Pub Date : 2010-05-20DOI: 10.1109/PERCOM.2010.5466986
M. Pijl, S. Par, Caifeng Shan
The topic of human activity modeling and recognition still provides many challenges, despite receiving considerable attention. These challenges include the large number of sensors often required for accurate activity recognition, and the need for user-specific training samples. In this paper, an approach is presented for recognition of activities of daily living (ADL) using only a single camera and microphone as sensors. Scene analysis techniques are used to classify audio and video events, which are used to model a set of activities using hidden Markov models. Data was obtained through recordings of 8 participants. The events generated by scene analysis algorithms are compared to events obtained through manual annotation. In addition, several model parameter estimation techniques are compared. In a number of experiments, it is shown that if activities are fully observed these models yield a class accuracy of 97% on annotated data, and 94% on scene analysis data. Using a sliding window approach to classify activities in progress yields a class accuracy of 79% on annotated data, and 73% on scene analysis data. It is also shown that a multi-modal approach yields superior results compared to either individual modality on scene analysis data. Finally, it can be concluded the created models perform well even across participants.
{"title":"An event-based approach to multi-modal activity modeling and recognition","authors":"M. Pijl, S. Par, Caifeng Shan","doi":"10.1109/PERCOM.2010.5466986","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466986","url":null,"abstract":"The topic of human activity modeling and recognition still provides many challenges, despite receiving considerable attention. These challenges include the large number of sensors often required for accurate activity recognition, and the need for user-specific training samples. In this paper, an approach is presented for recognition of activities of daily living (ADL) using only a single camera and microphone as sensors. Scene analysis techniques are used to classify audio and video events, which are used to model a set of activities using hidden Markov models. Data was obtained through recordings of 8 participants. The events generated by scene analysis algorithms are compared to events obtained through manual annotation. In addition, several model parameter estimation techniques are compared. In a number of experiments, it is shown that if activities are fully observed these models yield a class accuracy of 97% on annotated data, and 94% on scene analysis data. Using a sliding window approach to classify activities in progress yields a class accuracy of 79% on annotated data, and 73% on scene analysis data. It is also shown that a multi-modal approach yields superior results compared to either individual modality on scene analysis data. Finally, it can be concluded the created models perform well even across participants.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123082428","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 : 2010-05-20DOI: 10.1109/PERCOM.2010.5466977
Lu Han, Stephen Smaldone, P. Shankar, James Boyce, L. Iftode
People waste many hours driving each day. Although unavoidable, this time can be very boring to motorists. Similar to people taking mass transit who often pass the time socializing with those around them, motorists could benefit from social interactions if they were given broader social opportunities. Unfortunately, existing Multiparty Voice Communication (MVC) systems do not scale to large numbers of users and do not provide adequate access controls. We present RoadSpeak, a scalable MVC system that allows motorists to automatically join Voice Chat Groups (VCGs) along popular roadways. RoadSpeak achieves interruption-free communication through the use of voice chat message buffering, flow control and in-order delivery of voice messages to participants. We have implemented a RoadSpeak prototype on Nokia N95 smart phones using 3G cellular networking for voice message transfer. We have also built an MVC simulator to perform large-scale simulations that compare RoadSpeak with existing MVC systems. The results of our evaluation prove the feasibility of RoadSpeak and demonstrate that it performs similarly to a traditional MVC systems while supporting substantially larger groups of users.
{"title":"Ad-hoc voice-based group communication","authors":"Lu Han, Stephen Smaldone, P. Shankar, James Boyce, L. Iftode","doi":"10.1109/PERCOM.2010.5466977","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466977","url":null,"abstract":"People waste many hours driving each day. Although unavoidable, this time can be very boring to motorists. Similar to people taking mass transit who often pass the time socializing with those around them, motorists could benefit from social interactions if they were given broader social opportunities. Unfortunately, existing Multiparty Voice Communication (MVC) systems do not scale to large numbers of users and do not provide adequate access controls. We present RoadSpeak, a scalable MVC system that allows motorists to automatically join Voice Chat Groups (VCGs) along popular roadways. RoadSpeak achieves interruption-free communication through the use of voice chat message buffering, flow control and in-order delivery of voice messages to participants. We have implemented a RoadSpeak prototype on Nokia N95 smart phones using 3G cellular networking for voice message transfer. We have also built an MVC simulator to perform large-scale simulations that compare RoadSpeak with existing MVC systems. The results of our evaluation prove the feasibility of RoadSpeak and demonstrate that it performs similarly to a traditional MVC systems while supporting substantially larger groups of users.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121459007","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 : 2010-05-20DOI: 10.1109/PERCOM.2010.5466973
G. Vanderhulst, K. Luyten, K. Coninx
Efficient discovery of nearby devices and services is one of the preconditions to obtain a usable pervasive environment. Typical user interfaces in these environments hide the heterogeneity of the environment for end-users which often makes it hard to perceive the provided functionality. We present Pervasive Maps, an approach and tool that allows to create an intuitive user interface for exploring and controlling the environment. Pervasive Maps offers user-oriented views on the user's environment based on pictures of this environment. We show how users can model, explore and finally interact with complex pervasive environments using Pervasive Maps.
{"title":"Pervasive maps: Explore and interact with pervasive environments","authors":"G. Vanderhulst, K. Luyten, K. Coninx","doi":"10.1109/PERCOM.2010.5466973","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466973","url":null,"abstract":"Efficient discovery of nearby devices and services is one of the preconditions to obtain a usable pervasive environment. Typical user interfaces in these environments hide the heterogeneity of the environment for end-users which often makes it hard to perceive the provided functionality. We present Pervasive Maps, an approach and tool that allows to create an intuitive user interface for exploring and controlling the environment. Pervasive Maps offers user-oriented views on the user's environment based on pictures of this environment. We show how users can model, explore and finally interact with complex pervasive environments using Pervasive Maps.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124789247","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 : 2010-05-20DOI: 10.1109/PERCOM.2010.5466974
P. Stephan, G. Meixner, Holger Koessling, F. Floerchinger, Lisa Ollinger
Industrial production and supply chains face an increased demand for mass-customization and tightening regulations for the traceability of goods, leading to higher requirements concerning flexibility, adaptability and transparency of processes. Technologies for the “Internet of Things” such as smart products and semantic representations pave their way into future factories and supply chains to fulfill these challenging market demands. In this paper a backend-independent approach for information exchange in open-loop processes based on so-called digital object memories (DOM) is presented. By storing order-related data via smart labels on the item, relevant life cycle information is attached to the product itself. This way, information handover via several stages of the value chain with potentially different stakeholders including manufacturer, distributor, retailer, and end customer has been realized. To summarize first best-practice experiences regarding memory structure and content, a prototype implementation based on a scenario of processing dietary supplements in an adaptive process is illustrated.
{"title":"Product-mediated communication through digital object memories in heterogeneous value chains","authors":"P. Stephan, G. Meixner, Holger Koessling, F. Floerchinger, Lisa Ollinger","doi":"10.1109/PERCOM.2010.5466974","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466974","url":null,"abstract":"Industrial production and supply chains face an increased demand for mass-customization and tightening regulations for the traceability of goods, leading to higher requirements concerning flexibility, adaptability and transparency of processes. Technologies for the “Internet of Things” such as smart products and semantic representations pave their way into future factories and supply chains to fulfill these challenging market demands. In this paper a backend-independent approach for information exchange in open-loop processes based on so-called digital object memories (DOM) is presented. By storing order-related data via smart labels on the item, relevant life cycle information is attached to the product itself. This way, information handover via several stages of the value chain with potentially different stakeholders including manufacturer, distributor, retailer, and end customer has been realized. To summarize first best-practice experiences regarding memory structure and content, a prototype implementation based on a scenario of processing dietary supplements in an adaptive process is illustrated.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"377 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122047277","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 : 2010-05-20DOI: 10.1109/PERCOM.2010.5466970
M. Kranz, Carl Fischer, A. Schmidt
While there is more to context than location, localization and positioning must continue to be improved. Location-aware applications, such as Google Latitude, are enjoying great popularity. Location-based applications and services are widely used on platforms such as the iPhone. The localization itself thus remains an issue, especially in indoor scenarios.
{"title":"A comparative study of DECT and WLAN signals for indoor localization","authors":"M. Kranz, Carl Fischer, A. Schmidt","doi":"10.1109/PERCOM.2010.5466970","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466970","url":null,"abstract":"While there is more to context than location, localization and positioning must continue to be improved. Location-aware applications, such as Google Latitude, are enjoying great popularity. Location-based applications and services are widely used on platforms such as the iPhone. The localization itself thus remains an issue, especially in indoor scenarios.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134314892","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 : 2010-05-20DOI: 10.1109/PERCOM.2010.5466981
A. Matic, Andrei Papliatseyeu, V. Osmani, O. Mayora-Ibarra
Position of mobile users has become highly important information in pervasive computing environments. Indoor localization systems based on Wi-Fi signal strength fingerprinting techniques are widely used in office buildings with existing Wi-Fi infrastructure. Our previous work has proposed a solution based on exploitation of FM signal to deal with environments not covered with Wi-Fi signal or environments with only single Wi-Fi access point. However, a general problem of indoor wireless positioning systems pertains to signal degradation due to the environmental factors affecting signal propagation. Therefore, in order to maintain a desirable level of localization accuracy, it becomes necessary to perform periodic calibration of the system, which is either time consuming or requires dedicated equipment and expert knowledge. In this paper, we present a comparison of FM versus Wi-Fi positioning systems and a combination of both systems, exploiting their strengths for indoors positioning. Finally, we address the problem of recalibration by introducing a novel concept of spontaneous recalibration and demonstrate it using the FM localization system.
{"title":"Tuning to your position: FM radio based indoor localization with spontaneous recalibration","authors":"A. Matic, Andrei Papliatseyeu, V. Osmani, O. Mayora-Ibarra","doi":"10.1109/PERCOM.2010.5466981","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466981","url":null,"abstract":"Position of mobile users has become highly important information in pervasive computing environments. Indoor localization systems based on Wi-Fi signal strength fingerprinting techniques are widely used in office buildings with existing Wi-Fi infrastructure. Our previous work has proposed a solution based on exploitation of FM signal to deal with environments not covered with Wi-Fi signal or environments with only single Wi-Fi access point. However, a general problem of indoor wireless positioning systems pertains to signal degradation due to the environmental factors affecting signal propagation. Therefore, in order to maintain a desirable level of localization accuracy, it becomes necessary to perform periodic calibration of the system, which is either time consuming or requires dedicated equipment and expert knowledge. In this paper, we present a comparison of FM versus Wi-Fi positioning systems and a combination of both systems, exploiting their strengths for indoors positioning. Finally, we address the problem of recalibration by introducing a novel concept of spontaneous recalibration and demonstrate it using the FM localization system.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115935596","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 : 2010-03-01DOI: 10.1109/PERCOM.2010.5466975
H. Pham, Justin Mazzola Paluska
Debugging pervasive applications is difficult due to their distributed, asynchronous, and dynamic nature. To help ease the debugging process, we propose PerViz, a developer-targeted tool that enhances system visibility through real-time visualizations of system state, semi-automates application restarts and positioning, and enables both real-time and asynchronous collaboration in debugging between developers. Developers interact with PerViz through a web browser, which provides a convenient, centralized location to study and filter aggregated application debugging logs and state. In our experience with using PerViz, we have found its log aggregation and real-time visualizations to be key facilitators for effective debugging.
{"title":"PerViz: Painkillers for pervasive application debugging","authors":"H. Pham, Justin Mazzola Paluska","doi":"10.1109/PERCOM.2010.5466975","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466975","url":null,"abstract":"Debugging pervasive applications is difficult due to their distributed, asynchronous, and dynamic nature. To help ease the debugging process, we propose PerViz, a developer-targeted tool that enhances system visibility through real-time visualizations of system state, semi-automates application restarts and positioning, and enables both real-time and asynchronous collaboration in debugging between developers. Developers interact with PerViz through a web browser, which provides a convenient, centralized location to study and filter aggregated application debugging logs and state. In our experience with using PerViz, we have found its log aggregation and real-time visualizations to be key facilitators for effective debugging.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127268977","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 : 2010-03-01DOI: 10.1109/PERCOM.2010.5466996
Justin Mazzola Paluska, H. Pham
We present ChunkStream, a system for efficient streaming and interactive editing of online video. Rather than using a specialized protocol and stream format, ChunkStream makes use of a generic mechanism employing chunks. Chunks are fixed-size arrays that contain a mixture of scalar data and references to other chunks. Chunks allow programmers to expose large, but fine-grained, data structures over the network. ChunkStream represents video clips using simple data types like linked lists and search trees, allowing a client to retrieve and work with only the portions of the clips that it needs. ChunkStream supports resource-adaptive playback and “live” streaming of real-time video as well as fast, frame-accurate seeking; bandwidth-efficient high-speed playback; and compilation of editing decisions from a set of clips. Benchmarks indicate that ChunkStream uses less bandwidth than HTTP Live Streaming while providing better support for editing primitives.
我们提出了ChunkStream，一个有效的在线视频流和交互式编辑系统。ChunkStream不是使用专门的协议和流格式，而是使用使用块的通用机制。块是固定大小的数组，包含标量数据和对其他块的引用的混合。块允许程序员在网络上公开大型但细粒度的数据结构。ChunkStream表示视频剪辑使用简单的数据类型，如链表和搜索树，允许客户端检索和工作，只有剪辑的部分，它需要。ChunkStream支持资源自适应播放和实时视频的“现场”流，以及快速，帧精确的搜索;带宽高效高速回放;以及从一组剪辑中编辑决定的汇编。基准测试表明，ChunkStream比HTTP Live Streaming使用更少的带宽，同时为编辑原语提供更好的支持。
{"title":"Interactive streaming of structured data","authors":"Justin Mazzola Paluska, H. Pham","doi":"10.1109/PERCOM.2010.5466996","DOIUrl":"https://doi.org/10.1109/PERCOM.2010.5466996","url":null,"abstract":"We present ChunkStream, a system for efficient streaming and interactive editing of online video. Rather than using a specialized protocol and stream format, ChunkStream makes use of a generic mechanism employing chunks. Chunks are fixed-size arrays that contain a mixture of scalar data and references to other chunks. Chunks allow programmers to expose large, but fine-grained, data structures over the network. ChunkStream represents video clips using simple data types like linked lists and search trees, allowing a client to retrieve and work with only the portions of the clips that it needs. ChunkStream supports resource-adaptive playback and “live” streaming of real-time video as well as fast, frame-accurate seeking; bandwidth-efficient high-speed playback; and compilation of editing decisions from a set of clips. Benchmarks indicate that ChunkStream uses less bandwidth than HTTP Live Streaming while providing better support for editing primitives.","PeriodicalId":207774,"journal":{"name":"2010 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129197573","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}
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：