Pub Date : 2011-04-11DOI: 10.1109/WACI.2011.5953149
Chi-Keng Wu, P. Chung, Chih-Jen Wang
The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.
{"title":"Extracting coherent emotion elicited segments from physiological signals","authors":"Chi-Keng Wu, P. Chung, Chih-Jen Wang","doi":"10.1109/WACI.2011.5953149","DOIUrl":"https://doi.org/10.1109/WACI.2011.5953149","url":null,"abstract":"The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.","PeriodicalId":319764,"journal":{"name":"2011 IEEE Workshop on Affective Computational Intelligence (WACI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130262875","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 : 2011-04-11DOI: 10.1109/WACI.2011.5953151
Roman Miletitch, N. Sabouret, M. Ochs
Telling a story requires linking a series of significant events using statements to maintain tension, create suspense and allow time for the development of emotions. When automating this process, one major challenge is the generation of these filling sentences and ensuring that they are sufficiently consistent with the story. To this end we propose in this paper to use a knowledge representation model of a local coherent world. We present a scheme for automatic storytelling based on an ontological representation of concepts and natural language generation algorithms that dynamically build relations between concepts. Our algorithms scan the scenario to build a sentence skeleton that will be enriched using pseudo-random queries in the ontology. This allows us to enrich the story while keeping the storyline coherent. We end by discussing our evaluation and presenting our preliminary results.
{"title":"From socio-emotional scenarios to expressive virtual narrators","authors":"Roman Miletitch, N. Sabouret, M. Ochs","doi":"10.1109/WACI.2011.5953151","DOIUrl":"https://doi.org/10.1109/WACI.2011.5953151","url":null,"abstract":"Telling a story requires linking a series of significant events using statements to maintain tension, create suspense and allow time for the development of emotions. When automating this process, one major challenge is the generation of these filling sentences and ensuring that they are sufficiently consistent with the story. To this end we propose in this paper to use a knowledge representation model of a local coherent world. We present a scheme for automatic storytelling based on an ontological representation of concepts and natural language generation algorithms that dynamically build relations between concepts. Our algorithms scan the scenario to build a sentence skeleton that will be enriched using pseudo-random queries in the ontology. This allows us to enrich the story while keeping the storyline coherent. We end by discussing our evaluation and presenting our preliminary results.","PeriodicalId":319764,"journal":{"name":"2011 IEEE Workshop on Affective Computational Intelligence (WACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125496862","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 : 1900-01-01DOI: 10.1109/waci.2011.5953156
Ginevra Castellano, Queen Mary, Marc Schroeder
Taking into account emotions, or more generally affects, is currently widely explored to improve the quality of human-machine interaction and to ease the communication with users or potential customers. Affective or emotional computing covers a wide range of issues, challenges and approaches, both for emotion simulation (in particular for new generations of intelligent agents), emotion elicitation, expression and recognition. The latter is declined along several types of modalities and media data, such as physiological signals, facial expressions, speech, text, images and video. Thus, affective computing raises new challenges for computational intelligence, regarding e.g. computational representations of emotions and affective states, on the basis of psychological models, the architecture of systems modeling and processing these concepts as well as dedicated machine learning techniques appropriate to deal with the specificity of the related data. gathers papers from the various disciplines contributing to the domain, offering an overview of the current state of the art on this challenging and fast developing field, including both emotion simulation and emotion recognition, in particular from textual data.
{"title":"WACI 2011 committee","authors":"Ginevra Castellano, Queen Mary, Marc Schroeder","doi":"10.1109/waci.2011.5953156","DOIUrl":"https://doi.org/10.1109/waci.2011.5953156","url":null,"abstract":"Taking into account emotions, or more generally affects, is currently widely explored to improve the quality of human-machine interaction and to ease the communication with users or potential customers. Affective or emotional computing covers a wide range of issues, challenges and approaches, both for emotion simulation (in particular for new generations of intelligent agents), emotion elicitation, expression and recognition. The latter is declined along several types of modalities and media data, such as physiological signals, facial expressions, speech, text, images and video. Thus, affective computing raises new challenges for computational intelligence, regarding e.g. computational representations of emotions and affective states, on the basis of psychological models, the architecture of systems modeling and processing these concepts as well as dedicated machine learning techniques appropriate to deal with the specificity of the related data. gathers papers from the various disciplines contributing to the domain, offering an overview of the current state of the art on this challenging and fast developing field, including both emotion simulation and emotion recognition, in particular from textual data.","PeriodicalId":319764,"journal":{"name":"2011 IEEE Workshop on Affective Computational Intelligence (WACI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130105599","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：