Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Activity Recognition and Anomaly Detection in E-Health Applications Using Color-Coded Representation and Lightweight CNN Architectures
Date
2021-01-01
Author
Yatbaz, Hakan Yekta
Ever, Enver
Yazıcı, Adnan
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
446
views
0
downloads
Cite This
Health is becoming a vital industry and human activity recognition (HAR) is one of the most popular research areas of its scope. Although there are various studies on HAR, most of them come up with complex models that are not compatible with portable and wearable devices due to their limited computing capabilities. In this study, a new approach to data representation is presented with convolutional neural network architectures for high accuracy and lightweight activity detection. An anomaly detection framework is presented, which uses ECG data for the prediction of cardiac stress activities. The novel approach to data representation and the proposed deep learning model are tested on the MHEALTH dataset with two different validation techniques for accuracy and three different complexity metrics. The experimental results show that the proposed approaches can achieve up to 96.92% and 97.06% accuracy for the HAR and cardiac stress level, respectively. In addition, the models proposed for inertial data and ECG-based prediction are lighter than the existing approaches in the literature with sizes of 0.89 MB and 1.97 MB and complexities of 0.06 and 1.04 Giga FLOPS, respectively.
URI
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85101735900&origin=inward
https://hdl.handle.net/11511/90881
Journal
IEEE Sensors Journal
DOI
https://doi.org/10.1109/jsen.2021.3061458
Collections
Department of Computer Engineering, Article
Suggestions
OpenMETU
Core
Elicitation, prioritisation, observation: a research model to inform the early design phases with child-centred perspectives
Süner, Sedef; Erbuğ, Çiğdem; Department of Industrial Design (2018)
As children have become active users of diverse range of products and systems, the study of the experiences of child-users has become a specialised field of research, especially in the field of child-computer interaction. This has led to the recognition of children as a special user group with needs and interests different than that of adults. Incorporating child-driven perspectives into early design space is vital to inform the development of design concepts which can deliver meaningful interactions. Howev...
Location recommendation for groups on location-based social networks
Teoman, Hüseyin Alper; Karagöz, Pınar; Department of Computer Engineering (2022-1-31)
In research and business areas, location-based services have become a trending subject. With the increasing popularity of social networks and online communities, group recommendation systems arise in order to support users to interact with those having similar interests, and to provide recommendations for joint activities, such as eating out as a group or seeing a movie with friends. However, the techniques and approaches to provide recommendations to groups are limited, as most of the available studies foc...
Sleep Quality Monitoring with Ambient and Mobile Sensing
KAHVECİ, ali yavuz; Alemdar, Hande; ERSOY, CEM (2015-05-19)
Evaluating daily life quality is important in ambient intelligence applications targeted for health status monitoring. When we consider the fact that people approximately spend one-third of their lives sleeping, we need to monitor the sleep quality as well as the activities of daily living in order to be able to provide a seamless health monitoring system. In this paper, a seamless activity recognition system that makes use of multi-modal wireless sensor networks (WSNs) and mobile phones is proposed. The pr...
Preserving privacy of health data residing in HL7 FHIR repositories through de-identification
Şimşek Yılgın, Ezelsu; Karagöz, Pınar; Department of Computer Engineering (2022-1-28)
Collaboration and data sharing are essential aspects of health research. Nevertheless, the number of sensitive health data breaches is increasing and there is a significant need to ensure that the privacy of patients is preserved. Health data accumulated in different repositories can be useful for statistical analysis, data mining and machine learning tasks; which results in long-term value for both healthcare professionals and patients. Preserving the privacy and ensuring the security is essential while co...
Multi-period appointment planning and scheduling in healthcare.
Bilgiç, Utku Tarık; Batun, Sakine; Department of Industrial Engineering (2019)
Appointment planning and scheduling (APS) plays a crucial role in patient service quality as well as utilization of valuable resources in healthcare. In this study, we considered the integrated problem of appointment planning and scheduling in an outpatient procedure center (OPC) over a planning horizon of multiple periods. We formulated the problem as a two-stage stochastic mixed-integer linear program (SMILP) with uncertainty in surgery durations. The first-stage problem consists of period assignment of s...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
H. Y. Yatbaz, E. Ever, and A. Yazıcı, “Activity Recognition and Anomaly Detection in E-Health Applications Using Color-Coded Representation and Lightweight CNN Architectures,”
IEEE Sensors Journal
, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85101735900&origin=inward.