Pub Date : 2010-12-07DOI: 10.1109/SOCPAR.2010.5686076
K. Harmer, Shigang Yue, K. Guo, Karen Adams, A. Hunter
Blushing has been identified as an indicator of deception, shame, anxiety and embarrassment. Although normally associated with the skin coloration of the face, a blush response also affects skin surface temperature. In this paper, an approach to detect a blush response automatically is presented using the Argus P7225 thermal camera from e2v. The algorithm was tested on a sample population of 51 subjects, while using visual stimuli to elicit a response, and achieved recognition rates of ∼77% TPR and ∼60% TNR.
{"title":"Automatic blush detection in “Concealed information” test using visual stimuli","authors":"K. Harmer, Shigang Yue, K. Guo, Karen Adams, A. Hunter","doi":"10.1109/SOCPAR.2010.5686076","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686076","url":null,"abstract":"Blushing has been identified as an indicator of deception, shame, anxiety and embarrassment. Although normally associated with the skin coloration of the face, a blush response also affects skin surface temperature. In this paper, an approach to detect a blush response automatically is presented using the Argus P7225 thermal camera from e2v. The algorithm was tested on a sample population of 51 subjects, while using visual stimuli to elicit a response, and achieved recognition rates of ∼77% TPR and ∼60% TNR.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"54 26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124070295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686427
A. Hadjali, O. Pivert, H. Prade
We propose a possibility theory-based approach to the treatment of missing user preferences in skyline queries. To compensate this lack of knowledge, we show how a set of plausible preferences suitable for the current context can be derived either in a case-based reasoning manner, or using an extended possibilistic logic setting. Uncertain dominance relationships are defined in a possibilistic way and the notion of possibilistic contextual skyline is introduced. This kind of skyline allows us to return the tuples that are non-dominated with a high certainty. The paper also includes a structured overview of the different types of “fuzzy” skylines.
{"title":"Possibilistic contextual skylines with incomplete preferences","authors":"A. Hadjali, O. Pivert, H. Prade","doi":"10.1109/SOCPAR.2010.5686427","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686427","url":null,"abstract":"We propose a possibility theory-based approach to the treatment of missing user preferences in skyline queries. To compensate this lack of knowledge, we show how a set of plausible preferences suitable for the current context can be derived either in a case-based reasoning manner, or using an extended possibilistic logic setting. Uncertain dominance relationships are defined in a possibilistic way and the notion of possibilistic contextual skyline is introduced. This kind of skyline allows us to return the tuples that are non-dominated with a high certainty. The paper also includes a structured overview of the different types of “fuzzy” skylines.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115549320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686522
S. Darwish
Recently, much interest is being taken to protect the copyright of digital data and prevent illegal duplication of it. Towards this purpose, this paper proposes an imperceptible blind watermarking framework suitable for proving ownership claims for large 3D meshes. The basic idea is to decompose the original mesh into a series of details at different scales by using irregular lifting-based wavelet analysis; the watermark is then inserted in different resolution levels by modifying the statistical features of wavelet coefficients. The robustness of the presented framework is achieved by embedding the watermark in a normalized version of the host mesh, which are quite insensible to geometrical attacks. While, the intelligence is obtained by the use of a genetic algorithm to improve framework performance via choosing the optimal solution between the two conflicting objectives: robustness and invisibility. Simulation results show that both objectives can be achieved under different attack schemes.
{"title":"Intelligent copyright protection framework for irregular large 3D meshes","authors":"S. Darwish","doi":"10.1109/SOCPAR.2010.5686522","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686522","url":null,"abstract":"Recently, much interest is being taken to protect the copyright of digital data and prevent illegal duplication of it. Towards this purpose, this paper proposes an imperceptible blind watermarking framework suitable for proving ownership claims for large 3D meshes. The basic idea is to decompose the original mesh into a series of details at different scales by using irregular lifting-based wavelet analysis; the watermark is then inserted in different resolution levels by modifying the statistical features of wavelet coefficients. The robustness of the presented framework is achieved by embedding the watermark in a normalized version of the host mesh, which are quite insensible to geometrical attacks. While, the intelligence is obtained by the use of a genetic algorithm to improve framework performance via choosing the optimal solution between the two conflicting objectives: robustness and invisibility. Simulation results show that both objectives can be achieved under different attack schemes.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127679088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686086
Uwe Jänen, C. Paul, Michael Wittke, J. Hähner
In this article we present an approach for robust multi-object tracking. Typically the task of object tracking can be divided into two subtasks: object detection and object labeling. The main focus of the work presented here is on an approach for consistently labeling objects across a series of video frames using neural networks. Due to the specialization of object detection algortihms it is necessary to divide detection and labeling to enhance their individual skills. In the evaluation we show that the developed labeling is robust against occlusions and can handle low object detection rates.
{"title":"Multi-object tracking using feed-forward neural networks","authors":"Uwe Jänen, C. Paul, Michael Wittke, J. Hähner","doi":"10.1109/SOCPAR.2010.5686086","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686086","url":null,"abstract":"In this article we present an approach for robust multi-object tracking. Typically the task of object tracking can be divided into two subtasks: object detection and object labeling. The main focus of the work presented here is on an approach for consistently labeling objects across a series of video frames using neural networks. Due to the specialization of object detection algortihms it is necessary to divide detection and labeling to enhance their individual skills. In the evaluation we show that the developed labeling is robust against occlusions and can handle low object detection rates.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132127096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686732
Youdthachai Lertworaprachaya, Yingjie Yang, R. John
This paper proposes a novel improved model for fuzzy time series forecasting using high-order and Type-2 fuzzy time series. Some Type-1 fuzzy time series model based on first order and high-order fuzzy time series have already been developed, however the accuracy of the forecasting values sill needs to be improved. In this paper, we present a high-order fuzzy time series model using Type-2 fuzzy sets. The employment of Type-2 fuzzy sets enables the proposed method to achieve a better result compared with existing fuzzy time series models. Our experimental results demonstrate the improved forecasting accuracy and reliability in comparison with other existing fuzzy time series models.
{"title":"High-order Type-2 fuzzy time series","authors":"Youdthachai Lertworaprachaya, Yingjie Yang, R. John","doi":"10.1109/SOCPAR.2010.5686732","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686732","url":null,"abstract":"This paper proposes a novel improved model for fuzzy time series forecasting using high-order and Type-2 fuzzy time series. Some Type-1 fuzzy time series model based on first order and high-order fuzzy time series have already been developed, however the accuracy of the forecasting values sill needs to be improved. In this paper, we present a high-order fuzzy time series model using Type-2 fuzzy sets. The employment of Type-2 fuzzy sets enables the proposed method to achieve a better result compared with existing fuzzy time series models. Our experimental results demonstrate the improved forecasting accuracy and reliability in comparison with other existing fuzzy time series models.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130810586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686642
Arash Iranzad, Saeed Masoudnia, Fatemeh Cheraghchi, A. Nowzari-Dalini, R. Ebrahimpour
This paper investigates the effect of diversity caused by Negative Correlation Learning (NCL) in the combination of neural classifiers and presents an efficient way to improve combining performance. Decision Templates and Averaging, as two non-trainable combining methods and Stacked Generalization as a trainable combiner are investigated in our experiments. Utilizing NCL for diversifying the base classifiers leads to significantly better results in all employed combining methods. Experimental results on five datasets from UCI repository indicate that by employing NCL, the performance of the ensemble structure can be more favorable compared to that of an ensemble use independent base classifiers.
{"title":"Using NCL, an effective way to improve combination methods of neural classifiers","authors":"Arash Iranzad, Saeed Masoudnia, Fatemeh Cheraghchi, A. Nowzari-Dalini, R. Ebrahimpour","doi":"10.1109/SOCPAR.2010.5686642","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686642","url":null,"abstract":"This paper investigates the effect of diversity caused by Negative Correlation Learning (NCL) in the combination of neural classifiers and presents an efficient way to improve combining performance. Decision Templates and Averaging, as two non-trainable combining methods and Stacked Generalization as a trainable combiner are investigated in our experiments. Utilizing NCL for diversifying the base classifiers leads to significantly better results in all employed combining methods. Experimental results on five datasets from UCI repository indicate that by employing NCL, the performance of the ensemble structure can be more favorable compared to that of an ensemble use independent base classifiers.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130723555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686527
S. Pal, Aniruddha Basak, Swagatam Das, A. Abraham, I. Zelinka
Concentric Circular Antenna Array (CCAA) has several interesting features that makes it indispensable in mobile and communication applications. Here we have considered a uniform arrangement of elements where the inter-element spacing is kept half a wavelength. The main aim is to reduce the sidelobe levels and the primary lobe beamwidth as much as possible. Central to our design is a hybridization of two prominent metaheuristics of current interest namely the Invasive Weed Optimization (IWO) and Differential Evolution (DE). The results of the DIWO algorithm have been shown to perform better then other state-of-the-art metaheuristics like the Particle Swarm Optimization (PSO), DE and IWO.
{"title":"Concentric Circular Antenna Array synthesis using a differential Invasive Weed Optimization algorithm","authors":"S. Pal, Aniruddha Basak, Swagatam Das, A. Abraham, I. Zelinka","doi":"10.1109/SOCPAR.2010.5686527","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686527","url":null,"abstract":"Concentric Circular Antenna Array (CCAA) has several interesting features that makes it indispensable in mobile and communication applications. Here we have considered a uniform arrangement of elements where the inter-element spacing is kept half a wavelength. The main aim is to reduce the sidelobe levels and the primary lobe beamwidth as much as possible. Central to our design is a hybridization of two prominent metaheuristics of current interest namely the Invasive Weed Optimization (IWO) and Differential Evolution (DE). The results of the DIWO algorithm have been shown to perform better then other state-of-the-art metaheuristics like the Particle Swarm Optimization (PSO), DE and IWO.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132631676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5686424
Z. Csajbók
There are close links between mathematical morphology and rough set theory. Both theories are successfully applied among others to image processing and pattern recognition. This paper presents a new generalization of the classical rough set theory, called the partial approximative set theory (PAST). According to Pawlak's classic rough set theory, the vagueness of a subset of a finite universe is defined by the difference of its upper and lower approximations with respect to an equivalence relation on the universe. There are two most natural ways of the generalization of this idea. Namely, the equivalence relation is replaced by either any other type of binary relations on the universe or an arbitrary covering of the universe. In this paper, our starting point will be an arbitrary family of subsets of an arbitrary universe, neither that it covers the universe nor that the universe is finite will be assumed. We will give some reasons why this new approach is worth studying, and put our discussions into an overall treatment, called the general approximation framework.
{"title":"Partial approximative set theory: A generalization of the rough set theory","authors":"Z. Csajbók","doi":"10.1109/SOCPAR.2010.5686424","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5686424","url":null,"abstract":"There are close links between mathematical morphology and rough set theory. Both theories are successfully applied among others to image processing and pattern recognition. This paper presents a new generalization of the classical rough set theory, called the partial approximative set theory (PAST). According to Pawlak's classic rough set theory, the vagueness of a subset of a finite universe is defined by the difference of its upper and lower approximations with respect to an equivalence relation on the universe. There are two most natural ways of the generalization of this idea. Namely, the equivalence relation is replaced by either any other type of binary relations on the universe or an arbitrary covering of the universe. In this paper, our starting point will be an arbitrary family of subsets of an arbitrary universe, neither that it covers the universe nor that the universe is finite will be assumed. We will give some reasons why this new approach is worth studying, and put our discussions into an overall treatment, called the general approximation framework.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114504687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5685957
H. Kadima, M. Malek
Personalized search, navigation and content delivery techniques have attracted interest in the recommender systems as a means to decrease search ambiguity and return results most relevant to a particular user preferences. In this paper, we study the effect of incorporating user semantic profile derived from past user's behavior and preferences on the accuracy of a recommender system. We present a preliminary work which aims at tackling the most technical issues due to the integration of an ontology-based semantic user profile within a hybrid recommender system based on our early released guided recommender algorithm. A semantic user profile context is represented as an instance of a reference domain ontology in which concepts are annotated by interest scores.
{"title":"Toward ontology-based personalization of a recommender system in social network","authors":"H. Kadima, M. Malek","doi":"10.1109/SOCPAR.2010.5685957","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5685957","url":null,"abstract":"Personalized search, navigation and content delivery techniques have attracted interest in the recommender systems as a means to decrease search ambiguity and return results most relevant to a particular user preferences. In this paper, we study the effect of incorporating user semantic profile derived from past user's behavior and preferences on the accuracy of a recommender system. We present a preliminary work which aims at tackling the most technical issues due to the integration of an ontology-based semantic user profile within a hybrid recommender system based on our early released guided recommender algorithm. A semantic user profile context is represented as an instance of a reference domain ontology in which concepts are annotated by interest scores.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125902148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-12-01DOI: 10.1109/SOCPAR.2010.5685934
S. Darwish
Today, with the fast development of Extensible Markup Language (XML) and increasing amount of data that is published in the form of XML, copyright protection of these data is becoming an important requirement for numerous applications. This study is proposing a system that uses fingerprinting to trace illegal copies and detect any modification made to an XML data. However, the flexible construction of XML data poses a number of challenges to fingerprinting, such as reorganization and alteration. To overcome these challenges, the proposed system has to be based on the winnowing theory, which selects fingerprints from hashes of XML elements. This system is effective to make less distortion to the original data and to preserve usability constraints. Experimental results show that the probability of missing fingerprint detection is very low and the chance to locate changes in the XML data is very high.
{"title":"An optimized fingerprinting system for tamper proof and copy control of XML documents","authors":"S. Darwish","doi":"10.1109/SOCPAR.2010.5685934","DOIUrl":"https://doi.org/10.1109/SOCPAR.2010.5685934","url":null,"abstract":"Today, with the fast development of Extensible Markup Language (XML) and increasing amount of data that is published in the form of XML, copyright protection of these data is becoming an important requirement for numerous applications. This study is proposing a system that uses fingerprinting to trace illegal copies and detect any modification made to an XML data. However, the flexible construction of XML data poses a number of challenges to fingerprinting, such as reorganization and alteration. To overcome these challenges, the proposed system has to be based on the winnowing theory, which selects fingerprints from hashes of XML elements. This system is effective to make less distortion to the original data and to preserve usability constraints. Experimental results show that the probability of missing fingerprint detection is very low and the chance to locate changes in the XML data is very high.","PeriodicalId":397384,"journal":{"name":"2010 International Conference of Soft Computing and Pattern Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128632465","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：