Change search
Refine search result
1 - 12 of 12
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.
    Shahid, Zahraa
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Distributed Machine Learning for Anomalous Human Activity Recognition using IoT Systems2021Report (Other academic)
    Abstract [en]

    The growth of IoT-based services in homes, cities, and factories creates value for individuals, industries, and public organizations. For example, in homes, smart devices are embedded in the environment or attached to human bodies to support health monitoring systems—aging-related with different health problems, optimize energy usage, and IoT security systems. A need driven by an aging population, Sweden's elderly population is expected to increase by 45% and 87% for the two age groups, between 65–79 years and +80 years, respectively, by 2050. Older adults could be supported by developing Human Activity Recognition (HAR) techniques in smart homes based on IoT systems. Including Activity of Daily Living (ADL) and Ambient Assisted Living (AAL) applications. Advanced IoT devices and off-the-shelf sensors make it less expensive to collect sensors data. However, full deployment of such systems is challenging due to scalability, big datamanagement, and maintenance of large-scale deployments. Due to the emergence of IoT big data and various analysis tools in the last decade, AI/ML techniques utilization increased. One fundamental operation in the ML process and apparent in health monitoring systems is anomaly detection to support 1) the elderly and persons with special needs to live independently in their homes and 2) healthcare providers to reduce the pressure on them. However, most of HAR's earlierwork ignored the users’ recognized activities' privacy and security aspect. The traditional centralized approach in the ML process becomes unpractical since the data collection process conflicts with the data privacy laws in Europe, GDPR specifically. In order to enable efficient and secure services using real-world datasets collected from different application domains, we identified several research questions in this report which focuses on main areas of data science inthe context of HAR: IoT big data, centralized ML approach, FL and HAR in general, and the knowledge discovery in healthcare applications based IoT systems: (i) privacy of sensitive personal data is an essential aspect when choosing the data analysis approach and where it should be processed, (ii) methods to discover the entropy in datasets streamed from uncontrolled environments like real homes, (iii) combine offline and online training to consider changing living conditions, (iv) support multi occupants' smart homes, (v) FL implementation need to be extended to include other learning approaches such as RL, unsupervised learning, and online learning, (vi) the utilization and implementation of real-world non-IID datasets in FL. We expect that the identified challenges in this report remain a direction for future research in those mentioned above primary areas of data science.

    Download full text (pdf)
    fulltext
  • 2.
    Shahid, Zahraa
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Human Behaviour Recognition of Elderly in Single-Resident IoT Enabled Smart Homes: An Applied Machine Learning Approach2024Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    In Human Activity Recognition (HAR) systems, activities of daily living/human behaviour are recognized using sensor data by applying data mining techniques and machine learning algorithms to the collected data. This allows for customised and automated services to support humans’ daily living. Along with recognizing human behaviour, HAR can provide insights into the abnormal behaviour of individuals that might link to possible health conditions. Health monitoring applications are widely used for patients with chronic diseases, especially to give feedback to the users and promote self-awareness, for example, persons with dementia who need constant monitoring to minimize the risk of undesirable events. In developing HAR applications and services along with anomaly detection, obstacles and challenges remain that need to be addressed and motivate our research focusing on older adults living in real-world conditions. The need for care has increased, especially with the demographic developments and growing population of 65 years and over. Some of the challenges identified are installing IoT devices and sensors, collecting data and maintaining the system in an uncontrolled environment, and identifying valuable features to extract from sensors while ensuring the development of a non-intrusive and privacy-preserving system. Our research uses smart home sensors to infer ADLs (e.g., eating, sleeping, and bathroom visits) for older adults in single-resident homes. The research aims to develop and validate an anomaly detection based IoT system within HAR to support older adults in living longer independently and for the relatives (caregivers) to provide the necessary support. In addition, the system will help address the challenges of the ageing population and the increased burden on healthcare resources. This thesis identifies technologies and datasets suitable for IoT-enabled smart healthcare applications to recognize near real-time and short- and long-term behavioural changes.

    We propose to develop a life conditions model for each individual by understanding the routines and activities of daily living based on interviews with older adults and their caregivers and collecting datasets with a focus on motion sensors. The developed life condition model for each individual is used to recognize human behaviour (based on context information such as time and location) and to analyze overall behavioural change. Hence, we develop and build an anomaly detection system that preserves privacy for near real-time behavioural changes and supports large-scale deployment. Our research methodology follows a quantitative research methodology as well as a qualitative approach based on interviews. We defined activity models based on contextual information such as time and location to extract features suitable for inferring daily living activities, model behavioural patterns, and, after that, detect abnormal activities in each daily routine by utilizing motion sensors as suitable sensing devices for non-intrusive IoT enabled smart healthcare applications in single-resident homes. For example, we applied a statistical method to build a routine or habit model for each older adult. We utilized unsupervised clustering methods K-means and LOF and reinforcement learning sleeping to recognise sleep activity patterns and detect anomalies. Further, to recognise all variations of the person’s behaviour and detect short and long-term behavioural changes in older people’s daily behaviour, we applied LSTM and VAE algorithms. In addition, we developed an anomaly detection system that preserves privacy to support large-scale deployments by utilizing federated learning to build a generalizable model that learns from different persons models.

    Download full text (pdf)
    fulltext
  • 3.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Skellefteå Municipality, Sweden.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Autoencoders for Anomaly Detection in Electricity and District Heating Consumption: A Case Study in School Buildings in Sweden2023In: Proceedings - 2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe, (EEEIC / I&CPS Europe 2023), Institute of Electrical and Electronics Engineers Inc. , 2023Conference paper (Refereed)
    Abstract [en]

    Real-time anomaly detection in real-time energy consumption helps identify the technical and infrastructure issues and events that result in significant energy waste and provides the end users feedback to address the issues, which reduces drift operation costs and saves energy in the building. This study proposes deep learning reconstruction models to detect anomalies in daily energy consumption data for nine school buildings. We evaluated the performance of three proposed models, stacked RNN-LSTM autoencoder, CNN-LSTM autoencoder, and LSTM Variational Autoencoder (VAE), to learn the features of normal consumption in an unsupervised manner and detect anomalies based on reconstruction error. We used Exponential Moving Average (EMA) and static threshold to detect local and global anomalies. The experimental results demonstrate that the local CNN-LSTM autoencoder performs better than the local Stacked Autoencoder(AE), with RMSE values ranging between 8-13% for electricity and 11-19% for district heating compared to 12-17% and 15-34% resulting from AE model, respectively. Local LSTM-Variational Autoencoder (VAE) outperformed both methods, with RMSE 4-6% for electricity and 5-7% for district heating. LSTM-VAE trained model on grouped training datasets of schools with similar energy consumption and building profiles has improved the local model by lowering RMSE values to 2-3% for electricity and 3-4% in district heating.

  • 4.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Information Technology Department, Skellefteå Municipality, Skellefteå, SE.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Detecting Anomalies in Daily Activity Routines of Older Persons in Single Resident Smart Homes: Proof-of-Concept Study2022In: JMIR Aging, E-ISSN 2561-7605, Vol. 5, no 2, article id e28260Article in journal (Refereed)
    Abstract [en]

    Background: One of the main challenges of health monitoring systems is the support of older persons in living independently in their homes and with relatives. Smart homes equipped with internet of things devices can allow older persons to live longer in their homes. Previous surveys used to identify sensor-based data sets in human activity recognition systems have been limited by the use of public data set characteristics, data collected in a controlled environment, and a limited number of older participants.

    Objective: The objective of our study is to build a model that can learn the daily routines of older persons, detect deviations in daily living behavior, and notify these anomalies in near real-time to relatives.

    Methods: We extracted features from large-scale sensor data by calculating the time duration and frequency of visits. Anomalies were detected using a parametric statistical approach, unusually short or long durations being detected by estimating the mean (μ) and standard deviation (σ) over hourly time windows (80 to 355 days) for different apartments. The confidence level is at least 75% of the tested values within two (σ) from the mean. An anomaly was triggered where the actual duration was outside the limits of 2 standard deviations (μ−2σ, μ+2σ), activity nonoccurrence, or absence of activity.

    Results: The patterns detected from sensor data matched the routines self-reported by users. Our system observed approximately 1000 meals and bathroom activities and notifications sent to 9 apartments between July and August 2020. A service evaluation of received notifications showed a positive user experience, an average score of 4 being received on a 1 to 5 Likert-like scale. One was poor, two fair, three good, four very good, and five excellent. Our approach considered more than 75% of the observed meal activities were normal. This figure, in reality, was 93%, normal observed meal activities of all participants falling within 2 standard deviations of the mean.

    Conclusions: In this research, we developed, implemented, and evaluated a real-time monitoring system of older participants in an uncontrolled environment, with off-the-shelf sensors and internet of things devices being used in the homes of older persons. We also developed an SMS-based notification service and conducted user evaluations. This service acts as an extension of the health/social care services operated by the municipality of Skellefteå provided to older persons and relatives.

  • 5.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Forecasting and Detecting Anomalies in ADLs in Single-Resident Elderly Smart Homes2023In: RACS '23: Proceedings of the 2023 International Conference on Research in Adaptive and Convergent Systems, New York: Association for Computing Machinery , 2023, article id 20Conference paper (Refereed)
    Abstract [en]

    As the ageing population increases, predictive health applications for the elderly can provide opportunities for more independent living, increase cost efficiency and improve the quality of health services for senior citizens. Human activity recognition within IoT-based smart homes can enable the detection of early health risks related to mild cognitive impairment by providing proactive measurements and interventions to both the elderly and supporting healthcare givers. In this paper, we developed and evaluated a Multivariate long short-term memory (LSTM) to learn to forecast activities of daily living and detect anomalous behaviour using motion sensor data in 6 single-resident smart homes of the elderly. We use Mahalanobis distance to identify anomalies based on distance scores to build thresholds. The model's performance in terms of NMAE error values ranges between 2\% and 6\%. The experimental results show that the performance of LSTM for predicting the direct next activity versus the multiple forecasts is close. The method could identify participants' changing health conditions through the used predictive model and unsupervised anomaly detection method.

    Download full text (pdf)
    fulltext
  • 6.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Infrastructure, IT Department, Skellefteå Municipality, Sweden.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Forecasting Electricity and District Heating Consumption: A Case Study in Schools in Sweden2023In: 2023 IEEE Green Technologies Conference, GreenTech, IEEE , 2023, p. 169-175Conference paper (Refereed)
    Abstract [en]

    The growing population and demand for new public buildings contribute to increased energy consumption and greenhouse emissions. In Sweden, the largest amount of energy is consumed in school buildings, i.e., where schools form the highest number of public properties (30 million m2). In total, schools consumed 4 222 GWh of district heating and about 3 GWh of electricity for heating and other purposes in 2020. These figures lead to the realization of the need to apply effective measures to meet the European Green Deal target for 2030. Accurately forecasting energy usage is important for all stakeholders to conduct economic analysis and optimize decision-making. It is equally important in maintenance operations to allocate resources and enable the staff and students to adjust their behaviours and address the issues in buildings where peak forecasts occur. This paper develops and evaluates a power and district heating consumption for a single day and multiple days forecasting using Multivariate Recurrent Neural Network (RNN)-Long-Short term memory (LSTM) and convolutional neural networks (CNNs) and Autoencoders (AE), using daily real consumption data of six public schools provided by Skelefteå municipality in Sweden. The experimental results demonstrate that the hybrid model CNN-LSTM has achieved good accuracy compared to others, with RMSE and nRMSE error between 18%-25% and 5%-6% for electricity, respectively, and between 20%-30% RMSE and 5% nRMSE for district heating.

  • 7.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Skellefteå Municipality, Sweden.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Multi-Armed Bandits for Sleep Recognition of Elderly Living in Single-Resident Smart Homes2024In: IEEE Internet of Things Journal, ISSN 2327-4662, Vol. 11, no 3, p. 4414-4429Article in journal (Refereed)
    Abstract [en]

    Sleep is an essential activity that affects an individual’s health and ability to perform Activities of Daily Living (ADL). Inadequate sleep reduces cognitive capacity and leads to health-related issues such as cardiovascular diseases. Sleep disorders are more prevalent in older adults. Therefore, it is essential to recognize sleep patterns and support older adults and their caregivers. In our study, we collect data in real-world unconstrained and non-intrusive environments. This paper presents a novel sleep activity recognition method using motion sensors for recognizing nighttime and daytime sleep, which can further enable the development of insightful healthcare applications. The research objectives are to evaluate the application of using Multi-Armed Bandit methods to (i) learn normal sleep patterns, (ii) evaluate sleep quality, and (iii) detect anomalies in sleep activity for 11 elderly participants living in single-resident smart homes. We evaluate the performance of Thompson Sampling, Random Selection, and Upper Confidence Bound MAB methods. Thompson Sampling outperformed the other two methods. Our findings show most elderly participants slept between 6 and 8 hours with 85% sleep efficiency and up to 3 awakenings per night.

    Download full text (pdf)
    fulltext
  • 8.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Infrastructure, IT Department, Skellefteå Municipality.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Outlier Detection in IoT data for Elderly Care in Smart Homes2023In: 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC), Institute of Electrical and Electronics Engineers (IEEE), 2023, p. 1066-1073Conference paper (Refereed)
    Abstract [en]

    IoT-enabled innovative elderly healthcare facilitated by machine learning (ML) can address the challenges pertaining to the global aging population. For instance, it can enable the early detection of debilitating conditions such as Alzheimer's and dementia. This paper addresses this challenge by developing IoT and ML-based methods to recognize changes in long-term activities of daily living (ADLs) that may lead to the conditions mentioned above. In particular, we gather real-world long-term (approx. three years) data from 6 real-life single-resident elderly smart homes in Sweden, equipped with motion sensors in each room; and use unsupervised ML methods incorporating K-means clustering and local outlier factor to recognize changes in long-term behaviour efficiently. Our results have shown that K-means show similar performance in identifying outliers over all datasets while local outlier factorization fluctuates more but is more sensitive to identify small changes in living conditions. We foresee that our methods to detect long-term behaviour changes can support caregivers in carrying out their assessment for discovering the early onset of health conditions, thereby preventing further progression and providing timely treatment.

  • 9.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Recognizing Long-term Sleep Behaviour Change using Clustering for Elderly in Smart Homes2022In: 2022 IEEE International Smart Cities Conference (ISC2), IEEE, 2022Conference paper (Refereed)
    Abstract [en]

    The need for smart healthcare tools and techniques has increased due to the availability of low-cost IoT sensors and devices and the growing aging population in the world. Early detection of health conditions such as dementia and Parkinsons are important for treatment and medication. Out of the many symptoms of such health conditions, one critical behavior is sleep activity changes. In this paper, we evaluate and apply an unsupervised machine learning: K-Means, to detect changes in long-term sleep behavior in the bedroom using smart-home motion sensors installed in 6 real-life single resident elderly homes for approximately three years. Our method analyses the transformation of clusters for a participant over three years, 2019, 2020, and 2021. This is done using three features: duration of stay, the hour of the day, and duration frequency. Data clustering is used to group durations of being in the bedroom at different hours of the day. This is done to see if there is a shift in these clusters for elderly persons with healthy aging and those developing health conditions like dementia and Parkinsons. We foresee that such methods to detect long-term behavior changes can support caregivers in carrying out their assessment for discovering the early onset of health conditions, thereby preventing further progression and providing timely treatment.

  • 10.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science. Skellefteå Municipality, Sweden.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Recognizing Seasonal Sleep Patterns of Elderly in Smart Homes Using Clustering2024In: 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC), IEEE, 2024, p. 490-498Conference paper (Refereed)
  • 11.
    Shahid, Zahraa Khais
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Unsupervised Forecasting and Anomaly Detection of ADLs in single-resident elderly smart homes2023In: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, Association for Computing Machinery (ACM), 2023, p. 607-610Conference paper (Refereed)
    Abstract [en]

    As the aging population increases, predictive health applications for the elderly can provide opportunities for more independent living, increase cost efficiency and improve the quality of health services for senior citizens. Human activity recognition within IoT-based smart homes can enable detection of early health risks related to mild cognitive impairment by providing proactive measurements and interventions to both the elderly and supporting healthcare givers. In this paper, we develop and evaluate a method to forecast activities of daily living (ADL) and detect anomalous behaviour using motion sensor data from smart homes. We build a predictive Multivariate long short term memory (LSTM) model for forecasting activities and evaluate it using data from six real-world smart homes. Further, we use Mahalanobis distance to identify anomalies in user behaviors based on predictions and actual values. In all of the datasets used for forecasting both duration of stay and level of activities using duration of activeness/stillness features, the max NMAE error was about 6%, the values show that the performance of LSTM for predicting the direct next activity versus the seven coming activities are close.

  • 12.
    Shahid, Zahraa
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Saguna, Saguna
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Åhlund, Christer
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.
    Federated Learning for Unsupervised Anomaly Detection in ADLs of Elderly in Single-resident Smart Homes2024In: The 39th ACM/SIGAPP Symposium on Applied Computing (SAC ’24), April 8–12, 2024, Avila, Spain., New York, NY, USA,, 2024, p. -3Conference paper (Refereed)
    Abstract [en]

    One of the main concerns regarding the facilitation of the elderly well-being monitoring system is to preserve the participants’ privacy, enable the older adults to live longer independently, and support caregivers. Human Activity Recognition (HAR) in smart homes allows us to foresee the residents’ needs by identifying changes in behaviour that might link to possible health conditions. We propose a Federated learning (FL) model within the health monitoring application to generalize for diverse participant populations and to achieve comparable performance without disclosing the raw data to the traditional centralized approach, which raises privacy issues. In this study, we evaluate an unsupervised variational autoencoder (VAE) in centralized, individualized, compared to federated learning settings to learn the features of normal patterns of daily activities and build an anomaly detector based on reconstructed error resulting as outcomes by the trained model. Further, we validated our proposed approach on real-world datasets collected over three years from six single-resident elderly households. The individual and centralized-based learning models were used as a baseline to compare with FL. Our results show that the personalized FedAvg models achieve RMSE of about 1%, while the Global FL models achieve RMSE of approximately. 4%. The centralized model achieves RMSE of about 0.5%, and the RMSE of individual models based on local training ranges between 1% to 6%. The FL models are relatively comparable to the centralized baseline model.

1 - 12 of 12
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