Using change point detection to automate daily activity segmentation. Aminikhanghahi, S. & Cook, D. J. In 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), pages 262–267, March, 2017. doi abstract bibtex Real time detection of transitions between activities based on sensor data is a valuable but somewhat untapped challenge. Detecting these transitions is useful for activity segmentation, for timing notifications or interventions, and for analyzing human behavior. In this work, we design and evaluate real time machine learning-based methods for automatic segmentation and recognition of continuous human daily activity. We detect activity transitions and integrate the change point detection algorithm with smart home activity recognition to segment human daily activities into separate actions and correctly identify each action. Experiments with on real-world smart home datasets suggest that using transition aware activity recognition algorithms lead to best performance for detecting activity boundaries and streaming activity segmentation.
@inproceedings{aminikhanghahi_using_2017,
title = {Using change point detection to automate daily activity segmentation},
doi = {10.1109/PERCOMW.2017.7917569},
abstract = {Real time detection of transitions between activities based on sensor data is a valuable but somewhat untapped challenge. Detecting these transitions is useful for activity segmentation, for timing notifications or interventions, and for analyzing human behavior. In this work, we design and evaluate real time machine learning-based methods for automatic segmentation and recognition of continuous human daily activity. We detect activity transitions and integrate the change point detection algorithm with smart home activity recognition to segment human daily activities into separate actions and correctly identify each action. Experiments with on real-world smart home datasets suggest that using transition aware activity recognition algorithms lead to best performance for detecting activity boundaries and streaming activity segmentation.},
booktitle = {2017 {IEEE} {International} {Conference} on {Pervasive} {Computing} and {Communications} {Workshops} ({PerCom} {Workshops})},
author = {Aminikhanghahi, Samaneh and Cook, Diane J.},
month = mar,
year = {2017},
keywords = {Activity Recognition, Activity recognition, Change point detection, Context, Feature extraction, Hidden Markov models, Real-time systems, Segmentation, Smart home, Smart homes},
pages = {262--267},
}
Downloads: 0
{"_id":"HdBda9BYhXpYdtLzs","bibbaseid":"aminikhanghahi-cook-usingchangepointdetectiontoautomatedailyactivitysegmentation-2017","author_short":["Aminikhanghahi, S.","Cook, D. J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Using change point detection to automate daily activity segmentation","doi":"10.1109/PERCOMW.2017.7917569","abstract":"Real time detection of transitions between activities based on sensor data is a valuable but somewhat untapped challenge. Detecting these transitions is useful for activity segmentation, for timing notifications or interventions, and for analyzing human behavior. In this work, we design and evaluate real time machine learning-based methods for automatic segmentation and recognition of continuous human daily activity. We detect activity transitions and integrate the change point detection algorithm with smart home activity recognition to segment human daily activities into separate actions and correctly identify each action. Experiments with on real-world smart home datasets suggest that using transition aware activity recognition algorithms lead to best performance for detecting activity boundaries and streaming activity segmentation.","booktitle":"2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)","author":[{"propositions":[],"lastnames":["Aminikhanghahi"],"firstnames":["Samaneh"],"suffixes":[]},{"propositions":[],"lastnames":["Cook"],"firstnames":["Diane","J."],"suffixes":[]}],"month":"March","year":"2017","keywords":"Activity Recognition, Activity recognition, Change point detection, Context, Feature extraction, Hidden Markov models, Real-time systems, Segmentation, Smart home, Smart homes","pages":"262–267","bibtex":"@inproceedings{aminikhanghahi_using_2017,\n\ttitle = {Using change point detection to automate daily activity segmentation},\n\tdoi = {10.1109/PERCOMW.2017.7917569},\n\tabstract = {Real time detection of transitions between activities based on sensor data is a valuable but somewhat untapped challenge. Detecting these transitions is useful for activity segmentation, for timing notifications or interventions, and for analyzing human behavior. In this work, we design and evaluate real time machine learning-based methods for automatic segmentation and recognition of continuous human daily activity. We detect activity transitions and integrate the change point detection algorithm with smart home activity recognition to segment human daily activities into separate actions and correctly identify each action. Experiments with on real-world smart home datasets suggest that using transition aware activity recognition algorithms lead to best performance for detecting activity boundaries and streaming activity segmentation.},\n\tbooktitle = {2017 {IEEE} {International} {Conference} on {Pervasive} {Computing} and {Communications} {Workshops} ({PerCom} {Workshops})},\n\tauthor = {Aminikhanghahi, Samaneh and Cook, Diane J.},\n\tmonth = mar,\n\tyear = {2017},\n\tkeywords = {Activity Recognition, Activity recognition, Change point detection, Context, Feature extraction, Hidden Markov models, Real-time systems, Segmentation, Smart home, Smart homes},\n\tpages = {262--267},\n}\n\n","author_short":["Aminikhanghahi, S.","Cook, D. J."],"key":"aminikhanghahi_using_2017","id":"aminikhanghahi_using_2017","bibbaseid":"aminikhanghahi-cook-usingchangepointdetectiontoautomatedailyactivitysegmentation-2017","role":"author","urls":{},"keyword":["Activity Recognition","Activity recognition","Change point detection","Context","Feature extraction","Hidden Markov models","Real-time systems","Segmentation","Smart home","Smart homes"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["activity recognition","activity recognition","change point detection","context","feature extraction","hidden markov models","real-time systems","segmentation","smart home","smart homes"],"search_terms":["using","change","point","detection","automate","daily","activity","segmentation","aminikhanghahi","cook"],"title":"Using change point detection to automate daily activity segmentation","year":2017}