{"title":"A Comparative Study of Neural Network for Text Classification","authors":"X. Peng","doi":"10.1109/TOCS50858.2020.9339702","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339702","url":null,"abstract":"This With the popularity of artificial intelligence in recent years, Natural Language Processing (NLP) technology has also become the focus of research. NLP technology's unique machine translation and text sentiment analysis functions can prevent people from experiencing poor language communication when travelling abroad and help artificial intelligence understand people's language better. This article has made corresponding practice and analysis for the critical requirement of “text classification” in NLP. In the experiment, we used the Internet Movie Database (IMDB) film review forum as the dataset. Recurrent Neural Network (RNN) and the corresponding variants of RNN (Long Short Term Memory (LSTM)) are analyzed and compared from the theoretical aspect. Moreover, we introduced a bidirectional mechanism to optimize RNN and reduce the influence of parameter changes on model training by comparing specific neural network structures. We found the benefits of LSTM in text classification applications compared with RNN and simple neural networks by comparing experiments. Besides, we explored the role of the bidirectional mechanism for RNN. Finally, we create a two-way LSTM model for text classification model and obtain the model training results indicating less overfitting and less loss than other structures.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127641054","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 Fault Diagnosis Method of Power Grid Based on Artificial Intelligence","authors":"Jilei Xu, Haifeng Yue","doi":"10.1109/TOCS50858.2020.9339711","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339711","url":null,"abstract":"With the development of social science and technology and the rapid development of China's economy, people's living standards have been greatly improved, and there is an increasing demand for power resources in all walks of life and among the people. In the fault diagnosis of power grid, the scientific application of artificial intelligence technology can not only ensure the effective solution of power system operation faults, but also significantly improve the safety performance of power system. Electric power system is an important part to ensure the normal operation of people and enterprises. Because the power system needs to adapt to various working environments, once the power system fails, it will produce serious consequences. All kinds of protection measures in power system can timely generate alarm and abnormal changes of power state when problems occur. Based on this, this paper discusses the application of artificial intelligence technology in power grid fault diagnosis, and studies the power grid fault diagnosis method based on artificial intelligence.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"6 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114121376","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 Questions on Silica Melting Based on Image Analysis","authors":"Peng Dai, Yunsong Gu, Rongjiang Zhou, Jiabao Guo, Rujin Li, Yifei He, Wei Ji, Shujie Chen","doi":"10.1109/TOCS50858.2020.9339740","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339740","url":null,"abstract":"This paper makes a perfect and reasonable explanation and solution to the highly researchable problems under the melting of silica, and uses the methods of image matching, moving state target tracking, gray and binary methods to construct multiple linear regression. Equations, feature image matching models, background difference models, etc., are comprehensively solved using software such as MATLAB, and it is found that the silica particle coordinates and particle motion trajectories, generalized radius and area can represent changes in the silica melting process the conclusion of the melting rate of silicon oxide is finally combined with the model to verify the reliability of the conclusion.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"32-33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123639253","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}
Xia Zhao, Zilong Zhao, Qufei Shi, Meng Dou, R. Zheng, Lixia Cui
{"title":"Comparative Experimental Study on the Stability of Two Brands of Dry Block Furnace","authors":"Xia Zhao, Zilong Zhao, Qufei Shi, Meng Dou, R. Zheng, Lixia Cui","doi":"10.1109/TOCS50858.2020.9339692","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339692","url":null,"abstract":"Dry block furnaces are widely used in on-site measurement and calibration of food, petrochemical, pharmaceutical, semiconductor, and other manufacturing enterprises for their advantages such as pollution-free, simple operation, easy to carry, fast rise and fall, and wide usable temperature range. The accuracy of dry-block furnace temperature measurement is always a problem for calibrator. The stability of dry-block furnace is an important factor affecting its accuracy. In conventional dry block calibrators, the drift of the internal reference thermometer and temperature gradients in the normalization block are the main contributors to the accuracy. However, the experimental comparison of the stability of the different brands dry-block furnace at different calibration temperatures is rare. we carry out validation and evaluation project to evaluate the stability of dry-block furnaces of two brands at home and abroad, the relationship between calibration temperature and stability of dry well furnace is analyzed by experiments. The results show that the overall stability of RTC158 is better than that of Const660. The measurement accuracy of RTC158 is better than that of Const660. We hope that this experiment can provide more comprehensive and reliable experimental data for the application of dry well furnace in field temperature calibration, so as to improve the accuracy of temperature measurement.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125405628","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":"The characteristic analysis of gradient matching layer of wideband ultrasonic transducer -Comparison of different matching layers","authors":"Jinghao Xie, Ke Zhu, Da Huo, Rui Zhang","doi":"10.1109/TOCS50858.2020.9339704","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339704","url":null,"abstract":"On the basis of discussing the feasibility of gradient matching layer design, the simulation of single matching layer, double matching layer and triple matching layer is carried out by PiezoCAD software. The simulation results indicate that the energy utilization efficiency of ultrasonic transducers will increase with the increase of acoustic matching layers and the −6dB bandwidth. Based don simulation, the gradient acoustic matching layer is prepared, and the experiment results prove that the ultrasonic transducer prepared contains gradient acoustic matching layer has a wider bandwidth. The feasibility of the ultrasonic transducer with gradient impedance and the influence of the matched layer material on the acoustic attenuation coefficient is also discussed.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128818344","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":"Low Energy Consumption Routing Path for Space Ad Hoc Network of Spacecraft Cluster","authors":"Hua Zhai, Meiyan An","doi":"10.1109/TOCS50858.2020.9339722","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339722","url":null,"abstract":"Spacecraft cluster is a space system constructed by a certain number of modular spacecraft where information interaction and collaborative control can be realized through space wireless ad hoc network, so as to flexibly, efficiently and self-organized realize the combination, coordination and upgrading of various space capabilities. This will be one of the important development directions of space system. It is of great significance to use miniaturized and intelligent spacecraft to build spacecraft cluster, which can effectively reduce the construction cost of space system. In order to meet the requirement of low energy consumption for small spacecraft, this paper proposes a low energy consumption routing method for spacecraft cluster. Based on the analysis of wireless communication model and spacecraft relative motion equation, the low-energy routing path construction method of spacecraft cluster wireless ad hoc network is studied by using graph theory method, and the spacecraft cluster is simulated under various initial conditions.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129097430","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":"Adaptive Quantum Clustering and Its Incremental Training","authors":"Ping Ling, Xiangsheng Rong","doi":"10.1109/TOCS50858.2020.9339733","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339733","url":null,"abstract":"An Adaptive Quantum Clustering algorithm (AQC) and its incremental training approach are proposed. AQC employs Schrödinger Equation to find core data. The equation is equipped with density estimation and a new metric that are learned from support vector clustering process. Based on core data, the grouping method of AQC assigns core data into clusters. AQC is trained incrementally through selecting valuable data from coming batch. Experiments suggest AQC improves clustering accuracy and efficiency over its counterparts, and achieves competitive performance with some state of the arts.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114903388","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":"A Website Group Data Security Analysis Model Based on Word Embedding Expansion","authors":"Lei Peng, Gang Zeng","doi":"10.1109/TOCS50858.2020.9339734","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339734","url":null,"abstract":"To solve the problem of analysing website group data security, an analysis model based on word embedding expansion is proposed. Firstly, the word embedding method is used to expand the sensitive word dictionary. Then the crawled content is preprocessed and feeded into the filtering algorithm to filter the sensitive words. Finally, an analysis algorithm is designed to handle the final data and give the result. Experiments show the model proposed in this paper has a good security analysis performance.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134122326","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":"Simulation Research on Hydraulic Loading System of Wind Turbine Based on Particle Swarm PID Control","authors":"Yi Zhu, Yuan Sun, Guochu Chen","doi":"10.1109/TOCS50858.2020.9339746","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339746","url":null,"abstract":"As the key part of the wind turbine transmission chain to bear the load of the wind turbine, the quality of its working characteristics directly affects the basis of important performance such as the safety, stability and reliability of the system. This paper studies the hydraulic loading system of wind turbines. The mathematical model of the valve-controlled hydraulic loading system was established and simulated in MATLAB. The PID control method and the fuzzy PID control method based on particle swarm algorithm are selected to model and simulate the closed-loop control system of the hydraulic loading system. Through comparison, it is concluded that the hydraulic loading system based on PSO PID control has the advantages of fast response speed and stable system.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133356368","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":"To Become Fashionable: A Brief Review of Outfit Compatibility","authors":"Ruining Feng","doi":"10.1109/TOCS50858.2020.9339690","DOIUrl":"https://doi.org/10.1109/TOCS50858.2020.9339690","url":null,"abstract":"How to dress fashionably has become a major concern for people nowadays. In order to match a fashionable outfit, we need to make our outfit as compatible as possible. Thus, we need to exploit an effective outfit matching scheme and apply it to help people match their own clothes. Outfit compatibility is an emergent computer vision field which tackles this problem. It refers to whether multiple fashion items look good if worn together. Recently, researchers have proposed different compatibility algorithms and recommendation algorithms to make an outfit as compatible as possible and fulfill the users' personal need. In this paper, we present a detailed overview of major compatibility algorithms, such as neural network, and major recommendation algorithms, such as collaborative filtering in outfit compatibility. This paper evaluates the models based on different tasks and datasets and concludes current applications, challenges and possible solutions in outfit compatibility.","PeriodicalId":373862,"journal":{"name":"2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129401774","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}