1
|
Cherian J, Ray S, Taele P, Koh JI, Hammond T. Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition. SENSORS (BASEL, SWITZERLAND) 2024; 24:3898. [PMID: 38931682 PMCID: PMC11207638 DOI: 10.3390/s24123898] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/10/2024] [Revised: 06/07/2024] [Accepted: 06/13/2024] [Indexed: 06/28/2024]
Abstract
Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.
Collapse
Affiliation(s)
| | | | | | | | - Tracy Hammond
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA; (S.R.); (P.T.); (J.I.K.)
| |
Collapse
|
2
|
Context-Aware Edge-Based AI Models for Wireless Sensor Networks-An Overview. SENSORS 2022; 22:s22155544. [PMID: 35898044 PMCID: PMC9371178 DOI: 10.3390/s22155544] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 06/25/2022] [Accepted: 07/05/2022] [Indexed: 02/04/2023]
Abstract
Recent advances in sensor technology are expected to lead to a greater use of wireless sensor networks (WSNs) in industry, logistics, healthcare, etc. On the other hand, advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are becoming dominant solutions for processing large amounts of data from edge-synthesized heterogeneous sensors and drawing accurate conclusions with better understanding of the situation. Integration of the two areas WSN and AI has resulted in more accurate measurements, context-aware analysis and prediction useful for smart sensing applications. In this paper, a comprehensive overview of the latest developments in context-aware intelligent systems using sensor technology is provided. In addition, it also discusses the areas in which they are used, related challenges, motivations for adopting AI solutions, focusing on edge computing, i.e., sensor and AI techniques, along with analysis of existing research gaps. Another contribution of this study is the use of a semantic-aware approach to extract survey-relevant subjects. The latter specifically identifies eleven main research topics supported by the articles included in the work. These are analyzed from various angles to answer five main research questions. Finally, potential future research directions are also discussed.
Collapse
|
3
|
Samyoun S, Stankovic J. VoiceCare: A Voice-Interactive Cognitive Assistant on a Smartwatch for Monitoring and Assisting Daily Healthcare Activities. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2022; 2022:2438-2441. [PMID: 36086037 DOI: 10.1109/embc48229.2022.9871747] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Following several health activities in daily life (e.g., medication/exercise plans, handwashing, physiological monitoring) properly often requires monitoring and assistance support. Although the emergent smartwatch and wearable technologies have opened great opportunities to monitor these activities in the wild, existing smartwatch-based systems do not interactively guide the user and also lacks comprehensiveness to provide knowledge related to this set of daily activities. To overcome these limitations of the state-of-the-art, we present Voice Care, a wearable cognitive assistant on a smartwatch for daily life healthcare that interactively assists the user and monitors adherence to these activities. We conduct an extensive user study and thorough evaluation on collected data to show that VoiceCare effectively brings multiple health sensing solutions into one system while operating with minimal resource usage and helps improve the user conformance to daily health.
Collapse
|
5
|
Pandey R, Gautam V, Pal R, Bandhey H, Dhingra LS, Misra V, Sharma H, Jain C, Bhagat K, Arushi, Patel L, Agarwal M, Agrawal S, Jalan R, Wadhwa A, Garg A, Agrawal Y, Rana B, Kumaraguru P, Sethi T. A machine learning application for raising WASH awareness in the times of COVID-19 pandemic. Sci Rep 2022; 12:810. [PMID: 35039533 PMCID: PMC8764038 DOI: 10.1038/s41598-021-03869-6] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2021] [Accepted: 10/19/2021] [Indexed: 12/27/2022] Open
Abstract
The COVID-19 pandemic has revealed the power of internet disinformation in influencing global health. The deluge of information travels faster than the epidemic itself and is a threat to the health of millions across the globe. Health apps need to leverage machine learning for delivering the right information while constantly learning misinformation trends and deliver these effectively in vernacular languages in order to combat the infodemic at the grassroot levels in the general public. Our application, WashKaro, is a multi-pronged intervention that uses conversational Artificial Intelligence (AI), machine translation, and natural language processing to combat misinformation (NLP). WashKaro uses AI to provide accurate information matched against WHO recommendations and delivered in an understandable format in local languages. The primary aim of this study was to assess the use of neural models for text summarization and machine learning for delivering WHO matched COVID-19 information to mitigate the misinfodemic. The secondary aim of this study was to develop a symptom assessment tool and segmentation insights for improving the delivery of information. A total of 5026 people downloaded the app during the study window; among those, 1545 were actively engaged users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot "Satya" increased thus proving the usefulness of a mHealth platform to mitigate health misinformation. We conclude that a machine learning application delivering bite-sized vernacular audios and conversational AI is a practical approach to mitigate health misinformation.
Collapse
Affiliation(s)
- Rohan Pandey
- Shiv Nadar University, Noida, Uttar Pradesh, India
| | | | - Ridam Pal
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Harsh Bandhey
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Lovedeep Singh Dhingra
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India.,All India Institute of Medical Sciences, New Delhi, India
| | - Vihaan Misra
- Netaji Subhas University of Technology, Dwarka, New Delhi, India
| | - Himanshu Sharma
- GL Bajaj Institute of Tech and Management, Greater Noida, Uttar Pradesh, India
| | - Chirag Jain
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Kanav Bhagat
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Arushi
- All India Institute of Medical Sciences, New Delhi, India
| | - Lajjaben Patel
- All India Institute of Medical Sciences, New Delhi, India
| | - Mudit Agarwal
- All India Institute of Medical Sciences, New Delhi, India
| | | | - Rishabh Jalan
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Akshat Wadhwa
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Ayush Garg
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Yashwin Agrawal
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Bhavika Rana
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Ponnurangam Kumaraguru
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India
| | - Tavpritesh Sethi
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, Okhla Industrial Estate, Phase III, New Delhi, 110020, India.
| |
Collapse
|
6
|
Zhang Y, Xue T, Liu Z, Chen W, Vanrumste B. Detecting hand washing activity among activities of daily living and classification of WHO hand washing techniques using wearable devices and machine learning algorithms. Healthc Technol Lett 2021; 8:148-158. [PMID: 34938571 PMCID: PMC8667567 DOI: 10.1049/htl2.12018] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2021] [Revised: 10/29/2021] [Accepted: 10/30/2021] [Indexed: 01/09/2023] Open
Abstract
During COVID-19, awareness of proper hand washing has increased significantly. It is critical that people learn the correct hand washing techniques and adopt good hand washing habits. Hence, this study proposes using wearable devices to detect hand washing activity among other daily living activities (ADLs) and classify steps proposed by the World Health Organization (WHO). Two experiments were conducted with 16 participants, aged from 20 to 31. The first experiment was hand washing following WHO regulation (ten participants), and the second experiment was performing eight ADLs (eight participants). All participants wore two wearable devices equipped with accelerometers and gyroscopes; one on each wrist. Four machine learning classifiers were compared in classifying hand washing steps in the leave-one-subject-out (LOSO) mode. The SVM model with Gaussian kernel achieved the best performance in classifying 11 washing hands steps, with an average F1-score of 0.8501. When detected among the other ADLs, hand washing following WHO regulation obtained the F1-score of 0.9871. The study demonstrates that wearable devices are feasible to detect hand washing activity and the hand washing techniques as well. The classification results of getting the soap and rubbing thumbs are low, which will be the main focus in the future study.
Collapse
Affiliation(s)
- Yiyuan Zhang
- e‐Media Research LabKU LeuvenLeuvenBelgium
- STADIUS, Department of Electrical EngineeringKU LeuvenLeuvenBelgium
| | | | | | - Wei Chen
- Center for Intelligent Medical Electronics, School of Information Science and TechnologyFudan UniversityShanghaiChina
| | - Bart Vanrumste
- e‐Media Research LabKU LeuvenLeuvenBelgium
- STADIUS, Department of Electrical EngineeringKU LeuvenLeuvenBelgium
| |
Collapse
|
7
|
Gasteiger N, Dowding D, Ali SM, Scott AJS, Wilson P, van der Veer SN. Sticky apps, not sticky hands: A systematic review and content synthesis of hand hygiene mobile apps. J Am Med Inform Assoc 2021; 28:2027-2038. [PMID: 34180527 PMCID: PMC8363789 DOI: 10.1093/jamia/ocab094] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 04/29/2021] [Accepted: 05/05/2021] [Indexed: 12/15/2022] Open
Abstract
OBJECTIVE The study sought to identify smartphone apps that support hand hygiene practice and to assess their content, technical and functional features, and quality. A secondary objective was to make design and research recommendations for future apps. MATERIALS AND METHODS We searched the UK Google Play and Apple App stores for hand hygiene smartphone apps aimed at adults. Information regarding content, technical and functional features was extracted and summarized. Two raters evaluated each app, using the IMS Institute for Healthcare Informatics functionality score and the Mobile App Rating Scale (MARS). RESULTS A total of 668 apps were identified, with 90 meeting the inclusion criteria. Most (96%) were free to download. The majority (78%) intended to educate or inform or remind users to hand wash (69%), using behavior change techniques such as personalization and prompting practice. Only 20% and 4% named a best practice guideline or had expert involvement in development, respectively. Innovative means of engagement were used in 42% (eg, virtual or augmented reality or geolocation-based reminders). Apps included an average of 2.4 out of 10 of the IMS functionality criteria (range, 0-8). The mean MARS score was 3.2 ± 0.5 out of 5, and 68% had a minimum acceptability score of 3. Two had been tested or trialed. CONCLUSIONS Although many hand hygiene apps exist, few provide content on best practice. Many did not meet the minimum acceptability criterion for quality or were formally trialed or tested. Research should assess the feasibility and effectiveness of hand hygiene apps (especially within healthcare settings), including when and how they "work." We recommend that future apps to support hand hygiene practice are developed with infection prevention and control experts and align with best practice. Robust research is needed to determine which innovative methods of engagement create "sticky" apps.
Collapse
Affiliation(s)
- Norina Gasteiger
- Division of Nursing, Midwifery and Social Work, University of Manchester, Manchester, United Kingdom
- Division of Informatics, Imaging and Data Sciences, Centre for Health Informatics, University of Manchester, Manchester, United Kingdom
- Division of Population Health, Health Services Research and Primary Care, University of Manchester, Manchester, United Kingdom
| | - Dawn Dowding
- Division of Nursing, Midwifery and Social Work, University of Manchester, Manchester, United Kingdom
| | - Syed Mustafa Ali
- Division of Informatics, Imaging and Data Sciences, Centre for Health Informatics, University of Manchester, Manchester, United Kingdom
- Centre for Epidemiology Versus Arthritis, University of Manchester, Manchester, United Kingdom
- NIHR Manchester Musculoskeletal Biomedical Research Centre, Central Manchester University Hospitals NHS Foundation Trust, Manchester, United Kingdom
| | - Ashley Jordan Stephen Scott
- Division of Nursing, Midwifery and Social Work, University of Manchester, Manchester, United Kingdom
- Division of Nursing and Midwifery, School of Human and Health Sciences, University of Huddersfield, United Kingdom
| | - Paul Wilson
- Division of Population Health, Health Services Research and Primary Care, University of Manchester, Manchester, United Kingdom
| | - Sabine N van der Veer
- Division of Informatics, Imaging and Data Sciences, Centre for Health Informatics, University of Manchester, Manchester, United Kingdom
- Manchester Academic Health Science Centre, University of Manchester, Manchester, United Kingdom
| |
Collapse
|