{"title":"A novel music genre classification algorithm based on Continuous Wavelet Transform and Convolution Neural Network","authors":"Kang Xu, Md Al Alif, Gang He","doi":"10.1145/3501409.3501632","DOIUrl":"https://doi.org/10.1145/3501409.3501632","url":null,"abstract":"The automated genre categorization of musical audio signals plays a fundamental role in the application, spectral characteristics that have been averaged across a large number of audio frames are estimated by Continuous Wavelet Transform (CWT) and then converted to a gray-scale picture for training and classification. A Convolution Neural Networks (CNN) model is proposed in this paper and the results demonstrated that the classification accuracy of the proposed CWT+ CNN model is about 70% with the testing sample and 94% with the training sample. This may suggest good application potential for the music genre classification.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116765465","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}
{"title":"Development and Application of Computer Three-dimensional Auxiliary System in Dance Creation","authors":"Libin Chen","doi":"10.1145/3501409.3501660","DOIUrl":"https://doi.org/10.1145/3501409.3501660","url":null,"abstract":"The 21st century has completely entered the digital era, and computer has become a household tool. With the progress of science and technology and the development of the times, the era of mechanization has gradually moved towards people. Different from the past, technology has not been limited to culture, machinery and other fields. The digital field not only promotes the development of economy and culture, but also gets a certain development in the field of dance art, which makes the field of dance art have a more convenient and more relaxed development platform. The field of dance education also has a more convenient and intuitive method for people to understand and get familiar with this field. It is valued with greater ornamental nature, more perfect interaction and resource-saving advantages. Dance creation computer three-dimensional auxiliary system conforms to the development direction of dance art, as digital dance art, visual is the premise of the whole art form, under the premise of visual, reach a higher level of interaction, and dance creation computer three-dimensional auxiliary system meets the requirements of digital dance, through three-dimensional auxiliary system data collection, so that many difficult to express things become concrete, this is a great progress for mankind.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116770489","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}
Qinglan Meng, Xiyu Pang, G. Jiang, Yanli Zheng, Xin Tian
{"title":"Further Non-local and Multiple Granularity Network for Vehicle Re-identification","authors":"Qinglan Meng, Xiyu Pang, G. Jiang, Yanli Zheng, Xin Tian","doi":"10.1145/3501409.3501627","DOIUrl":"https://doi.org/10.1145/3501409.3501627","url":null,"abstract":"An algorithm that can effectively distinguish different vehicles with high similarity by identifying vehicle photos collected from multiple angles is called vehicle recognition algorithm. This algorithm has been extensively applicable to the region of intelligent transportation and urban computing, but it is always challenging to implement the algorithm. In this paper, an modified feature extraction method is provided, which enhances the traditional nonlocal neural networks and improves its ability to capture the relationship between different positions in the image. At the same time, we adopt a multi-branch global and local information learning strategy, which not merely captures the global features, moreover, those local parts of the feature can be more focused on finer discrimi-nating information in each part of the partition and filtering information on other partitions as the number of partitions increases. Finally, a hybrid relationship between channel feature fusion and channel level is introduced based on this learning strategy. The experimental results show that the MAP and Rank-1 indexes on the VERI-776 mainstream public dataset are 78.9% and 93.86%, which are the highest running scores in this dataset at the present stage, proving that the proposed algorithm is excelled other main stream design.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127718329","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}
{"title":"Research on multi-objective flow shop scheduling problem based on improved NSGA-III algorithm","authors":"Xi Zhang, Yuxing Wang","doi":"10.1145/3501409.3501618","DOIUrl":"https://doi.org/10.1145/3501409.3501618","url":null,"abstract":"Under the background of intelligence, this paper studies the actual workshop scheduling problem of the impeller company. From the perspective of reducing carbon emissions, combining the makespan and total operating cost of the machine as optimization indexes, a multi-objective mathematical model is established. Meanwhile, an improved NSGA-III algorithm was designed to solve the model. Compared with the experimental results of the genetic simulated annealing algorithm, better results were obtained in the three aspects of minimizing carbon emissions, minimizing total operating cost, and shortest completion time, to obtain the optimal scheduling scheme.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"5 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133170511","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}
{"title":"Research on the application of cloud computing technology in computer big data analysis","authors":"Gen-Kuo Chen","doi":"10.1145/3501409.3501630","DOIUrl":"https://doi.org/10.1145/3501409.3501630","url":null,"abstract":"With the development of the times, computer technology is making continuous progress. People's every move is generating data. In the face of such a large amount of data information, the traditional data processing technology has been unable to meet people's needs. Big data analysis and cloud computing technology came into being. Cloud computing and big data technology have far exceeded the traditional data processing technology in terms of accuracy and speed. Now cloud computing and big data analysis have become hot words in the society, and relevant experts and scholars are constantly studying these two technologies. Starting from the elaboration of cloud computing technology and big data technology, this paper explores the advantages and problems of cloud computing, deeply analyzes the application of cloud computing technology in computer big data, imagines the future of cloud computer technology, and provides some references for the future development of cloud computing technology.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133615199","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}
{"title":"Investment capacity prediction of Power Grid Enterprise based on Self-organizing Data Mining Technology","authors":"Juhua Hong, Lin Liu, Ziqiang Tang, Keyao Lin, Xiaofeng Li, Mou Yu","doi":"10.1145/3501409.3501588","DOIUrl":"https://doi.org/10.1145/3501409.3501588","url":null,"abstract":"With the expansion of power grid investment demand and investment scale, the research on power grid enterprises' investment capacity is particularly important. This paper expounds the basic principle of self-organizing Data Mining technology, and on this basis, establishes the GMDH model of power grid enterprises' investment capacity prediction, describes the process of establishing the model in detail. Then, the indicator system of power grid enterprises' investment capacity factors is constructed, and the GMDH model is used to forecast and analyze the investment capacity of HM Grid Company based on the data of factors from 2008 to 2020. The research results show that the GMDH model of grid enterprise investment capacity prediction is robust, not only can avoid artificial interference, self-organized selection of influencing factors, and meet the requirements of objectivity and authenticity, but also has a good prediction performance, high prediction accuracy, and more reliable prediction results, which provides new thoughts and approaches of measuring the investment capacity of grid enterprise.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134277624","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}
Tongtong Zhou, Lu Zheng, Yueping Peng, Rongqi Jiang
{"title":"Research on Crowd Counting and Density Estimation Algorithms Based on Deep Learning","authors":"Tongtong Zhou, Lu Zheng, Yueping Peng, Rongqi Jiang","doi":"10.1145/3501409.3501578","DOIUrl":"https://doi.org/10.1145/3501409.3501578","url":null,"abstract":"Thanks to the rapid development of computer vision technology, methods based on deep learning have gradually replaced counting methods based on traditional machine learning, and substantial progress has been made in counting accuracy and real-time detection. Firstly, the research background and application fields of target counting are introduced. Secondly, according to the classification of model tasks, the deep learning hotspot models are classified into three categories, and the crowd density estimation algorithms based on multi-scale strategies, multi-stage models and attention mechanisms, and multi-feature fusion are introduced from different perspectives. An introduction to the three algorithm models. Finally, it summarizes the shortcomings of the current target counting model, and looks forward to the future research directions.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134379800","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}
{"title":"Distribution big data technology of active distribution Network based on edge computing","authors":"Wei Zhang, Tianjun Wang, Hao Wang","doi":"10.1145/3501409.3501637","DOIUrl":"https://doi.org/10.1145/3501409.3501637","url":null,"abstract":"Aiming at the problems of cloud communication and storage congestion and computing delay caused by massive heterogeneous distribution data, a hierarchical architecture model of active distribution network based on edge computing was proposed. Firstly, the edge computing framework based on the functional architecture of industrial Internet is proposed, and the internal and external interaction modes of edge computing node data are specifically sorted out. According to the established data interaction modes, the interactive processing mechanism of cloud-edge collaboration is proposed. Then, according to the logical protocol and physical architecture of active distribution network, the hierarchical architecture model of active distribution network based on edge computing is established to collect, interact and monitor the operating status, operating environment and electricity quantity data of distribution equipment. Finally, based on big data technology, the typical application scenarios of edge computing technology in actual power distribution are analyzed, and the efficiency, real-time, security and accuracy of edge computation-based power distribution big data system for local data storage and processing are verified.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114788664","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}
Fan Wu, Yantao Zong, Rui Zhao, Tzuyang Yu, Xiaqing Tang, Ximing He
{"title":"Visual odometery for UAV navigation based on deep learning","authors":"Fan Wu, Yantao Zong, Rui Zhao, Tzuyang Yu, Xiaqing Tang, Ximing He","doi":"10.1145/3501409.3501673","DOIUrl":"https://doi.org/10.1145/3501409.3501673","url":null,"abstract":"Taking UAV as the application background, this paper studies the visual odometery for deep learning in UAV navigation. Firstly, the dataset FLYING is made through UAV aerial photography. Secondly, pretraining and testing the established G-LSTM VO and attention VO models through the KITTI dataset. Thirdly, by means of transfer learning, training and testing the pre trained model based on FLYING dataset. Finally, the model is tested. The performance of the model in UAV mission is analyzed from the aspects of trajectory, pose estimation accuracy and algorithm time-consuming. The experimental results show that the monocular visual odometery method based on depth neural network is effective in the field of UAV navigation.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"5 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102871","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}
Dunyang Geng, Changsheng Ai, Lei Zheng, Zhengguang Qi, Zhiquan Feng, Jiebing Yan
{"title":"Research on Lane Location and Navigation Technology Based on Binocular Camera","authors":"Dunyang Geng, Changsheng Ai, Lei Zheng, Zhengguang Qi, Zhiquan Feng, Jiebing Yan","doi":"10.1145/3501409.3501435","DOIUrl":"https://doi.org/10.1145/3501409.3501435","url":null,"abstract":"Aiming at the problem that the traditional single sensor of AGV cannot meet the indoor and outdoor operating conditions and the cost of multi-sensor is too high, this paper studies a navigation method for lane detection and positioning based on binocular camera. Based on the analysis of lane line equation coefficient variation, several dynamic filtering noise reduction methods are compared. The results show that the lane line detection method based on feature can accurately extract the lane line in multi-scenario. The variance of Kalman filter method is at least one order of magnitude lower than that of other filtering methods, which can effectively improve the stability of the system. According to the lane line equation, a relatively stable body posture deviation is obtained. The extracted yaw angle is less than 1 degree and the lateral deviation is less than 4 cm, which provides a basis for AGV vehicle control","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116586556","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}