Pub Date : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874177
Gao Hu, Qingwei Zeng, Chao Long, Dianyou Geng
In order to effectively speed up the model training time, reduce the model training parameters and improve the accuracy of raw speech isolated word recognition. An interpretable convolutional filter structure (sincnet) combined with convolutional neural network (CNN) is proposed for the task of raw speech isolated word recognition. On the premise of ensuring the speech recognition rate, the model structure becomes lightweight and the computational complexity is reduced. The experimental results show that compared with the traditional neural network model, the proposed model can effectively improve the performance of raw speech isolated word recognition.
{"title":"Research on raw speech isolated word recognition based on Sincnet-CNN model","authors":"Gao Hu, Qingwei Zeng, Chao Long, Dianyou Geng","doi":"10.1109/ISPDS56360.2022.9874177","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874177","url":null,"abstract":"In order to effectively speed up the model training time, reduce the model training parameters and improve the accuracy of raw speech isolated word recognition. An interpretable convolutional filter structure (sincnet) combined with convolutional neural network (CNN) is proposed for the task of raw speech isolated word recognition. On the premise of ensuring the speech recognition rate, the model structure becomes lightweight and the computational complexity is reduced. The experimental results show that compared with the traditional neural network model, the proposed model can effectively improve the performance of raw speech isolated word recognition.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134090433","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874100
Zehua Han
In this big data era, personal information and privacy protection sound no longer unfamiliar to us. From using all sorts of computational software and online platforms, registering and using vast amount of social medias in everyday life, to conducting high-technical science researches and national statistical census, people's social announcements, purchase records, health data, daily commutes, career movements, financial status and even personal relationships are enough to constitute a complex and massive data network. Analytic hierarchy process dynamic model; Pricing mechanism and transaction mechanism are used in this paper. Based on the comprehensive consideration of social science theories such as microeconomics and macroeconomics, the pricing structure and bargaining range of privacy information are formulated firstly. Then a discrete choice model with time and dynamic factors is formulated. Secondly, the price trends of different age and occupation analysis models are considered. Thirdly, the social model is improved because the social network is highly correlated. Then use panel data to verify the model, and finally put forward relevant policy recommendations.
{"title":"Charging model and application of personal data under Internet background","authors":"Zehua Han","doi":"10.1109/ISPDS56360.2022.9874100","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874100","url":null,"abstract":"In this big data era, personal information and privacy protection sound no longer unfamiliar to us. From using all sorts of computational software and online platforms, registering and using vast amount of social medias in everyday life, to conducting high-technical science researches and national statistical census, people's social announcements, purchase records, health data, daily commutes, career movements, financial status and even personal relationships are enough to constitute a complex and massive data network. Analytic hierarchy process dynamic model; Pricing mechanism and transaction mechanism are used in this paper. Based on the comprehensive consideration of social science theories such as microeconomics and macroeconomics, the pricing structure and bargaining range of privacy information are formulated firstly. Then a discrete choice model with time and dynamic factors is formulated. Secondly, the price trends of different age and occupation analysis models are considered. Thirdly, the social model is improved because the social network is highly correlated. Then use panel data to verify the model, and finally put forward relevant policy recommendations.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115440443","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874162
Lifa Nong, Wei Wu, Xingshu Wang, Xin Ma
A three-dimensional (3D) attitude measurement approach for planar target based on correlated frames is proposed to solve the problem of low off-plane angle measurement accuracy for 3D relative attitude estimation using planar target as cooperative target. First, the target attitude of each frame of image is calculated by attitude estimation approach by a single-frame image. Second, the high-precision angle information provided by the fiber-optic gyro unit is used to realize the correlation of adjacent frames of target images. Finally, the 3D attitude of planar target is estimated by superimposing multiple frames of correlated images. This approach makes full use of the high-accuracy of short-time attitude of the fiber-optic gyro unit, and reduces the influence of image random noise on attitude measurement by correlating sequence image. Simulation and experimental results show that when the relative attitude angle varies from −2° to 2°, the proposed approach improves the measurement accuracy of the off-plane angle by a factor of 6 compared with the traditional ones.
{"title":"Relative Attitude Estimation Approach Based on Correlated Frames Using Planar Target","authors":"Lifa Nong, Wei Wu, Xingshu Wang, Xin Ma","doi":"10.1109/ISPDS56360.2022.9874162","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874162","url":null,"abstract":"A three-dimensional (3D) attitude measurement approach for planar target based on correlated frames is proposed to solve the problem of low off-plane angle measurement accuracy for 3D relative attitude estimation using planar target as cooperative target. First, the target attitude of each frame of image is calculated by attitude estimation approach by a single-frame image. Second, the high-precision angle information provided by the fiber-optic gyro unit is used to realize the correlation of adjacent frames of target images. Finally, the 3D attitude of planar target is estimated by superimposing multiple frames of correlated images. This approach makes full use of the high-accuracy of short-time attitude of the fiber-optic gyro unit, and reduces the influence of image random noise on attitude measurement by correlating sequence image. Simulation and experimental results show that when the relative attitude angle varies from −2° to 2°, the proposed approach improves the measurement accuracy of the off-plane angle by a factor of 6 compared with the traditional ones.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116274827","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874234
H. Zhao, Shanmei Liu
Aiming to solve the problems of low search efficiency, more redundant nodes and path turning points in the traditional A* algorithm for mobile robot path planning, an improved time and space efficient A* algorithm called $mathbf{TSE}_{-}mathbf{A}^{ast}$ algorithm is proposed. Firstly, an adaptive heuristic function is designed according to the number of environmental obstacles, the starting point and the ending point of the path, which makes the algorithm perform well in different environments. Then, by optimizing the node selection strategy, we can improve the efficiency of the algorithm and reduce the running time of the algorithm, reduce redundant nodes and optimize the path, so as to make the path more smooth. The results show that the proposed $mathbf{TSE}_{-}mathbf{A}^{ast}$ algorithm is much better than the traditional $mathbf{A}^{ast}$ and the Time-Efficient $mathbf{A}^{ast}$ algorithm not only in path length and the number of turning points, but also in search time.
{"title":"Path planning for mobile robots based on the Time&Space-Efficient improved A* algorithm","authors":"H. Zhao, Shanmei Liu","doi":"10.1109/ISPDS56360.2022.9874234","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874234","url":null,"abstract":"Aiming to solve the problems of low search efficiency, more redundant nodes and path turning points in the traditional A* algorithm for mobile robot path planning, an improved time and space efficient A* algorithm called $mathbf{TSE}_{-}mathbf{A}^{ast}$ algorithm is proposed. Firstly, an adaptive heuristic function is designed according to the number of environmental obstacles, the starting point and the ending point of the path, which makes the algorithm perform well in different environments. Then, by optimizing the node selection strategy, we can improve the efficiency of the algorithm and reduce the running time of the algorithm, reduce redundant nodes and optimize the path, so as to make the path more smooth. The results show that the proposed $mathbf{TSE}_{-}mathbf{A}^{ast}$ algorithm is much better than the traditional $mathbf{A}^{ast}$ and the Time-Efficient $mathbf{A}^{ast}$ algorithm not only in path length and the number of turning points, but also in search time.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124404199","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}
Obtaining the learning status information of stu-dents in class is the premise of realizing intelligent education, and heart rate (HR) is important information reflecting the learning status of students. Imaging Photoplethysmography (iPPG) is a non-contact measuring technology of physiological indicators, which is beneficial to the promotion of intelligent education. In this paper, a non-contact multi-person heart rate measurement system based on video is designed for teaching scenarios. First, the raw signal with a high signal-to-noise ratio (SNR) is obtained through a new spatial averaging method that effectively uses the HR information contained in every part of the face. Next, unde-sirable various noises in the raw signal are removed by combining the color-distortion filtering and plane-orthogonal-to-skin based method. The experimental results show that this system has high HR measurement performance while the mean absolute error, root mean squared error, and Pearson correlation coeffi-cient is 0.90 bpm, 1.7 bpm, and 0.98, respectively.
{"title":"Research on Non-contact Multi-person Heart Rate Measurement Method for Intelligent Education","authors":"Yueqi Lian, JongSong Ryu, Suqiu Wang, Shili Liang, Oh Kyongil","doi":"10.1109/ISPDS56360.2022.9874225","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874225","url":null,"abstract":"Obtaining the learning status information of stu-dents in class is the premise of realizing intelligent education, and heart rate (HR) is important information reflecting the learning status of students. Imaging Photoplethysmography (iPPG) is a non-contact measuring technology of physiological indicators, which is beneficial to the promotion of intelligent education. In this paper, a non-contact multi-person heart rate measurement system based on video is designed for teaching scenarios. First, the raw signal with a high signal-to-noise ratio (SNR) is obtained through a new spatial averaging method that effectively uses the HR information contained in every part of the face. Next, unde-sirable various noises in the raw signal are removed by combining the color-distortion filtering and plane-orthogonal-to-skin based method. The experimental results show that this system has high HR measurement performance while the mean absolute error, root mean squared error, and Pearson correlation coeffi-cient is 0.90 bpm, 1.7 bpm, and 0.98, respectively.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132518117","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874009
Fengqian Pang, Yue Li
In the field of action recognition, it is crucial to capture the temporal evolution of video content compactly and effectively. One of the solutions is the rank pooling method that enables acquiring the evolution of video content. To further enhance temporal discrimination of the rank pooling, we proposed two improved rank pooling strategies, named the Minimum Volume Enclosing Ellipsoids (MVEE) and the Temporal Minimum Volume Enclosing Ellipsoids (TMVEE). The proposed methods are compatible with rank pooling and characterize the data distribution in other orthogonal directions to improve the temporal discrimination. We performed experiments on the ChaLearn gesture recognition and HMDB51 database, the results reveal that our proposed methods outperform other mainstreaming methos.
{"title":"Improved Rank Pooling Strategy for Action Recognition","authors":"Fengqian Pang, Yue Li","doi":"10.1109/ISPDS56360.2022.9874009","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874009","url":null,"abstract":"In the field of action recognition, it is crucial to capture the temporal evolution of video content compactly and effectively. One of the solutions is the rank pooling method that enables acquiring the evolution of video content. To further enhance temporal discrimination of the rank pooling, we proposed two improved rank pooling strategies, named the Minimum Volume Enclosing Ellipsoids (MVEE) and the Temporal Minimum Volume Enclosing Ellipsoids (TMVEE). The proposed methods are compatible with rank pooling and characterize the data distribution in other orthogonal directions to improve the temporal discrimination. We performed experiments on the ChaLearn gesture recognition and HMDB51 database, the results reveal that our proposed methods outperform other mainstreaming methos.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125278246","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874217
Zhi-Jie Liu, Yi-Meng Li, Michael Abebe Berwo, Yi-Meng Wang, Yong-Hao Li, Nan Yang
Vehicle detection technology has been widely used in the field of intelligent transportation, and the performance of existing vehicle detection technology in both detection accuracy and detection speed has been continuously improved. However, when encountering complex road environments, problems such as low vehicle detection rate and poor real-time performance can occur. To address these problems, an improved YOLOv5s vehicle detection algorithm is proposed. Firstly, in the feature fusion module of neck part, a new detection scale is added and the original FPN+PAN structure is replaced with an improved Bi-directional Feature Pyramid Network (BiFPN). Secondly, the Triplet Attention (TA) module l is added to the backbone part and the improved neck part to enhance the feature extraction capability. Finally, the improved algorithm is tested on the MS COCO 2017 dataset, and the experimental results show that the algorithm improves the mean average precision (mAP) by 1.34% to 67.64% compared with the original YOLOv5s algorithm. The detection effect of small-scale vehicle targets is better than the original YOLOv5s algorithm, and the detection accuracy is higher.
{"title":"Vehicle Detection Based on Improved Yolov5s Algorithm","authors":"Zhi-Jie Liu, Yi-Meng Li, Michael Abebe Berwo, Yi-Meng Wang, Yong-Hao Li, Nan Yang","doi":"10.1109/ISPDS56360.2022.9874217","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874217","url":null,"abstract":"Vehicle detection technology has been widely used in the field of intelligent transportation, and the performance of existing vehicle detection technology in both detection accuracy and detection speed has been continuously improved. However, when encountering complex road environments, problems such as low vehicle detection rate and poor real-time performance can occur. To address these problems, an improved YOLOv5s vehicle detection algorithm is proposed. Firstly, in the feature fusion module of neck part, a new detection scale is added and the original FPN+PAN structure is replaced with an improved Bi-directional Feature Pyramid Network (BiFPN). Secondly, the Triplet Attention (TA) module l is added to the backbone part and the improved neck part to enhance the feature extraction capability. Finally, the improved algorithm is tested on the MS COCO 2017 dataset, and the experimental results show that the algorithm improves the mean average precision (mAP) by 1.34% to 67.64% compared with the original YOLOv5s algorithm. The detection effect of small-scale vehicle targets is better than the original YOLOv5s algorithm, and the detection accuracy is higher.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124990031","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 : 2022-06-08DOI: 10.1109/iceast55249.2022.9826336
Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA01923. For reprint or republication permission, email to IEEE Copyrights Manager at pubs-permissions@ieee.org.
{"title":"Copyright and Reprint Permission","authors":"","doi":"10.1109/iceast55249.2022.9826336","DOIUrl":"https://doi.org/10.1109/iceast55249.2022.9826336","url":null,"abstract":"Libraries are permitted to photocopy beyond the limit of U.S. copyright law for private use of patrons those articles in this volume that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA01923. For reprint or republication permission, email to IEEE Copyrights Manager at pubs-permissions@ieee.org.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115618080","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：