We have a lot of interests to wearable computer as an IT technology has been advanced. Although aids for disabled persons are also developed variously, those for visually impaired persons were limited. In this study, we proposed a wearable system that can do walk safely to the destination for the visually impaired persons. Our system guides a user to arrive at destination using marker information detected by camera. Also it uses multiple ultrasonic sensors array to detect and avoid obstacles. After recognizing position and orientation of markers attached on the indoor ceiling, we can estimate relative direction to destination. At the same time, we simplify a complex spatial structure in front of user into some patterns by means of ultrasonic sensors and determine an avoidance direction by estimating the patterns. Our system helps users to arrive to destination safely without others help.
{"title":"Wearable Computer System Reflecting Spatial Context","authors":"Jin-Hee Lee, Ei-Kyu Choi, Sukhyun Lim, B. Shin","doi":"10.1109/IWSCA.2008.9","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.9","url":null,"abstract":"We have a lot of interests to wearable computer as an IT technology has been advanced. Although aids for disabled persons are also developed variously, those for visually impaired persons were limited. In this study, we proposed a wearable system that can do walk safely to the destination for the visually impaired persons. Our system guides a user to arrive at destination using marker information detected by camera. Also it uses multiple ultrasonic sensors array to detect and avoid obstacles. After recognizing position and orientation of markers attached on the indoor ceiling, we can estimate relative direction to destination. At the same time, we simplify a complex spatial structure in front of user into some patterns by means of ultrasonic sensors and determine an avoidance direction by estimating the patterns. Our system helps users to arrive to destination safely without others help.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133965008","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}
Minghao Piao, J. Park, H. Lee, Jin Shin, Duck JinChai, K. Ryu
The aim of this paper is to investigate the potential of air conditioning load management by solve the temperature regression model of load patterns for Banks and the temperature sensitivity depends on temperature change. The load survey system has been applied to record the Bank load of sampling Banks in Korea power system. To analyze the impact of temperature rise to the Bank load data, we executed statistic polynomial regression and the temperature sensitivity analysis on the Bank load data. Before that, we applied data preprocessing to make the data clear. It found that the week time is more sensitive than weekend and when the temperature is less deviated from the main tendency, the regression model can predict the load patterns with higher accuracy.
{"title":"Assessment of Temperature Sensitivity Analysis and Temperature Regression Model for Predicting Seasonal Bank Load Patterns","authors":"Minghao Piao, J. Park, H. Lee, Jin Shin, Duck JinChai, K. Ryu","doi":"10.1109/IWSCA.2008.34","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.34","url":null,"abstract":"The aim of this paper is to investigate the potential of air conditioning load management by solve the temperature regression model of load patterns for Banks and the temperature sensitivity depends on temperature change. The load survey system has been applied to record the Bank load of sampling Banks in Korea power system. To analyze the impact of temperature rise to the Bank load data, we executed statistic polynomial regression and the temperature sensitivity analysis on the Bank load data. Before that, we applied data preprocessing to make the data clear. It found that the week time is more sensitive than weekend and when the temperature is less deviated from the main tendency, the regression model can predict the load patterns with higher accuracy.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133406638","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}
In anomaly detection, one important issue how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior from the activities of a user, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes an anomaly detection method that continuously models the normal behavior of a user over the multi-dimensional audit data stream. Each cluster represents the frequent range of the activities with respect to a set of features. As a result, without physically maintaining any historical activity of a user, the new activities of the user can be continuously reflected onto the on-going result. At the same time, various statistics of the activities related to the identified clusters are additionally modeled to improve the performance of anomaly detection. The proposed algorithm is analyzed by a series of experiments to identify various characteristics.
{"title":"Anomaly Detection over Clustering Multi-dimensional Transactional Audit Streams","authors":"N. Park, W. Lee","doi":"10.1109/IWSCA.2008.17","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.17","url":null,"abstract":"In anomaly detection, one important issue how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior from the activities of a user, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes an anomaly detection method that continuously models the normal behavior of a user over the multi-dimensional audit data stream. Each cluster represents the frequent range of the activities with respect to a set of features. As a result, without physically maintaining any historical activity of a user, the new activities of the user can be continuously reflected onto the on-going result. At the same time, various statistics of the activities related to the identified clusters are additionally modeled to improve the performance of anomaly detection. The proposed algorithm is analyzed by a series of experiments to identify various characteristics.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130603761","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}
Jin-Guk Jung, Seung-Bo Park, Sang-Jin Cha, Geun-Sik Jo
In the logistics, there are the variety of available data formats. This should make it difficult to quickly implement a system to communicate with other application systems. Furthermore, once the system which can handle the data formats agreed with each other has been implemented, a considerable amount of effort is still required to reformat the data for utilization in any other services like which shippers are able to monitor and track their freight on Web. To overcome these problems, we apply semantic Web service technology, which provides a promising common interoperable framework in which information is given well-defined meaning in unambiguous and machine-interpretable form by using ontology such that data and services can be used for more effective discovery, automation, integration, and reuse across various applications. Finally, we have shown the reasonability of adopting semantic Web service as a case study.
{"title":"Semantic Web Service for Freight Management System","authors":"Jin-Guk Jung, Seung-Bo Park, Sang-Jin Cha, Geun-Sik Jo","doi":"10.1109/IWSCA.2008.27","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.27","url":null,"abstract":"In the logistics, there are the variety of available data formats. This should make it difficult to quickly implement a system to communicate with other application systems. Furthermore, once the system which can handle the data formats agreed with each other has been implemented, a considerable amount of effort is still required to reformat the data for utilization in any other services like which shippers are able to monitor and track their freight on Web. To overcome these problems, we apply semantic Web service technology, which provides a promising common interoperable framework in which information is given well-defined meaning in unambiguous and machine-interpretable form by using ontology such that data and services can be used for more effective discovery, automation, integration, and reuse across various applications. Finally, we have shown the reasonability of adopting semantic Web service as a case study.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115606670","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}
The TACTE system proposed in this paper focuses on one problem in natural language processing, namely recognizing textual entailment involving temporal expressions. The system consists of two components: one for temporal expression extraction and anchoring, and the other one for recognizing textual entailment based on events. The entailment rules are constructed using a small set of temporal expression relations and lexical resources. Several experiments are conducted, and various aspects of the system performance are illustrated. The evaluation on different data sets shows the great improvement of our TACTE system in comparison with the baseline. As a system potentially to be integrated into a larger framework, TACTE is shown to be very promising as a specialized module on entailment cases where temporal expression information is available.
{"title":"Recognizing Textual Entailment with Temporal Expressions in Natural Language Texts","authors":"Rui Wang, Yajing Zhang","doi":"10.1109/IWSCA.2008.25","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.25","url":null,"abstract":"The TACTE system proposed in this paper focuses on one problem in natural language processing, namely recognizing textual entailment involving temporal expressions. The system consists of two components: one for temporal expression extraction and anchoring, and the other one for recognizing textual entailment based on events. The entailment rules are constructed using a small set of temporal expression relations and lexical resources. Several experiments are conducted, and various aspects of the system performance are illustrated. The evaluation on different data sets shows the great improvement of our TACTE system in comparison with the baseline. As a system potentially to be integrated into a larger framework, TACTE is shown to be very promising as a specialized module on entailment cases where temporal expression information is available.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129855867","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}
Traditional classification methods, such as neural network approaches, have suffered difficulties with generalization and producing models. Support vector machine (SVM) approach is considered a good candidate because of its high generalization performance without the need to add a priori knowledge, even when the dimension of the input space is very high. In this paper, SVM approach is proposed to segment images and we evaluate thoroughly its segmentation performance. Experimental results show that: (1) the effect of kernel function, model parameters and input vectors on the segmentation performance is significant; (2) SVM approach is suitably used as learning machine under the condition of small sample sizes; (3) SVM approach is less sensitive to noise in image segmentation.
{"title":"Performance Evaluation of SVM in Image Segmentation","authors":"Xing Fan, Guoping Zhang, Xuezhi Xia","doi":"10.1109/IWSCA.2008.15","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.15","url":null,"abstract":"Traditional classification methods, such as neural network approaches, have suffered difficulties with generalization and producing models. Support vector machine (SVM) approach is considered a good candidate because of its high generalization performance without the need to add a priori knowledge, even when the dimension of the input space is very high. In this paper, SVM approach is proposed to segment images and we evaluate thoroughly its segmentation performance. Experimental results show that: (1) the effect of kernel function, model parameters and input vectors on the segmentation performance is significant; (2) SVM approach is suitably used as learning machine under the condition of small sample sizes; (3) SVM approach is less sensitive to noise in image segmentation.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121120377","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 : 2008-07-10DOI: 10.1007/978-3-540-88906-9_52
Geon-Ha Lee, Yoe-Jin Yoon, Seung-Hyun Lee, Kee-Hyun Choi, D. Shin
{"title":"Design of Directory Facilitator for Agent-Based Service Discovery in Ubiquitous Computing Environments","authors":"Geon-Ha Lee, Yoe-Jin Yoon, Seung-Hyun Lee, Kee-Hyun Choi, D. Shin","doi":"10.1007/978-3-540-88906-9_52","DOIUrl":"https://doi.org/10.1007/978-3-540-88906-9_52","url":null,"abstract":"","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132527215","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}
XML data are being a standard in many areas such as internet and public documentation. Therefore, there are many kinds of documentation or web sites which are using XML expressions. To extract some useful data among multiple XML data, we need to research data mining algorithm to XML data. And many kinds of techniques have been researched to speed up the query performance about XML data. In this paper, we analyze the XML query pattern and propose the data mining technique which extracts the similar XML query pattern. The proposed method based on Weighted-FP-growth algorithm is applied to XML query subtrees. And we experimented our technique compared with FP-growth algorithm and Apriori algorithm. The proposed method outperforms any other methods in query result of the repeatedly occurring queries.
{"title":"Mining the Weighted Frequent XML Query Pattern","authors":"M. Gu, J. Hwang, D. Chai, K. Ryu","doi":"10.1109/IWSCA.2008.37","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.37","url":null,"abstract":"XML data are being a standard in many areas such as internet and public documentation. Therefore, there are many kinds of documentation or web sites which are using XML expressions. To extract some useful data among multiple XML data, we need to research data mining algorithm to XML data. And many kinds of techniques have been researched to speed up the query performance about XML data. In this paper, we analyze the XML query pattern and propose the data mining technique which extracts the similar XML query pattern. The proposed method based on Weighted-FP-growth algorithm is applied to XML query subtrees. And we experimented our technique compared with FP-growth algorithm and Apriori algorithm. The proposed method outperforms any other methods in query result of the repeatedly occurring queries.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133819814","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}
In the Web 2.0 Age, Web bloggers have become major Web content providers, and the volume of blogs continues to increase rapidly. Although keyword-based tags are widely used to classify submitted blogs and to search for retrieval, this keyword-based approach provides less optimal classification, leading to less satisfactory search results because this approach is not a semantic approach. To address this problem, prior to this paper, a system called STSS was developed in order to facilitate users to build semantic tags for their blogs and to retrieve more relevant search results. The STSS test results demonstrated that use of the semantic approach led to more accurate content classification and more relevant search results although there were performance issues. In this paper, we describe our efforts to improve STSS by employing an optimization and caching approach. The test results show that the performance of new approach exceeds that of the previous one.
{"title":"Optimization and Load Balancing of the Semantic Tagging and Searching System","authors":"J. Yelloz, Taehyung Wang","doi":"10.1109/IWSCA.2008.33","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.33","url":null,"abstract":"In the Web 2.0 Age, Web bloggers have become major Web content providers, and the volume of blogs continues to increase rapidly. Although keyword-based tags are widely used to classify submitted blogs and to search for retrieval, this keyword-based approach provides less optimal classification, leading to less satisfactory search results because this approach is not a semantic approach. To address this problem, prior to this paper, a system called STSS was developed in order to facilitate users to build semantic tags for their blogs and to retrieve more relevant search results. The STSS test results demonstrated that use of the semantic approach led to more accurate content classification and more relevant search results although there were performance issues. In this paper, we describe our efforts to improve STSS by employing an optimization and caching approach. The test results show that the performance of new approach exceeds that of the previous one.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130644208","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}
As business organizations have become more complicated and large-scale, so have collaboration among business partners and enterprise information integration become more common. A number of integration approaches to semantic collaboration have been addressed. Over the past few decades, ontology-based integration approaches have been the focus. Ontology is considered to be one of the typical semantic representation methods. As logistics enables business networks, and as logistics data is stored in distributed information systems, semantic information integration is required among logistics partners. In the present study, we addressed the issue of an ontological approach to integration of event-centric logistics information into EPC-based logistics. We formalized the logistics and logistics events, and generalized and extended a previously developed logistics ontology. In this paper, we introduce an ontological method for integrating distributed logistics information into the EPC network.
{"title":"Ontological Approach to Integration of Event-Centric Logistics Information into EPC Network","authors":"Dae-Won Park, Gyeongtaek Lee, H. Kwon","doi":"10.1109/IWSCA.2008.30","DOIUrl":"https://doi.org/10.1109/IWSCA.2008.30","url":null,"abstract":"As business organizations have become more complicated and large-scale, so have collaboration among business partners and enterprise information integration become more common. A number of integration approaches to semantic collaboration have been addressed. Over the past few decades, ontology-based integration approaches have been the focus. Ontology is considered to be one of the typical semantic representation methods. As logistics enables business networks, and as logistics data is stored in distributed information systems, semantic information integration is required among logistics partners. In the present study, we addressed the issue of an ontological approach to integration of event-centric logistics information into EPC-based logistics. We formalized the logistics and logistics events, and generalized and extended a previously developed logistics ontology. In this paper, we introduce an ontological method for integrating distributed logistics information into the EPC network.","PeriodicalId":425055,"journal":{"name":"2008 IEEE International Workshop on Semantic Computing and Applications","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121760016","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：