The amount of data within the Linking Open Data (LOD) cloud is steadily increasing and resembles a rich source of information. Since Context-aware Services (CAS) can highly benefit from background information, e.g., about the environment of a user, it makes sense to leverage that enormous amount of data already present in the LOD cloud to enhance the quality of these services. Within this work, the applicability of the LOD cloud as provider for contextual information to enrich CAS is investigated. For this purpose, non-functional criteria of discoverability and availability are analyzed, followed by a presentation of an overview of the different domains covered by the LOD cloud. In order to ease the process of finding a dataset that matches the information needs of a developer of a CAS, techniques for retrieving contents of LOD datasets are discussed and different approaches to condense the dataset to its most important concepts are shown.
{"title":"Analyzing the Applicability of the Linking Open Data Cloud for Context-Aware Services","authors":"M. Hoffen, A. Uzun, Axel Küpper","doi":"10.1109/ICSC.2014.27","DOIUrl":"https://doi.org/10.1109/ICSC.2014.27","url":null,"abstract":"The amount of data within the Linking Open Data (LOD) cloud is steadily increasing and resembles a rich source of information. Since Context-aware Services (CAS) can highly benefit from background information, e.g., about the environment of a user, it makes sense to leverage that enormous amount of data already present in the LOD cloud to enhance the quality of these services. Within this work, the applicability of the LOD cloud as provider for contextual information to enrich CAS is investigated. For this purpose, non-functional criteria of discoverability and availability are analyzed, followed by a presentation of an overview of the different domains covered by the LOD cloud. In order to ease the process of finding a dataset that matches the information needs of a developer of a CAS, techniques for retrieving contents of LOD datasets are discussed and different approaches to condense the dataset to its most important concepts are shown.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125254537","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}
Chia-Wei Liao, Kai-Hsuan Chan, Wen-Tsung Chang, Sheng-Tsung Tu
The amount of the internet video has been growing rapidly in recent years. Efficient video indexing and retrieval, therefore, is becoming an important research and system-design issue. Reliably extracting metadata from video as indexes is one major step toward efficient video management. There are numerous video types, and everyone can define new video types of his own. We believe an open video analysis framework should help when one needs to automatically process various types of videos. More, the nature of video can be so different that we may end up having a dedicated video analysis module for each video type. It is infeasible to design a system to automatically process every type of video. In the paper, we propose a scene-based video analytic studio that comes with (1) an open video analysis framework where the video analysis modules are developed and deployed as plug-ins, (2) an authoring tool where videos can be manually tagged, and (3) an HTML5-based video player the play backs videos using the metadata we generate. In addition, it provides a runtime environment with standard libraries and proprietary rule-based automaton modules to facilitate the plug-in development. At the end, we will show its application to click able (shoppable) videos, which we plan to apply to our e-learning projects.
{"title":"Scene-Based Video Analytics Studio","authors":"Chia-Wei Liao, Kai-Hsuan Chan, Wen-Tsung Chang, Sheng-Tsung Tu","doi":"10.1109/ICSC.2014.56","DOIUrl":"https://doi.org/10.1109/ICSC.2014.56","url":null,"abstract":"The amount of the internet video has been growing rapidly in recent years. Efficient video indexing and retrieval, therefore, is becoming an important research and system-design issue. Reliably extracting metadata from video as indexes is one major step toward efficient video management. There are numerous video types, and everyone can define new video types of his own. We believe an open video analysis framework should help when one needs to automatically process various types of videos. More, the nature of video can be so different that we may end up having a dedicated video analysis module for each video type. It is infeasible to design a system to automatically process every type of video. In the paper, we propose a scene-based video analytic studio that comes with (1) an open video analysis framework where the video analysis modules are developed and deployed as plug-ins, (2) an authoring tool where videos can be manually tagged, and (3) an HTML5-based video player the play backs videos using the metadata we generate. In addition, it provides a runtime environment with standard libraries and proprietary rule-based automaton modules to facilitate the plug-in development. At the end, we will show its application to click able (shoppable) videos, which we plan to apply to our e-learning projects.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122050327","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}
SemioTag is an approach towards tagging that utilizes the semiotic sign categories icon, index, and symbol as classification structures to be used by users during the annotation and search of images within social media-oriented repositories. We compared the influence of this approach on the tagging and querying behaviour of users, with respect to usability, efficiency, and user experience, between the standard Flickr tagging and querying method and the one used in SemioTag. Our results show that semiotic tagging is considered more tedious and takes about twice the time as standard tagging. However, subjects produced a larger number of tags with semiotic tagging. Finally, querying with semiotic tags is not considered more cumbersome than querying using standard tags. Subjects stated that semiotic-based search provides more reasonable results than search based on standard tagging because it provided more control on the query. Semiotic search turned out to be faster. Overall, the findings clearly indicate to further investigate in the direction of semiotic tagging. We anticipate application of semiotics for particular types of human-centered IR such as explorative search.
{"title":"Semiotic Tagging: Enriching the Semantics of Tags for Improved Image Retrieval","authors":"F. Nack, A. Scherp, Chantal Neuhaus","doi":"10.1109/ICSC.2014.10","DOIUrl":"https://doi.org/10.1109/ICSC.2014.10","url":null,"abstract":"SemioTag is an approach towards tagging that utilizes the semiotic sign categories icon, index, and symbol as classification structures to be used by users during the annotation and search of images within social media-oriented repositories. We compared the influence of this approach on the tagging and querying behaviour of users, with respect to usability, efficiency, and user experience, between the standard Flickr tagging and querying method and the one used in SemioTag. Our results show that semiotic tagging is considered more tedious and takes about twice the time as standard tagging. However, subjects produced a larger number of tags with semiotic tagging. Finally, querying with semiotic tags is not considered more cumbersome than querying using standard tags. Subjects stated that semiotic-based search provides more reasonable results than search based on standard tagging because it provided more control on the query. Semiotic search turned out to be faster. Overall, the findings clearly indicate to further investigate in the direction of semiotic tagging. We anticipate application of semiotics for particular types of human-centered IR such as explorative search.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"4 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131710095","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}
Location-based Services (LBS) are one of the longest-standing value-added services in the mobile communications industry. The location of a user is the fundamental factor shaping such services and is usually computed solely in terms of the physical location relying on Reverse Geocoding APIs. It does not take into consideration the semantics of the location, but rather only the geographic spatial information, which significantly restricts the intelligibility of the provided LBS. In order to overcome the aforementioned limitations, we have introduced a Semantic Positioning Platform in a previous work being capable of providing semantically enriched self-referencing LBS. In this paper, we extend the platform by enabling cross-referencing proactive LBS (i.e., third-party tracking) based on semantically modeled user-specific location profiles (e.g., school or office) in combination with social relations among users. Furthermore, the independent platforms delivering the Semantic Positioning functionality (i.e., the Positioning Enabler and the Open Mobile Network) have been integrated into the Context Data Cloud, which is a context management ecosystem for delivering semantically enriched context-aware services. In addition, the Context Data Cloud for Android application including a Friend Tracker function has been implemented as a proof of concept. The evaluation in terms of battery consumption and positioning accuracy highlights the added value of our approach.
{"title":"Exploiting Location Semantics for Realizing Cross-Referencing Proactive Location-Based Services","authors":"A. Uzun, Mohamed Salem, Axel Küpper","doi":"10.1109/ICSC.2014.26","DOIUrl":"https://doi.org/10.1109/ICSC.2014.26","url":null,"abstract":"Location-based Services (LBS) are one of the longest-standing value-added services in the mobile communications industry. The location of a user is the fundamental factor shaping such services and is usually computed solely in terms of the physical location relying on Reverse Geocoding APIs. It does not take into consideration the semantics of the location, but rather only the geographic spatial information, which significantly restricts the intelligibility of the provided LBS. In order to overcome the aforementioned limitations, we have introduced a Semantic Positioning Platform in a previous work being capable of providing semantically enriched self-referencing LBS. In this paper, we extend the platform by enabling cross-referencing proactive LBS (i.e., third-party tracking) based on semantically modeled user-specific location profiles (e.g., school or office) in combination with social relations among users. Furthermore, the independent platforms delivering the Semantic Positioning functionality (i.e., the Positioning Enabler and the Open Mobile Network) have been integrated into the Context Data Cloud, which is a context management ecosystem for delivering semantically enriched context-aware services. In addition, the Context Data Cloud for Android application including a Friend Tracker function has been implemented as a proof of concept. The evaluation in terms of battery consumption and positioning accuracy highlights the added value of our approach.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132445245","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}
This paper presents an approach for semantic word comparison by coupling natural text descriptions with semi-structured knowledge for revealing more precise context information. The goal of the study is to present how popularity of a word's sense can affect semantic relatedness when two words are compared.
{"title":"Advancing the Semantic Relatedness Approach by Using Sense Popularity","authors":"Ivana Donevska","doi":"10.1109/ICSC.2014.46","DOIUrl":"https://doi.org/10.1109/ICSC.2014.46","url":null,"abstract":"This paper presents an approach for semantic word comparison by coupling natural text descriptions with semi-structured knowledge for revealing more precise context information. The goal of the study is to present how popularity of a word's sense can affect semantic relatedness when two words are compared.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133050292","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}
It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification.
{"title":"Facebook Users Relationships Analysis Based on Sentiment Classification","authors":"D. Terrana, A. Augello, G. Pilato","doi":"10.1109/ICSC.2014.59","DOIUrl":"https://doi.org/10.1109/ICSC.2014.59","url":null,"abstract":"It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"37 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132988189","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}
There is a growing need to make sense of all the raw data available on the Internet, hence, the purpose of this study is to explore the capabilities of data mining algorithms applied to social networks. We propose a system to mine public Twitter data for information relevant to obesity and health as an initial case study. This paper details the findings of our project and critiques the use of social networks for data mining purposes.
{"title":"Social Network Data Mining Using Natural Language Processing and Density Based Clustering","authors":"David Khanaferov, Christopher Luc, Taehyung Wang","doi":"10.1109/ICSC.2014.48","DOIUrl":"https://doi.org/10.1109/ICSC.2014.48","url":null,"abstract":"There is a growing need to make sense of all the raw data available on the Internet, hence, the purpose of this study is to explore the capabilities of data mining algorithms applied to social networks. We propose a system to mine public Twitter data for information relevant to obesity and health as an initial case study. This paper details the findings of our project and critiques the use of social networks for data mining purposes.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125775217","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 recent years, developing needed software applications via the technique Web Service Composition (WSC) has been more and more popular. Moreover, benefit from the Semantic Web Services (SWSs) technology, it is possible to even automatically conduct WSC, i.e. the Automated Web Service composition (AWSC). Currently the AWSC is a well-studied research subject and which means the existence of a large number of related research efforts. To existing AWSC researches, our goal is to make complete and referable surveys of them, and in this paper we adopt a strategy which may be more efficient than directly reviewing original research papers that we inspect and focus on the already-published AWSC surveys, trying to take advantages of them. With an AWSC survey framework proposed by us previously, we present a modest review on the selected AWSC surveys which inspected the AWSC researches that largely benefit from the SWSs technology. For each selected AWSC survey, in this review we indicate what AWSC research concerns defined by us in the survey framework are covered by it and precisely describe its contents. With this review, the reader can easily and quickly find out proper AWSC surveys for more advanced information and reading.
{"title":"A Review of the Automatic Web Service Composition Surveys","authors":"Yang Syu, Yong-Yi Fanjiang, J. Kuo, Shang-Pin Ma","doi":"10.1109/ICSC.2014.41","DOIUrl":"https://doi.org/10.1109/ICSC.2014.41","url":null,"abstract":"In recent years, developing needed software applications via the technique Web Service Composition (WSC) has been more and more popular. Moreover, benefit from the Semantic Web Services (SWSs) technology, it is possible to even automatically conduct WSC, i.e. the Automated Web Service composition (AWSC). Currently the AWSC is a well-studied research subject and which means the existence of a large number of related research efforts. To existing AWSC researches, our goal is to make complete and referable surveys of them, and in this paper we adopt a strategy which may be more efficient than directly reviewing original research papers that we inspect and focus on the already-published AWSC surveys, trying to take advantages of them. With an AWSC survey framework proposed by us previously, we present a modest review on the selected AWSC surveys which inspected the AWSC researches that largely benefit from the SWSs technology. For each selected AWSC survey, in this review we indicate what AWSC research concerns defined by us in the survey framework are covered by it and precisely describe its contents. With this review, the reader can easily and quickly find out proper AWSC surveys for more advanced information and reading.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124921670","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}
R. Techentin, D. Foti, Peter W. Li, E. Daniel, B. Gilbert, D. Holmes, Sinan Al-Saffar
We have developed a large semi-synthetic, semantically rich dataset, modeled after the medical record of a large medical institution. Using the highly diverse data.gov data repository and a multivariate data augmentation strategy, we can generate arbitrarily large semi-synthetic datasets which can be used to test new algorithms and computational platforms. The construction process and basic data characterization are described. The databases, as well as code for data collection, consolidation, and augmentation are available for distribution.
{"title":"Development of a Semi-synthetic Dataset as a Testbed for Big-Data Semantic Analytics","authors":"R. Techentin, D. Foti, Peter W. Li, E. Daniel, B. Gilbert, D. Holmes, Sinan Al-Saffar","doi":"10.1109/ICSC.2014.45","DOIUrl":"https://doi.org/10.1109/ICSC.2014.45","url":null,"abstract":"We have developed a large semi-synthetic, semantically rich dataset, modeled after the medical record of a large medical institution. Using the highly diverse data.gov data repository and a multivariate data augmentation strategy, we can generate arbitrarily large semi-synthetic datasets which can be used to test new algorithms and computational platforms. The construction process and basic data characterization are described. The databases, as well as code for data collection, consolidation, and augmentation are available for distribution.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124941043","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}
Connecting ontological representations and data models is a crucial need in enterprise knowledge management, above all in the case of federated enterprises where corporate ontologies are used to share information coming from different databases. OWL to ERD transformations are a challenging research field in this scenario, due to the loss of expressiveness arising when OWL axioms have to be represented using ERD notation. In this paper we propose an innovative technique for estimating the most likely composition of ERD constructs that correspond to a given sequence of OWL axioms. We model such a process using a Hidden Markov Model (HMM) where the OWL inputs are the observable states, while ERD structures are the hidden states. Transition and emission probabilities have been set up heuristically through the analysis of a purposely defined grammar describing the ERD syntax, and all the OWL/ERD mapping rules presented in the literature. The theoretical model is explained in detail, a case study is exploited, and the experimental results are presented.
{"title":"A Hidden Markov Model for Automatic Generation of ER Diagrams from OWL Ontology","authors":"A. Pipitone, R. Pirrone","doi":"10.1109/ICSC.2014.19","DOIUrl":"https://doi.org/10.1109/ICSC.2014.19","url":null,"abstract":"Connecting ontological representations and data models is a crucial need in enterprise knowledge management, above all in the case of federated enterprises where corporate ontologies are used to share information coming from different databases. OWL to ERD transformations are a challenging research field in this scenario, due to the loss of expressiveness arising when OWL axioms have to be represented using ERD notation. In this paper we propose an innovative technique for estimating the most likely composition of ERD constructs that correspond to a given sequence of OWL axioms. We model such a process using a Hidden Markov Model (HMM) where the OWL inputs are the observable states, while ERD structures are the hidden states. Transition and emission probabilities have been set up heuristically through the analysis of a purposely defined grammar describing the ERD syntax, and all the OWL/ERD mapping rules presented in the literature. The theoretical model is explained in detail, a case study is exploited, and the experimental results are presented.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125491689","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：