Change search
Link to record
Permanent link

Direct link
Hossain, Mohammad ShahadatORCID iD iconorcid.org/0000-0002-7473-8185
Publications (10 of 78) Show all publications
Mahmud, T., Barua, K., Habiba, S. U., Sharmen, N., Hossain, M. S. & Andersson, K. (2024). An Explainable AI Paradigm for Alzheimer’s Diagnosis Using Deep Transfer Learning. Diagnostics, 14(3), Article ID 345.
Open this publication in new window or tab >>An Explainable AI Paradigm for Alzheimer’s Diagnosis Using Deep Transfer Learning
Show others...
2024 (English)In: Diagnostics, ISSN 2075-4418, Vol. 14, no 3, article id 345Article in journal (Refereed) Published
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.

Place, publisher, year, edition, pages
Multidisciplinary Digital Publishing Institute (MDPI), 2024
Keywords
Alzheimer’s disease, explainable AI (XAI), grad-CAM, saliency maps, transfer learning
National Category
Computer Sciences
Research subject
Cyber Security
Identifiers
urn:nbn:se:ltu:diva-104357 (URN)10.3390/diagnostics14030345 (DOI)001160341800001 ()2-s2.0-85184719181 (Scopus ID)
Note

Validerad;2024;Nivå 2;2024-04-09 (marisr);

Full text licence: CC BY

Available from: 2024-02-22 Created: 2024-02-22 Last updated: 2024-04-09Bibliographically approved
Rahman, M. A., Begum, M., Mahmud, T., Hossain, M. S. & Andersson, K. (2024). Analyzing Sentiments in eLearning: A Comparative Study of Bangla and Romanized Bangla Text using Transformers. IEEE Access, 12, 89144-89162
Open this publication in new window or tab >>Analyzing Sentiments in eLearning: A Comparative Study of Bangla and Romanized Bangla Text using Transformers
Show others...
2024 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 12, p. 89144-89162Article in journal (Refereed) Published
Abstract [en]

In the modern world, learning is becoming increasingly critical due to rapid technological breakthroughs, which highlight the need for continuous skill development in both the personal and professional spheres. As a result, eLearning is a cutting-edge approach to education that delivers lessons, courses, and instructional materials remotely via digital technology and the Internet. It makes learning more flexible and accessible by enabling users to interact with teachers online and access classes or other content. Sentiment analysis is an eLearning technique that evaluates user opinions, typically via written feedback, to improve the overall quality of instruction in a course. Sentiment analysis for e-learning feedback has been extensively studied in several languages, except Bangla and Romanized Bangla. The three datasets produced were one for Bangla, one for Romanized Bangla, and one for a combination of Bangla and Romanized. Three datasets contained 3178 Bangla, 3090 Romanized Bangla, and 6268 Bangla and Romanized Bangla texts. The feedback has been divided into three categories: positive, negative, and neutral. The validation of the datasets was conducted using Krippendorff’s alpha and Cohen’s kappa metrics, ensuring the reliability and consistency of the dataset annotations. Several techniques were used to train the preprocessed datasets, including transformers, deep learning, machine learning, ensemble learning, and hybrid approaches. Transformer-based algorithms, such as XLM-RoBERTa, outperformed the others in terms of accuracy, achieving the highest values of 89.46% and 85.81% for the Bangla and Combined datasets. At 89.59%, ANN demonstrated exceptional performance on the Romanized Bangla dataset.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2024
Keywords
Accuracy, eLearning, Electronic learning, Ensemble Learning, Natural Language Processing, Reviews, Sentiment analysis, Social networking (online), Transformers, Video on demand, Web sites
National Category
Media and Communication Technology Computer Sciences
Research subject
Cyber Security
Identifiers
urn:nbn:se:ltu:diva-108307 (URN)10.1109/ACCESS.2024.3419024 (DOI)2-s2.0-85197070858 (Scopus ID)
Note

Validerad;2024;Nivå 2;2024-07-08 (joosat);

Full text: CC BY-NC-ND License;

Available from: 2024-07-08 Created: 2024-07-08 Last updated: 2024-07-08Bibliographically approved
Umme Habiba, S., Debnath, T., Islam, M. K. K., Nahar, L., Hossain, M. S., Basnin, N. & Andersson, K. (2023). Transfer Learning-Assisted DementiaNet: A Four Layer Deep CNN for Accurate Alzheimer’s Disease Detection from MRI Images. In: Yu Zhang, Hongzhi Kuai & Emily P. Stephen (Ed.), BI 2023: Brain Informatics, Proceedings: . Paper presented at 16th International Conference on Brain Informatics (BI 2023), Hoboken, NJ, United States, August 1-3, 2023 (pp. 383-394). Springer
Open this publication in new window or tab >>Transfer Learning-Assisted DementiaNet: A Four Layer Deep CNN for Accurate Alzheimer’s Disease Detection from MRI Images
Show others...
2023 (English)In: BI 2023: Brain Informatics, Proceedings / [ed] Yu Zhang, Hongzhi Kuai & Emily P. Stephen, Springer, 2023, p. 383-394Conference paper, Published 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.

Place, publisher, year, edition, pages
Springer, 2023
Series
Lecture Notes in Artificial Intelligence (Lecture Notes in Computer Science), ISSN 0302-9743, E-ISSN 1611-3349 ; 13974
Keywords
Alzheimer’s disease, Convolutional Neural Network, Data Augmentation, DementiaNet, EfficientNet, Feature Extraction, MRI, Preprocessing, Transfer Learning
National Category
Medical Image Processing Computer Sciences
Research subject
Pervasive Mobile Computing; Cyber Security
Identifiers
urn:nbn:se:ltu:diva-103371 (URN)10.1007/978-3-031-43075-6_33 (DOI)2-s2.0-85172413214 (Scopus ID)
Conference
16th International Conference on Brain Informatics (BI 2023), Hoboken, NJ, United States, August 1-3, 2023
Note

ISBN for host publication: 978-3-031-43074-9  (print), 978-3-031-43075-6 (electronic)

Available from: 2024-01-03 Created: 2024-01-03 Last updated: 2024-01-03Bibliographically approved
Kabir, S., Islam, R. U., Hossain, M. S. & Andersson, K. (2022). An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai. Code Ocean
Open this publication in new window or tab >>An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai
2022 (English)Data 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.

Place, publisher, year
Code Ocean, 2022
Keywords
Artificial Intelligence, Convolutional Neural Network, Air Quality, Expert System, Nonlinear Model Predictive Control, Uncertainty
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-93419 (URN)10.24433/CO.8230207.v1 (DOI)
Note

Code: MIT license; Data: No Rights Reserved (CC0)

Available from: 2022-10-04 Created: 2022-10-04 Last updated: 2023-09-05Bibliographically approved
Kaiser, M. S., Hossain, M. S., Mahmud, M. & Andersson, K. (2022). Energy-Efficient Routing for Cooperative Multi-AUV System. Paper presented at 6th IFAC Symposium on Telematics Applications TA 2022, Nancy, France, 15-17 June, 2022. IFAC-PapersOnLine, 55(8), 112-116
Open this publication in new window or tab >>Energy-Efficient Routing for Cooperative Multi-AUV System
2022 (English)In: IFAC-PapersOnLine, E-ISSN 2405-8963, Vol. 55, no 8, p. 112-116Article in journal (Refereed) Published
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.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Multi-hop network, sensors, artificial intelligence, autonomous underwater vehicles, routing algorithm
National Category
Computer Systems
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-92820 (URN)10.1016/j.ifacol.2022.08.019 (DOI)000852728500019 ()2-s2.0-85140083837 (Scopus ID)
Conference
6th IFAC Symposium on Telematics Applications TA 2022, Nancy, France, 15-17 June, 2022
Note

Godkänd;2022;Nivå 0;2022-09-06 (johcin);Konferensartikel i tidskrift

Available from: 2022-09-06 Created: 2022-09-06 Last updated: 2024-03-07Bibliographically approved
Raihan, S., Zisad, S. N., Islam, R. U., Hossain, M. S. & Andersson, K. (2021). A Belief Rule Base Approach to Support Comparison of Digital Speech Signal Features for Parkinson’s Disease Diagnosis. In: Mufti Mahmud, M Shamim Kaiser, Stefano Vassanelli, Qionghai Dai, Ning Zhong (Ed.), Brain Informatics: 14th International Conference, BI 2021, Virtual Event, September 17–19, 2021, Proceedings. Paper presented at 14th International Conference on Brain Informatics (BI 2021), virtual, September 17-19, 2021 (pp. 388-400). Springer
Open this publication in new window or tab >>A Belief Rule Base Approach to Support Comparison of Digital Speech Signal Features for Parkinson’s Disease Diagnosis
Show others...
2021 (English)In: Brain Informatics: 14th International Conference, BI 2021, Virtual Event, September 17–19, 2021, Proceedings / [ed] Mufti Mahmud, M Shamim Kaiser, Stefano Vassanelli, Qionghai Dai, Ning Zhong, Springer, 2021, p. 388-400Conference paper, Published paper (Refereed)
Abstract [en]

Parkinson’s disease is a neurological disorder. It affects the structures of the central and peripheral nervous system that control movement. One of the symptoms of Parkinson’s disease is difficulty in speaking. Hence, analysis of speech signal of patients may provide valuable features for diagnosing. Previous works on diagnosis based on speech data have employed machine learning and deep learning techniques. However, these approaches do not address the various uncertainties in data. Belief rule based expert system (BRBES) is an approach that can reason under various forms of data uncertainty. Thus, the main objective of this research is to compare the potential of BRBES on various speech signal features of patients of parkinson’s disease. The research took into account various types of standard speech signal features such MFCCs, TQWTs etc. A BRBES was trained on a dataset of 188 patients of parkinson’s disease and 64 healthy candidates with 5-fold cross validation. It was optimized using an exploitive version of the nature inspired optimization algorithm called BRB-based adaptive differential evolution (BRBaDE). The optimized model performed better than explorative BRBaDE, genetic algorithm and MATLAB’s FMINCON optimization on most of these features. It was also found that for speech based diagnosis of Parkinson’s disease under uncertainty, the features such as Glottis Quotient, Jitter variants, MFCCs, RPDE, DFA and PPE are relatively more suitable. 

Place, publisher, year, edition, pages
Springer, 2021
Series
Lecture Notes in Artificial Intelligence, ISSN 0302-9743, E-ISSN 1611-3349 ; 12960
Keywords
CNN, Speech emotion, RAVDESS, MFCC, Data augmentation
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-87120 (URN)10.1007/978-3-030-86993-9_35 (DOI)000768819800035 ()2-s2.0-85115862334 (Scopus ID)
Conference
14th International Conference on Brain Informatics (BI 2021), virtual, September 17-19, 2021
Note

ISBN för värdpublikation: 978-3-030-86992-2; 978-3-030-86993-9

Available from: 2021-09-20 Created: 2021-09-20 Last updated: 2023-09-05Bibliographically approved
Hossain Mazumder, S., Hossain, M. S. & Andersson, K. (2021). A Belief Rule-Based Expert System to Assess Multiple Human Reaction in the Context of Facebook Posts under Uncertainty. In: Golam Faruque, Kazi Abu Taher, M. Shamim Kaiser, Mohammed Nasir Uddin (Ed.), 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings. Paper presented at 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), Dhaka, Bangladesh, February 27-28, 2021 (pp. 389-394). IEEE
Open this publication in new window or tab >>A Belief Rule-Based Expert System to Assess Multiple Human Reaction in the Context of Facebook Posts under Uncertainty
2021 (English)In: 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD): Conference Proceedings / [ed] Golam Faruque, Kazi Abu Taher, M. Shamim Kaiser, Mohammed Nasir Uddin, IEEE, 2021, p. 389-394Conference paper, Published paper (Refereed)
Abstract [en]

Human may have multiple reactions at a time. Social media is a real-life example where people can express their reactions or opinions. For example, Facebook has become a widely used social media where users express their opinion on different posts such as status or photo post. Therefore, user opinions can easily be achieved through social media and then analyzed and applied in different practical fields. Reaction assessment of Social media can be an excellent source of information. Therefore, an accurate assessment of human reaction is a must. Facebook provides six emoticons for each of the posts of its users. The six emoticons define six types of reactions. The user, who wants to react to any post, have to choose only one of the six emoticons. There is no scope for a user to express multiple reactions at a time. Moreover, if a user selects an emoticon, then the system takes that input as 100% of that corresponding reaction, or 0% if not selected, thus the reaction assessment system becomes a Boolean system. Therefore, the assessment of multiple reactions of the user cannot be measured with 100% certainty due to the existence of various types of uncertainties such as vagueness, imprecision, randomness, ignorance, incompleteness, and ambiguity in the system. Therefore, to assess multiple human reactions, an expert system is needed to handle all these uncertainties. The system design, development process, and applications of an expert system to assess multiple human reactions are described in this paper. For the development of the expert system, the Belief Rule-Based Inference Methodology using the Evidential Reasoning (RIMER) approach has been used and the system is named as a Belief Rule-Based Expert System (BRBES). The developed BRBES can mitigate all the uncertainties mentioned above.

Place, publisher, year, edition, pages
IEEE, 2021
Keywords
Belief Rule-Base (BRB), ER, RIMER, reaction, uncertainty
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-82804 (URN)10.1109/ICICT4SD50815.2021.9397016 (DOI)2-s2.0-85104571589 (Scopus ID)
Conference
2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), Dhaka, Bangladesh, February 27-28, 2021
Note

ISBN för värdpublikation: 978-1-6654-1460-9

Available from: 2021-02-06 Created: 2021-02-06 Last updated: 2021-10-25Bibliographically approved
Progga, N. I., Rezoana, N., Hossain, M. S., Islam, R. U. & Andersson, K. (2021). A CNN Based Model for Venomous and Non-venomous Snake Classification. In: Mufti Mahmud; M. Shamim Kaiser; Nikola Kasabov; Khan Iftekharuddin; Ning Zhong (Ed.), Applied Intelligence and Informatics: First International Conference, AII 2021, Nottingham, UK, July 30–31, 2021, Proceedings. Paper presented at 1st International Conference on Applied Intelligence and Informatics (AII 2021), Nottingham, UK (online), July 30-31, 2021 (pp. 216-231). Springer
Open this publication in new window or tab >>A CNN Based Model for Venomous and Non-venomous Snake Classification
Show others...
2021 (English)In: Applied Intelligence and Informatics: First International Conference, AII 2021, Nottingham, UK, July 30–31, 2021, Proceedings / [ed] Mufti Mahmud; M. Shamim Kaiser; Nikola Kasabov; Khan Iftekharuddin; Ning Zhong, Springer, 2021, p. 216-231Conference paper, Published paper (Refereed)
Abstract [en]

Snakes are curved, limbless, warm blooded reptiles of the phylum serpents. Any characteristics, including head form, body shape, physical appearance, texture of skin and eye structure, might be used to individually identify nonvenomous and venomous snakes, that are not usual among non-experts peoples. A standard machine learning methodology has also been used to create an automated categorization of species of snake dependent upon the photograph, in which the characteristics must be manually adjusted. As a result, a Deep convolutional neural network has been proposed in this paper to classify snakes into two categories: venomous and non-venomous. A set of data of 1766 snake pictures is used to implement seven Neural network with our proposed model. The amount of photographs even has been increased by utilizing various image enhancement techniques. Ultimately, the transfer learning methodology is utilized to boost the identification process accuracy even more. Five-fold cross-validating for SGD optimizer shows that the proposed model is capable of classifying the snake images with a high accuracy of 91.30%. Without Cross validation the model shows 90.50% accuracy. 

Place, publisher, year, edition, pages
Springer, 2021
Series
Communications in Computer and Information Science, ISSN 1865-0929, E-ISSN 1865-0937 ; 1435
Keywords
Snake, CNN, Data augmentation, Deep learning, Transfer learning, Cross validation
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-86501 (URN)10.1007/978-3-030-82269-9_17 (DOI)000851326800017 ()2-s2.0-85113550559 (Scopus ID)
Conference
1st International Conference on Applied Intelligence and Informatics (AII 2021), Nottingham, UK (online), July 30-31, 2021
Note

ISBN för värdpublikation: 978-3-030-82268-2; 978-3-030-82269-9

Available from: 2021-07-30 Created: 2021-07-30 Last updated: 2023-09-05Bibliographically approved
Ilma Progga, N., Hossain, M. S. & Andersson, K. (2021). A Deep Transfer Learning Approach to Diagnose Covid-19 using X-ray Images. In: Proceedings of 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE): . Paper presented at 6th IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE 2020), Bhubaneswar, India (Virtual), December 26-27, 2020 (pp. 177-182). IEEE
Open this publication in new window or tab >>A Deep Transfer Learning Approach to Diagnose Covid-19 using X-ray Images
2021 (English)In: Proceedings of 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), IEEE, 2021, p. 177-182Conference paper, Published paper (Refereed)
Abstract [en]

The Covid-19 disease which was caused by novel coronavirus (SARS-CoV-2) has already become a great threat for humans beings. The virus is spreading rapidly around the world. Therefore, we crucially need quick diagnostic tests to identify affected patients and to minimize the spread of the virus. With the advancements of Machine Learning, the detection of Covid-19 in the early stage would facilitate taking precautions as early as possible. However, because of the lack of data-sets, especially chest X-ray images of Covid-19 affected patients, it has become challenging to detect this disease. In this paper, a deep transfer learning-based pre-trained model is named VGG16 along with adapt histogram equalization has been developed to diagnose Covid-19 by using X-ray images. An image processing technique named adaptive histogram equalization has been used to generate more images by using the existing data set. It can be observed that VGG-16 provides the highest accuracy which is 98.75% in comparison to two other pre-trained models such as VGG-19 and Mobilnenet-V2(97% accuracy for VGG-19, 92.65% accuracy for Mobilenet-V2).

Place, publisher, year, edition, pages
IEEE, 2021
Keywords
Adapt Histogram Equalization, Coronavirus, Chest X-ray, Convolutional Neural Network, Transfer Learning
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-82117 (URN)10.1109/WIECON-ECE52138.2020.9398037 (DOI)000671104100044 ()2-s2.0-85104602119 (Scopus ID)
Conference
6th IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE 2020), Bhubaneswar, India (Virtual), December 26-27, 2020
Note

ISBN för värdpublikation: 978-1-6654-1917-8, 978-0-7381-3144-3 

Available from: 2020-12-27 Created: 2020-12-27 Last updated: 2021-10-25Bibliographically approved
Hossain, E., Shariff, M. A., Hossain, M. S. & Andersson, K. (2021). A Novel Deep Learning Approach to Predict Air Quality Index. In: M. Shamim Kaiser, Anirban Bandyopadhyay, Mufti Mahmud, Kanad Ray (Ed.), Proceedings of International Conference on Trends in Computational and Cognitive Engineering: Proceedings of TCCE 2020. Paper presented at 2nd International Conference on Trends in Computational and Cognitive Engineering (TCCE 2020), 17-18 December, 2020, Dhaka, Bangladesh (pp. 367-381). Singapore: Springer
Open this publication in new window or tab >>A Novel Deep Learning Approach to Predict Air Quality Index
2021 (English)In: Proceedings of International Conference on Trends in Computational and Cognitive Engineering: Proceedings of TCCE 2020 / [ed] M. Shamim Kaiser, Anirban Bandyopadhyay, Mufti Mahmud, Kanad Ray, Singapore: Springer, 2021, p. 367-381Conference paper, Published paper (Refereed)
Abstract [en]

In accordance with the World Health Organization’s instruction, the air quality in Bangladesh is considered perilous. A productive and precise air quality index (AQI) is a must and one of the obligatory conditions for helping the society to be viable in lieu of the consequences of air contamination. If we know the index of air quality in advance, then it would be of a great help saving our health from air contamination. This study introduces an air quality index prediction model for two mostly polluted cities in Bangladesh: Dhaka and Chattogram. Gated recurrent unit (GRU), long short-term memory (LSTM) are the two robust variation of recurrent neural network (RNN). This model combines these two together. We have used GRU as first hidden layer and LSTM as the second hidden layer of the model, followed by two dense layers. After collecting and processing the data, the model was trained on 80% of the data and then validated against the remaining data. We have evaluated the performance of the model considering MSE, RMSE, and MAE to see how much error does the model produce. Results reflect that our model can follow the actual AQI trends for both cities. At last, we have juxtaposed the performance of our proposed hybrid model against a standalone GRU model and a standalone LSTM model. Results also show that combining these two models improves the overall model’s performance.

Place, publisher, year, edition, pages
Singapore: Springer, 2021
Series
Advances in Intelligent Systems and Computing, ISSN 2194-5357, E-ISSN 2194-5365 ; 1309
Keywords
Air quality index, AQI prediction, Time series analysis, Deep learning, Hybrid neural network
National Category
Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-82071 (URN)10.1007/978-981-33-4673-4_29 (DOI)2-s2.0-85098283614 (Scopus ID)
Conference
2nd International Conference on Trends in Computational and Cognitive Engineering (TCCE 2020), 17-18 December, 2020, Dhaka, Bangladesh
Note

ISBN för värdpublikation: 978-981-33-4672-7, 978-981-33-4673-4

Available from: 2020-12-19 Created: 2020-12-19 Last updated: 2021-10-25Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-7473-8185

Search in DiVA

Show all publications