Pub Date : 2019-11-01DOI: 10.1109/iske47853.2019.9170452
{"title":"ISKE 2019 Cover Page","authors":"","doi":"10.1109/iske47853.2019.9170452","DOIUrl":"https://doi.org/10.1109/iske47853.2019.9170452","url":null,"abstract":"","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126324200","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170203
Zhuyang Xie, B. Peng, Junzhou Chen
With the development of various 3D sensors, it has become easier for humans to obtain information in the 3D world, more and more people turn their attention to the problem of point clouds understanding. At present, most of methods focus on directly extracting features from point clouds, where feature extraction is performed by Multi-Layer Perception (MLP) and fusion is by local pooling. However, they do not consider the spatial relationship within the local point sets. We propose a directed connected graph network (DCGN), which can effectively capture the spatial relationship of local point sets by constructing the directed connected graph (DCG). Specifically, in the feature learning stage, the connection directions from neighbor points to the center point are constructed for each local point set to learn the feature transferring weights from neighbor points to center point. In order to further model the spatial distribution of local point sets, we use a distance-weighted method to perform local feature fusion. Extensive experimental results demonstrate that our method can achieve competitive performance on some standard data sets.
{"title":"Point Clouds Learning Using Directed Connected Graph","authors":"Zhuyang Xie, B. Peng, Junzhou Chen","doi":"10.1109/ISKE47853.2019.9170203","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170203","url":null,"abstract":"With the development of various 3D sensors, it has become easier for humans to obtain information in the 3D world, more and more people turn their attention to the problem of point clouds understanding. At present, most of methods focus on directly extracting features from point clouds, where feature extraction is performed by Multi-Layer Perception (MLP) and fusion is by local pooling. However, they do not consider the spatial relationship within the local point sets. We propose a directed connected graph network (DCGN), which can effectively capture the spatial relationship of local point sets by constructing the directed connected graph (DCG). Specifically, in the feature learning stage, the connection directions from neighbor points to the center point are constructed for each local point set to learn the feature transferring weights from neighbor points to center point. In order to further model the spatial distribution of local point sets, we use a distance-weighted method to perform local feature fusion. Extensive experimental results demonstrate that our method can achieve competitive performance on some standard data sets.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"127 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126275710","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170375
Raad Bin Tareaf, S. Alhosseini, Philipp Berger, Patrick Hennig, C. Meinel
We demonstrate that easy accessible digital records of behavior such as Facebook Likes can be obtained and utilized to automatically distinguish a wide range of highly delicate personal traits such as the Big Five personality traits. The analysis presented based on a dataset of over 738,000 users conferred their Facebook Likes (95 million unique Like objects), social network activities, posts, egocentric network, demographic characteristics, and results of various self-reported psychometric tests. The proposed model uses a new and unique mapping technique between each Facebook Like object to their corresponding Facebook page category/sub-category object extracted from the API calls as Likes metadata, which is then evaluated as features for a set of machine learning algorithms to predict individual psychodemographic profiles from users Likes. Traditionally, entities where able to access an individual’s personality through having them fill out psychological questionnaires. In this paper, we present a method which indicates that a person’s Big Five personality score can be easily predicted by leveraging the information about the pages a person liked on Facebook.
{"title":"Towards Automatic Personality Prediction Using Facebook Likes Metadata","authors":"Raad Bin Tareaf, S. Alhosseini, Philipp Berger, Patrick Hennig, C. Meinel","doi":"10.1109/ISKE47853.2019.9170375","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170375","url":null,"abstract":"We demonstrate that easy accessible digital records of behavior such as Facebook Likes can be obtained and utilized to automatically distinguish a wide range of highly delicate personal traits such as the Big Five personality traits. The analysis presented based on a dataset of over 738,000 users conferred their Facebook Likes (95 million unique Like objects), social network activities, posts, egocentric network, demographic characteristics, and results of various self-reported psychometric tests. The proposed model uses a new and unique mapping technique between each Facebook Like object to their corresponding Facebook page category/sub-category object extracted from the API calls as Likes metadata, which is then evaluated as features for a set of machine learning algorithms to predict individual psychodemographic profiles from users Likes. Traditionally, entities where able to access an individual’s personality through having them fill out psychological questionnaires. In this paper, we present a method which indicates that a person’s Big Five personality score can be easily predicted by leveraging the information about the pages a person liked on Facebook.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120961247","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170399
Yiling Zhang, Yan Yang, Wei Zhou, Xiaocao Ouyang, Xiaobo Zhang
Multitask multiview clustering involves multitask algorithms and multiview algorithms in clustering. As there exists certain relationship among multiple tasks and abundant features in various views, multitask multiview clustering utilizing latent structures to promote the performance for single task, has received much attention recently. We propose a consensus clustering method in this paper for multitask multiview situation $(C^{2} {MTMV})$. It firstly integrates the features from various views to produce a consistent representation for each task. Then it further explores the knowledge existing in within-task and between-tasks and transfers them into other related tasks to assist in clustering. Experimental results comparing with 6 existing algorithms on 5 datasets show the superiority of our method.
{"title":"A Consensus Clustering Algorithm for Multitask Multiview Learning","authors":"Yiling Zhang, Yan Yang, Wei Zhou, Xiaocao Ouyang, Xiaobo Zhang","doi":"10.1109/ISKE47853.2019.9170399","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170399","url":null,"abstract":"Multitask multiview clustering involves multitask algorithms and multiview algorithms in clustering. As there exists certain relationship among multiple tasks and abundant features in various views, multitask multiview clustering utilizing latent structures to promote the performance for single task, has received much attention recently. We propose a consensus clustering method in this paper for multitask multiview situation $(C^{2} {MTMV})$. It firstly integrates the features from various views to produce a consistent representation for each task. Then it further explores the knowledge existing in within-task and between-tasks and transfers them into other related tasks to assist in clustering. Experimental results comparing with 6 existing algorithms on 5 datasets show the superiority of our method.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124963836","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 : 2019-11-01DOI: 10.1109/iske47853.2019.9170464
Hongya Wang, Lixia Yu
For the images characteristic With intensity inhomogeneity, this paper proposes an improved model of contour evolution LBF energy function, Which combines the global CV model energy term accelerated evolution rate and the combined local mean LBF model information, While the introduction of a global image of the local variance and variance information. Experimental results show that this method can provide accurate smooth closed boundary, precision can reach sub-pixel level. The recognition accuracy rate is high.
{"title":"Research on Improved of Level Set Image Segmentation Algorithms Based on LBF Model","authors":"Hongya Wang, Lixia Yu","doi":"10.1109/iske47853.2019.9170464","DOIUrl":"https://doi.org/10.1109/iske47853.2019.9170464","url":null,"abstract":"For the images characteristic With intensity inhomogeneity, this paper proposes an improved model of contour evolution LBF energy function, Which combines the global CV model energy term accelerated evolution rate and the combined local mean LBF model information, While the introduction of a global image of the local variance and variance information. Experimental results show that this method can provide accurate smooth closed boundary, precision can reach sub-pixel level. The recognition accuracy rate is high.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121450325","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170313
Yuan Rong, Qiaoqiao Zhang, Xiaofang Lu, Zheng Pei
Spherical fuzzy set (SFS) is a more effective tool to represent fuzzy and indeterminate information than picture fuzzy set (PFS). TODIM (Portuguese abbreviation for interactive multi-criteria decision-making) technique can describe the psychological behavior of decision-makers under risk, which is already widely applied to deal with multi-criteria decision making (MCDM) problems. In this article, the streamlined spherical fuzzy TODIM approach is established based on the picture fuzzy TODIM method and classic TODIM method and a paradox of SF TODIM approach is analyzed. What’s more, the generalized Spherical fuzzy TODIM approach is developed inspired by the generalized TODIM method. Ultimately, we verify the valid and practicability of the propounded method by utilizing illustrative examples, as well as the comparative analysis and advantages of presented approaches are demonstrated by comparing with existing approaches.
{"title":"Generalized Spherical Fuzzy TODIM Approach to Multiple Criteria Decision Making","authors":"Yuan Rong, Qiaoqiao Zhang, Xiaofang Lu, Zheng Pei","doi":"10.1109/ISKE47853.2019.9170313","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170313","url":null,"abstract":"Spherical fuzzy set (SFS) is a more effective tool to represent fuzzy and indeterminate information than picture fuzzy set (PFS). TODIM (Portuguese abbreviation for interactive multi-criteria decision-making) technique can describe the psychological behavior of decision-makers under risk, which is already widely applied to deal with multi-criteria decision making (MCDM) problems. In this article, the streamlined spherical fuzzy TODIM approach is established based on the picture fuzzy TODIM method and classic TODIM method and a paradox of SF TODIM approach is analyzed. What’s more, the generalized Spherical fuzzy TODIM approach is developed inspired by the generalized TODIM method. Ultimately, we verify the valid and practicability of the propounded method by utilizing illustrative examples, as well as the comparative analysis and advantages of presented approaches are demonstrated by comparing with existing approaches.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132112984","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170278
Chao Wang, B. Peng, Xun Gong, Zeng Yu, Tianrui Li
In the image segmentation task, different understandings of the image content will lead to different granularities of segmentation results. Existing segmentation evaluation methods generally use one or more reference segmentations to evaluate the quality of image segmentation. But the limited number of reference segmentations can not give an comprehensive definition on the image granularity division. To solve the this problem, we present a segmentation evaluation method based on tree structure. Firstly, the regional granularity analysis is performed on multiple reference segmentations of the same image. A multilevel region tree is constructed and different layers in the region tree will correspond to different granularities of the reference segmentations; Secondly, for a segmentation to be evaluated, we adaptively select a layer in the region tree as a reference segmentation, which has similar region granularity with the input segmentation. The proposed evaluation method utilizes multilevel information in the image content, which leads to a more accurate and objective evaluation.
{"title":"Evaluating Segmentation Quality via Reference Segmentations in Tree-like Structure","authors":"Chao Wang, B. Peng, Xun Gong, Zeng Yu, Tianrui Li","doi":"10.1109/ISKE47853.2019.9170278","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170278","url":null,"abstract":"In the image segmentation task, different understandings of the image content will lead to different granularities of segmentation results. Existing segmentation evaluation methods generally use one or more reference segmentations to evaluate the quality of image segmentation. But the limited number of reference segmentations can not give an comprehensive definition on the image granularity division. To solve the this problem, we present a segmentation evaluation method based on tree structure. Firstly, the regional granularity analysis is performed on multiple reference segmentations of the same image. A multilevel region tree is constructed and different layers in the region tree will correspond to different granularities of the reference segmentations; Secondly, for a segmentation to be evaluated, we adaptively select a layer in the region tree as a reference segmentation, which has similar region granularity with the input segmentation. The proposed evaluation method utilizes multilevel information in the image content, which leads to a more accurate and objective evaluation.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134516408","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170286
Kaiyan Yang, L. Shu
We combine dual interval valued hesitant fuzzy sets with rough sets to construct a hybrid uncertainty theory. According to the proposed dual interval valued hesitant fuzzy relation, our paper firstly investigated the two rough approximation operators, lower and upper of dual interval valued hesitant fuzzy set. Properties of the two rough approximation operators, their relationships between three specific dual interval valued hesitant fuzzy sets as well as four special fuzzy relations, serial, reflexive, symmetric and transitive relations of the dual interval valued hesitant fuzzy are further studied. Finally, We show the proposed dual interval valued hesitant fuzzy rough set anastz can help making decisions in clinic medical diagnosis.
{"title":"Constructive Method for Dual Interval Valued Hesitant Fuzzy Rough Sets","authors":"Kaiyan Yang, L. Shu","doi":"10.1109/ISKE47853.2019.9170286","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170286","url":null,"abstract":"We combine dual interval valued hesitant fuzzy sets with rough sets to construct a hybrid uncertainty theory. According to the proposed dual interval valued hesitant fuzzy relation, our paper firstly investigated the two rough approximation operators, lower and upper of dual interval valued hesitant fuzzy set. Properties of the two rough approximation operators, their relationships between three specific dual interval valued hesitant fuzzy sets as well as four special fuzzy relations, serial, reflexive, symmetric and transitive relations of the dual interval valued hesitant fuzzy are further studied. Finally, We show the proposed dual interval valued hesitant fuzzy rough set anastz can help making decisions in clinic medical diagnosis.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133078878","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}
Relation classification is a fundamental ingredient in various information extraction systems. To extract personal entity relation from Chinese text, a novel deep neural network architecture is proposed this paper, which employs bidirectional Gated Recurrent Unit (Bi-GRU) by adding attention mechanism to capture important semantic information in a sentence without hand-crafted features. Considering the complexity of Chinese text, word representation is obtained as a concatenation of word embeddings and character embeddings. Besides, the relative distances of the current word to the entities are added to the word representation to improve the performance of the relation classification. At last, the experimental results demonstrate the proposed model is more effective than state-of-the-art methods.
{"title":"Inter-Person Relation Classification via AttentionBased Bidirectional Gated Recurrent Unit","authors":"Dandan Zhao, Degen Huang, Jiana Meng, Jing Zhang, Shichang Sun, Yuhai Yu","doi":"10.1109/ISKE47853.2019.9170461","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170461","url":null,"abstract":"Relation classification is a fundamental ingredient in various information extraction systems. To extract personal entity relation from Chinese text, a novel deep neural network architecture is proposed this paper, which employs bidirectional Gated Recurrent Unit (Bi-GRU) by adding attention mechanism to capture important semantic information in a sentence without hand-crafted features. Considering the complexity of Chinese text, word representation is obtained as a concatenation of word embeddings and character embeddings. Besides, the relative distances of the current word to the entities are added to the word representation to improve the performance of the relation classification. At last, the experimental results demonstrate the proposed model is more effective than state-of-the-art methods.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117144497","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 : 2019-11-01DOI: 10.1109/ISKE47853.2019.9170397
Shengwu Wang, Hongmei Chen, Xin-Nan Fan
Aiming at the problem that the high computational complexity of calculating information entropy and mutual information of a neighborhood rough set, a fast calculation method based on data sorting was proposed to estimate neighborhood mutual information speedily. This method can reduce the computational complexity of neighborhood entropy from O(n2) to O(nlogn). Under this premise, the method can calculate the approximation of the joint neighborhood entropy by infinite-norm-calculated neighborhood relation, thus to estimate the neighborhood mutual information quickly. For the reason that the method is based on neighborhood entropy, it is also effective for mixed data. Experimental results show that this method can significantly shorten the computational time of neighborhood mutual information and ensure high approximation quality when using large-scale data sets.
{"title":"Fast Algorithm for Neighborhood Entropy and Neighborhood Mutual Information Based on Column Sorting","authors":"Shengwu Wang, Hongmei Chen, Xin-Nan Fan","doi":"10.1109/ISKE47853.2019.9170397","DOIUrl":"https://doi.org/10.1109/ISKE47853.2019.9170397","url":null,"abstract":"Aiming at the problem that the high computational complexity of calculating information entropy and mutual information of a neighborhood rough set, a fast calculation method based on data sorting was proposed to estimate neighborhood mutual information speedily. This method can reduce the computational complexity of neighborhood entropy from O(n2) to O(nlogn). Under this premise, the method can calculate the approximation of the joint neighborhood entropy by infinite-norm-calculated neighborhood relation, thus to estimate the neighborhood mutual information quickly. For the reason that the method is based on neighborhood entropy, it is also effective for mixed data. Experimental results show that this method can significantly shorten the computational time of neighborhood mutual information and ensure high approximation quality when using large-scale data sets.","PeriodicalId":399084,"journal":{"name":"2019 IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123545890","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：