Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments最新文献_第2页

Large-Scale Self-Supervised Human Activity Recognition 大规模自监督人类活动识别

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534720

Mohammad Zaki Zadeh, Ashish Jaiswal, Hamza Reza Pavel, Aref Hebri, Rithik Kapoor, F. Makedon

引用次数: 0

Complexity management as an ethical challenge for AI-based age tech 复杂性管理是人工智能时代技术面临的伦理挑战

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534752

Giovanni Rubeis

{"title":"Complexity management as an ethical challenge for AI-based age tech","authors":"Giovanni Rubeis","doi":"10.1145/3529190.3534752","DOIUrl":"https://doi.org/10.1145/3529190.3534752","url":null,"abstract":"Assistive technologies for older adults (age tech) may support individuals in living a mostly independent life in their own home environment for as long as possible. Especially age tech based on artificial intelligence (AI)-applications may enable a personalization of health and care services and facilitate quality of life. These technologies collect and process large amounts of individual data generated in the daily life and home environment of older adults through various sensors, monitor technologies, and smart wearables. Due to their focus on individual data, these technologies may be tools for tailoring health and care services to the individual needs and benefits of older adults. However, AI-based age tech comes with ethical issues linked to complexity management, i.e. the set of technical means and strategies for dealing with complex or ambiguous data, e.g. user characteristics or behavioral data. Algorithmic standardization might thus conflict with the goal of personalization. In this paper, I identify the crucial ethics issues related to AI-based age tech. I also discuss strategies for dealing with these issues and the fundamental trade-off between complexity management and the personalization of care services through AI-based age tech","PeriodicalId":439387,"journal":{"name":"Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116922985","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

Haptic Wearable System to Assist Visually-Impaired People in Obstacle Detection 帮助视障人士检测障碍物的可穿戴触觉系统

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3529217

B. Leporini, Michele Rosellini, N. Forgione

引用次数: 3

Automated System to Measure Static Balancing in Children to Assess Executive Function 测量儿童静态平衡以评估执行功能的自动系统

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534750

Hamza Reza Pavel, Enamul Karim, Mohammad Zaki Zadeh, Ashish Jaiswal, Rithik Kapoor, F. Makedon

引用次数: 2

Simultaneous Real-Time Human Fall Detection and Reidentification Based on Multisensors Data 基于多传感器数据的实时人体跌倒检测与再识别

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534728

Matteo Bastico, Verónica Ruiz Bejerano, Alberto Belmonte-Hernández

{"title":"Simultaneous Real-Time Human Fall Detection and Reidentification Based on Multisensors Data","authors":"Matteo Bastico, Verónica Ruiz Bejerano, Alberto Belmonte-Hernández","doi":"10.1145/3529190.3534728","DOIUrl":"https://doi.org/10.1145/3529190.3534728","url":null,"abstract":"Fall detection and reidentification are active areas of research with a wide variety of applications in many fields. Nowadays, wearable devices capable of recording multisensors measurements are being increasingly introduced in people’s daily lives, such as smartphones and smartwatches. Often, these devices are used in healthcare rehabilitation scenarios to monitor patients activities and, eventually, detect important events like falls. In some cases, the equipped Inertial Measurements Unit (IMU) lacks of gyroscope and magnetometer, allowing to acquire only accelerations measures. In this conditions, the detection tasks become more complex and many false detections can arise. Additionally, other methods, such as monitoring cameras, are usually used in the environment to overcome this problem and further track the patients. But, due to the lack of personal identifiers in the camera tracking system, it is not straightforward to associate falls, when detected, to a particular person. In this paper, we propose a complete real-time system to detect falls reducing false positives and simultaneously reidentify the patients using 3D skeleton points, given by a tracking camera, and 3-axis accelerometer data. Firstly, the system performs fall detection by means of a mathematical analysis of the skeleton points evolution along different frames. At the same time, fall detection is computed on the acceleration data using a Finite State Machine approach. If a fall is detected with both mechanisms, reidentification is carried out to associate the skeleton with the wearable device. A dataset of fall sequences has been recorded and is available for testing purposes. The final accuracy of our fall detection and reidentification algorithm is 100% on our dataset.","PeriodicalId":439387,"journal":{"name":"Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129156487","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

COPD Severity Prediction in Elderly with ML Techniques 用ML技术预测老年人COPD严重程度

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534748

Elias Dritsas, Sotirios Alexiou, K. Moustakas

引用次数: 9

Learning Progression-based Automated Scoring of Visual Models 学习基于进度的视觉模型自动评分

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3529192

Ari Sagherian, Suhasini Lingaiah, M. Abouelenien, C. W. Leong, Lei Liu, Mengxuan Zhao, Blake Lafuente, Shu-Hsin Chen, Yi Qi

引用次数: 0

CareCam: Towards user-tailored Interventions at the Workplace using a Webcam CareCam:在工作场所使用网络摄像头进行用户定制干预

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3534778

Dimitri Kraft, Angelina Schmidt, Lea Büttner, F. M. Oschinsky, Fabienne Lambusch, Kristof Van Laerhoven, G. Bieber, M. Fellmann

{"title":"CareCam: Towards user-tailored Interventions at the Workplace using a Webcam","authors":"Dimitri Kraft, Angelina Schmidt, Lea Büttner, F. M. Oschinsky, Fabienne Lambusch, Kristof Van Laerhoven, G. Bieber, M. Fellmann","doi":"10.1145/3529190.3534778","DOIUrl":"https://doi.org/10.1145/3529190.3534778","url":null,"abstract":"High visual and cognitive demands characterize computer work. Therefore, preventive, health-promoting support at the workplace plays a central role in the competitiveness of companies. The evaluation of camera images, e.g. with a simple webcam, offers the possibility of gaining health-relevant data and using them for corporate health management. We, therefore, present the CareCam, a concept that can be used to record various data such as blink rate, pulse rate and upper body posture at the workplace. These data allow conclusions to be drawn about the health burden at the workplace and can be used for personalized interventions or health-promoting recommendations. However, how the collected data can best be used for interventions to minimize health risks at the VDU (Visual Display Unit) workplace in the long term has not yet been clarified. Therefore, this work outlines a basic concept for health interventions at the VDU workplace based on camera data. We utilize the facial expression, blinking rate, eye distance to screen and upper body posture to provide a targeted reminder and use their frequency as a marker to provide targeted user-tailored interventions at the workplace using a simple webcam.","PeriodicalId":439387,"journal":{"name":"Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123073862","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

Development and Evaluation of a Low-cost Wheelchair Simulator for the Haptic Rendering of Virtual Road Conditions 面向虚拟路况触觉渲染的低成本轮椅模拟器的开发与评价

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3529195

K. Ly, Pascal Karg, Julian Kreimeier, T. Götzelmann

{"title":"Development and Evaluation of a Low-cost Wheelchair Simulator for the Haptic Rendering of Virtual Road Conditions","authors":"K. Ly, Pascal Karg, Julian Kreimeier, T. Götzelmann","doi":"10.1145/3529190.3529195","DOIUrl":"https://doi.org/10.1145/3529190.3529195","url":null,"abstract":"Many streets and buildings are not accessible for wheelchair users, which impedes a major challenge for their mobility. Often, such challenges can be considered during the planning stage, which is why it is important to include this user group in the planning process. Ideally, these planning efforts should also be made visually and haptically navigable using Virtual Reality (VR) technology to allow for better imagination, accurate conclusions, and awareness of wheelchair users. This work optimizes previous approaches so that different roadway conditions can be made haptically perceptible. The proposed prototype provides a non-contact and adjustable brake for simulating inclined planes, which can be adjusted depending on personal and environmental parameters. In addition, it can simulate roads such as cobblestones using a tactile transducer. The individually optimized components were combined into a complete VR system and integrated into a virtual environment for evaluation. The qualitative and quantitative results showed that realistic simulation is possible, but further development steps towards holistic and dissemination-capable hardware and software are needed. To this end, our contribution aims to improve the long-term involvement of wheelchair users in planning processes and increase awareness of their mobility situation.","PeriodicalId":439387,"journal":{"name":"Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116101021","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: 2

Learn from the Best: Harnessing Expert Skill and Knowledge to Teach Unskilled Workers 向最好的人学习:利用专家技能和知识来教非技术工人

Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments Pub Date : 2022-06-29 DOI: 10.1145/3529190.3529203

H. Dhiman, Didarul Alam, Y. Qiao, Matthias Upmann, C. Röcker

{"title":"Learn from the Best: Harnessing Expert Skill and Knowledge to Teach Unskilled Workers","authors":"H. Dhiman, Didarul Alam, Y. Qiao, Matthias Upmann, C. Röcker","doi":"10.1145/3529190.3529203","DOIUrl":"https://doi.org/10.1145/3529190.3529203","url":null,"abstract":"Experts make complex skills look easy, but learning from experts is not only a matter of observation, but also feedback and reflection. Whereas industrial tasks in the domains of manufacturing and assembly assume a standardized work procedure supported by precision manufactured parts, several other domains where natural products are processed demand a high degree of background knowledge and skill from workers due to high within-product variability. The potential of using assistants in these domains to transfer this expert knowledge to novice workers has rarely been explored. In this paper, we explore how in the rarely studied domain of food-processing, expert know-how in accomplishing a complex task can be analyzed via state-of-the-art machine learning techniques in a multi-modal manner, so that specific features can be detected and tracked to instruct and provide feedback to beginners. We report on the performance and limitations of our approach to activity tracking and discuss its feasibility. A final review with the expert provided additional insights, which we integrated into our approach. We conclude with a summarized framework for capturing and conveying expert knowledge in the industrial domain.","PeriodicalId":439387,"journal":{"name":"Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121810581","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: 2