Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition

Sun, Han Xu; Chen, Yu

doi:10.1109/ismict56646.2022.9828343

Cited by 15 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) The emergency alarm highly relies on the emerging artificial intelligence technology including machine learning and information fusion. Apart from the skeleton recognition algorithm [2], we need to investigate more onsite diagnosis mechanisms and integrate them into our framework to improve accuracy of identifying emergent events for senior safety.…”

Section: Discussionmentioning

confidence: 99%

“…With the unprecedented increasing of population aging and more elders living alone, seniors safety is a compelling need in healthcare systems, which necessitates 24/7 realtime monitoring and timely dangerous action recognition. Nowadays, IoMT devices like wearable sensors and optical cameras are widely used for remote safety monitoring and action recognition in personal healthcare services [2]. Utilizing digitized information, such as real-time IoMT data and electronic medical records (EMR), continuously monitoring and simulation play very important roles in seniors safety, especially for abnormal behaviors recognition, unusual activity predication and medical resource allocation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Lightweight Authentication Framework for Privacy-Preserving Virtual Health Services

Qi¹,

Xu²,

Sun³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Seniors safety is a compelling need, which necessitates 24/7 real-time monitoring and timely dangerous action recognition. Being able to mirror characteristics of physical objects (PO) to corresponding logical objects (LO) and seamlessly monitor their footprints thus detect anomaly parameters, Digital Twins (DT) has been considered a practical way to provide virtual health services for seniors safety. Meanwhile, widely adopted Internet of Medical Things (IoMT) consisting of wearable sensors and non-contact optical cameras for self and remote health data monitoring also raises concerns on information security and privacy violation. Therefore, security of POs, LOs and reliable data sharing among healthcare professionals are challenging as constructing trust and privacy-preserving virtual health services. Thanks to characteristics of decentralization, traceability and unalterability, Blockchain is promising to enhance security and privacy properties in many areas like data analysis, finance and healthcare. This paper envisions a lightweight authentication framework (LAF) to enable secure and privacy-preserving virtual healthcare services. Leveraging Non-Fungible Token (NFT) technology to tokenize LOs and data streams on blockchain, anyone can certify the authenticity of a digital LO along with its synchronized data between PO without relying on a third-party agency. In addition, the NFT-based tokenization not only allows owners fully control their IoMT devices and data, but it also enables verifiable ownership and traceable transferability during data sharing process. Moreover, NFT only contains references to encrypted raw data that are saved on off-chain storage like local files or distributed databases, such a hybrid storage strategy ensures privacy-preservation for sensitive information. A proof-of-concept prototype is implemented and tests are conducted on a case study of seniors safety. The experimental evaluation shows the feasibility and effectiveness of the proposed LAF solution.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Lightweight Authentication Framework for Privacy-Preserving Virtual Health Services

Qi¹,

Xu²,

Sun³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Human action recognition is thus the automated labelling process of human actions within a given sequence of visual frames. Due to its widespread practical applications, ranging from safety [117] to healthcare [161], particularly for COVID [95] and many other downstream tasks [32,35,94], human action recognition has historically received significant attention within the vision research community. Recent years have also seen the emergence of numerous multimodal approaches for this task, which define the research direction of Multimodal Human Action Recognition (MHAR).…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fusion for Audio-Image and Video Action Recognition

et al. 2023

View full text Add to dashboard Cite

“…Several new developments in the area of elderly surveillance are addressing the privacy concerns of the older adults. As presented in [31,32], vision-based systems are being developed where only skeletal data obtained after post processing the raw video feed are used to generate the actions and events data of those being monitored. In recent years, environmental sensors and wearables are also gaining popularity to assist the elderly in living independently and minimally obstructing their privacy and data security [33][34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Exploring Older Adults’ Willingness to Install Home Surveil-Lance Systems in Taiwan: Factors and Privacy Concerns

Wang

Lin

2023

Healthcare

View full text Add to dashboard Cite

Taiwan has a rapidly increasing aging population with a considerably high life expectancy rate, which poses challenges for healthcare and medical systems. This study examines three key factors: safety concerns, family expectations, and privacy concerns, and their influence on surveillance system installation decisions. A cross-sectional study was conducted involving a group of physically active older adults in Taiwan, using a questionnaire to collect data on the reasons for in-stalling a surveillance system and preferences for three image privacy protection techniques: blurring the face and transformation to a 2D or 3D character. The study concluded that while safety concerns and family expectations facilitate the adoption of surveillance systems, privacy concerns serve as a significant barrier. Furthermore, older adults showed a clear preference for avatar-based privacy protection methods over simpler techniques, such as blurring. The outcomes of this research will be instrumental in shaping the development of privacy-conscious home surveillance technologies, adeptly balancing safety and privacy. This understanding can pave the way for technology design that skillfully balances privacy concerns with remote monitoring quality, thereby enhancing the well-being and safety of this demographic. These results could possibly be extended to other demographics as well.

show abstract

Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition

Cited by 15 publications

References 29 publications

A Lightweight Authentication Framework for Privacy-Preserving Virtual Health Services

A Lightweight Authentication Framework for Privacy-Preserving Virtual Health Services

Multimodal Fusion for Audio-Image and Video Action Recognition

Exploring Older Adults’ Willingness to Install Home Surveil-Lance Systems in Taiwan: Factors and Privacy Concerns

Contact Info

Product

Resources

About