2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)最新文献

{"title":"A Convolution Neural Network-based Method for Sea Ice Remote Sensing using GNSS-R Data","authors":"Heng Xie, Shanbao He, Xing Cheng","doi":"10.1109/CISCE55963.2022.9851159","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851159","url":null,"abstract":"Sea ice remote sensing is of great significance to the understanding of polar climate change. At present, the global navigation satellite system reflector (GNSS-R) technology has been applied to the study of sea ice remote sensing and achieved good results. In this paper, a convolution neural network (CNN) based method for sea ice recognition (SIR) and estimation of sea ice concentration (SIC) using GNSS-R data is proposed. Specifically, a CNN model is designed to solve the classification problem of SIR and the regression problem of SIC estimation. In the stage of data set construction, first, the global GNSS-R data (TDS-l), in a certain period of time, is spatiotemporally matched with the relatively reliable sea ice data (NSIDC), and then the matched GNSS-R data is extracted to balance the amount of seawater data and sea ice data. In the stage of CNN model construction, the feature learning ability of the model is enhanced by adding convolution layer, pooling layer and full connection layer. Simulation results show that the proposed CNN -based scheme has a higher prediction accuracy of SIR and lower estimation error of SIC than other existing methods.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121098509","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 Volleyball Players Tracking Based on Improved DeepSORT","authors":"Zipei Pan, Jing Zhu, Xizhe Bao, Jingyi Lin, Jiahui Ming","doi":"10.1109/CISCE55963.2022.9851084","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851084","url":null,"abstract":"In order to reduce the problems of identity switching caused by occlusion in volleyball video, we propose a method named Vol-DeepSORT based on DeepSORT for tracking volleyball players. According to the principle that the number of players is unchanged in a fixed playing area, we improved the DeepSORT algorithm that rematches the new tracks with the vanishing tracks by the minimum Euclidean Distance, so as to realize the recovery of the player identity. We use the improved algorithm Vol-DeepSORT combined with YOLOv5 to detect and track the players. Experimental results show that the MOTA of Vol-DeepSORT is 90.07%, and the frequency of identity switching is reduced by 30% compared with the original DeepSORT. The proposed algorithm can reduce the frequency of identity switching on players to a certain extent and achieve a good tracking performance.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126617642","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 Network Topology Discovery Algorithm Based on IS-IS","authors":"Jianfei Cai, Guozheng Yang, Jingju Liu","doi":"10.1109/CISCE55963.2022.9851181","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851181","url":null,"abstract":"Efficiently, accurately and automatically discovering the network topology is an important research content of network measurement. This paper analyses the hierarchical structure of IS-IS protocol and the types and functions of LSP. Then topological relationship analytical methods based on LSP information are studied. For the shortcomings of the current algorithm, a network topology discovery algorithm of heuristic judgment based on LSP information is designed. Finally, by experimenting typical network layout scenario, the effectiveness and correctness of the algorithm are verified.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126736945","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":"Design of medical robot control system based on single-chip microcomputer","authors":"Kaixuan Fan, Zilin Xin, Peiran Cui","doi":"10.1109/CISCE55963.2022.9851043","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851043","url":null,"abstract":"In order to save manpower, improve the management of COVID-19 prevention and prevent the spread of the epidemic, this paper proposes and designs a medical robot based on a one-chip computer. The single-chip STC89C52 is used as the main control core. Obstacles are detected by infrared sensors. And the robot uses the tracking module to determine the path. The working states of the two DC motors are then changed by the IO-port control L298N drive template, thereby changing the motion state of the robot through the speed difference between the motors on both sides. In the intelligent tracking module, the robot first uses a genetic algorithm to find the best path forward inspection and then enters the ward. After disinfection, the robot uses STM32F4 to drive the OV2640 camera to collect data and detect the mask using the yolov5s algorithm. Finally, it sends the collected information to the computer to realize the real-time monitoring of the patient's condition. The simulation results show that the medical robot can effectively and accurately realize the requirements of path planning, facial mask recognition, and wireless communication. This will significantly improve the efficiency and safety of medical staff.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126901019","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":"When Edge Computing Meets Agile Software Development","authors":"Linkai Zhu, Shiyang Song, Zhe Xu, Wennan Wang, Sheng Peng, Shanwen Hu","doi":"10.1109/CISCE55963.2022.9851104","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851104","url":null,"abstract":"Agile development has been a common methodology in software development. In response to the covid-19, most software development teams choose to work remotely. As a result of the different network environments, the company cloud center network load cannot meet the requirements of remote development and fault tolerance requirements of the agile development process. We designed a mixed-method called the Edge Development approach for improving Agile software development during the decision-making process. The extensive literature review provided us with three categories of challenges as well as solutions to support Edge Development's decision-support process. In the light of the survey, Five main software development decision-making challenges were identified in this study. In addition, we made a series of recommendations to improve the decision-making process of Edge Development from a variety of perspectives.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129432125","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":"Design of Temperature Monitoring System of Fresh Product Self-collection Cabinet Based on LoRa","authors":"Yang Yang, Yan Jiang, C. Du","doi":"10.1109/CISCE55963.2022.9851010","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851010","url":null,"abstract":"For the delivery within the fresh food industry, it is difficult to coordinate the courier and customer pickup time, and the customer cannot pick up the goods in time. Especially in the summer or winter temperature extremes in the environment of fresh food more prone to spoilage. A LoRa-based wireless temperature control cabinet monitoring system is designed to solve this problem. The system incorporates various IoT technologies and consists of a terminal controller, sensors, actuation units and a host computer. This design uses STM32F407 microprocessor as the core to monitor the temperature inside the cabinet in real time and control the electric heating film and semiconductor cooler for temperature control through PID algorithm. The monitoring terminal receives the temperature through the LoRa sensor and visualizes it. It is also possible to set the temperature you want to achieve in the host computer. The test results show that the system achieves real-time monitoring of the fresh cabinet with stable data transmission and has good prospects.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121399667","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 industrial Internet Platform Technology based on machine learning algorithm","authors":"Zhengqin Wang","doi":"10.1109/CISCE55963.2022.9851027","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851027","url":null,"abstract":"Industrial Internet, is a new generation of information technology and industrial system full range of deep integration of the product, mainly for the transformation and upgrading of the manufacturing industry, can greatly boost the development of productivity, to pull the real economy has an important role. However, as the industrial Internet is an emerging industry, its development and construction experience and capacity are still in the initial stage. The report to the 19th National Congress of the Communist Party of China made it clear that we will promote the deep integration of the Internet, big data, artificial intelligence and the real economy. After the financial crisis, the manufacturing industry once again became the focus of global attention. With the digital transformation of the manufacturing industry, the industrial Internet platform based on cloud computing, big data, Internet of Things, artificial intelligence and other new generation of information technology emerged. With the development of machine learning and deep learning, machine learning models such as genetic algorithm and gradient optimization have achieved good results in data classification, regression and fitting. Internet project evaluation based on industry characteristics, puts forward the improved analytic hierarchy process (ahp) based on machine learning methods, and machine learning algorithms and hierarchical analysis method, puts forward a new solution to the problem of the expert scoring to determine judgment matrix and in order to achieve the consistency and accuracy of the algorithm and introduce the weight of the particle swarm algorithm to adjust and sorting, Reduce the inaccuracy and complexity of ahp algorithm in the face of complex problems. To achieve the expert scoring more comprehensive consideration method, as well as more intelligent consistency adjustment and final weight calculation, the index of the industrial Internet design scheme weight calculation, finally according to the scoring scheme and the final hair there are final evaluation scores and further analysis and explanation of the results.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127679081","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 classification algorithm for door and window air tightness detection based on particle swarm optimization","authors":"Xin Deng, Yan Jiang","doi":"10.1109/CISCE55963.2022.9851106","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851106","url":null,"abstract":"In the modern construction technology industry, on-site gas tightness detection is widely used in building doors and Windows, which can reduce unnecessary energy consumption in the application process of building, and achieve energy conservation and emission reduction targets. In order to increase the speed and efficiency of field detection of doors and Windows, this paper proposes a data transmission method based on WIFI wireless transmission, combines the particle swarm with CART algorithm to classify the detection data in real time, and uses this algorithm to optimize CART algorithm to improve the classification accuracy. We demonstrate the effectiveness through numerical simulation experiments.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127693870","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 Column Searching-based Multiple-point Statistics for Efficient Image Generation","authors":"Chen Guo, H. Zhang, Chen Zuo","doi":"10.1109/CISCE55963.2022.9851013","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851013","url":null,"abstract":"With the rapid development of digital image generation technology, geological image modeling and analysis have shown great potential in groundwater management and oil exploration. Reconstructed images are used to investigate the spatial structure and petrophysical properties. As a powerful method of geological modeling, Multiple-point Statistics (MPS) algorithms are able to create high-quality 2D or 3D models on the basis of Training Image (TI). Within MPS framework the dataset is a key component to store the spatial structures. However, a key limitation is computational efficiency, mostly attributed to the slow speed of finding desired patterns in datasets. To improve the efficiency of image generation, we propose a multiple-point statistics method called Column Searching Simulation (CSSIM). The core idea is to apply column searching to quickly search similar patterns in the dataset. In addition, an early-stopping strategy is designed to facilitate geometrical structure reproduction. We apply the proposed method to 2D channelized reservoir image generation. The variogram and Analysis of Distance are applied to assess image generation quality. Compared with the existing method, our CSSIM significantly improves the image generation efficiency while yielding comparable quality.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128107174","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":"GNN-Guided Track Branch Formation For Multiple Hypothesis Tracking","authors":"Wenge Xing, Dingbao Xie, Jin Wang","doi":"10.1109/CISCE55963.2022.9851012","DOIUrl":"https://doi.org/10.1109/CISCE55963.2022.9851012","url":null,"abstract":"Multiple Hypothesis Tracking (MHT) has shown its powerful performance in multiple target tracking applications. To reduce the number of formed track hypotheses, MHT usually defines three correlation gates called extrapolation, initiation and correlation gate, and create track hypotheses based on the observation falling in the gate. However, in closely spaced multitarget scenarios, observations of new target may fall within the initiation gate of existing track for a long time, leading to the difficulty of track initialization. Similarly, the track may also break due to the gating rules. In this paper, we propose to utilize global nearest neighbor (GNN) association result to guide track branch formation in MHT and format track branches based on the GNN association result. Simulation experiments show that the proposed GNN-guided approach is able to solve the above problems and controls the computational complexity well.","PeriodicalId":388203,"journal":{"name":"2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128116051","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}