Wei Liu, Renze Xiong, Ning N. Cheng, Yiming Y. Sun
To accurately express the fuzzy relation between word features and texts, and fuzzy relation between word features and categories respectively. A text classification method is proposed based on Fuzzy Relation and Feature Distribution Variance (FRFDV). This method firstly performs feature reduction and category feature word extraction according to the distribution of features in inter-category and intra-category. Then the method defines the word feature set, test text set and category set as fuzzy sets. Next, each text and category are represented respectively by defining the membership function of the word feature set to the test text set and the category set. When using word feature sets to represent categories, pay attention to the membership degree of features to categories and their distribution between categories; when using feature sets to represent test texts, give categorical feature words and non-categorical feature words with different weights. Finally, the fuzzy set correlation formula is used to calculate the correlation between the text and each category, and the category with the largest correlation is the category of the text. Comparing with the XGBOOST [Fang, 2020, Gong and Wang, 2018] algorithm and SVM algorithm, it is proved that the text classification method based on FRFDV is feasible. The accuracy of the results is higher by 2 % and 4 % respectively.
准确表达词特征与文本的模糊关系、词特征与类别的模糊关系。提出一种基于模糊关系和特征分布方差(FRFDV)的文本分类方法。该方法首先根据特征在类别间和类别内的分布进行特征约简和类别特征词提取。然后将词特征集、测试文本集和类别集定义为模糊集。接下来，通过定义单词特征集对测试文本集和类别集的隶属函数来分别表示每个文本和类别。在使用词特征集表示类别时，要注意特征与类别的隶属度及其在类别之间的分布;在使用特征集表示测试文本时，给出不同权重的分类特征词和非分类特征词。最后，利用模糊集关联公式计算文本与各类别之间的关联，关联度最大的类别即为该文本所属的类别。对比XGBOOST [Fang, 2020, Gong and Wang, 2018]算法和SVM算法，证明了基于FRFDV的文本分类方法是可行的。结果的准确度分别提高了2%和4%。
{"title":"Text Classification Method with Combination of Fuzzy Relation and Feature Distribution Variance","authors":"Wei Liu, Renze Xiong, Ning N. Cheng, Yiming Y. Sun","doi":"10.1145/3437802.3437829","DOIUrl":"https://doi.org/10.1145/3437802.3437829","url":null,"abstract":"To accurately express the fuzzy relation between word features and texts, and fuzzy relation between word features and categories respectively. A text classification method is proposed based on Fuzzy Relation and Feature Distribution Variance (FRFDV). This method firstly performs feature reduction and category feature word extraction according to the distribution of features in inter-category and intra-category. Then the method defines the word feature set, test text set and category set as fuzzy sets. Next, each text and category are represented respectively by defining the membership function of the word feature set to the test text set and the category set. When using word feature sets to represent categories, pay attention to the membership degree of features to categories and their distribution between categories; when using feature sets to represent test texts, give categorical feature words and non-categorical feature words with different weights. Finally, the fuzzy set correlation formula is used to calculate the correlation between the text and each category, and the category with the largest correlation is the category of the text. Comparing with the XGBOOST [Fang, 2020, Gong and Wang, 2018] algorithm and SVM algorithm, it is proved that the text classification method based on FRFDV is feasible. The accuracy of the results is higher by 2 % and 4 % respectively.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120955800","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 this work, we address the algorithm selection problem for classification via meta-learning and generative adversarial networks. We focus on the dataset representation question. The matrix representation of classification dataset is not sensitive to swapping any two rows or any two columns. We suggest a special method to reduce a dataset to a unified form. This allows to apply generative adversarial networks to classification dataset generation. In this setting, a generator generates new classification datasets in a matrix form, while a conditional discriminator is trying to predict for a dataset and an algorithm if the dataset is real and the algorithm would show the best performance on this dataset. We also suggest a graph convolutional network as a discriminator that is capable to work with such forms, which encode a dataset as a weighted graph with nodes representing objects.
{"title":"Graph Convolutional Network Based Generative Adversarial Networks for the Algorithm Selection Problem in Classification","authors":"Gleb Drozdov, Alexey Zabashta, A. Filchenkov","doi":"10.1145/3437802.3437818","DOIUrl":"https://doi.org/10.1145/3437802.3437818","url":null,"abstract":"In this work, we address the algorithm selection problem for classification via meta-learning and generative adversarial networks. We focus on the dataset representation question. The matrix representation of classification dataset is not sensitive to swapping any two rows or any two columns. We suggest a special method to reduce a dataset to a unified form. This allows to apply generative adversarial networks to classification dataset generation. In this setting, a generator generates new classification datasets in a matrix form, while a conditional discriminator is trying to predict for a dataset and an algorithm if the dataset is real and the algorithm would show the best performance on this dataset. We also suggest a graph convolutional network as a discriminator that is capable to work with such forms, which encode a dataset as a weighted graph with nodes representing objects.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121174069","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}
Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. We propose a new GG-CNN architecture for DexNet, provide a new way for dataset generation for the GG-CNN and describe practical improvements that increase the model validation accuracy and other performance aspects of the whole system
{"title":"A Cloud-based Network of 3D Objects for Robust Grasp Planning","authors":"S. Muravyov, A. Filchenkov","doi":"10.1145/3437802.3437820","DOIUrl":"https://doi.org/10.1145/3437802.3437820","url":null,"abstract":"Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. We propose a new GG-CNN architecture for DexNet, provide a new way for dataset generation for the GG-CNN and describe practical improvements that increase the model validation accuracy and other performance aspects of the whole system","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123293943","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 study aimed to apply supervised machine learning techniques to one domain of psychological research: vocational interests. Socio-demographic factors can be considered strong predictors of vocational interests, which might have far-reaching practical implications for professional counselling and social network analysis. The dataset used in this study is a collection of answers to the RIASEC (Holland Codes) psychological test. Different Machine Learning architectures were used to predict RIASEC scales using socio-demographic features. The problem was treated as a multioutput regression task, multiclass and multilabel classification. The following models were used: independent regression, regression chains, three-letter code classification, inferring label relations. Models comparison showed that the models that exploit intercorrelations between RIASEC scales yielded the best results.
{"title":"Predicting Vocational Personality Type from Socio-demographic Features Using Machine Learning Methods","authors":"E. Bogacheva, Filipp Tatarenko, I. Smetannikov","doi":"10.1145/3437802.3437819","DOIUrl":"https://doi.org/10.1145/3437802.3437819","url":null,"abstract":"This study aimed to apply supervised machine learning techniques to one domain of psychological research: vocational interests. Socio-demographic factors can be considered strong predictors of vocational interests, which might have far-reaching practical implications for professional counselling and social network analysis. The dataset used in this study is a collection of answers to the RIASEC (Holland Codes) psychological test. Different Machine Learning architectures were used to predict RIASEC scales using socio-demographic features. The problem was treated as a multioutput regression task, multiclass and multilabel classification. The following models were used: independent regression, regression chains, three-letter code classification, inferring label relations. Models comparison showed that the models that exploit intercorrelations between RIASEC scales yielded the best results.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131852258","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}
A unitary root signal classification (Root-MUSIC) combined with subspace modification for uniform circular microphone arrays is proposed. Firstly, the subspace is modified by eliminating the two undesirable terms in the covariance matrix, which cause the subspace leakage, thus improving the estimation accuracy of subspace. Secondly, a real-valued Root-MUSIC algorithm for circular microphone arrays is developed by unitary transformation. The proposed method can reduce the computational complexity of complex-valued Root-MUSIC by 75%. Some simulation results demonstrate the effectiveness of the proposed method
{"title":"Unitary Root-MUSIC Combined with Subspace Modification for Circular Microphone Array","authors":"Tingwei Chen, Jucai Lin, Jun Yin","doi":"10.1145/3437802.3437814","DOIUrl":"https://doi.org/10.1145/3437802.3437814","url":null,"abstract":"A unitary root signal classification (Root-MUSIC) combined with subspace modification for uniform circular microphone arrays is proposed. Firstly, the subspace is modified by eliminating the two undesirable terms in the covariance matrix, which cause the subspace leakage, thus improving the estimation accuracy of subspace. Secondly, a real-valued Root-MUSIC algorithm for circular microphone arrays is developed by unitary transformation. The proposed method can reduce the computational complexity of complex-valued Root-MUSIC by 75%. Some simulation results demonstrate the effectiveness of the proposed method","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126445851","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}
A reference signal is the target for a plant to track. When the reference signal is incomplete over a prediction horizon for model predictive control, a constant prediction of a reference is generally used to take place of the unknown reference signal. However, the complement of the constant reference prediction would lead to a discontinuity if the reference were not a constant signal. Moreover, the plant output signal is not supposed to follow a discontinuous reference especially for a tracking problem. In this paper, a model predictive control method based on B-spline fitting is presented. The B-spline fitting is used to interpolate the known reference signal and then a B-spline extension or extrapolation is employed to extend the reference curve in a continuous and smooth way. The new B-spline-treated reference then takes part in the optimization process of the model predictive control to generate the optimal input signal. The smooth extension could be closer to the actual trend of the reference, so it improves the performance of the model predictive controller. Simulation results show that this method works well when the prediction horizon is not large.
{"title":"A modified model predictive control based on B-spline fitting","authors":"Meng Liu, Hao Wu, Jun Wang","doi":"10.1145/3437802.3437803","DOIUrl":"https://doi.org/10.1145/3437802.3437803","url":null,"abstract":"A reference signal is the target for a plant to track. When the reference signal is incomplete over a prediction horizon for model predictive control, a constant prediction of a reference is generally used to take place of the unknown reference signal. However, the complement of the constant reference prediction would lead to a discontinuity if the reference were not a constant signal. Moreover, the plant output signal is not supposed to follow a discontinuous reference especially for a tracking problem. In this paper, a model predictive control method based on B-spline fitting is presented. The B-spline fitting is used to interpolate the known reference signal and then a B-spline extension or extrapolation is employed to extend the reference curve in a continuous and smooth way. The new B-spline-treated reference then takes part in the optimization process of the model predictive control to generate the optimal input signal. The smooth extension could be closer to the actual trend of the reference, so it improves the performance of the model predictive controller. Simulation results show that this method works well when the prediction horizon is not large.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122598736","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}
To solve the problem that the accuracy of transformer fault diagnosis is seriously affected by support vector machine parameters, a transformer fault diagnosis method based on the sparrow search algorithm is proposed. First, through very sparse random projection to remove redundant features. Then use the sparrow search algorithm to dynamically optimize the kernel function parameters and penalty coefficients of the support vector machine, and obtain the fault diagnosis model of the support vector machine optimized by the SSA. Finally input the processed data into SSA-SVM for fault diagnosis, and compared it with GA-SVM and GWO-SVM. The results show that the test accuracy of the support vector machine optimized by the sparrow search algorithm (SSA-SVM) reaches 86.67%, which is 6.67% and 8.34% higher than that of GWO-SVM and GA-SVM, So it can be effectively applied to fault diagnosis.
{"title":"Study of Transformer Fault Diagnosis Based on Sparrow Optimization Algorithm","authors":"H. Li, Yong Zhang","doi":"10.1145/3437802.3437813","DOIUrl":"https://doi.org/10.1145/3437802.3437813","url":null,"abstract":"To solve the problem that the accuracy of transformer fault diagnosis is seriously affected by support vector machine parameters, a transformer fault diagnosis method based on the sparrow search algorithm is proposed. First, through very sparse random projection to remove redundant features. Then use the sparrow search algorithm to dynamically optimize the kernel function parameters and penalty coefficients of the support vector machine, and obtain the fault diagnosis model of the support vector machine optimized by the SSA. Finally input the processed data into SSA-SVM for fault diagnosis, and compared it with GA-SVM and GWO-SVM. The results show that the test accuracy of the support vector machine optimized by the sparrow search algorithm (SSA-SVM) reaches 86.67%, which is 6.67% and 8.34% higher than that of GWO-SVM and GA-SVM, So it can be effectively applied to fault diagnosis.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123360441","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}
The research significance of this article is to realize the scene storytelling of animation based on the visualization of UnrealTM game engine. In the scene preview, the characters’ moving speed and path are simulated and controlled to realize the real-time interaction of the virtual character to know the effect of the whole story development in advance. We illustrate a method for the core role of artificial actors in interactive storytelling and how to participate in the creation of dynamic storylines. User autonomous behavior the artificial characters and the interactive storytelling of artificial intelligence of the virtual actors allow interaction between the virtual characters and the characters from users. Autonomous virtual actors generate dynamic plots based on the dynamic interaction between the characters and according to the storytelling plot to increase user entertainment.
{"title":"Application of Artificial Intelligence Interactive storytelling in Animated","authors":"Manyu Zhang","doi":"10.1145/3437802.3437809","DOIUrl":"https://doi.org/10.1145/3437802.3437809","url":null,"abstract":"The research significance of this article is to realize the scene storytelling of animation based on the visualization of UnrealTM game engine. In the scene preview, the characters’ moving speed and path are simulated and controlled to realize the real-time interaction of the virtual character to know the effect of the whole story development in advance. We illustrate a method for the core role of artificial actors in interactive storytelling and how to participate in the creation of dynamic storylines. User autonomous behavior the artificial characters and the interactive storytelling of artificial intelligence of the virtual actors allow interaction between the virtual characters and the characters from users. Autonomous virtual actors generate dynamic plots based on the dynamic interaction between the characters and according to the storytelling plot to increase user entertainment.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123046754","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}
Jing Su, Yuan Liu, Yaqing Si, Liyong Duan, Yujing Gong
Because data products are characterized by wide variety, large quantity, fast updating and difficult to determine the value, data transaction relies on the credit service provided by the trans-action platform as the core of the credit check not only is difficult to avoid credit risk, but also cannot meet the demand of multi-directional development of data transaction. Therefore, it is necessary to improve the data market credit service system, provide a new credit evaluation model. This paper constructs the credit evaluation index system and credit evaluation rating of the seller enterprise of the data transaction. The OWA operator is used to assign weights in this model, and the multi-level fuzzy comprehensive evaluation method is combined to establish the credit evaluation model of the enterprise of the data transaction. This method is also suitable for constructing the credit evaluation model of other business entities in the data market.
{"title":"Research on enterprise credit evaluation model of data transaction based on OWA operator and Fuzzy comprehensive evaluation","authors":"Jing Su, Yuan Liu, Yaqing Si, Liyong Duan, Yujing Gong","doi":"10.1145/3437802.3437823","DOIUrl":"https://doi.org/10.1145/3437802.3437823","url":null,"abstract":"Because data products are characterized by wide variety, large quantity, fast updating and difficult to determine the value, data transaction relies on the credit service provided by the trans-action platform as the core of the credit check not only is difficult to avoid credit risk, but also cannot meet the demand of multi-directional development of data transaction. Therefore, it is necessary to improve the data market credit service system, provide a new credit evaluation model. This paper constructs the credit evaluation index system and credit evaluation rating of the seller enterprise of the data transaction. The OWA operator is used to assign weights in this model, and the multi-level fuzzy comprehensive evaluation method is combined to establish the credit evaluation model of the enterprise of the data transaction. This method is also suitable for constructing the credit evaluation model of other business entities in the data market.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124798791","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 a novel trajectory tracking control method for a manipulator of 6-DOF (6 Degrees of Freedom) based on robust nonlinear predictive control. The design of such control requires the establishment of dynamic nonlinear model of the manipulator and the application of improved robust predictive control law which gives different weights to tracking errors in different stages of dynamic prediction time. Stability of the system is analyzed using Lyapunov stability theory. Comparative 6-DOF simulation results show that proposed controller design can ensure higher tracking precision and faster convergence, as well as demonstrate the effectiveness of our improved method.
{"title":"Trajectory Tracking of Manipulators Based on Improved Robust Nonlinear Predictive Control","authors":"Chenxin Lu, Kaimeng Wang, Hao Xu","doi":"10.1145/3437802.3437804","DOIUrl":"https://doi.org/10.1145/3437802.3437804","url":null,"abstract":"This paper presents a novel trajectory tracking control method for a manipulator of 6-DOF (6 Degrees of Freedom) based on robust nonlinear predictive control. The design of such control requires the establishment of dynamic nonlinear model of the manipulator and the application of improved robust predictive control law which gives different weights to tracking errors in different stages of dynamic prediction time. Stability of the system is analyzed using Lyapunov stability theory. Comparative 6-DOF simulation results show that proposed controller design can ensure higher tracking precision and faster convergence, as well as demonstrate the effectiveness of our improved method.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127914699","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：