A Review of Abnormal Behavior Detection in Activities of Daily Living

Tay, Nian Chi; Connie, Tee; Ong, Thian Song; Teoh, Andrew Beng Jin; Teh, Pin Shen

doi:10.1109/access.2023.3234974

Cited by 24 publications

(7 citation statements)

References 131 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, a support vector machine (SVM) was employed to detect falls by combining the three feature vectors. The authors of [15] presented a novel approach for fall detection, which replaces motion-based methods with a system that relies on human pixel-level recognition. In their approach, fall incidents were treated as atypical data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Mobsite,

Alaoui,

Boulmalf

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In the realm of senior care, falls remain the primary cause of hospitalization and mortality. Early detection can facilitate timely medical interventions and mitigate the associated risks. Hence, it is beneficial to set up a mechanism to identify and track such incidents. While wearable sensors are commonly used for this purpose, they may not be feasible for daily use. In contrast, surveillance cameras provide an unobtrusive and convenient monitoring solution. Despite the intricate nature of video frames, employing deep learning techniques for human recognition can enhance the performance of such systems. In our approach, activity classification is triggered only when a person is detected in the environment. We then process the extracted Global History of Motion (GHM) images with our Lightweight Deep Neural Network (LDNN). Additionally, we employ a dilated Convolution Long Short Term Memory (ConvLSTM) coupled with our LDNN to analyze the extracted sequence of monocular depth frames. Ultimately, the decision is made based on the combined information from both streams. Empirical results demonstrate the good performance of our fall detection system on the UP-Fall and UR datasets compared to the state-of-the-art. In terms of person classification, the Xception network achieved an F1-score of 98.46% on a sub-dataset derived from the COCO dataset, and 100% on the UP-Fall dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Finally, we extracted 128 feature maps from the GHM image with the size of (15,15). These maps will be combined with the output from the second stream to classify the overall activity.…”

Section: Figure 3 Motion Information Of Different Activitiesmentioning

confidence: 99%

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Mobsite,

Alaoui,

Boulmalf

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A significant number of works developed technologies in the laboratory, whereas fewer studies used commercial devices. Inertial sensors are the most common wearable elements used for HAR in AAL; in some cases, accelerometers ( Tay et al, 2023 ), gyroscopes, magnetometers, temperature and object sensors may be applied, mainly worn on the waist or the hip ( Pierleoni et al, 2019 ; Sarabia-Jácome et al, 2020 ).…”

Section: Monitoring Solutionsmentioning

confidence: 99%

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions

Guerra,

Torti,

Marenzi

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

Ambient Assisted Living is a concept that focuses on using technology to support and enhance the quality of life and well-being of frail or elderly individuals in both indoor and outdoor environments. It aims at empowering individuals to maintain their independence and autonomy while ensuring their safety and providing assistance when needed. Human Activity Recognition is widely regarded as the most popular methodology within the field of Ambient Assisted Living. Human Activity Recognition involves automatically detecting and classifying the activities performed by individuals using sensor-based systems. Researchers have employed various methodologies, utilizing wearable and/or non-wearable sensors, and employing algorithms ranging from simple threshold-based techniques to more advanced deep learning approaches. In this review, literature from the past decade is critically examined, specifically exploring the technological aspects of Human Activity Recognition in Ambient Assisted Living. An exhaustive analysis of the methodologies adopted, highlighting their strengths and weaknesses is provided. Finally, challenges encountered in the field of Human Activity Recognition for Ambient Assisted Living are thoroughly discussed. These challenges encompass issues related to data collection, model training, real-time performance, generalizability, and user acceptance. Miniaturization, unobtrusiveness, energy harvesting and communication efficiency will be the crucial factors for new wearable solutions.

show abstract

“…The method includes activity preference features such as time sequence, duration, period, and location, and uses reasoning to determine family roles such as mother, father, daughter, etc. The paper [102] provides an extensive review and comparison of abnormal human behavior recognition approaches.…”

Section: Abnormal Human Behavior Recognitionmentioning

confidence: 99%

A hybrid and context-aware framework for normal and abnormal human behavior recognition

Mojarad,

Chibani,

Attal

et al. 2023

Soft Comput

View full text Add to dashboard Cite

Human behavior recognition is one of the significant components of Ambient Assisted Living (AAL) systems and personal assistive robots allowing to improve the quality of their lives in terms of safety, autonomy, and well-being. A critical aspect of preventing dangerous situations for users, especially elderlies, is to recognize abnormal human behavior. In spite of the extensive exploration of abnormality recognition in various fields, there remain some challenges in developing effective approaches for recognizing abnormal human behaviors in AAL systems due to the limitations of data-driven and knowledge-driven approaches. In this paper, a context-aware framework combining data-driven and knowledge-driven approaches is proposed to better characterize human behaviors and recognize abnormal behaviors using commonsense reasoning while considering human behavior context. The proposed framework comprises five main modules, which leverage Long Short-Term Memory (LSTM) models and Probabilistic Answer Set Programming (PASP)-based commonsense reasoning to recognize human activities and represent abnormal human behaviors, as well as reason about those behaviors. The proposed framework is evaluated using two datasets, namely Orange4Home and UCI HAR. The obtained results indicate the capability of the proposed framework to characterize human behaviors and recognize abnormal human behaviors with high performance.

show abstract

A Review of Abnormal Behavior Detection in Activities of Daily Living

Cited by 24 publications

References 131 publications

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Activity Classification and Fall Detection Using Monocular Depth and Motion Analysis

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions

A hybrid and context-aware framework for normal and abnormal human behavior recognition

Contact Info

Product

Resources

About