Machine Learning Techniques for Anomaly Detection in Smart Healthcare

Kavitha, M.; Srinivas, P V V S; Kalyampudi, P. S. Latha; F, Choragudi S.; Srinivasulu, Singaraju

doi:10.1109/icirca51532.2021.9544795

Cited by 12 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, it employs best practices when scaling to large datasets, fast clustering of categorical data, and the number of clusterings is known [70]. The researchers in [72] used K-medoids to detect anomalies in smart healthcare.…”

Section: K-medoidsmentioning

confidence: 99%

A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges

Rahman

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

Recently, various sophisticated methods, including machine learning and artificial intelligence, have been employed to examine health-related data. Medical professionals are acquiring enhanced diagnostic and treatment abilities by utilizing machine learning applications in the healthcare domain. Medical data have been used by many researchers to detect diseases and identify patterns. In the current literature, there are very few studies that address machine learning algorithms to improve healthcare data accuracy and efficiency. We examined the effectiveness of machine learning algorithms in improving time series healthcare metrics for heart rate data transmission (accuracy and efficiency). In this paper, we reviewed several machine learning algorithms in healthcare applications. After a comprehensive overview and investigation of supervised and unsupervised machine learning algorithms, we also demonstrated time series tasks based on past values (along with reviewing their feasibility for both small and large datasets).

show abstract

Section: K-medoidsmentioning

confidence: 99%

A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges

Rahman

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Thus, security in the B5G network focuses on supreme-built-in encryption (security as software); versatile security systems (AI-based security and applying AI in cybersecurity); and various manufactured based-automation (security automation) [88]. This has resulted in the development of various AI-based intrusion detection systems for wearable devices [89]- [92]. It also ensures data confidentiality and privacy is maintained in wearable devices resulting in increase in the trustworthiness and reliability of the end-users in the system.…”

Section: B Smartnessmentioning

confidence: 99%

Key Wearable Device Technologies Parameters for Innovative Healthcare Delivery in B5G Network: A Review

et al. 2022

View full text Add to dashboard Cite

The future of healthcare relies heavily on the connection of humans to intelligent devices via communication networks for rapid medical response. Hence, the evaluation of the performance of smart wearable devices as veritable tools for prompt, pervasive, and proactive healthcare delivery to end-users in response to socio-economic dynamics is imperative especially as 5G unwinds and B5G emerges. Despite the boom in the wearable market and significant improvement in communication technologies, the translation of wearable data from clinical trials to valuable assets for practical medical application is burdened with varying challenges. This review provides an introspective analysis of the performance of unobtrusive wearable devices based on identified key performance indicators (KPIs) in relation to evolving generation networks in achieving innovative health care delivery. A total of 2751 articles pooled from 5 digital libraries were screened and 16 were selected for this review using PRISMA. The identified E-DISC wearable KPIs; energy efficiency, discretization, intelligence, secured network, and customizable standards are currently engrossed with both reliability and real-time issues that undermine its performance, perceptibility, and acceptability by end-users. The transformation of smart wearable devices' data from clinical trials into intangible resources for medical application is the fulcrum of innovative healthcare actualization. Further insight on how the identified challenges can be streamlined for smooth device alignment and transition to the emerging B5G network and its eco-friendly environment is also discussed. It is hoped that this will serve as a rallying point for research direction in translating prospective wearable solutions into a valuable resource for actualizing p-health.

show abstract

A Comparative Analysis of Anomaly Detection Methods for Predictive Maintenance in SME

Qasim¹,

Khan

Mehmood

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Machine Learning Techniques for Anomaly Detection in Smart Healthcare

Cited by 12 publications

References 17 publications

A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges

A Comprehensive Review on Machine Learning in Healthcare Industry: Classification, Restrictions, Opportunities and Challenges

Key Wearable Device Technologies Parameters for Innovative Healthcare Delivery in B5G Network: A Review

A Comparative Analysis of Anomaly Detection Methods for Predictive Maintenance in SME

Contact Info

Product

Resources

About