{"title":"An Algorithm of Data Classification Based on PCA and K-Means++","authors":"Ruirui Huang, Qianshuai Cheng, Zhengquan Chen","doi":"10.1109/TOCS53301.2021.9688593","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688593","url":null,"abstract":"Principal component analysis (PCA) and K-means++ algorithm are used to classify and analyze eight main variables of the average annual consumption expenditure of urban households in 31 Provinces and cities in China in a given year, so as to better build the reasonable consumption level of each area. In this paper, a data classification method based on PCA and improved K-means++ is proposed. In this method, PCA was used to extract eight variable characteristics of consumer expenditure, and K-means++ algorithm was used to classify the data. The experimental results show that this method reduces the dependence of the characteristic dimension of variable data and the k-means++ algorithm on the initial classification center of gravity, and improves the accuracy and stability of data classification results.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127894041","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":"Project-Driven Shift Register Realizes Cyclic Color Light Control","authors":"Ying Chen, Miao Zhang, Liyun Zhang","doi":"10.1109/TOCS53301.2021.9688847","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688847","url":null,"abstract":"Project-led teaching is a teaching activity carried out by teachers and students through the joint implementation of a complete “project” work. It selects and organizes teaching content with work tasks as the center, and completes work tasks as the main learning method and the ultimate goal. Compared with traditional teaching methods, this teaching mode can not only solve the shortcomings of traditional teaching, but also cultivate the professional abilities that students need in the professional context. Project-based teaching, with its “project introduction, task-driven” teaching form, enables students to acquire knowledge while also training their comprehensive quality capabilities. This thesis takes the use of a shift register to design and realize the control of cyclic lights as an example to describe the implementation process of the project-based teaching method.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128961447","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":"Fusion Deep Learning and Machine Learning for Multi-source Heterogeneous Military Entity Recognition","authors":"Hui Li, Lin Yu, Mingqi Lyu, Yuwen Qian","doi":"10.1109/TOCS53301.2021.9688813","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688813","url":null,"abstract":"Currently, there is less research works on military entity recognition across corpus. Three types of military entity recognition corpus, namely abbreviated, scientific or English name, novel and random, are constructed to improve the construction of sub-scenario datasets, according to the heterogeneous characteristics of military entities in different military data sets, such as military documents, reconnaissance intelligence, simulation training mission conception, military books, military blogs, military reviews and military websites. With respect to the fuzzy boundaries of military heterogeneous entities we improve the entity annotation mechanism for entity with fuzzy boundaries based on related research works. We apply a BERT-BiLSTM-CRF model fusing deep learning and machine learning to recognize military entities, and design multiple types of experiments to verify the practical effects of the model. Experimental results show that the recognition effect of the model keeps improving with the increasing size of the corpus in the multi-data source scenario, with the F-score increasing from 73.56% to 84.53%.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129375245","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 interactive design of smart home supplies based on visual perception intensity","authors":"Yan You, Xu Yi","doi":"10.1109/TOCS53301.2021.9688895","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688895","url":null,"abstract":"Natural interaction is a more natural, intuitive and human-computer interaction method closer to human behavior, which enables people to interact with machines in a more natural and meta way, and use computers as naturally as talking with people. In order to provide better and convenient services for the public in using smart home supplies, this paper proposes an interactive design of smart home supplies based on visual perception intensity. As visual perception, it is the main research content of this paper that how to carry out interface visual design in order to promote the user’s convenient and efficient use of smart home. Reconstruct the top-down design process of smart home in the future from the perspective of service system design, focus on user experience, and combine the future business system, supply chain and service mode to construct the supplies system and interface design of smart home.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672805","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":"Sentiment Analysis of Online Comments through Semantic Networks and ROST Text Mining Software*","authors":"Wu Di, Yao Limei","doi":"10.1109/TOCS53301.2021.9688923","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688923","url":null,"abstract":"Collecting the evaluation and feelings of tourists on the image of tourist destinations through network texts, and using data mining methods to get the feelings of tourists during their play has become an important way to study the image of tourism. Take Gulangyu Island in Xiamen as an example, take the text data of tourist review websites as samples, and use ROST ContentMining software to extract high-frequency feature words of Gulangyu tourism online reviews to understand the content and themes of Gulangyu tourism image; use content analysis methods to construct social networks and semantic networks, And conduct sentiment analysis to analyze the degree of satisfaction of tourists with Gulangyu tourism.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117221359","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":"Joint Antenna Selection and Intelligent Reflecting Surface Aided MISO Downlink Networks","authors":"Shang Xia, Peichang Zhang, Zheng-Ming Jiang, Li Li, Xiaojun Wang, Shuo Feng","doi":"10.1109/TOCS53301.2021.9688728","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688728","url":null,"abstract":"Intelligent Reflecting Surface (IRS) has been recognized as one of the effective ways to enhance the system performance of multiple input single output (MISO) downlink communication system. In order to reduce energy consumption and further improve system performance in the entire MISO system, we incorporate the transmitter antenna selection (AS) technology into the IRS-aided MISO communication system. We aim to maximize the user instantaneous receiver signal-to-noise ratio (SNR) by jointly optimizing antenna subset, transmit beamforming of the access point (AP) and passive phase-shift matrix of the IRS. We propose to solve the problem using a novel discrete cuckoo algorithm combined with optimization theory (NDCOT). NDCOT consists of AS and optimization steps. In AS steps, a novel discrete cuckoo algorithm is exploited to reduce the complexity of AS. In the optimization step, the semidefinite relaxation (SDR) algorithm is employed to obtain the optimal transmit beamforming vector at the transmitter and phase matrix at the IRS. The simulation results validate the effectiveness of AS in reducing energy consumption and improving the performance of the IRS-aided MISO communication system.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115658254","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":"Multi-modal Sensor Fusion Method Based on Kalman Filter","authors":"Jiankai Qin, Zongren Liu","doi":"10.1109/TOCS53301.2021.9688970","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688970","url":null,"abstract":"This paper proposes a multi-modal sensor fusion framework, which provides a method that meets both the accuracy and real-time requirements to fuse multiple sensors, such as lidar, IMU sensors and wheel odometry, and can be used without visual features. Or achieve robust state estimation in scenarios where the spatial structure is degraded. Different from the Classical Algorithm, this article introduces the system that uses the IMU odometry as the main processing thread, and combines the advantages of loose coupling and tight coupling methods to restore motion by error correction. The framework consists of four parts: IMU odometry, wheel odometry, lidar inertial odometry and data preprocessing module. The data preprocessing module accepts IMU raw data, wheel odometry data and lidar positioning data, and provides synchronized data for IMU odometry. The IMU odometry uses the angular velocity integral provided by the IMU to obtain the direction information, combined with the speed information provided by the wheel odometry, to obtain high-frequency positioning information, and receives movement observations from the lidar inertial odometry for pose correction. The high-frequency output data of the IMU odometry provides input to the tightly coupled part of the lidar inertial odometry, further improving the accuracy of the lidar inertial odometry. The system was tested on a small unmanned vehicle, and the test results were quite satisfactory.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116191156","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":"Task Pre-migration Strategy in Mobile Edge Computing Environment","authors":"Zhang Zhihao, Ju Shuangshuang, S. Wei","doi":"10.1109/TOCS53301.2021.9688893","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688893","url":null,"abstract":"In the mobile edge computing environment, the requirements for low latency are relatively urgent, especially for high data volume computational migration, such as driverless system, real-time monitoring. When the user leaves the edge server coverage, data interruption occurs, and the user needs to re-upload the data to the server for calculation, which leads to extended time of the edge server service and increased power consumption of the mobile device. To solve this problem, this paper proposes a data pre-migration mechanism between servers in the mobile edge computing environment, which pre-puts user-related data to the edge server in the user’s moving direction. When the task is interrupted, the user does not need to re-upload data. The seamless connection of tasks can effectively reduce server service time and reduce device power consumption.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125606515","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 Financial Analysis Based on Nonlinear Dynamics","authors":"Zihao Deng","doi":"10.1109/TOCS53301.2021.9689002","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9689002","url":null,"abstract":"Using nonlinear dynamics theories and methods, taking the impact of the new crown epidemic on my country’s economy as the starting point, combing and analyzing the impact of the epidemic on my country’s financial market. On this basis, by studying the differences in the four dimensions of the epidemic in the scope of infection, external environment, development stage, and economic structure, discuss the impact of the epidemic on my country’s financial market, industrial chain and supply chain, and anti-globalization, so as to explore the epidemic The impact on my country’s economy during the period of domestic outbreak and during the period of global spread. Using dynamics principles, control and forecasting technical means and methods to accurately predict the development trend and direction of the financial situation, in order to overcome the impact of the new crown epidemic and promote my country’s economic and social development, to do a good job of normalized management of prevention and control, and to actively and orderly promote the overall Resume work and production, promote economic growth, stabilize the financial market and provide technical means and methods.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128139078","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 Preparation of C4 Olefins Based on Multiple Regression Analysis and Genetic Algorithm Optimization","authors":"Li Xiaokang, Tang Xin, Yuan Yukun","doi":"10.1109/TOCS53301.2021.9688858","DOIUrl":"https://doi.org/10.1109/TOCS53301.2021.9688858","url":null,"abstract":"In this paper, aiming at the process of preparing C4 olefins from ethanol through coupling reaction, a multi-objective optimization model is established with the goal of C4 olefin yield, and the system parameters such as catalyst combination mode and temperature are searched and solved. Firstly, it is found that there is a certain relationship between ethanol conversion, C4 olefin selectivity and temperature change, and multiple functions are used for regression analysis. Taking catalyst A1 as an example, the best regression model between ethanol conversion and temperature is y<inf>1</inf> = 0.003x<sup>2</sup> – 1.193x + 141.807. The best regression model between C4 olefin selectivity and temperature is y<inf>2</inf> = 0.001x<sup>2</sup> – 0.681x + 88.406. Ethylene selectivity time optimal model: y<inf>3</inf> = – 8.936e – 05x<sup>2</sup> + 0.030x + 2.252. Then, the influence model of ethanol conversion rate is established, the model is solved by the least square method, and the genetic algorithm is used to optimize the model. The optimal model of ethanol conversion rate is:<inf>w</inf><inf>1</inf> = 83.9812p<inf>ethanol</inf> + 0.9895t + 0.4925β<inf>Co/Sio</inf><inf>2</inf> – 84.2251. The optimal model of C4 olefin absorption is: w<inf>2</inf> = –2.2047λ<inf>co</inf> + 0.6778t + 0.5841β<inf>Co/Sio</inf><inf>2</inf> – 44.4423.","PeriodicalId":360004,"journal":{"name":"2021 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125866010","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}