Pub Date : 2019-04-01DOI: 10.1109/ICIASE45644.2019.9074150
Ren Mingqiu, Wang Bingqie, Leng Yi
This paper presents a novel resources scheduling method for multi-function radar based on target priority assessment which is useful to analyze and design the radar task sequence in complex target environment. According to the work mode and task of the phased array radar, a resource scheduling model using ANFIS was established which preprocess the factors of amount, position of geometry centre and polarimetric characteristics and et al to obtain the task importance ordering of radar scheduler. The multi-function radar scheduling flowchart was designed which can provide the fuzzy-reasoning results of different target environment using ANFIS. The proposed model can greatly improve the effectiveness of the phased array radar scheduler compared with the traditional methods and make the radar task resources management more convenient and highly efficient.
{"title":"Phased Array Radar Resources Scheduling Based on Complex Target Environment Cognition using ANFIS","authors":"Ren Mingqiu, Wang Bingqie, Leng Yi","doi":"10.1109/ICIASE45644.2019.9074150","DOIUrl":"https://doi.org/10.1109/ICIASE45644.2019.9074150","url":null,"abstract":"This paper presents a novel resources scheduling method for multi-function radar based on target priority assessment which is useful to analyze and design the radar task sequence in complex target environment. According to the work mode and task of the phased array radar, a resource scheduling model using ANFIS was established which preprocess the factors of amount, position of geometry centre and polarimetric characteristics and et al to obtain the task importance ordering of radar scheduler. The multi-function radar scheduling flowchart was designed which can provide the fuzzy-reasoning results of different target environment using ANFIS. The proposed model can greatly improve the effectiveness of the phased array radar scheduler compared with the traditional methods and make the radar task resources management more convenient and highly efficient.","PeriodicalId":206741,"journal":{"name":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131310708","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 : 2019-04-01DOI: 10.1109/ICIASE45644.2019.9074074
Jiancheng Zou, Xiuling Cao, Sai Zhang, Bailin Ge
In order to solve the problems of low recognition rate and complex algorithm of traditional facial expression recognition methods, an improved facial expression recognition algorithm based on convolutional neural network (CNN) was proposed. The convolutional neural network uses batch regularization and ReLU activation function to solve the problem of gradient disappearance. The Dropout technology is introduced to solve the problem of network overfitting. Experimental results show that the improved convolutional neural network can improve the accuracy of face expression image recognition.
{"title":"A Facial Expression Recognition Based on Improved Convolutional Neural Network","authors":"Jiancheng Zou, Xiuling Cao, Sai Zhang, Bailin Ge","doi":"10.1109/ICIASE45644.2019.9074074","DOIUrl":"https://doi.org/10.1109/ICIASE45644.2019.9074074","url":null,"abstract":"In order to solve the problems of low recognition rate and complex algorithm of traditional facial expression recognition methods, an improved facial expression recognition algorithm based on convolutional neural network (CNN) was proposed. The convolutional neural network uses batch regularization and ReLU activation function to solve the problem of gradient disappearance. The Dropout technology is introduced to solve the problem of network overfitting. Experimental results show that the improved convolutional neural network can improve the accuracy of face expression image recognition.","PeriodicalId":206741,"journal":{"name":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128433020","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 : 2019-04-01DOI: 10.1109/ICIASE45644.2019.9074033
Jin-Wei Wang, Yong-Qiang Cheng
Firstly, 2D images is susceptible to the face-pose, illumination etc. Secondly, image recognition are mostly based on image low-level visual features, while human perception of images are based on high-level semantic knowledge, which results in the "semantic gap" between them. For this reason, a new 3D facial expression recognition method is proposed based on semantic knowledge of Gaussian mixture model. The method uses Gaussian curvature and mean curvature to extract several key points of low-level visual features of 3D facial expressions, and uses European-style distance to form several key points into a set of low-level visual feature vectors. Then the Gaussian mixture model and the AHP hierarchical model are combined to calculate the high-level semantic feature vector, which solves the "semantic gap" between the low-level visual features and the high-level semantic knowledge of facial expression images, and improve the robustness and recognition rate of 3D facial expression recognition.
{"title":"The new 3D facial expression recognition method based on semantic knowledge of Gaussian mixture model","authors":"Jin-Wei Wang, Yong-Qiang Cheng","doi":"10.1109/ICIASE45644.2019.9074033","DOIUrl":"https://doi.org/10.1109/ICIASE45644.2019.9074033","url":null,"abstract":"Firstly, 2D images is susceptible to the face-pose, illumination etc. Secondly, image recognition are mostly based on image low-level visual features, while human perception of images are based on high-level semantic knowledge, which results in the \"semantic gap\" between them. For this reason, a new 3D facial expression recognition method is proposed based on semantic knowledge of Gaussian mixture model. The method uses Gaussian curvature and mean curvature to extract several key points of low-level visual features of 3D facial expressions, and uses European-style distance to form several key points into a set of low-level visual feature vectors. Then the Gaussian mixture model and the AHP hierarchical model are combined to calculate the high-level semantic feature vector, which solves the \"semantic gap\" between the low-level visual features and the high-level semantic knowledge of facial expression images, and improve the robustness and recognition rate of 3D facial expression recognition.","PeriodicalId":206741,"journal":{"name":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126439227","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 : 2019-04-01DOI: 10.1109/ICIASE45644.2019.9074048
W. Chien, Jia-Xin Xu, C. Chiu, Yu-Ting Cheng, Yu-Lin Lee
The main research in this paper is an ultra-wideband (UWB) three-dimensional (3D) circular antenna array and we highlight the importance of elevation angles and their influence of the system performance. The 3D channel is calculated by 3D shooting and bouncing ray/image techniques which specify multipath elevation angles and azimuth for horizontal plane angles. The capacities of the two-dimensional (2D) and three-dimensional transmitting antenna arrays have been presented. Beam-synthesizing techniques are used at the transmitter to focus the transmitter energy for reducing the multi-path effect and increasing channel capacity. Asynchronous Particle Swarm Optimization (APSO) methods are used to adjust the length of the feed line on each array element for maximizing the capacity. The higher directive gain obtained from the 3D antenna arrays results in high channel capacity compared to 2D azimuth-only antenna arrays. It is found the capacity for the 3D array increases more than 10% compared to that for the 2D array. Our research not only provides qualitative results, but also provides quantitative results.
{"title":"3D Beamforming Techniques for Indoor UWB Wireless Communications","authors":"W. Chien, Jia-Xin Xu, C. Chiu, Yu-Ting Cheng, Yu-Lin Lee","doi":"10.1109/ICIASE45644.2019.9074048","DOIUrl":"https://doi.org/10.1109/ICIASE45644.2019.9074048","url":null,"abstract":"The main research in this paper is an ultra-wideband (UWB) three-dimensional (3D) circular antenna array and we highlight the importance of elevation angles and their influence of the system performance. The 3D channel is calculated by 3D shooting and bouncing ray/image techniques which specify multipath elevation angles and azimuth for horizontal plane angles. The capacities of the two-dimensional (2D) and three-dimensional transmitting antenna arrays have been presented. Beam-synthesizing techniques are used at the transmitter to focus the transmitter energy for reducing the multi-path effect and increasing channel capacity. Asynchronous Particle Swarm Optimization (APSO) methods are used to adjust the length of the feed line on each array element for maximizing the capacity. The higher directive gain obtained from the 3D antenna arrays results in high channel capacity compared to 2D azimuth-only antenna arrays. It is found the capacity for the 3D array increases more than 10% compared to that for the 2D array. Our research not only provides qualitative results, but also provides quantitative results.","PeriodicalId":206741,"journal":{"name":"2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126870847","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：