Pub Date : 2017-12-01DOI: 10.1109/ICOT.2017.8336079
Zhuo Zhang, Cuntai Guan
Traditional sleep monitoring conducted in professional sleep labs and scored by sleep specialist is costly and labor intensive. Recent development of light-weight headband EEG provides possible solution for home-based sleep monitoring. This study proposed a machine learning approach for automatic sleep stage detection. A set of effective and efficient features are extracted from EEG data. The utilization of a collection of well annotated sleep data ensures the quality of learning model. A feature mapping algorithm is proposed to map the feature spaces generated from EEG data acquired through different electrodes. We collected headband EEG data for 1 hour naps in experiments conducted in our sleep lab. Preliminary result shows that sleep stages detected by proposed method are highly agreeable with the sleepiness score we obtained.
{"title":"An accurate sleep staging system with novel feature generation and auto-mapping","authors":"Zhuo Zhang, Cuntai Guan","doi":"10.1109/ICOT.2017.8336079","DOIUrl":"https://doi.org/10.1109/ICOT.2017.8336079","url":null,"abstract":"Traditional sleep monitoring conducted in professional sleep labs and scored by sleep specialist is costly and labor intensive. Recent development of light-weight headband EEG provides possible solution for home-based sleep monitoring. This study proposed a machine learning approach for automatic sleep stage detection. A set of effective and efficient features are extracted from EEG data. The utilization of a collection of well annotated sleep data ensures the quality of learning model. A feature mapping algorithm is proposed to map the feature spaces generated from EEG data acquired through different electrodes. We collected headband EEG data for 1 hour naps in experiments conducted in our sleep lab. Preliminary result shows that sleep stages detected by proposed method are highly agreeable with the sleepiness score we obtained.","PeriodicalId":297245,"journal":{"name":"2017 International Conference on Orange Technologies (ICOT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130558967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICOT.2017.8336086
Suzanne-Kae Rocknathan, Wa Thone, Yeoh Tze Xuan, Andrew Yapp Wei Rong, Anisha Roy, Deepak Alagusubramanian, Aung Aung Phyo Wai
Sleep is the most essential part of everyone's daily life. With prevalence of wearable and mobile technologies, several consumer solutions have emerged, targeting home-based sleep assessment. This study aims to investigate the performance of EEG and actigraphy devices in assessing sleep quality. Various ambient factors affecting sleep quality and usability of such wearable devices were also evaluated. The study protocol consists of an online opinion survey, subjective sleep assessment and multi-night data recording with or without white noise. From survey results, 94.2% of respondents had no prior experience in using sleep-tracking devices but 37.3% of total respondents encounter sleep problems. We collected multi-night sleep data with 18 high school student subjects. Significant correlation was found between sleep parameters and factors like naps, caffeine and stress. Playing white noise during sleep showed improvement in the occurrence and duration of deep sleep, possibly a positive effect of sound-based sleep assistance. Our analysis showed the sleep quality parameters derived from EEG are more complete and accurate than actigraphy. However, actigraphy surpassed EEG headband in usability aspects such as comfort, ease of use. Despite that, outcomes from our product design survey showed no significance difference in preference between eye-mask and wristband. We hope that our findings contribute to further development of home-based sleep solution with better usability, reliable sleep assessment, for early identification and treatment of sleep related problems.
{"title":"Empirical evaluation of consumer EEG and actigraphy devices for home-based sleep assessment","authors":"Suzanne-Kae Rocknathan, Wa Thone, Yeoh Tze Xuan, Andrew Yapp Wei Rong, Anisha Roy, Deepak Alagusubramanian, Aung Aung Phyo Wai","doi":"10.1109/ICOT.2017.8336086","DOIUrl":"https://doi.org/10.1109/ICOT.2017.8336086","url":null,"abstract":"Sleep is the most essential part of everyone's daily life. With prevalence of wearable and mobile technologies, several consumer solutions have emerged, targeting home-based sleep assessment. This study aims to investigate the performance of EEG and actigraphy devices in assessing sleep quality. Various ambient factors affecting sleep quality and usability of such wearable devices were also evaluated. The study protocol consists of an online opinion survey, subjective sleep assessment and multi-night data recording with or without white noise. From survey results, 94.2% of respondents had no prior experience in using sleep-tracking devices but 37.3% of total respondents encounter sleep problems. We collected multi-night sleep data with 18 high school student subjects. Significant correlation was found between sleep parameters and factors like naps, caffeine and stress. Playing white noise during sleep showed improvement in the occurrence and duration of deep sleep, possibly a positive effect of sound-based sleep assistance. Our analysis showed the sleep quality parameters derived from EEG are more complete and accurate than actigraphy. However, actigraphy surpassed EEG headband in usability aspects such as comfort, ease of use. Despite that, outcomes from our product design survey showed no significance difference in preference between eye-mask and wristband. We hope that our findings contribute to further development of home-based sleep solution with better usability, reliable sleep assessment, for early identification and treatment of sleep related problems.","PeriodicalId":297245,"journal":{"name":"2017 International Conference on Orange Technologies (ICOT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132326746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICOT.2017.8336089
P. Hu, ShaoZhen Ye, Liang-Chih Yu, K. R. Lai
The increasing incidence of depression has attracted increased attention to mental-health document retrieval techniques which aims to help individuals efficiently locate documents and resources relevant to their depressive problems. However, current retrieval systems generally have low accuracy. We propose combining a Valence-Arousal-based (VA-based) retrieval model and other word-based retrieval models to improve the precision of retrieval results. The VA-based retrieval model considers affective words extracted from queries, which help provide a better understanding of user queries. Experimental results demonstrate that the combined methods outperform the word-based retrieval models which adopt word-level information alone, such as vector space model and BM25 model.
{"title":"Valence-arousal analysis for mental-health document retrieval","authors":"P. Hu, ShaoZhen Ye, Liang-Chih Yu, K. R. Lai","doi":"10.1109/ICOT.2017.8336089","DOIUrl":"https://doi.org/10.1109/ICOT.2017.8336089","url":null,"abstract":"The increasing incidence of depression has attracted increased attention to mental-health document retrieval techniques which aims to help individuals efficiently locate documents and resources relevant to their depressive problems. However, current retrieval systems generally have low accuracy. We propose combining a Valence-Arousal-based (VA-based) retrieval model and other word-based retrieval models to improve the precision of retrieval results. The VA-based retrieval model considers affective words extracted from queries, which help provide a better understanding of user queries. Experimental results demonstrate that the combined methods outperform the word-based retrieval models which adopt word-level information alone, such as vector space model and BM25 model.","PeriodicalId":297245,"journal":{"name":"2017 International Conference on Orange Technologies (ICOT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126142845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}