This work investigates and contrasts two approaches for trajectory tracking control strategies for robotic operating systems: model-free adaptive algorithm and radial basis function (RBF) neural network adaptive algorithm. The tracking for high precision systems is then finished using a computational torque control approach in conjunction with a compensating controller designed based on this algorithm. The model-free adaptive control technique just employs these I/O data to construct the controller and only needs to know the input and output data of the controlled system. It is not required to know the specific model information of the controlled system. Last but not least, the experimental trajectory tracking results show that the RBF neural network can better track the trajectory of the manipulator with a relatively small tracking error.
{"title":"Robotic Arm Trajectory Tracking Control Based on An RBF Neural Network Adaptive Control Algorithm","authors":"Baojian Qin, Wenhao Zhang, Shijian Dong, Shenquan Wang, Yu-lian Jiang","doi":"10.1109/ICIST55546.2022.9926773","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926773","url":null,"abstract":"This work investigates and contrasts two approaches for trajectory tracking control strategies for robotic operating systems: model-free adaptive algorithm and radial basis function (RBF) neural network adaptive algorithm. The tracking for high precision systems is then finished using a computational torque control approach in conjunction with a compensating controller designed based on this algorithm. The model-free adaptive control technique just employs these I/O data to construct the controller and only needs to know the input and output data of the controlled system. It is not required to know the specific model information of the controlled system. Last but not least, the experimental trajectory tracking results show that the RBF neural network can better track the trajectory of the manipulator with a relatively small tracking error.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133652045","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926765
Qingyuan Li, Tian Chen, Yueyuan Zhang, Jun Huang, Lei Yu
In this article, the issue of the distributed observer design for nonlinear multi-agent systems with semi-Markov jump topologies is discussed. At first, based on adjacency matrices, a new distributed observer framework for nonlinear multi-agent systems is proposed. Unlike other existing papers, the nonlinear iteam of this paper satisfies the incremental quadratic constraint. Then the error between distributed observer and multi-agent system is proved to be stochastic stable by Lyapunov and Dynkin's formula. In addition, the existence condition of the distributed observer is written in the form of linear matrix inequalities, which can be easily solved by the LMI toolbox in MATLAB. Finally, the main results are verified by an example.
{"title":"Distributed Observer Design For Multi-agent Systems With Semi-Markov Switching Topology And Incremental Quadratic Constraints","authors":"Qingyuan Li, Tian Chen, Yueyuan Zhang, Jun Huang, Lei Yu","doi":"10.1109/ICIST55546.2022.9926765","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926765","url":null,"abstract":"In this article, the issue of the distributed observer design for nonlinear multi-agent systems with semi-Markov jump topologies is discussed. At first, based on adjacency matrices, a new distributed observer framework for nonlinear multi-agent systems is proposed. Unlike other existing papers, the nonlinear iteam of this paper satisfies the incremental quadratic constraint. Then the error between distributed observer and multi-agent system is proved to be stochastic stable by Lyapunov and Dynkin's formula. In addition, the existence condition of the distributed observer is written in the form of linear matrix inequalities, which can be easily solved by the LMI toolbox in MATLAB. Finally, the main results are verified by an example.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130220670","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926900
Shunxiang Yang, Cheng Lian, Zhigang Zeng
In recent years, self-supervised methods have been widely used in representation learning for electrocardiogram (ECG), but most of the existing methods are based on contrastive learning. Contrastive learning methods usually rely on a large number of negative sample pairs and data augmentation. In this paper, we propose a masked autoencoder-based ECG representation learning model. Our approach is to mask the original ECG signal with a high ratio and then use the autoencoder to reconstruct the original ECG signal. To obtain better ECG features, our model not only extracts local features of ECG using multi-scale convolution, but also global features of ECG using transformer. Our model first pre-trains on the ECG datasets and then fine-tunes on each ECG classification task. Experimental results show that our model outperforms the extant SOTA models for self-supervised learning.
{"title":"Masked Autoencoder for ECG Representation Learning","authors":"Shunxiang Yang, Cheng Lian, Zhigang Zeng","doi":"10.1109/ICIST55546.2022.9926900","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926900","url":null,"abstract":"In recent years, self-supervised methods have been widely used in representation learning for electrocardiogram (ECG), but most of the existing methods are based on contrastive learning. Contrastive learning methods usually rely on a large number of negative sample pairs and data augmentation. In this paper, we propose a masked autoencoder-based ECG representation learning model. Our approach is to mask the original ECG signal with a high ratio and then use the autoencoder to reconstruct the original ECG signal. To obtain better ECG features, our model not only extracts local features of ECG using multi-scale convolution, but also global features of ECG using transformer. Our model first pre-trains on the ECG datasets and then fine-tunes on each ECG classification task. Experimental results show that our model outperforms the extant SOTA models for self-supervised learning.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121824022","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926827
Hanguang Su, Xinyang Luan, Yiwen Zheng, Qianhui Xu, Jinzhu Yang
In this work, we proposed a new online decentralized event-triggered control method which is applicable to some of large-scale systems with nonlinear inter-connection affected by unknown inside system dynamics. This work first designs a recognizer based on neural network to rebuild the uncertain internal dynamics in interconnected system. In the presence of an event triggering mechanism, we next study an approximate optimal control method by adopting the adaptive critic learning method. In this paper, the decentralized event trigger conditions are influenced by only partial state messages of the relevant subsystems, so are controllers. Thus this approach eliminates some problems arising from the process of transmitting status information between subsystems via wireless communication networks. By using Lyapunov's theorem, we show that the state and critical weight estimation errors of the developed closed-loop control system are uniformly ultimately bounded. At last, two cases confirm the validity and suitability of the approach which designed in this paper.
{"title":"Online Event-Triggered Adaptive Optimal Control of Nonlinear Large-Scale Systems","authors":"Hanguang Su, Xinyang Luan, Yiwen Zheng, Qianhui Xu, Jinzhu Yang","doi":"10.1109/ICIST55546.2022.9926827","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926827","url":null,"abstract":"In this work, we proposed a new online decentralized event-triggered control method which is applicable to some of large-scale systems with nonlinear inter-connection affected by unknown inside system dynamics. This work first designs a recognizer based on neural network to rebuild the uncertain internal dynamics in interconnected system. In the presence of an event triggering mechanism, we next study an approximate optimal control method by adopting the adaptive critic learning method. In this paper, the decentralized event trigger conditions are influenced by only partial state messages of the relevant subsystems, so are controllers. Thus this approach eliminates some problems arising from the process of transmitting status information between subsystems via wireless communication networks. By using Lyapunov's theorem, we show that the state and critical weight estimation errors of the developed closed-loop control system are uniformly ultimately bounded. At last, two cases confirm the validity and suitability of the approach which designed in this paper.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122600041","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926847
Guanghu Kuang, Jichao Wang, Jianchao Fan, Jun Wang
China has the largest aquaculture area in the world and is still expanding. Extracting the area of marine aquaculture can prevent the overexploitation of marine aquaculture and protect the marine environment. MDOAU-net has an excellent performance in marine aquaculture extraction of SAR images which drives researchers to explore the performance of MDOAU-net in optical remote sensing images. Unlike SAR images, optical remote sensing images needn't consider speckles noises problem. To suit optical remote sensing images, a new method named MDOAU2-net is proposed to accurately extract marine aquaculture areas, which could keep the discriminative character and filter fake objects with similar features. It follows the structure of the U-net and is contained by a multi-scale block and some offset convolution blocks. In experiments, using the images shot by GF-2 satellite as data and compared to other five networks to verify the validity of MDOAU2-net in optical remote sensing images of marine aquaculture extraction.
{"title":"Marine Aquaculture Information Extraction from Optical Remote Sensing Images via MDOAU2-net","authors":"Guanghu Kuang, Jichao Wang, Jianchao Fan, Jun Wang","doi":"10.1109/ICIST55546.2022.9926847","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926847","url":null,"abstract":"China has the largest aquaculture area in the world and is still expanding. Extracting the area of marine aquaculture can prevent the overexploitation of marine aquaculture and protect the marine environment. MDOAU-net has an excellent performance in marine aquaculture extraction of SAR images which drives researchers to explore the performance of MDOAU-net in optical remote sensing images. Unlike SAR images, optical remote sensing images needn't consider speckles noises problem. To suit optical remote sensing images, a new method named MDOAU2-net is proposed to accurately extract marine aquaculture areas, which could keep the discriminative character and filter fake objects with similar features. It follows the structure of the U-net and is contained by a multi-scale block and some offset convolution blocks. In experiments, using the images shot by GF-2 satellite as data and compared to other five networks to verify the validity of MDOAU2-net in optical remote sensing images of marine aquaculture extraction.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113935865","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926851
Jianxu Xing, F. Lu, Liang Cen, Xiaoming Yin, Kang Pan, Hai-Fen Liu, Xiaofei Chen, Chao Li
This article studies the energy carbon emission (ECE) evaluation problem for enterprises, and designs ECE-codes to conduct multi-factor grading evaluation of the ECE. The ECE evaluation results of enterprises need to be displayed to non-professionals such as consumers. Therefore, in addition to being able to characterize the ECE level, the ECE evaluation results of enterprise should be intuitive and easy to understand. For this purpose, the ECE-codes are designed, including the horizontal identification code (HIC), the efficiency identification code (EIC), and the neutralization identification code (NIC). Define carbon emission intensity (CEI) as the ECEs required to produce an unit of profit. The HIC is formed by dividing the CEI of enterprises into three levels, and is used to grade an enterprise's carbon emission level in the entire industrial sector. The EIC is formed through five-level evaluation of CEI in sector (CEIS), which is used to measure the CEI level of an enterprise in its sector. The CEIS is the ratio of CEI to the average value of the sector CEI. NIC is used to display an enterprise's carbon neutrality process, which is the ratio of carbon neutrality to total carbon emissions. To achieve effective grading of CEI and CEIS, a Gaussian mixture model (GMM) is established to describe the distribution of the CEI and CEIS, and the model parameters are identified by the expectation maximization (EM) algorithm. Then, the grading thresholds can be obtained according to the GMM probability density function with given percentage parameters. The effectiveness of the ECE-codes based grading evaluation method is verified by applying this method to the carbon emission evaluation of the registered enterprises in Huzhou, china.
{"title":"A novel energy carbon emission codes based carbon efficiency evaluation method for enterprises","authors":"Jianxu Xing, F. Lu, Liang Cen, Xiaoming Yin, Kang Pan, Hai-Fen Liu, Xiaofei Chen, Chao Li","doi":"10.1109/ICIST55546.2022.9926851","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926851","url":null,"abstract":"This article studies the energy carbon emission (ECE) evaluation problem for enterprises, and designs ECE-codes to conduct multi-factor grading evaluation of the ECE. The ECE evaluation results of enterprises need to be displayed to non-professionals such as consumers. Therefore, in addition to being able to characterize the ECE level, the ECE evaluation results of enterprise should be intuitive and easy to understand. For this purpose, the ECE-codes are designed, including the horizontal identification code (HIC), the efficiency identification code (EIC), and the neutralization identification code (NIC). Define carbon emission intensity (CEI) as the ECEs required to produce an unit of profit. The HIC is formed by dividing the CEI of enterprises into three levels, and is used to grade an enterprise's carbon emission level in the entire industrial sector. The EIC is formed through five-level evaluation of CEI in sector (CEIS), which is used to measure the CEI level of an enterprise in its sector. The CEIS is the ratio of CEI to the average value of the sector CEI. NIC is used to display an enterprise's carbon neutrality process, which is the ratio of carbon neutrality to total carbon emissions. To achieve effective grading of CEI and CEIS, a Gaussian mixture model (GMM) is established to describe the distribution of the CEI and CEIS, and the model parameters are identified by the expectation maximization (EM) algorithm. Then, the grading thresholds can be obtained according to the GMM probability density function with given percentage parameters. The effectiveness of the ECE-codes based grading evaluation method is verified by applying this method to the carbon emission evaluation of the registered enterprises in Huzhou, china.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114555451","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926921
Yayun Wang, Shiwei Fu, Chun Liu
As a commonly used format of 3D data, point clouds preserve the original geometric information in 3D space without any discretization. In recent years, many deep learning methods have been proposed for recognizing and classifying 3D point cloud data. These methods often require a large number of labeled point clouds for training. However, it is obviously difficult to obtain enough labeled samples for all classes of point clouds in practice. To address this issue, this paper proposes a relation network based on point cloud classification method which can recognize the objects that the point cloud data represents with only few labeled samples. In order to better obtain the local neighborhood information, we use EdgeConv operator to extract the features of each point of the point clouds. And the class of a point cloud will be predicted by measuring the similarity between its feature and the prototypes of a few marked point clouds. Based on the dataset of ModelNet40, the experiments have shown that the proposed method can achieve 92.48% in accuracy and shows better performance compared with related works.
{"title":"A Relation Network Based Approach for Few-Shot Point Cloud Classification","authors":"Yayun Wang, Shiwei Fu, Chun Liu","doi":"10.1109/ICIST55546.2022.9926921","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926921","url":null,"abstract":"As a commonly used format of 3D data, point clouds preserve the original geometric information in 3D space without any discretization. In recent years, many deep learning methods have been proposed for recognizing and classifying 3D point cloud data. These methods often require a large number of labeled point clouds for training. However, it is obviously difficult to obtain enough labeled samples for all classes of point clouds in practice. To address this issue, this paper proposes a relation network based on point cloud classification method which can recognize the objects that the point cloud data represents with only few labeled samples. In order to better obtain the local neighborhood information, we use EdgeConv operator to extract the features of each point of the point clouds. And the class of a point cloud will be predicted by measuring the similarity between its feature and the prototypes of a few marked point clouds. Based on the dataset of ModelNet40, the experiments have shown that the proposed method can achieve 92.48% in accuracy and shows better performance compared with related works.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127201072","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926789
Pan Zhang, Yuhan Liu, Wei Zhang
In order to improve the efficiency and safety of airline baggage loading, an automatic airline baggage palletizing system based on depth camera is designed. The point cloud data of baggage and baggage stack are obtained through the depth cameras. According to the point cloud information, the posture of robot receiving baggage and the position of placing baggage are determined. Then, the kinematic model is analyzed to plan the trajectory of baggage palletizing. Experiments show that the palletizing system can stably receive and place baggage, the space utilization rate of the scheme is 87.63 % and the terminal execution movement is stable during the operation, which verifies the feasibility of automatic airline baggage palletizing system based on depth camera.
{"title":"Design of Airline Baggage Automatic Handling System Based on Depth Camera","authors":"Pan Zhang, Yuhan Liu, Wei Zhang","doi":"10.1109/ICIST55546.2022.9926789","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926789","url":null,"abstract":"In order to improve the efficiency and safety of airline baggage loading, an automatic airline baggage palletizing system based on depth camera is designed. The point cloud data of baggage and baggage stack are obtained through the depth cameras. According to the point cloud information, the posture of robot receiving baggage and the position of placing baggage are determined. Then, the kinematic model is analyzed to plan the trajectory of baggage palletizing. Experiments show that the palletizing system can stably receive and place baggage, the space utilization rate of the scheme is 87.63 % and the terminal execution movement is stable during the operation, which verifies the feasibility of automatic airline baggage palletizing system based on depth camera.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125795695","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926881
Ji Lu, Jianzhen Xiao, Canhui Chen, Mingzhi Mao, Yunong Zhang
In this paper, we first introduce a continuous model for time-varying matrix generalized Sinkhorn scaling (TVMGSS) on the basis of the continuous Zhang neural dynamics (ZND) model. Subsequently, a high-precision 10-instant Zhang time discretization (ZTD) formula with theoretical analysis is presented. Further, we utilize the 10-instant ZTD formula to discretize the continuous ZND model, resulting in a discrete ZND algorithm named 10-instant discrete ZND (10IDZND) algorithm for TVMGSS. For comparison, two other time discretization formulas are also considered, and the corresponding discrete algorithms for TVMGSS are derived. The comparative numerical experiments are performed, and the results substantiate the effectiveness and superior accuracy of the 10IDZND algorithm. In addition, we verify the effectiveness of the 10IDZND algorithm for higher-dimensional TVMGSS through numerical experiments. Finally, we experimentally investigate the effects of the design parameters and the sampling period on the convergence of the 10IDZND algorithm.
{"title":"Discrete Zhang Neural Dynamics Algorithms for Time-Varying Matrix Generalized Sinkhorn Scaling","authors":"Ji Lu, Jianzhen Xiao, Canhui Chen, Mingzhi Mao, Yunong Zhang","doi":"10.1109/ICIST55546.2022.9926881","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926881","url":null,"abstract":"In this paper, we first introduce a continuous model for time-varying matrix generalized Sinkhorn scaling (TVMGSS) on the basis of the continuous Zhang neural dynamics (ZND) model. Subsequently, a high-precision 10-instant Zhang time discretization (ZTD) formula with theoretical analysis is presented. Further, we utilize the 10-instant ZTD formula to discretize the continuous ZND model, resulting in a discrete ZND algorithm named 10-instant discrete ZND (10IDZND) algorithm for TVMGSS. For comparison, two other time discretization formulas are also considered, and the corresponding discrete algorithms for TVMGSS are derived. The comparative numerical experiments are performed, and the results substantiate the effectiveness and superior accuracy of the 10IDZND algorithm. In addition, we verify the effectiveness of the 10IDZND algorithm for higher-dimensional TVMGSS through numerical experiments. Finally, we experimentally investigate the effects of the design parameters and the sampling period on the convergence of the 10IDZND algorithm.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125091716","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 : 2022-10-14DOI: 10.1109/ICIST55546.2022.9926909
Yadi Wang, Xiangyu Wang, Xianyu Zuo, Hangjun Che, Baojun Qiao, Ying Du
Feature selection has been widely used in various application areas such as machine learning, bioinformatics, and natural language processing. Common drawbacks of most of the current feature selection methods are the lack of information about the dynamic change of selected features with the class, and the selection of redundant and irrelevant features. In this paper, we develop a novel feature selection method called Normalized Dynamic Change of Selected Feature with Class (NDCSF), which consider the normalized dynamic information changes between the selected features and the classes by using conditional mutual information and entropy. Moreover, a normalized feature redundancy by using mutual information and entropy is introduced into NDCSF. The experimental results on several benchmark datasets verify that the NDCSF can significantly improve the other several feature selection methods.
{"title":"Feature Selection via Normalized Dynamic Change of Selected Feature with Class","authors":"Yadi Wang, Xiangyu Wang, Xianyu Zuo, Hangjun Che, Baojun Qiao, Ying Du","doi":"10.1109/ICIST55546.2022.9926909","DOIUrl":"https://doi.org/10.1109/ICIST55546.2022.9926909","url":null,"abstract":"Feature selection has been widely used in various application areas such as machine learning, bioinformatics, and natural language processing. Common drawbacks of most of the current feature selection methods are the lack of information about the dynamic change of selected features with the class, and the selection of redundant and irrelevant features. In this paper, we develop a novel feature selection method called Normalized Dynamic Change of Selected Feature with Class (NDCSF), which consider the normalized dynamic information changes between the selected features and the classes by using conditional mutual information and entropy. Moreover, a normalized feature redundancy by using mutual information and entropy is introduced into NDCSF. The experimental results on several benchmark datasets verify that the NDCSF can significantly improve the other several feature selection methods.","PeriodicalId":211213,"journal":{"name":"2022 12th International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121961034","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：