Pub Date : 2024-06-28DOI: 10.1109/mprv.2024.3409014
{"title":"IEEE Computer Society Career Center","authors":"","doi":"10.1109/mprv.2024.3409014","DOIUrl":"https://doi.org/10.1109/mprv.2024.3409014","url":null,"abstract":"","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"33 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141532167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1109/mprv.2024.3383956
Lakmal Meegahapola
Xuhai “Orson” Xu: Passive sensing data from mobile and wearable devices could be used to train machine learning (ML) models that infer stress, depression, energy expenditure, and activities of daily living, among many other aspects. My research in this direction aims to address the deployability challenges of such behavior models trained with passive sensing data. My work focuses on three of them, including 1) Interpretability,1 which is about obtaining understandable human insights from the data and model. This is slightly different from the definition of interpretability in explainable artificial intelligence (XAI), where the aim is to better understand how a model works. In my work, the aim is to understand how humans behave. The idea is to extract interpretable behavior rules, such as “when X happens, Y will also happen,” that are easier for humans to understand; 2) Personalization,2 which is about making sure that our model works for each individual. The idea is that given a target user; we leverage other users whose behavior has either a very strong positive or negative correlation so that we can use these users to better predict the target user’s health outcomes; and 3) Generalizability,3 which aims to ensure that a model can work robustly across different datasets collected from populations and times. For example, a model trained from 2020 to 2023, should also work well in 2024, and a model trained in one university on the east coast of the USA, should also work in another university on the west coast. The idea is to capture something common among everyone’s behavior data so that the model can learn generalizable representations. Although everyone’s behavior patterns can be very different, they all have this fundamental property of “being continuous.” So, we define novel algorithms to capture this.
{"title":"Xuhai “Orson” Xu: “Toward Building Computational Well-Being Ecosystems”","authors":"Lakmal Meegahapola","doi":"10.1109/mprv.2024.3383956","DOIUrl":"https://doi.org/10.1109/mprv.2024.3383956","url":null,"abstract":"Xuhai “Orson” Xu: Passive sensing data from mobile and wearable devices could be used to train machine learning (ML) models that infer stress, depression, energy expenditure, and activities of daily living, among many other aspects. My research in this direction aims to address the deployability challenges of such behavior models trained with passive sensing data. My work focuses on three of them, including 1) Interpretability,1 which is about obtaining understandable human insights from the data and model. This is slightly different from the definition of interpretability in explainable artificial intelligence (XAI), where the aim is to better understand how a model works. In my work, the aim is to understand how humans behave. The idea is to extract interpretable behavior rules, such as “when X happens, Y will also happen,” that are easier for humans to understand; 2) Personalization,2 which is about making sure that our model works for each individual. The idea is that given a target user; we leverage other users whose behavior has either a very strong positive or negative correlation so that we can use these users to better predict the target user’s health outcomes; and 3) Generalizability,3 which aims to ensure that a model can work robustly across different datasets collected from populations and times. For example, a model trained from 2020 to 2023, should also work well in 2024, and a model trained in one university on the east coast of the USA, should also work in another university on the west coast. The idea is to capture something common among everyone’s behavior data so that the model can learn generalizable representations. Although everyone’s behavior patterns can be very different, they all have this fundamental property of “being continuous.” So, we define novel algorithms to capture this.","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"15 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141532172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1109/mprv.2024.3411925
{"title":"IEEE Computer Society Has You Covered!","authors":"","doi":"10.1109/mprv.2024.3411925","DOIUrl":"https://doi.org/10.1109/mprv.2024.3411925","url":null,"abstract":"","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"43 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1109/mprv.2024.3409020
{"title":"Get Published in the New IEEE Transactions on Privacy","authors":"","doi":"10.1109/mprv.2024.3409020","DOIUrl":"https://doi.org/10.1109/mprv.2024.3409020","url":null,"abstract":"","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"5 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141526786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-03DOI: 10.1109/mprv.2024.3385528
Florian Alt, Pascal Knierim, Julie Williamson, Joe Paradiso
The pervasive multiverse, an interconnected web of diverse and dynamic digital landscapes, promises to redefine our understanding of computing's reach and impact. Hereby, it extends beyond the traditional boundaries of pervasive computing: digital ecosystems seamlessly intertwine with the physical, creating an immersive and interconnected experience across devices, contexts, and users.
{"title":"The Pervasive Multiverse","authors":"Florian Alt, Pascal Knierim, Julie Williamson, Joe Paradiso","doi":"10.1109/mprv.2024.3385528","DOIUrl":"https://doi.org/10.1109/mprv.2024.3385528","url":null,"abstract":"The pervasive multiverse, an interconnected web of diverse and dynamic digital landscapes, promises to redefine our understanding of computing's reach and impact. Hereby, it extends beyond the traditional boundaries of pervasive computing: digital ecosystems seamlessly intertwine with the physical, creating an immersive and interconnected experience across devices, contexts, and users.","PeriodicalId":55021,"journal":{"name":"IEEE Pervasive Computing","volume":"13 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141252073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：