Pub Date : 2015-02-01DOI: 10.1109/ICOSC.2015.7050822
Sungkwang Eom, Sangjin Shin, Kyong-Ho Lee
In this paper, we propose a method for processing spatiotemporal queries on semantic data streams generated from diverse sensors. On the Internet of Things (IoT) environment, the number of mobile sensors greatly increases and their locations are becoming more important. IoT services may not be fully supported when only considering the temporal feature of streaming data. Accordingly, stream processing should be performed with consideration into both temporal and spatial factors. However, existing researches have a limitation of processing spatial queries since they focus on the temporal processing of streaming data. To support spatiotemporal query processing on semantic data streams, we propose a query language, which integrates temporal and geospatial properties. Specifically, we construct a spatiotemporal index to process the proposed spatiotemporal query language efficiently. The experimental results with a prototype implementation show that the proposed method processes spatiotemporal queries in an acceptable time.
{"title":"Spatiotemporal query processing for semantic data stream","authors":"Sungkwang Eom, Sangjin Shin, Kyong-Ho Lee","doi":"10.1109/ICOSC.2015.7050822","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050822","url":null,"abstract":"In this paper, we propose a method for processing spatiotemporal queries on semantic data streams generated from diverse sensors. On the Internet of Things (IoT) environment, the number of mobile sensors greatly increases and their locations are becoming more important. IoT services may not be fully supported when only considering the temporal feature of streaming data. Accordingly, stream processing should be performed with consideration into both temporal and spatial factors. However, existing researches have a limitation of processing spatial queries since they focus on the temporal processing of streaming data. To support spatiotemporal query processing on semantic data streams, we propose a query language, which integrates temporal and geospatial properties. Specifically, we construct a spatiotemporal index to process the proposed spatiotemporal query language efficiently. The experimental results with a prototype implementation show that the proposed method processes spatiotemporal queries in an acceptable time.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127876366","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050805
Shifu Hou, Lifei Chen, E. Tas, Igor Demihovskiy, Yanfang Ye
With explosive growth of malware and due to its damage to computer security, malware detection is one of the cyber security topics that are of great interests. Many research efforts have been conducted on developing intelligent malware detection systems applying data mining techniques. Such techniques have successes in clustering or classifying particular sets of malware samples, but they have limitations that leave a large room for improvement. Specifically, based on the analysis of the file contents extracted from the file samples, existing researches apply only specific clustering or classification methods, but not integrate them together. Actually, the learning of class boundaries for malware detection between overlapping class patterns is a difficult problem. In this paper, resting on the analysis of Windows Application Programming Interface (API) calls extracted from the file samples, we develop the intelligent malware detection system using cluster-oriented ensemble classifiers. To the best of our knowledge, this is the first work of applying such method for malware detection. A comprehensive experimental study on a real and large data collection from Comodo Cloud Security Center is performed to compare various malware detection approaches. Promising experimental results demonstrate that the accuracy and efficiency of our proposed method outperform other alternate data mining based detection techniques.
{"title":"Cluster-oriented ensemble classifiers for intelligent malware detection","authors":"Shifu Hou, Lifei Chen, E. Tas, Igor Demihovskiy, Yanfang Ye","doi":"10.1109/ICOSC.2015.7050805","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050805","url":null,"abstract":"With explosive growth of malware and due to its damage to computer security, malware detection is one of the cyber security topics that are of great interests. Many research efforts have been conducted on developing intelligent malware detection systems applying data mining techniques. Such techniques have successes in clustering or classifying particular sets of malware samples, but they have limitations that leave a large room for improvement. Specifically, based on the analysis of the file contents extracted from the file samples, existing researches apply only specific clustering or classification methods, but not integrate them together. Actually, the learning of class boundaries for malware detection between overlapping class patterns is a difficult problem. In this paper, resting on the analysis of Windows Application Programming Interface (API) calls extracted from the file samples, we develop the intelligent malware detection system using cluster-oriented ensemble classifiers. To the best of our knowledge, this is the first work of applying such method for malware detection. A comprehensive experimental study on a real and large data collection from Comodo Cloud Security Center is performed to compare various malware detection approaches. Promising experimental results demonstrate that the accuracy and efficiency of our proposed method outperform other alternate data mining based detection techniques.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114540136","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050832
Yu Sun, Hyojoon Bae, S. Manna, Jules White, M. G. Fard
Today's industry emphasize greatly on data-driven and data engineering technologies, triggering a tremendous amount of structured and unstructured data across different domains. As a result of which, semantic information is implicitly available in the knowledge base, mainly in the form of data descriptions, and needs to be extracted automatically to better serve the users' need. But how to deliver the data to the end-users in an effective and efficient way, has posed a new challenge, particularly in the context of big data and mobile computing. Traditional search-based approach may suffer from the degraded user experience or scalability. It is very essential to understand meaning (i.e., semantics) rather than pure keywords matching, that might lead to entirely spurious results of no relevance. In this paper, we present the usage of an Augmented Reality (AR) solution to bridge the existing semantic data and information with the real-world physical objects. The AR solution - HD4AR (Hybrid 4-Dimensional Augmented Reality) has been commercialized as a startup company to provide AR service to industry patterns to associate valuable semantic information with the objects in specific contexts, so that users can easily retrieve the data by snapping a photo and having the semantic information rendered on the photo accurately and quickly. Followed by a brief overview of the technology, we present a few use cases as well as the lessons learned from the industry collaboration experience.
{"title":"Bridging semantics with physical objects using augmented reality","authors":"Yu Sun, Hyojoon Bae, S. Manna, Jules White, M. G. Fard","doi":"10.1109/ICOSC.2015.7050832","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050832","url":null,"abstract":"Today's industry emphasize greatly on data-driven and data engineering technologies, triggering a tremendous amount of structured and unstructured data across different domains. As a result of which, semantic information is implicitly available in the knowledge base, mainly in the form of data descriptions, and needs to be extracted automatically to better serve the users' need. But how to deliver the data to the end-users in an effective and efficient way, has posed a new challenge, particularly in the context of big data and mobile computing. Traditional search-based approach may suffer from the degraded user experience or scalability. It is very essential to understand meaning (i.e., semantics) rather than pure keywords matching, that might lead to entirely spurious results of no relevance. In this paper, we present the usage of an Augmented Reality (AR) solution to bridge the existing semantic data and information with the real-world physical objects. The AR solution - HD4AR (Hybrid 4-Dimensional Augmented Reality) has been commercialized as a startup company to provide AR service to industry patterns to associate valuable semantic information with the objects in specific contexts, so that users can easily retrieve the data by snapping a photo and having the semantic information rendered on the photo accurately and quickly. Followed by a brief overview of the technology, we present a few use cases as well as the lessons learned from the industry collaboration experience.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"80 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120824872","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050830
Yoo-mi Park, Hyunkyung Yoo, Cinyoung Hur, Hyunjoo Bae, Yuchul Jung
A service mashup goes through several processes, which it takes much time and efforts for developers to mashup of many heterogeneous web services. To mitigate the complexity of a service mashup and automate the mashup process, the present paper proposes semantic service discovery and matching technologies. The semantic service discovery technology is capable of finding out more appropriate and ranked services with a given query, and the semantic service matching technology enables searching for compatible and interoperable services automatically across a number of heterogeneous web services. The semantic service discovery and matching technologies are based on the service ontology and service metadata that play important roles in relieving the semantic gap between a user's natural query and the technical service description. To verify the usability and effectiveness of the proposed technologies on this environment, experiments and simple use cases are shown. The results indicate that the proposed technologies help developers create new mashup applications more effectively and conveniently.
{"title":"Semantic service discovery and matching for semi-automatic service mashup","authors":"Yoo-mi Park, Hyunkyung Yoo, Cinyoung Hur, Hyunjoo Bae, Yuchul Jung","doi":"10.1109/ICOSC.2015.7050830","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050830","url":null,"abstract":"A service mashup goes through several processes, which it takes much time and efforts for developers to mashup of many heterogeneous web services. To mitigate the complexity of a service mashup and automate the mashup process, the present paper proposes semantic service discovery and matching technologies. The semantic service discovery technology is capable of finding out more appropriate and ranked services with a given query, and the semantic service matching technology enables searching for compatible and interoperable services automatically across a number of heterogeneous web services. The semantic service discovery and matching technologies are based on the service ontology and service metadata that play important roles in relieving the semantic gap between a user's natural query and the technical service description. To verify the usability and effectiveness of the proposed technologies on this environment, experiments and simple use cases are shown. The results indicate that the proposed technologies help developers create new mashup applications more effectively and conveniently.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128457363","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050812
Keira Zhou, J. J. Fox, Ke Wang, Donald E. Brown, K. Skadron
Semantic analysis often uses a pipeline of Natural Language Processing (NLP) tools such as part-of-speech (POS) tagging. Brill tagging is a classic rule-based algorithm for POS tagging within NLP. However, implementation of the tagger is inherently slow on conventional Von Neumann architectures. In this paper, we accelerate the second stage of Brill tagging on the Micron Automata Processor, a new computing architecture that can perform massive pattern matching in parallel. The designed structure is tested with a subset of the Brown Corpus using 218 contextual rules. The results show a 38X speed-up for the second stage tagger implemented on a single AP chip, compared to a single thread implementation on CPU. This speed-up is linear with the number of rules, thus making large and/or complex rule sets computationally practical. This paper introduces the use of this new accelerator for computational linguistic tasks, particularly those that involve rule-based or pattern-matching approaches.
{"title":"Brill tagging on the Micron Automata Processor","authors":"Keira Zhou, J. J. Fox, Ke Wang, Donald E. Brown, K. Skadron","doi":"10.1109/ICOSC.2015.7050812","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050812","url":null,"abstract":"Semantic analysis often uses a pipeline of Natural Language Processing (NLP) tools such as part-of-speech (POS) tagging. Brill tagging is a classic rule-based algorithm for POS tagging within NLP. However, implementation of the tagger is inherently slow on conventional Von Neumann architectures. In this paper, we accelerate the second stage of Brill tagging on the Micron Automata Processor, a new computing architecture that can perform massive pattern matching in parallel. The designed structure is tested with a subset of the Brown Corpus using 218 contextual rules. The results show a 38X speed-up for the second stage tagger implemented on a single AP chip, compared to a single thread implementation on CPU. This speed-up is linear with the number of rules, thus making large and/or complex rule sets computationally practical. This paper introduces the use of this new accelerator for computational linguistic tasks, particularly those that involve rule-based or pattern-matching approaches.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123979615","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 : 2015-02-01DOI: 10.1142/S1793351X15400103
Qingliang Miao, Ruiyu Fang, Yao Meng
The development of modern health care and clinical practice increase the need of nutritional and medical data extraction and integration across heterogeneous data sources. It can be useful for researchers and patients if there is a way to extract relevant information and organize it as easily shared and machine-processable linked data. In this paper, we describe an automatic approach that extracts and publishes nutritional linked data including nutritional concepts and relationships extracted from nutritional data sources. Moreover, we link the nutritional data with Linked Open Data. In particular, a CRF-based approach is used to mine food, ingredient, disease entities and their relationships from nutritional text. And then, an extended nutritional ontology is used to organize the extracted data. Finally, we assign semantic links between food, ingredient, disease entities and other equivalent entities in DBPedia, Diseasome and LinkedCT.
{"title":"Extracting and integrating nutrition related linked data","authors":"Qingliang Miao, Ruiyu Fang, Yao Meng","doi":"10.1142/S1793351X15400103","DOIUrl":"https://doi.org/10.1142/S1793351X15400103","url":null,"abstract":"The development of modern health care and clinical practice increase the need of nutritional and medical data extraction and integration across heterogeneous data sources. It can be useful for researchers and patients if there is a way to extract relevant information and organize it as easily shared and machine-processable linked data. In this paper, we describe an automatic approach that extracts and publishes nutritional linked data including nutritional concepts and relationships extracted from nutritional data sources. Moreover, we link the nutritional data with Linked Open Data. In particular, a CRF-based approach is used to mine food, ingredient, disease entities and their relationships from nutritional text. And then, an extended nutritional ontology is used to organize the extracted data. Finally, we assign semantic links between food, ingredient, disease entities and other equivalent entities in DBPedia, Diseasome and LinkedCT.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127374155","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050790
M. Davoudpour, A. Sadeghian, H. Rahnama
In the past few years, the advances in context-aware systems and sensor technologies, has elevated the Internet of Things (IoT) development greatly and rather quickly. Services of IoT systems must be reasonably designed to provide not only the user's requirements and requests, but also perceive the environmental context and customized services to get user's satisfaction. Systematic modeling methodologies are essential to control the correctness of the services and the systems behaviors among dynamic changing contexts. The presented solution will be a novel IoT framework, “CANthings” (Context-Aware Networks for the Design of Connected Things) to identify IoT needs.This paper mainly promotes and analyzes an IoT system modeling methodology based on Timed Colored Petri Net (TCPN) to check the effectiveness of the provided services in the CANthings framework. Our goal is to present a standard solution that can be used in high-technical research and industrial projects.
{"title":"“CANthings”(Context Aware Network for the Design of Connected Things) service modeling based on Timed CPN","authors":"M. Davoudpour, A. Sadeghian, H. Rahnama","doi":"10.1109/ICOSC.2015.7050790","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050790","url":null,"abstract":"In the past few years, the advances in context-aware systems and sensor technologies, has elevated the Internet of Things (IoT) development greatly and rather quickly. Services of IoT systems must be reasonably designed to provide not only the user's requirements and requests, but also perceive the environmental context and customized services to get user's satisfaction. Systematic modeling methodologies are essential to control the correctness of the services and the systems behaviors among dynamic changing contexts. The presented solution will be a novel IoT framework, “CANthings” (Context-Aware Networks for the Design of Connected Things) to identify IoT needs.This paper mainly promotes and analyzes an IoT system modeling methodology based on Timed Colored Petri Net (TCPN) to check the effectiveness of the provided services in the CANthings framework. Our goal is to present a standard solution that can be used in high-technical research and industrial projects.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126432384","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050796
H. Mochizuki
This paper describes a method to replace commonly used scales with personalized scales. We explain a notion of personalized scales and describe our replacement system, the MyScale interface. Two prototypes of MyScale are shown. MyScale: heights, distances, weights and areas replaces numeric expressions of common scales with personalized scales in order to assist a user's intuitive understanding. MyScale: Map provides an interface so that the distance and location on the original map can be compared directly with familiar locations on the user's map.
{"title":"MyScale: Making personal paraphrases and replacement of scales","authors":"H. Mochizuki","doi":"10.1109/ICOSC.2015.7050796","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050796","url":null,"abstract":"This paper describes a method to replace commonly used scales with personalized scales. We explain a notion of personalized scales and describe our replacement system, the MyScale interface. Two prototypes of MyScale are shown. MyScale: heights, distances, weights and areas replaces numeric expressions of common scales with personalized scales in order to assist a user's intuitive understanding. MyScale: Map provides an interface so that the distance and location on the original map can be compared directly with familiar locations on the user's map.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131826135","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050786
Jinho Shin, Sungkwang Eom, Kyong-Ho Lee
In this paper, we address the problem of processing semantic data streams. The semantic annotation of sensor data is one of the solutions to the heterogeneous nature of sensor data streams. Existing systems for publishing semantic streaming data collect stream data and transmit the semantic streaming data to query engines regardless of the queries registered in the query engines. As a large number of sensing devices become available, there is an increasing amount of the stream data, resulting in the performance degradation of a query engine. To remedy this problem, we propose a query-adaptive method of filtering semantic streams. The proposed method filters out sensors and semantic streaming data, which are not related with queries registered in a semantic stream query engine. The approach fairly reduces the data size necessary to answer semantic stream queries and consequently improves the performance of the query processing. To demonstrate the efficiency of our proposal, we present extensive experimental performance evaluations under a variety of sensor streams and query types. Experimental results show that the proposed method dramatically improves the performance of query processing compared to a non-filtering approach.
{"title":"Q-ASSF: Query-adaptive semantic stream filtering","authors":"Jinho Shin, Sungkwang Eom, Kyong-Ho Lee","doi":"10.1109/ICOSC.2015.7050786","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050786","url":null,"abstract":"In this paper, we address the problem of processing semantic data streams. The semantic annotation of sensor data is one of the solutions to the heterogeneous nature of sensor data streams. Existing systems for publishing semantic streaming data collect stream data and transmit the semantic streaming data to query engines regardless of the queries registered in the query engines. As a large number of sensing devices become available, there is an increasing amount of the stream data, resulting in the performance degradation of a query engine. To remedy this problem, we propose a query-adaptive method of filtering semantic streams. The proposed method filters out sensors and semantic streaming data, which are not related with queries registered in a semantic stream query engine. The approach fairly reduces the data size necessary to answer semantic stream queries and consequently improves the performance of the query processing. To demonstrate the efficiency of our proposal, we present extensive experimental performance evaluations under a variety of sensor streams and query types. Experimental results show that the proposed method dramatically improves the performance of query processing compared to a non-filtering approach.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129640439","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 : 2015-02-01DOI: 10.1109/ICOSC.2015.7050803
Quanzeng You, Jianbo Yuan, Jiaqi Wang, Philip J. Guo, Jiebo Luo
The increasing popularity of smartphones has significantly changed the way we live. Today's powerful mobile systems provide us with all kinds of convenient services. Thanks to the wide variety of available apps, it has never been so easy for people to shop, to navigate, and to communicate with others. However, for some tasks we can further improve the user experience by employing newly developed algorithms. In this work, we try to improve visual search based mobile shopping experience by using machine and crowd intelligence. In particular, our system enables precise object selection, which would lead to more accurate visual search results. We also use crowdsourcing to further extend the system's prowess. We conduct experiments on user interface design and retrieval performance, which validate the effectiveness and ease of use of the proposed system. Meanwhile, components in the system are quite modular, allowing the flexibility of adding or improving different modules of the whole system.
{"title":"Snap n' shop: Visual search-based mobile shopping made a breeze by machine and crowd intelligence","authors":"Quanzeng You, Jianbo Yuan, Jiaqi Wang, Philip J. Guo, Jiebo Luo","doi":"10.1109/ICOSC.2015.7050803","DOIUrl":"https://doi.org/10.1109/ICOSC.2015.7050803","url":null,"abstract":"The increasing popularity of smartphones has significantly changed the way we live. Today's powerful mobile systems provide us with all kinds of convenient services. Thanks to the wide variety of available apps, it has never been so easy for people to shop, to navigate, and to communicate with others. However, for some tasks we can further improve the user experience by employing newly developed algorithms. In this work, we try to improve visual search based mobile shopping experience by using machine and crowd intelligence. In particular, our system enables precise object selection, which would lead to more accurate visual search results. We also use crowdsourcing to further extend the system's prowess. We conduct experiments on user interface design and retrieval performance, which validate the effectiveness and ease of use of the proposed system. Meanwhile, components in the system are quite modular, allowing the flexibility of adding or improving different modules of the whole system.","PeriodicalId":126701,"journal":{"name":"Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128650139","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：