Deep Learning of Micro-Doppler Features for Aided and Unaided Gait Recognition

Date

2017-01-01

Author

Seyfioglu, Mehmet Saygin
Gurbuz, Sevgi Zubeyde
Ozbayoglu, Ahmet Murat
Yüksel Turgut, Ayşe Melda

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

37
views

0
downloads

Remote health monitoring is a topic that has gained increased interest as a way to improve the quality and reduce costs of health care, especially for the elderly. Falling is one of the leading causes for injury and death among the elderly, and gait recognition can be used to detect and monitor neuromuscular diseases as well as emergency events such as heart attack and seizures. In this work, the potential for radar to discriminate a large number of classes of human aided and unaided motion is demonstrated. Deep learning of micro-Doppler features is used with a 3-layer auto-encoder structure to achieve 89% correct classification, a 17% improvement in performance over the benchmark support vector machine classifier supplied with 127 pre-defined features.

Subject Keywords

micro-Doppler classification, radar, deep learning, CLASSIFICATION

URI

https://hdl.handle.net/11511/96636

DOI

https://doi.org/10.1109/radar.2017.7944373

Conference Name

IEEE Radar Conference (RadarConf)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy Ali, Sharib; et. al. (2021-05-01) The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identif...
A Knowledge Based Search Tool for Performance Measures in Health Care Systems Beyan, Oya D.; Baykal, Nazife (2012-02-01) Performance measurement is vital for improving the health care systems. However, we are still far from having accepted performance measurement models. Researchers and developers are seeking comparable performance indicators. We developed an intelligent search tool to identify appropriate measures for specific requirements by matching diverse care settings. We reviewed the literature and analyzed 229 performance measurement studies published after 2000. These studies are evaluated with an original theoretica...
A cross-sectional investigation of acceptance of health information technology: A nationwide survey of community pharmacists in Turkey Sezgin, Emre; Özkan Yıldırım, Sevgi (2016-11-01) Background: Health information technologies have become vital to health care services. In that regard, successful use of information technologies in pharmaceutical services is important to manage, control and maintain pharmaceutical transactions, which increase the quality of health care delivery.
Achieving Clinical Statement Interoperability Using R-MIM and Archetype-Based Semantic Transformations Kılıç, Özgün Ozan (2009-07-01) Effective use of electronic healthcare records (EHRs) has the potential to positively influence both the quality and the cost of health care. Consequently, sharing patient's EHRs is becoming a global priority in the healthcare information technology domain. This paper addresses the interoperability of EHR structure and content. It describes how two different EHR standards derived from the same reference information model (RIM) can be mapped to each other by using archetypes, refined message information mode...
An agent-based alert distribution system for intelligent healthcare monitoring Akçay, Buğrahan; Doğaç, Asuman; Department of Computer Engineering (2006) With the high-level developments in the information technologies, there is a big movement in the e-health area both to give better healthcare services and to reduce cost. Monitoring the patients from their home location is one of the important branches of e-health with the aging societies. In this work, an agentbased alert system is introduced which analyzes the alert message requests and sends the alert messages within the appropriate structure and communication channel to the related healthcare user. A gu...

Citation Formats

M. S. Seyfioglu, S. Z. Gurbuz, A. M. Ozbayoglu, and A. M. Yüksel Turgut, “Deep Learning of Micro-Doppler Features for Aided and Unaided Gait Recognition,” presented at the IEEE Radar Conference (RadarConf), Washington, Amerika Birleşik Devletleri, 2017, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/96636.