Daily life behaviour monitoring for health assessment using machine learning: bridging the gap between domains

Date

2015-02-01

Author

Alemdar, Hande
Ersoy, Cem

Metadata

Show full item record

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

Item Usage Stats

122
views

0
downloads

Analysis of human behaviour for deducing health and well-being information is one of the contemporary challenges given the ageing in place. To this end, existing and newly developed machine learning methods are needed to be evaluated using annotated real-world data sets. However, the metrics used in performance evaluation are directly taken from the machine learning domain, and they do not necessarily consider the specific needs of human behaviour analysis such as recognizing the duration, start time and frequency of the activities. Moreover, the commonly used metrics such as accuracy or F-measure can be misleading in the presence of skewed class distributions as in the case of human behaviour recognition. In this study, we evaluate the performance of two machine learning methods, hidden Markov model and time windowed neural network on five different real-world data sets through human behaviour understanding for health assessment perspective. According to the experimental results, standard metrics fail to reveal the actual performance of the two compared machine learning methods in terms of behaviour recognition. On the other hand, the proposed evaluation mechanism which considers three different activity categories leads to a more realistic evaluation of the overall performance.

Subject Keywords

Activities of daily living, Behaviour monitoring, Performance evaluation, Machine learning, Smart homes

URI

https://hdl.handle.net/11511/57676

Journal

PERSONAL AND UBIQUITOUS COMPUTING

DOI

https://doi.org/10.1007/s00779-014-0823-y

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Disability salience as an indicator of loss anxiety: an alternative explanation for the fundamental fear of human beings Atabey, Cemile Müjde; Öner Özkan, Bengi; Department of Psychology (2011) The aim of the present research was to investigate the issue of loss anxiety within the framework of disability and terror management theory. A questionnaire package was administered to 217 participants twice to examine the effects of mortality salience and disability salience. Besides mortality salience, paralysis salience was found to be effective. Highly conservative participants were becoming more conservative in the paralysis salience and mortality salience conditions. Content analysis was also conduct...
Health anxiety During COVID-19: Predictive Roles of Health Promoting Behaviors and Sensory Processing Sensitivity Güneş, Seren; Bulut, Burcu Pınar (2021-01-01) © 2022 Taylor & Francis Group, LLC.Objective: The emergence of the COVID-19 pandemic resulted in major changes in daily life and economic conditions while heightening physical and mental health problems, including health anxiety. Health authorities and elected officials have encouraged individuals to engage in health behaviors. Perceptions of and reactions to these changes could be subject to individual differences. In this line, the current study investigated the predictive roles of health promoting behavi...
Boşanma Sürecinde Psikolojik Müdahaleler Üzerine Bir Derleme Sayan Karahan, Ayşegül (ODTÜ- AYNA Klinik Psikoloji Destek Ünitesi, 2022-2) Bu derlemede boşanma sürecinde etkili uygulamalara temel oluşturmasına katkı sağlamak amacıyla psikolojik müdahaleler betimsel düzeyde ele alınmaktadır. Bir kriz durumu olan boşanmanın eşler ve varsa çocukları üzerinde olumsuz etkileri bulunmaktadır. Son yıllarda ise buna ek olarak yapıcı ve sağlıklı boşanma kavramlarından bahsedilmektedir. Boşanma oranlarındaki artış ile beraber boşanma sonrası yaşam düzenlemelerine destek ihtiyacı da artmaktadır. Ruh sağlığı alanında çalışanların boşanma sonrası uyum ile ...
Social, cognitive and emotional strategies in the grief process Aksöz Efe, İdil; Erdur Baker, Özgür; Department of Educational Sciences (2015) The purpose of this study is to examine the influence of meta-mood processes, emotion regulation strategies, ruminative responses and perceptions of social constraints of bereaved individuals on their grief process. The sample of the study consisted of 708 bereaved adults, who had an experience of loss in the last five years. The Two-Track Model of Bereavement Questionnaire, Social Constraints Scale, Trait Meta-Mood Scale, Ruminative Responses Scale and Emotion Regulation Questionnaire were administered in ...
Subjective and Relational Experiences of Young Adults with Panic Disorder: Interpretative Phenomenological Analysis Topcuoğlu, Büşra; Gençöz, Faruk; Canbolat, Fazilet; Department of Psychology (2022-7-5) The current thesis aims to examine subjective and relational experiences of young adults with panic disorder. Qualitative research method was used to gain a deeper understanding of the subjective and relational experiences of panic attacks for individuals. Semi-structured interviews were conducted with eight individuals with panic disorder, five of whom were female and three were male. Interpretive Phenomenological Analysis method was used to analyze the data. In the current thesis, six superordinate themes...

Citation Formats

H. Alemdar and C. Ersoy, “Daily life behaviour monitoring for health assessment using machine learning: bridging the gap between domains,” PERSONAL AND UBIQUITOUS COMPUTING, pp. 303–315, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/57676.