paper (Refereed)
    Abstract [en]

    Automatic real-time emotion recognition based on GSR and ECG signals becomes an effective computer-aided tool for emotional recognition as a challenge to pattern recognition. Traditional machine learning methods require the development and extraction of various features dependent on extensive domain knowledge. As a result, non-domain experts can find these methods challenging. On the other hand, deep learning methods have been widely used in several current studies to learn features and identify various types of data. In this paper, to characterize human emotion states, we proposed a hybrid neural network that combines ‘Convolutional Neural Network (CNN)’ and ‘Long-Term Short-Term Memory (LSTM)’. Our dataset consists of four types of emotions which are happy, sad, fear, angry. We have trained our model with CNN-LSTM. Our proposed CNN-LSTM model gives 100% training accuracy and 99.05% validation accuracy with RMSProp optimizer. We also compare our result with machine learning algorithms: Random forest, Logistic Regression, Support Vector Machine, and Naïve Bayes. The comparison result clearly shows that our proposed CNN-LSTM gives the best result among the other classifiers.

  • 35.
    Neloy, Md. Arif Istiek
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    A Weighted Average Ensemble Technique to Predict Heart Disease2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 17-29Conference paper (Refereed)
  • 36.
    Maisha, Sabrina Jahan
    et al.
    BGC Trust University Bangladesh, Chandanaish, Chattogram, Bangladesh.
    Biswangri, Ety
    University Bangladesh, Chandanaish, Chattogram, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An Approach to Detect Chronic Kidney Disease (CKD) by Removing Noisy and Inconsistent Values of UCI Dataset2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 457-472Conference paper (Refereed)
  • 37.
    Kabir, Sami
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hossain, Mohammad Shahadat
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai2022Data set
    Abstract [en]

    Accurate monitoring of air quality can reduce its adverse impact on earth. Ground-level sensors can provide fine particulate matter (PM2.5) concentrations and ground images. But, such sensors have limited spatial coverage and require deployment cost. PM2.5 can be estimated from satellite-retrieved Aerosol Optical Depth (AOD) too. However, AOD is subject to uncertainties associated with its retrieval algorithms and constrain the spatial resolution of estimated PM2.5. AOD is not retrievable under cloudy weather as well. In contrast, satellite images provide continuous spatial coverage with no separate deployment cost. Accuracy of monitoring from such satellite images is hindered due to uncertainties of sensor data of relevant environmental parameters, such as, relative humidity, temperature, wind speed and wind direction . Belief Rule Based Expert System (BRBES) is an efficient algorithm to address these uncertainties. Convolutional Neural Network (CNN) is suitable for image analytics. Hence, we propose a novel model by integrating CNN with BRBES to monitor air quality from satellite images with improved accuracy. We customized CNN and optimized BRBES to increase monitoring accuracy further. An obscure image has been differentiated between polluted air and cloud based on relationship of PM2.5 with relative humidity. Valid environmental data (temperature, wind speed and wind direction) have been adopted to further strengthen the monitoring performance of our proposed model. Three-year observation data (satellite images and environmental parameters) from 2014 to 2016 of Shanghai have been employed to analyze and design our proposed model.

    Download full text (pdf)
    fulltext
  • 38.
    Kabir, Sami
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Shahadat Hossain, Mohammad
    Department of Computer Science & Engineering, University of Chittagong, Chattogram 4331, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai2022In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 206, article id 117905Article in journal (Refereed)
    Abstract [en]

    Accurate monitoring of air quality can reduce its adverse impact on earth. Ground-level sensors can provide fine particulate matter (PM2.5) concentrations and ground images. But, such sensors have limited spatial coverage and require deployment cost. PM2.5 can be estimated from satellite-retrieved Aerosol Optical Depth (AOD) too. However, AOD is subject to uncertainties associated with its retrieval algorithms and constrain the spatial resolution of estimated PM2.5. AOD is not retrievable under cloudy weather as well. In contrast, satellite images provide continuous spatial coverage with no separate deployment cost. Accuracy of monitoring from such satellite images is hindered due to uncertainties of sensor data of relevant enviromental parameters, such as, relative humidity, temperature, wind speed and wind direction . Belief Rule Based Expert System (BRBES) is an efficient algorithm to address these uncertainties. Convolutional Neural Network (CNN) is suitable for image analytics. Hence, we propose a novel model by integrating CNN with BRBES to monitor air quality from satellite images with improved accuracy. We customized CNN and optimized BRBES to increase monitoring accuracy further. An obscure image has been differentiated between polluted air and cloud in our model. Valid environmental data (temperature, wind speed and wind direction) have been adopted to further strengthen the monitoring performance of our proposed model. Three-year observation data (satellite images and environmental parameters) from 2014 to 2016 of Shanghai have been employed to analyze and design our proposed model. The results conclude that the accuracy of our model to monitor PM2.5 of Shanghai is higher than only CNN and other conventional Machine Learning methods. Real-time validation of our model on near real-time satellite images of April-2021 of Shanghai shows average difference between our calculated PM2.5 concentrations and the actual one within ±5.51.

    Download full text (pdf)
    fulltext
  • 39.
    Ahmed, Tawsin Uddin
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Jamil, Mohammad Newaj
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    An Integrated Deep Learning and Belief Rule Base Intelligent System to Predict Survival of COVID-19 Patient under Uncertainty2022In: Cognitive Computation, ISSN 1866-9956, E-ISSN 1866-9964, Vol. 14, no 2, p. 660-676Article in journal (Refereed)
    Abstract [en]

    The novel Coronavirus-induced disease COVID-19 is the biggest threat to human health at the present time, and due to the transmission ability of this virus via its conveyor, it is spreading rapidly in almost every corner of the globe. The unification of medical and IT experts is required to bring this outbreak under control. In this research, an integration of both data and knowledge-driven approaches in a single framework is proposed to assess the survival probability of a COVID-19 patient. Several neural networks pre-trained models: Xception, InceptionResNetV2, and VGG Net, are trained on X-ray images of COVID-19 patients to distinguish between critical and non-critical patients. This prediction result, along with eight other significant risk factors associated with COVID-19 patients, is analyzed with a knowledge-driven belief rule-based expert system which forms a probability of survival for that particular patient. The reliability of the proposed integrated system has been tested by using real patient data and compared with expert opinion, where the performance of the system is found promising.

  • 40.
    Sumi, Tahmina Akter
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Automated Acute Lymphocytic Leukemia (ALL) Detection Using Microscopic Images: An Efficient CAD Approach2022In: Proceedings of Trends in Electronics and Health Informatics: TEHI 2021 / [ed] M. Shamim Kaiser; Anirban Bandyopadhyay; Kanad Ray; Raghvendra Singh; Vishal Nagar, Springer, 2022, p. 363-376Conference paper (Refereed)
    Abstract [en]

    Leukemia, which is caused by the excessive and aberrant reproduction of white blood cells, completely destroys the immune system of our body and leads to death. Among four different types of leukemia, the progress of acute lymphocytic leukemia is rapid and becomes fatal even in weeks if it is kept untreated. So, early diagnosis of ALL is quite necessary. In manual methods, pathologists diagnose ALL by the microscopic test of blood specimen or bone marrow test. Though this is the most efficient process to diagnose ALL, it is a time-consuming matter. In this case, computer-aided diagnosis (CAD) may be considered as a great associative diagnostic tool for ALL identification. Numerous supervised and unsupervised machine learning algorithms have been proposed for ALL detection for years. This paper concerns with establishing a CNN- based CAD system for automated ALL detection from the microscopic blood images which is collected from ALL-IDB dataset. In this regard, at first the images have been preprocessed applying median filter and histogram equalization for the purpose of reducing the noise and enhancing the image. Being smaller in size, data augmentation has been applied on the dataset which increases the images by including slightly modified copies of images that already exist in the dataset. Finally, the modified images are passed through a CNN model for training purpose where feature extraction and classification are performed by convolution, ReLU, pooling layer, and a fully connected layer. Here, the dataset is also trained using some pretrained model to show a comparison of our model with other models. It is observed that our proposed model results as a well fitting model with 100% training accuracy and 97.89% testing accuracy which is promising.

  • 41.
    Akter, Nasrin
    et al.
    BGC Trust University Bangladesh, Bidyanagar, Chandanaish, Bangladesh.
    Junjun, Jubair Ahmed
    BGC Trust University Bangladesh, Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    BGC Trust University Bangladesh, Bidyanagar, Chandanaish, Bangladesh.
    Shahadat Hossain, Mohammad
    University of Chittagong, University-4331, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Hoassain, Md. Sazzad
    University of Liberal Arts Bangladesh, Dhaka, 1209, Bangladesh.
    Brain Tumor Classification using Transfer Learning from MRI Images2022In: Proceedings of International Conference on Fourth Industrial Revolution and Beyond 2021 / [ed] Sazzad Hossain, Md. Shahadat Hossain, M. Shamim Kaiser, Satya Prasad Majumder, Kanad Ray, Springer, 2022, p. 575-587Chapter in book (Refereed)
    Abstract [en]

    One of the most vital parts of medical image analysis is the classification of brain tumors. Because tumors are thought to be origins to cancer, accurate brain tumor classification can save lives. As a result, CNN (Convolutional Neural Network)-based techniques for classifying brain cancers are frequently employed. However, there is a problem: CNNs are exposed to vast amounts of training data in order to produce good performance. This is where transfer learning enters into the picture. We present a 4-class transfer learning approach for categorizing Glioma, Meningioma, and Pituitary tumors and non-tumors in this study. The three most prevalent types of brain tumors are glioma, meningioma, and pituitary tumors. Our presented method, which employs the theory of transfer learning, utilizes a pre-trained InceptionResnetV1 method for classifying brain MRI images by extracting features from them using the softmax classifier method. The proposed approach outperforms all prior techniques with a mean classification accuracy of 93.95%. For the evaluation of our method we use kaggle dataset. Precision, recall, and F-score are one of the key performance metrics employed in this study.

  • 42.
    Sumi, Tahmina Akter
    et al.
    University of Chittagong, Chittagong, Bangladesh.
    Nath, Tanuja
    University of Chittagong, Chittagong, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Classifying Brain Tumor from MRI Images Using Parallel CNN Model2022In: Brain Informatics: 15th International Conference, BI 2022, Padua, Italy, July 15–17, 2022, Proceedings / [ed] Mufti Mahmud, Jing He, Stefano Vassanelli, André van Zundert, Ning Zhong, Springer, 2022, p. 264-276Conference paper (Refereed)
    Abstract [en]

    Brain tumor, commonly known as intracranial tumor, is the most general and deadly disease which leads to a very short lifespan. It occurs due to the uncontrollable growth of cells which is unchecked by the process that is engaged in monitoring the normal cells. The survival rate due to this disease is the lowest and consequently the detection and classification of brain tumor has become crucial in early stages. In manual approach, brain tumors are diagnosed using (MRI). After the MRI displays the tumor in brain, the type of the tumor is identified by examining the result of biopsy of sample tissue. But having some limitations such as accurate measurement is achieved for finite number of image and also being time consuming matter, the automated computer aided diagnosis play a crucial rule in the detection of brain tumor. Several supervised and unsupervised machine learning algorithms have been established for the classification of brain tumor for years. In this paper, we have utilized both image processing and deep learning for successful classification of brain tumor from the MRI images. At first in the image preprocessing step, the MRI images are normalized and through image augmentation the number of images is enriched. Further the preprocessed images are passed through a parallel CNN network where the features of the images are extracted and classified. Our experimental result shows an accuracy of 89% that is promising.

  • 43.
    Alizadeh, Morteza
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Schelén, Olov
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.
    Comparative Analysis of Decentralized Identity Approaches2022In: IEEE Access, E-ISSN 2169-3536, Vol. 10, p. 92273-92283Article in journal (Refereed)
    Abstract [en]

    Decentralization is essential when trust and performance must not depend on a single organization. Distributed Ledger Technologies (DLTs) and Decentralized Hash Tables (DHTs) are examples where the DLT is useful for transactional events, and the DHT is useful for large-scale data storage. The combination of these two technologies can meet many challenges. The blockchain is a DLT with immutable history protected by cryptographic signatures in data blocks. Identification is an essential issue traditionally provided by centralized trust anchors. Self-sovereign identities (SSIs) are proposed decentralized models where users can control and manage their identities with the help of DHT. However, slowness is a challenge among decentralized identification systems because of many connections and requests among participants. In this article, we focus on decentralized identification by DLT and DHT, where users can control their information and store biometrics. We survey some existing alternatives and address the performance challenge by comparing different decentralized identification technologies based on execution time and throughput. We show that the DHT and machine learning model (BioIPFS) performs better than other solutions such as uPort, ShoCard, and BBID.

    Download full text (pdf)
    fulltext
  • 44.
    Alizadeh, Morteza
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Schelén, Olov
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.
    DHT- and Blockchain-based Smart Identification for Video Conferencing2022In: Blockchain: Research and Applications, ISSN 2096-7209, Vol. 3, no 2, article id 100066Article in journal (Refereed)
    Abstract [en]

    Video conferencing applications help people communicate via the Internet and provide a significant and consistent basis for virtual meetings. However, integrity, security, identification, and authentication problems are still universal. Current video conference technologies typically rely on cloud systems to provide a stable and secure basis for executing tasks and processes. At the same time, video conferencing applications are being migrated from centralized to decentralized solutions for better performance without the need for third-party interactions. This article demonstrates a decentralized smart identification scheme for video conferencing applications based on biometric technology, machine learning, and a decentralized hash table combined with blockchain technology. We store users' information on a distributed hash table and transactional events on the distributed ledger after identifying users by implementing machine learning functions. Furthermore, we leverage distributed ledger technology's immutability and traceability properties and distributed hash table unlimited storage feature to improve the system's storage capacity and immutability by evaluating three possible architectures. The experimental results show that an architecture based on blockchain and distributed hash table has better efficiency but needs a longer time to execute than the two other architectures using a centralized database.

  • 45.
    Kaiser, M Shamim
    et al.
    Institute of Information Technology, Jahangirnagar University, Savar, Dhaka, 1342, Bangladesh.
    Hossain, Mohammad Shahadat
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Department of Computer Science, Nottingham Trent University, Clifton, NG11 8NS, Nottingham, UK; Medical Technology Innovation Facility, Nottingham Trent University, NG11 8NS, Nottingham, UK.
    Mahmud, Mufti
    Department of Computer Science and Engineering, University of Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Energy-Efficient Routing for Cooperative Multi-AUV System2022In: IFAC-PapersOnLine, E-ISSN 2405-8963, Vol. 55, no 8, p. 112-116Article in journal (Refereed)
    Abstract [en]

    Underwater robots, also known as autonomous underwater vehicles (AUVs), are amazing machines that are becoming increasingly important in a variety of disciplines, including sea environment exploration, data collection (for climate change), industry, and the military. Wireless nodes and relay nodes are randomly distributed and incorrectly selected, leading to void holes. Autonomous Underwater Vehicles (AUVs) for the UWSN were explored as a solution to the problem of void holes. The selection of an energy-efficient routing path that reduces the number of void holes has been presented using a neuro-fuzzy-based cluster-head selection and a k-means-based cluster creation. The creation of energy-efficient clusters is ensured by dynamic scheduling, which is also utilized to save energy. This protocol can deal with node failures in packet transmission in a timely way because of multi-hop routing. Simulated network performance is evaluated using the NS3 (AquaSim module) simulator, which includes the performance metrics such as average energy consumption, latency and packet delivery rate as well as throughput.

    Download full text (pdf)
    fulltext
  • 46.
    Neloy, Md. Arif Istiak
    et al.
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Biswas, Anik
    BGC Trust University Bangladesh Bidyanagar, Chandanaish, Bangladesh.
    Nahar, Nazmun
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Epilepsy Detection from EEG Data Using a Hybrid CNN-LSTM Model2022In: Brain Informatics: 15th International Conference, BI 2022, Padua, Italy, July 15–17, 2022, Proceedings / [ed] Mufti Mahmud, Jing He, Stefano Vassanelli, André van Zundert, Ning Zhong, Springer, 2022, p. 253-263Conference paper (Refereed)
    Abstract [en]

    ‘An epileptic seizure’, a neurological disorder, occurs when electric burst travel over the brain, causing the person to lose control or consciousness. Anticipating epilepsy when the event happen is beneficial for epileptic control with medication or neurological pre-surgical planning. To detect epilepsy using electroencephalogram (EEG) data, machine learning and computational approaches are applied. Because of their better categorization skills, deep learning (DL) and machine learning (ML) approaches have recently been applied in the automated identification of epileptic events. ML and DL models can reliably diagnose diverse seizure disorders from vast EEG data and supply relevant findings for neurologists. To detect epilepsy, we developed a hybrid network that combines a ‘Convolutional Neural Network (CNN)’ and a ‘Long Term Short Term Memory (LSTM)’. Our dataset is divided into two categories: epilepsy and normal. CNN-LSTM has been used to train our algorithm. With the Adam optimizer, our proposed CNN-LSTM model achieves 94.98% training accuracy and 82.21% validation accuracy. We also evaluate our results to those of machine learning methods such as Decision Tree, Logistic Regression and Naive Bayes. The comparative results clearly reveal that our suggested CNN-LSTM classifier outperforms the other learners.

  • 47.
    Ahmed, Mumtahina
    et al.
    Department of Computer Science and Engineering, Port City International University, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Islam, Raihan Ul
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Explainable Text Classification Model for COVID-19 Fake News Detection2022In: Journal of Internet Services and Information Security (JISIS), ISSN 2182-2069, E-ISSN 2182-2077, Vol. 12, no 2, p. 51-69Article in journal (Refereed)
    Abstract [en]

    Artificial intelligence has achieved notable advances across many applications, and the field is recently concerned with developing novel methods to explain machine learning models. Deep neural networks deliver the best performance accuracy in different domains, such as text categorization, image classification, and speech recognition. Since the neural network models are black-box types, they lack transparency and explainability in predicting results. During the COVID-19 pandemic, Fake News Detection is a challenging research problem as it endangers the lives of many online users by providing misinformation. Therefore, the transparency and explainability of COVID-19 fake news classification are necessary for building the trustworthiness of model prediction. We proposed an integrated LIME-BiLSTM model where BiLSTM assures classification accuracy, and LIME ensures transparency and explainability. In this integrated model, since LIME behaves similarly to the original model and explains the prediction, the proposed model becomes comprehensible. The performance of this model in terms of explainability is measured by using Kendall’s tau correlation coefficient. We also employ several machine learning models and provide a comparison of their performances. Therefore, we analyzed and compared the computation overhead of our proposed model with the other methods because the model takes the integrated strategy.

  • 48.
    Rezoana, Noortaz
    et al.
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Face Mask Detection in the Era of COVID-19: A CNN-Based Approach2022In: Proceedings of the Third International Conference on Trends in Computational and Cognitive Engineering: TCCE 2021 / [ed] M. Shamim Kaiser; Kanad Ray; Anirban Bandyopadhyay; Kavikumar Jacob; Kek Sie Long, Springer Nature, 2022, p. 3-15Conference paper (Refereed)
  • 49.
    Hossain, Emam
    et al.
    Department of Information Systems, University of Maryland Baltimore County, USA.
    Hossain, Mohammad Shahadat
    Department of Computer Science and Engineering, University of Chittagong, Bangladesh.
    Zander, Pär-Ola
    Department of Learning and Philosophy, Aalborg University, Aalborg, Denmark.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Machine learning with Belief Rule-Based Expert Systems to predict stock price movements2022In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 206, article id 117706Article in journal (Refereed)
    Abstract [en]

    Price prediction of financial assets has been a key interest for researchers over the decades. Numerous techniques to predict the price movements have been developed by the researchers over the years. But a model loses its credibility once a large number of traders start using the same technique. Therefore, the traders are in continuous search of new and efficient prediction techniques. In this research, we propose a novel machine learning technique using technical analysis with Belief Rule-Based Expert System (BRBES), and incorporating the concept of Bollinger Band to forecast stock price in the next five days. A Bollinger Event is triggered when the closing price of the stock goes down the Lower Bollinger Band. The BRBES approach has never been applied to stock markets, despite its potential and the appetite of the financial markets for expert systems. We predict the price movement of the Swedish company TELIA as a proof of concept. The knowledge base of the initial BRBES is constructed by simulating the historical data and then the learning parameters are optimized using MATLAB’s fmincon function. We evaluate the performance of the trained BRBES in terms of Accuracy, Area Under ROC Curve, Root Mean Squared Error, type I error, type II error,  value, and profit/loss ratio. We compare our proposed model against a similar rule-based technique, Adaptive Neuro-Fuzzy Inference System (ANFIS), to understand the significance of the improved rule base of BRBES. We also compare the performance against Support Vector Machine (SVM), one of the most popular machine learning techniques, and a simple heuristic model. Finally, the trained BRBES is compared against recent state-of-the-art deep learning approaches to show how competitive the performance of our proposed model is. The results show that the trained BRBES produces better performance than the non-trained BRBES, ANFIS, SVM, and the heuristic approaches. Also, it indicates better or competitive performance against the deep learning approaches. Thus BRBES exhibits its potential in predicting financial asset price movement.

  • 50.
    Nahar, Nazmun
    et al.
    Noakhali Science and Technology University, Noakhali, Bangladesh.
    Hossain, Mohammad Shahadat
    University of Chittagong University-4331, Chittagong, Bangladesh.
    Andersson, Karl
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Medical Image Analysis Using Machine Learning and Deep Learning: A Comprehensive Review2022In: Rhythms in Healthcare / [ed] M. Shamim Kaiser; Mufti Mahmud; Shamim Al Mamun, Springer Nature, 2022, p. 147-161Chapter in book (Other academic)
    Abstract [en]

    Medical imaging is essential in a variety of medical applications, like medical treatments had been used for early identification, tracking, prognosis, and diagnosis testing of different medical problems. Machine learning is critical in the field of image processing and computer vision. Machine learning (ML) techniques are used to analyze information from visual data in problems ranging from image segmentation and registration to formation, object classification, and scene understanding. Deep learning (DL) is being used to analyze medical images, which is a growing field. DL methodologies and their applications to computer-aided diagnosis involve standard machine learning techniques in the field of computer vision, deep learning ML models, and applications to medical image processing. Many of the most recent machine learning technologies in computer-aided diagnosis and medical image processing are the classification of objects such as lesions into specific classes associated with the input attributes such as contrast and area acquired from segmented object classes. Theoretically, an artificial neural network is influenced by neural structures. The Neocognitron, CNNs, and neural filters all are significant deep learning techniques. Image-based machine learning, which includes deep learning, is a useful and high-performing technology. In the upcoming years, deep learning will become the standard technology for medical image analysis. We present a review of recent machine learning and deep learning approaches for detecting four diseases, including tuberculosis, lung cancer, pneumonia, and COVID-19, in this study. We review the disease which are detected and classified from X-ray images. We intend to explore the most accurate technique for detecting various diseases as part of this study, which will be useful in the future.

12345 1 - 50 of 242
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf