Victoria López, Pavel Llamocca, Diego Urgelés, Yury Jiménez, César Guevara, C. Viñals, Maria Espinosa
{"title":"Verification of the integration process of algorithms and sensor data for\u0000 mental health applications","authors":"Victoria López, Pavel Llamocca, Diego Urgelés, Yury Jiménez, César Guevara, C. Viñals, Maria Espinosa","doi":"10.54941/ahfe1004158","DOIUrl":"https://doi.org/10.54941/ahfe1004158","url":null,"abstract":"Mood disorders are becoming more frequent and, especially after the\u0000 pandemic years, the importance of analysing and preventing such disorders\u0000 has become clear. In the worst cases, people can suffer from depression or\u0000 bipolar disorder leading to hospitalization or sick leave with serious\u0000 economic and social consequences for the individual and their environment.\u0000 Thanks to the development of technology, there are increasingly useful\u0000 portable devices for monitoring individual daily activity. The data\u0000 collected is very useful for understanding not only the individual's\u0000 environment but also for characterizing their emotional profile. However,\u0000 good monitoring requires the use of a diverse set of information sources.\u0000 Medical consultations are the traditional source of information but in many\u0000 cases this information is lacking or insufficient. The new sources of\u0000 information are diverse: smart devices such as smart watches or even the\u0000 mobile phone itself, portable sensors of various types and even activity\u0000 records on social networks. All these data can be integrated and processed\u0000 in such a way that a characterization profile of behaviour related to the\u0000 emotional state of the individual is determined. However, the manufacturers\u0000 of these devices apply aggregation algorithms to the monitored data to\u0000 provide the client with a friendlier and easier to interpret version, but\u0000 they do not usually provide the raw data collected by the sensors\u0000 (accelerometer, gyroscope, temperature, etc.). There is still no regulated\u0000 standardization that obliges the manufacturer to provide the data to the\u0000 owners of the devices. Both raw data and aggregation algorithms work like a\u0000 black box in most cases. The information presented by the device\u0000 applications (generally apps) is very relevant and the interpretation of the\u0000 users has direct consequences on their behaviour (behaviour modification,\u0000 medication administration, etc.). For this reason, it is essential to verify\u0000 the algorithms used in the previous process, guaranteeing that the\u0000 information integrated (and presented) really corresponds to the information\u0000 collected by the sensors. In this paper we present a suitable system for the\u0000 verification of aggregated data from personal activity monitoring sensors.\u0000 The system includes a parsing algorithm that makes the data structure and\u0000 relates it to the output. The effectiveness of the algorithm has been tested\u0000 with real data over a period of two years and for both daytime activity and\u0000 sleep quality monitoring. The algorithm is perfectly scalable to be used on\u0000 any device, so the computer system presented can be useful for future\u0000 computer auditing of this type of process.","PeriodicalId":231376,"journal":{"name":"Human Systems Engineering and Design (IHSED 2023): Future Trends\n and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130617662","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}