智慧家庭 (Attentive Home) 研究群
研究成果

 
回首頁
學術成果
技術成果
 

Academic Research Achievements (學術研究成果)

Human-Centric Context Aware Pervasive Service Composition

Year: 2009-2010

Contributors(s): 張馨之, 廖峻鋒

Recently, service composition in pervasive systems is attracting increasing interests. In such systems, the criteria for selecting and ranking services are usually specified by users, which tend to be vague and subjective. Moreover, the deployment of pervasive services here is usually not as well-planned as that in traditional enterprise environments. Hence, the criteria can be contradictory and the activated services can interfere with one another. In this researach, we address these issues by first defining the Preference Expression Language (PEL) that is capable of specifying both enumerative/numeric as well as mandatory/negotiable user preferences. Second, a set of unification rules for conflictive preferences is presented. Third, the degree of interference is modeled and estimated by using fuzzy reasoning approaches. By incorporating the abovementioned mechanisms, we propose a preference aware service composition framework that can avoid service interferences autonomously.

Publications:

H.-S. Chang, C.-F. Liao, and L.-C. Fu, "Unification of Multiple Preferences and Avoidance of Service Interference for Service Composition in Context-Aware Pervasive Systems," in Proc. of 7th ACM International Conference on Pervasive Services (ACM ICPS'10), Berlin, Germany, 2010.

H.-S. Chang, C.-F. Liao, Y.-C. Liu, and L.-C. Fu, "A Spontaneous Preference Aware Service Composition Framework for Message-Oriented Pervasive Systems," in Proceedings of the 4th International Conference on Pervasive Computing and Applications (ICPCA'09), Taiwan, 2009.


Multiple-Resident Activity Recognition using Non-Obtrusive Sensors

Year: 2009-2010

Contributors(s): 徐國鐘, 陸敬互
The goal of this research work was to build a system which learns multiple-resident activity models to facilitate reliable activity recognition of each resident. The proposed system has three main contributions. Firstly, we designed a model which can infer the data association. Secondly, the CHMM-based inference model further involved the interaction among residents. Finally, we designed a mechanism which can automatically annotate the data association.

Publications:

Y.-T. Chiang, K.-C. Hsu, C.-H. Lu, Y.-J. Hsu, and L.-C. Fu “Interaction Models for Multiple-Resident Activity Recognition in a Smart Home,”in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), 2010.

Y.-T. Chiang, K.-C. Hsu, G.-Y. Lin, C.-H. Lu, Y.-J. Hsu and L.-C. Fu “Strategies on Training Conditional Random Fields for Multiple Resident Activity Recognition in a Smart Home,” The Twenty Third International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, (IEA-AIE 2010)


Traffic Reduction Techniques for UPnP-based Home Networks

Year: 2009-2010

Contributors(s): 廖峻鋒

The use of message-oriented architectures in pervasive systems has increased noticeably because of their failure tolerant and loosely-coupled natures. Meanwhile, decentralized service management protocols such as UPnP are believed to be more suitable for small scale pervasive environments such as smart homes. These protocols are usually realized by using IP multicast, which, if not carefully designed, often suffer from network flooding problems due to the replications of too many unnecessary messages. In this work, we designed and analyzed of efficiency boosting techniques that reduce the replications of unnecessary messages when decentralized service management protocols are used to manage message-oriented pervasive systems. The analytical predictions agree well with the simulated results, which show that the message counts of SSDPbased presence and leave announcements, node discovery, and heartbeat can be greatly reduced.

Publications:

Chun-Feng Liao, Shin-Chih Chang, and Li-Chen Fu, "Boosting the Efficiency of the Reliable Service Management Protocol for Message-Oriented Pervasive Systems," in Proceedings of the IEEE International Conference on Service-Oriented Computing and Applications (SOCA'09), Taipei, Taiwan, 2009.


Cooperative Context-Aware ADL (Activity of Daily Living) Infrastructure

Year: 2009-2010

Contributors(s): 陸敬互

In order to address the system-related dynamic events, we implement a cooperative context-aware ADL (activity of daily living) infrastructure to adapt to the changes regarding system reconfiguration. These changes include upgrade, or addition/removal of smart components (currently focusing primarily on activity models) which are often tightly coupled with an AR system. In addition, the ADL infrastructure can increase service/context reusability and this advantage can reduce the efforts in maintaining and establishment of an Activity Recognition system involving multi-model cooperation.

Publications:

C.-H. Lu, C.-L. Wu and L.-C. Fu, “A Reciprocal and Extensible Architecture for Multiple Target Tracking in a Smart Home,” IEEE Transactions on System, Man, and Cybernetics -- Part C: Applications and Reviews, 2010 (To Appear).

C.-H. Lu and L.-C. Fu, “A Human-Centric and Cooperative Architecture for Multiple Target Tracking in a Smart Home,” in the 4th International Conference on Pervasive Computing and Applications (ICPCA2009), Taiwan, 2009.

C.-H. Lu, W.-H. Liao, C.-L. Wu, and L.-C. Fu, “Power-Efficient Extensible Architecture for RFID-Assisted Multiple Target Tracking,” in IEEE International Conference on Systems, Man and Cybernetics, 2006. (SMC '06), 2006, pp. 1068-1073.


A Guideline-Driven Platform for Healthcare Services in Smart Home Environments

Year: 2009-2010

Contributors(s): 廖峻鋒, 張馨之

The guidelines are usually established by medical ex-perts, according to the symptom of disease. Based on the biological information, habits, and the surrounding environment information form sensors, the guideline engine makes the appropriate care decisions and then alerts after the information is observed. Further-more, the proposed platform can gather feedback information about the reaction follow-ing collecting the implementation of the guidelines by monitoring system. In case of emergency, the platform uses the short message system to inform the relevant units im-mediately. The smart home integration platform can therefore reduce the burdens of care and unexpected events with effectiveness; therefore it enhances the quality of family care.

Publications:

廖峻鋒、張馨之、傅立成,"以醫療照護指引技術為基礎的智慧型居家健康照護平台," 電信研究雙月刊, 智慧化生活應用技術特輯, vol.39, no. 5, Oct 2009.

C.-F. Liao, S.-C. Chang, and L.-C. Fu, “A Guideline-Driven Platform for Healthcare Services in Smart Home Environments,” in Proceedings of 8th International Conference on Smart Homes and Health Telematics (ICOST 2010), Seoul, Korea, 2010.


Hybrid User-assisted Model Adaptation (HUMA)

Year: 2008

Contributors(s): 陸敬互, 陳意函, 徐國鐘

Since human’s behavior and daily schedule are so unpredictable, we propose Hybrid User-assisted Model Adaptation (HUMA) to let the inherent model adapt to situations with behavior/preference changes from residents in order to address the human-related uncertainties in a single-user dynamic smart-home environment. With this learning approach, our goal is to equip an activity model with the ability to detect the occurrence of human-related dynamic events, and meanwhile to minimize users’ burden in annotating newly-collected unlabeled data (containing the clues about human-related dynamic events) such that the system can maintain as much performance of activity recognition as possible, which could be hardly possible in a dynamic environment.

Publications:

C.-H. Lu, Y.-C. Ho, Y.-H. Chen, L.-C. Fu, “Adaptive Activity Recognition in a Dynamic Environment,” submitted to IEEE Transactions on Automation Science and Engineering 2010. (Under Revision)

K.-C. Hsu, Y.-T. Chiang, C.-H. Lu, Y.-J. Hsu, and L.-C. Fu “Interaction Models for Multiple-Resident Activity Recognition in a Smart Home,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), Taipei, Taiwan, 2010.

Y.-T. Chiang, K.-C. Hsu, G.-Y. Lin, C.-H. Lu, Y.-J. Hsu and L.-C. Fu, “Strategies on Training Conditional Random Fields for Multiple Resident Activity Recognition in a Smart Home,” in the Twenty Third International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA-AIE 2010), Cordoba (Spain), 2010.

Y.-H. Chen, C.-H. Lu, K.-C. Hsu, L.-C. Fu, Y.-J. Yeh, and L.-C. Kuo, “Preference Model Assisted Activity Recognition Learning in a Smart Home Environment,” in IEEE International Conference on Intelligent Robots and Systems, 2009 (IROS 2009).


Reliable Service Management in Message-Oriented Pervasive Systems

Year: 2008-2010

Contributors(s): 廖峻鋒, 鍾亞文

Reliability is one of the key challenges of Pervasive systems. Numerous Message-Oriented architectures and service discovery protocols have been proposed to support service management in Pervasive systems. Nevertheless, few researches have been done to improve the reliability of Pervasive systems. This research attempts to propose a reliable service management framework by formally defining a Message-Oriented service application model and protocols that facilitate autonomous composition, failure detection and recovery of services. Proposed approaches are realized by constructing a developer’s toolkit that enables rapid-prototyping of services. The recovery rate of systems can be greatly improved by the proposed approach. Furthermore, the services developed by using the proposed approach are capable of integrating heterogeneous software/hardware, and can be deployed in dissimilar sites with little efforts.

Publications:

C.-F. Liao, Y.-W. Jong and L.-C. Fu, "Toward Reliable Service Management in Message-Oriented Pervasive Systems," in IEEE Transactions on Service Computing, 2010. (to appear in the special issue on Service Composition and Virtualization Technologies).

C.-F. Liao, Y.-W. Jong and L.-C. Fu, "Toward a Message-Oriented Application Model and its Middleware Support in Ubiquitous Environments," International Journal of Hybrid Information Technology, vol.1, no.3, July 2008.

陳志明、廖峻鋒、鍾亞文、傅立成、張慶年,"以訊息為導向之數位家庭服務應用技術," 電信研究雙月刊, 智慧化生活應用技術特輯, vol.39, no. 5, Oct 2009.

C.-F. Liao, Y.-W. Jong, and L.-C. Fu, "PSMP: A Fast Self-Healing and Self-Organizing Pervasive Service Management Protocol for Smart Home Environments," in Proceedings of 2008 IEEE Asia-Pacific Services Computing Conference (IEEE APSCC 2008), Yilan, Taiwan, 2008.

C.-F. Liao, Y.-W. Jong, and L.-C. Fu, "Community-based Autonomous Service Activation and Failure Recovery in a Message-Oriented Pervasive Middleware," in Proceedings of 2008 International Workshop on Context-Aware Pervasive Communities: Infrastructures, Services and Applications (CAPC 2008, Held in Conjunction with Pervasive 2008), Sydney, Australia, 2008.

C.-F. Liao, Y.-W. Jong, and L.-C. Fu, "Toward a Message-Oriented Application Model and its Middleware Support in Ubiquitous Environments," in Proceedings of 2008 International Conference on Multimedia and Ubiquitous Engineering (MUE 2008), Busan, Korea, 2008.


A Novel Self-Healing and Self-Organizing Method for Smart Home Service Management Systems

Year: 2008-2009

Contributors(s): 鍾亞文

More and more intelligent devices are becoming part of our life. In the near future, these intelligent devices will also be brought to our homes to provide comfort and convenience to habitants. A considerable number of studies have been made on service management systems for pervasive environments in order to coordinate these intelligent devices; however only few or none of them have addressed the system availability and robustness issue. These two aspects are fundamental for service management systems in smart homes, because there are usually pervasive services that are critical to the habitants’ health and life. In this research, we propose a Pervasive Service Management System (PSMS) with self-organizing ability. Additionally, we have designed a failure detection and recovery protocol to enhance the availability and robustness of the PSMS. Experiment results show that the proposed solution can detect software failure efficiently without causing network instability, hence preserving the availability and robustness of the PSMS.

Publications:

Y.-W. Jong, C.-F. Liao, and L.-C. Fu, "A Rotating Roll-call-based Adaptive Failure Detection and Recovery Protocol for Smart Home Environments," in Proceedings of 7th International Conference On Smart homes and health Telematics (ICOST 2009, Springer Lecture Notes in Computer Sciences 5597), Tours, France, 2009.

Y.-W. Jong, C.-F. Liao, and Li-Chen Fu, "An Efficient Autonomous Failure Recovery Mechanism for UPnP-based Message-Oriented Pervasive Services," in Proceedings of 2008 IEEE International Conference on System, Man, and Cybernetics (IEEE SMC 2008) , Singapore,Oct 2008.


Preference Model Assisted Activity Recognition in a Smart Home

Year: 2008-2009

Contributors(s): 陳意函

Understanding a user’s preferences and then providing corresponding services is substantial in a smart home environment nowadays. Meanwhile, reliable recognition of activities from cluttered sensory data is also a challenging task for a smart home to provide desirable services. In this work, we aim to develop a hybrid system which is the first trial to model the relationship of a preference model and an activity model so that the causal relation among activities and personal preferences can assist to recover the accuracy of activity recognition in the dynamic environment. Based on the learned model, the smart home system provides services to the user so that the hybrid system can better interact with the user and also gain his/her feedback to adjust the learned preference model. Afterwards, both of the activity model and preference model will be simultaneously adapted by the analysis of the feedback.

Publications:

Y.-H. Chen, C.-H. Lu, K.-C. Hsu, L.-C. Fu, Y.-J. Yeh, and L.-C. Kuo, "Preference Model Assisted Activity Recognition Learning in a Smart Home Environment," in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009), 2009.



Ambient Intelligence Compliant Object (AICO)

Year: 2007

Contributors(s): 陸敬互, 何育誠

In order to improve the performance of activity recognition under device uncertainties in a dynamic environment, we propose making use of WSN technologies and a non-obtrusive deployment strategy to enhance regular household objects (such as an appliance, or a furniture, etc.) into various Ambient Intelligence Compliant Objects (AICOs). An AICO is an enhanced household object whose design helps secure WSN sensors from unexpected damage via a seamless (or non-obtrusive) deployment strategy, which can further prevent device-related dynamic events regarding device breakdown and malfunction.

Publications:

C.-H. Lu and L.-C. Fu, “Robust Location-Aware Activity Recognition Using Wireless Sensor Networks in an Attentive Home, ” IEEE Transactions on Automation Science and Engineering, Volume 6, Issue 4, Oct. 2009 Page(s):598 – 609.

C.-H. Lu, Y.-C. Lin, and L.-C. Fu, “Hide and Not Easy to Seek: A Hybrid Weaving Strategy for Context-Aware Service Provision in a Smart Home,” in IEEE Asia-Pacific Services Computing Conference (APSCC), 2008, pp. 595-600.

C.-H. Lu, Y.-C. Ho, and L.-C. Fu, “Creating Robust Activity Maps Using Wireless Sensor Network in a Smart Home,” in IEEE International Conference on Automation Science and Engineering, 2007. (CASE 2007)., pp. 741-746, 2007.


A Human-System Interaction Framework and Algorithm for Smart Homes

Year: 2007-2008

Contributors(s): 吳兆麟

Current smart home is a ubiquitous computing environment consisting of multiple agent-based autonomous spaces, and it brings both advantage and challenge that a service interacting with users can be performed with multiple choices of configuration in space, hardware, software, and quality. And besides being smart in the technology phase, a smart home should also satisfy the “home” feeling when interacting with its inhabitants. In this work, from the perspective of human-computer interaction, we analyze the relationship between services, spaces, and users, and then propose a framework as well as a corresponding algorithm to model their interaction, thus for a smart home to behave both smart and as a home when interacting with its inhabitants.

Publications:

Chao-Lin Wu and Li-Chen Fu, "A Human-System Interaction Framework and Algorithm for UbiComp-Based Smart Home," in IEEE Conference on Human System Interactions, 25-27 May, 2008.



Service-Oriented Smart Home Architecture based on OSGi and Mobile Agent Technology

Year: 2004-2006

Contributors(s): 吳兆麟, 廖峻鋒

The architecture of a conventional smart home is usually server-centric and thus causes many problems. Mobile devices and dynamic services cause the dynamically changing environment, which can result in very difficult interaction. In addition, how to provide services efficiently and appropriately is always an important issue for a smart home. To solve the problems caused by traditional architectures, to deal with the dynamic environment, and to provide appropriate service, we propose a service-oriented architecture for smart home environments, based on OSGi and mobile agent technology. This architecture is a Peer-to-Peer model based on multiple OSGi platforms, in which service-oriented mechanisms are used for system components to interact with one another, and mobile agent technology is applied to augment the interaction mechanisms

Publications:

C.-L. Wu, C.-F. Liao and L.-C. Fu, "Service-Oriented Smart Home Architecture based on OSGi and Mobile Agent Technology," IEEE Transactions on Systems, Man and Cybernetics - Part C, Special Issue on Networking, Sensing, and Control, vol.37, no.2 , 2007.

W.-R. Jih, J. Y.-J Hsu, C.-L. Wu, C.-F. Liao, and S.-Y. Cheng, "A Multi-Agent Service Framework for Context-Aware Elder Care," Proceedings of Workshop of Service-Oriented Computing and Agent-Based Engineering (SOCABE'2006), Hakodate, JAPAN, 2006.



                                                                                                                                                                                                                                   

 
 
Copyright (C)2010 NTU CSIE All rights reserved.