Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments最新文献

筛选
英文 中文
A pipeline for automated face dataset creation from unlabeled images 从未标记的图像自动创建人脸数据集的管道
Zahra Anvari, V. Athitsos
{"title":"A pipeline for automated face dataset creation from unlabeled images","authors":"Zahra Anvari, V. Athitsos","doi":"10.1145/3316782.3321522","DOIUrl":"https://doi.org/10.1145/3316782.3321522","url":null,"abstract":"Computer vision tasks are very dataset dependent and with the emerging growth of image processing tasks and their applications, there is a huge demand for more datasets in terms of variety or size. Considering many face datasets are assembled largely manually, the process of manual dataset construction could be very time-consuming and labor intensive. In addition, some face datasets are constructed automatically over the past few years, but they are all constructed with previous knowledge of labels to some extent. In this work, we focus on automated face dataset generation from unlabeled images. We present a novel and effective pipeline for generating face datasets automatically from unlabeled and raw data for face-related tasks. We evaluated our pipeline on several datasets and it achieved a significant improvement compared to clustering-only approaches, which shows its potential towards practical solutions for automated face dataset generation.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130592609","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}
引用次数: 10
The quantified older adult as design requirements for accessible wellbeing interventions 量化的老年人作为无障碍健康干预的设计要求
Andrew R. McNeill, Miglena Campbell, L. Coventry
{"title":"The quantified older adult as design requirements for accessible wellbeing interventions","authors":"Andrew R. McNeill, Miglena Campbell, L. Coventry","doi":"10.1145/3316782.3321533","DOIUrl":"https://doi.org/10.1145/3316782.3321533","url":null,"abstract":"In this paper we describe how we engaged a group of healthy older adults in lifelogging and how we used their data to help design a healthy-aging intervention. 35 participants (mean age = 73.6, age range 59-88, Men=15, Women = 20) were tracked longitudinally for 18 months. Participants provided data at three time points. This involved the use of activity trackers, GPS trackers, and paper diaries. A number of well-established psychometric scales were also administered to gather standardised measures of health and wellbeing. While the data provides insight into the relationship between physical and social activity with regards to wellbeing, we aim to show that the nature of these relationships provide insight into how to design effective healthy-living interventions for older adults. By using the better predictors of wellbeing, we can target change in specific areas and assess change in those areas. While our sample is of relatively high-functioning older adults, we argue that understanding how they maintain wellbeing allows us to understand how to promote wellbeing amongst more inactive and frail older adults. Results showed the importance of specific types of social involvement such as meeting activity-group members and we propose that recommender systems should target these more important predictors of well-being.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125746942","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}
引用次数: 3
Fuzzy transfer learning of human activities in heterogeneous feature spaces 异质特征空间中人类活动的模糊迁移学习
D. Adama, Ahmad Lotfi, Robert Ranson
{"title":"Fuzzy transfer learning of human activities in heterogeneous feature spaces","authors":"D. Adama, Ahmad Lotfi, Robert Ranson","doi":"10.1145/3316782.3322786","DOIUrl":"https://doi.org/10.1145/3316782.3322786","url":null,"abstract":"Data-driven machine learning methods usually require large amounts of annotated data to be able to develop high performance learning systems. In practical situations, such large amounts of data are not easily obtainable. Transfer Learning evolved as one of the solutions to this challenge. It aims to make use of knowledge acquired in one domain to facilitate prediction in a target domain. Transfer learning can be a daunting task when feature spaces which require transfer differ in their distribution of information. A case of this is in the application of assisted robotics, where a robot is required to learn a task by mere observation of a human perform the task. The differences in the feature spaces poses a challenge in the effective transfer of such tasks. In this paper, we propose a method of effective transfer learning across heterogeneous feature spaces for the purpose of learning in assisted living environments. A fuzzy latent space exploration is used to obtain mappings of feature spaces. This approach is used in simplifying the learning for an assistive robot seeking to execute human actions.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131040849","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}
引用次数: 0
Spiking networks for improved cognitive abilities of edge computing devices 提高边缘计算设备认知能力的尖峰网络
Anton Akusok, Kaj-Mikael Björk, L. E. Leal, Y. Miché, Renjie Hu, A. Lendasse
{"title":"Spiking networks for improved cognitive abilities of edge computing devices","authors":"Anton Akusok, Kaj-Mikael Björk, L. E. Leal, Y. Miché, Renjie Hu, A. Lendasse","doi":"10.1145/3316782.3321546","DOIUrl":"https://doi.org/10.1145/3316782.3321546","url":null,"abstract":"This concept paper highlights a recently opened opportunity for large scale analytical algorithms to be trained directly on edge devices. Such approach is a response to the arising need of processing data generated by natural person (a human being), also known as personal data. Spiking Neural networks are the core method behind it: suitable for a low latency energy-constrained hardware, enabling local training or re-training, while not taking advantage of scalability available in the Cloud.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"18 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134122639","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}
引用次数: 3
A novel framework for physical therapy rehabilitation monitoring and assessment in Parkinson disease patients using depth information 基于深度信息的帕金森病患者物理治疗康复监测与评估新框架
Alberto Belmonte-Hernández, T. Theodoridis, M. B. González, Gustavo Hernández-Peñaloza, V. Solachidis, J. J. Ramos, Federico Álvarez, N. Vretos, L. Carrasco, P. Daras
{"title":"A novel framework for physical therapy rehabilitation monitoring and assessment in Parkinson disease patients using depth information","authors":"Alberto Belmonte-Hernández, T. Theodoridis, M. B. González, Gustavo Hernández-Peñaloza, V. Solachidis, J. J. Ramos, Federico Álvarez, N. Vretos, L. Carrasco, P. Daras","doi":"10.1145/3316782.3322759","DOIUrl":"https://doi.org/10.1145/3316782.3322759","url":null,"abstract":"Parkinson Disease (PD) is a type of neurodegenerative disease mainly characterised by the progressive declination of motor and cognitive skills. Physical therapies have been shown to be helpful to mitigate the degenerative impact of PD patients by stimulating the patient to maintain activity. However, problems associated to these therapies such as subjective evaluations or lack of accessibility, rise some barriers to professionals and related stakeholders to reach fully functional integrated healthcare systems. In this paper, a novel framework to continuously monitor and assess PD patients in their therapies is presented. This framework is composed of a sensorial system that captures movement information from patients while they perform physical rehabilitation therapies and a tool for processing this information, extracting movement patterns and providing an objective evaluation of the performed exercises. The system has been deployed and tested in a real-world environment with PD patients at different stages of the disease. The evaluation of the system underlined the added value of objective data in measuring patient movement evolution and how this helps in personalizing treatment according to patients needs.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134144624","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}
引用次数: 5
Singular race models: addressing bias and accuracy in predicting prisoner recidivism 单一种族模型:解决预测囚犯累犯的偏见和准确性
Bhanu Jain, M. Huber, L. Fegaras, R. Elmasri
{"title":"Singular race models: addressing bias and accuracy in predicting prisoner recidivism","authors":"Bhanu Jain, M. Huber, L. Fegaras, R. Elmasri","doi":"10.1145/3316782.3322787","DOIUrl":"https://doi.org/10.1145/3316782.3322787","url":null,"abstract":"As machine learning based predictive systems pervade many aspects of our lives, an inherent bias and unfairness surface from time to time in the form of mispredictions in various domains. Recidivism, the tendency of offenders to reoffend after release from prison on parole, is one such domain where one race-based sub-population has been found to be treated more harshly than others. Current practices have focused on eliminating race information from datasets to reduce the predictive bias. In contrast to this, we built Singular Race Models, a novel approach of segmenting the dataset based on race, to train and test single race-based models to increase prediction accuracy and reduce racially inspired bias by considering only one race at a time. We created Singular Race Models for four different crime categories and compared these with base models created using all crimes and all races. This modeling choice helped us increase accuracy and analyze race related discrimination. A three-layered artificial neural network was utilized to do the heavy weight-lifting of recidivism prediction. With the help of several suitable metrics, in this paper, we demonstrate the increase in predictive accuracy of these Singular Race Models in various crime categories and analyze the causes and the secondary effect on bias.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133366118","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}
引用次数: 11
A virtual and augmented reality platform for the training of first responders of the ambulance bus 一个虚拟和增强现实平台,用于培训救护车的第一响应者
G. Koutitas, K. Smith, G. Lawrence, V. Metsis, C. Stamper, Mark H. Trahan, Ted Lehr
{"title":"A virtual and augmented reality platform for the training of first responders of the ambulance bus","authors":"G. Koutitas, K. Smith, G. Lawrence, V. Metsis, C. Stamper, Mark H. Trahan, Ted Lehr","doi":"10.1145/3316782.3321542","DOIUrl":"https://doi.org/10.1145/3316782.3321542","url":null,"abstract":"AmBus is a bus-sized ambulance that EMS personnel utilize during large-scale emergencies. Although EMS personnel receive annual training, evidence shows current training efforts leave some personnel unfamiliar with the AmBus system and unprepared to respond to an emergency. This work presents a novel interactive training application, utilizing emerging technologies in virtual and augmented reality, that can be delivered remotely to the distributed EMS personnel before they assemble, or as they are assembling. Our initial findings show that such an application can better prepare first responders to be as effective as possible in using the life-saving features of the AmBus. The methodology described in this work can be expanded to include other first responders, and, ultimately, lives may be saved because personnel are better prepared.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132788095","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}
引用次数: 16
APS
H. Elsayed, M. Weigel, Julius von Willich, Markus Funk, Max Mühlhäuser
{"title":"APS","authors":"H. Elsayed, M. Weigel, Julius von Willich, Markus Funk, Max Mühlhäuser","doi":"10.1145/3316782.3324012","DOIUrl":"https://doi.org/10.1145/3316782.3324012","url":null,"abstract":"Human body postures are an important input modality for motion guidance and other application domains in HCI, e.g. games, character animations, and interaction with public displays. However, for training and guidance of body postures prior research had to define their own whole body gesture sets. Hence, the interaction designs and evaluation results are difficult to compare, due to a lack of a standardized posture set. In this work, we contribute APS (APS Posture Set), a novel posture set including 40 body postures. It is based on prior research, sports, and body language. For each identified posture, we collected 3D posture data using a Microsoft Kinect. We make the skeleton data, 3D mesh objects and SMPL data available for future research. Taken together, APS can be used to facilitate design of interfaces that use body gestures and as a reference set for future user studies and system evaluations.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"64 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114016236","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}
引用次数: 1
Wearable musical haptic sleeves for people with hearing impairment 听觉障碍人士可穿戴音乐触觉袖
Urvish Trivedi, Redwan Alqasemi, R. Dubey
{"title":"Wearable musical haptic sleeves for people with hearing impairment","authors":"Urvish Trivedi, Redwan Alqasemi, R. Dubey","doi":"10.1145/3316782.3316796","DOIUrl":"https://doi.org/10.1145/3316782.3316796","url":null,"abstract":"Music is a multi-dimensional entity and can be experienced in different forms, such as sound, vibrations or visual displays. This experience is typically confined to people without hearing impairments, but for people with hearing impairments, it can be difficult or impossible to enjoy and experience this form of art. Recent technological advancement offers some opportunities through which attempts can be made to provide musical experience to people with hearing impairment. The purpose of this research is to develop an affordable wearable haptic device for people with hearing disabilities to experience music. This device can be helpful for people with reduced hearing as well as with complete deafness. In this project, we adopt a design development strategy which is based on testing different assistive technologies and to check their efficacy to transmit musical notes into other human sensory inputs. The final prototype consists of Vibrotactile sleeves with bone conduction speakers. These sleeves provide sensory input of vibrations via bone conduction speakers. The prototype is developed based on subjects' surveys and feedback on different assistive technologies. To test our prototype, we developed a visualization system which gives visual clues that represent the given musical notes. A formal user testing with five participants suggests that this system can be used to provide the musical experience to people with hearing impairments.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114223672","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}
引用次数: 14
Acceptance and sustainability of health promotion solutions for the elderly in Taiwan: evidence from SHI-LIN elderly university in Taipei 台湾老年人健康促进方案的接受度与可持续性:来自台北世麟老年大学的证据
I. Y. Wu, Ying Yu, S. Cheng, Wei-Ju Tu, T. Sung
{"title":"Acceptance and sustainability of health promotion solutions for the elderly in Taiwan: evidence from SHI-LIN elderly university in Taipei","authors":"I. Y. Wu, Ying Yu, S. Cheng, Wei-Ju Tu, T. Sung","doi":"10.1145/3316782.3321529","DOIUrl":"https://doi.org/10.1145/3316782.3321529","url":null,"abstract":"Faced with the obvious changes in the demographic structure, governments in all countries are actively developing long-term social welfare policies in response to the impact of the ageing population. Aging issues in Taiwan is becoming serious, as Taiwan already entered into an aging society in 2018 and become one of the fast aging country in the world. In this research, following the first phase research for identifying three senior participants' group namely as \"Active Health,\" \"Confident Health\" and \"Carefree Health\" with different lifestyles, through workshop with semi-structured questionnaire, we analyze the acceptance and sustainability of three health promotion solutions, namely, S1 (10-minute exercise), S2 (smart bracelet) and S3 (health chatbot). This research found that the elderly in Group A tends to use solution 3 (health chatbot) with high acceptance and sustainability with the triggers by \"professionalism\" & \"self-demanding.\" And Group B tends to take the solution 1 (10-minute exercise) with high acceptance and sustainability triggered by \"affect\" & \"interpersonal influences.\" C Group's opinions are more widely distributed. Based on our findings from experiment on three health promotion solutions, we will continue to make the next stage research on scale testing to validate the acceptance, sustainability and triggers for better understanding the health promotion behaviors for elderly in Taiwan.","PeriodicalId":264425,"journal":{"name":"Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126979851","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}
引用次数: 3
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信