{"title":"A Survey of Large-scale Complex Information Network Representation Learning Methods","authors":"Xiaoxian Zhang","doi":"10.1109/ICCECE58074.2023.10135535","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135535","url":null,"abstract":"With the increasing growth of data scale and the increasing complexity of network structure, the heterogeneity, high sparsity, heterogeneity and high dimensionality of large-scale complex networks have become increasingly prominent. How to represent network information reasonably and effectively so as to better serve subsequent network analysis tasks has become the key problem of network analysis. Network representation learning aims to represent the components (nodes, edges, subnets, etc.) in the network as low dimensional dense vectors. This vector can fully retain the original network structure information and other heterogeneous information, and has the advantages of improving computing efficiency, mitigating the impact of data sparsity, and effectively merging heterogeneous information. This research focuses on homogeneous networks and heterogeneous networks, summarizes and analyzes advantages and shortcomings of the network representation learning methods in recent years, and gives the possible research directions and contents in the future work.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116553504","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":"Comparison and Analysis of Four Signal Detection Algorithms in Different MIMO-VLC Systems","authors":"Chong Li, Yufeng Shao, An-rong Wang, Peng-Ying Chen, Yanlin Li, Renjie Zuo, Shuanfan Liu, J. Yuan","doi":"10.1109/ICCECE58074.2023.10135532","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135532","url":null,"abstract":"In indoor high-speed visible light communication (VLC) systems, the detection sensitivities of several access signals are often affected due to the mutual interference of different light-emitting diodes (LED) emission signals and the multipath effect from different transmission channels, which hinders the wide application of multiple-input multiple-output-VLC(MIMO-VLC) technology. In this work, high speed VLC signal using 16 quadrature amplitude modulation (16QAM) modulation format is selected, and four signal detection algorithms are compared and analyzed in different MIMO-VLC systems. The results show that the bit error rate (BER) performance while suing zero forcing-successive interference cancellation (SIC-ZF) is significantly better than that of ZF and minimum mean square error (MMSE) signal detection algorithms in complex indoor environments. At the SNR $mathbf{leqslant 10dB}$ case, the value of BER in 4×6 MIMO system can reach 10−5 using SIC-ZF ignoring impacts of non-line-of-sight (NLOS) links.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128848425","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":"Robot Path Planning Based on Grid Map Using Improved Ant Colony Algorithm","authors":"Farong Kou, Wei Xiao, H He, Kailun Hu","doi":"10.1109/ICCECE58074.2023.10135377","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135377","url":null,"abstract":"For the problems of slow convergence and easy to fall into local optimum of traditional ant colony algorithm (ACO) for robot path planning, An improved ant colony algorithm (IACO)based on grid map is proposed in this paper. Firstly, in order to improve the positive feedback ability of pheromone in the later period, an adaptive adjustment factor is introduced into the heuristic function. Secondly, the rotation function is introduced into the pheromone state transition probability to balance the relationship between path length and angle. Finally, in order to ensure the quality of participating pheromone update nodes, local optimization strategies are designed based on cross optimization and redundant point deletion, and different quality paths are updated with pheromone difference mechanism to achieve convergence of high-quality nodes. The experimental results show that IACO can make the robot obtain the global optimal path, and it will have good stability and environmental adaptability.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127726765","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":"Visual recognition of wheel hubs with convolutional neural network","authors":"Yining Dai, Zaojun Fang, Caiming Zhong","doi":"10.1109/ICCECE58074.2023.10135372","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135372","url":null,"abstract":"The traditional recognition methods of wheel hubs are mainly based on extracted feature matching. In practical production, their accuracy, robustness and processing speed are usually greatly affected. To overcome these problems, this paper proposes a recognition method based on convolutional neural network. The basic steps include two parts: wheel image pre-processing and wheel model classification. The image processing method, mainly using the detection algorithm of hough circles, obtains the center coordinates and radius of the wheel. Then it maps the ring-shaped wheel in right-angle coordinates to polar coordinates by the center coordinates and radius. This stepcan extract the ring-shaped feature information of the wheel image and reduce the influence generated by redundant features. Then a network architecture with an improved Resnet is designed to classify the wheel models. Finally, the wheel model recognition algorithm is evaluated, and the effectiveness of the method is verified through the comparison experiments of SVM, KNN and other models. The experiments show that the recognition accuracy can reach about 99.8% for 10 kinds of wheels.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129941178","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":"LDAGB: A Lightweight DAG-based Blockchain","authors":"Pengliu Tan, Shikun Wang, Ye Zhou","doi":"10.1109/ICCECE58074.2023.10135476","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135476","url":null,"abstract":"To solve the problems of low query efficiency and high storage redundancy of traditional blockchain technology, a lightweight DAG-based blockchain (LDAGB) architecture is proposed. The block of the LDAGB architecture is called a unit, which stores a transaction, the wallet addresses of the sender and receiver of the transaction, and two parent unit hashes. When a new unit is generated, one parent unit hash value in the unit points to the current latest unit of the transaction sender (wallet address), and the other parent unit hash value points to the current latest unit of the transaction receiver (wallet address). Based on the concept of light wallets, each lightweight node stores only its own units, avoiding huge storage costs caused by data growth. In addition, a lightweight PoW consensus mechanism is used to reduce the computing cost of unit packaging, and a voting mechanism is used to avoid the possible fork of LDAGB. The experimental results show that LDAGB can significantly improve the efficiency of transaction query and verification and reduce the storage cost, compared with the traditional blockchain architecture.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129978816","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":"Optimization of random forest algorithm based on mixed sampling additional feature selection","authors":"Haobo Cui, Hongmei Xu, Jingxin Li","doi":"10.1109/ICCECE58074.2023.10135433","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135433","url":null,"abstract":"Because of the poor performance of the Random Forest algorithm in processing the classification of high-dimensional unbalanced data, a Hybrid Samping&Feature Selection Random Forest optimization strategy (Hybrid Samping&Feature Selection Random Forest (HF_RF) is proposed in this paper. First, from the data level, the high-dimensional unbalanced data set is preprocessed by SMOTE algorithm combined with random undersampling to achieve balanced unbalanced data. At the same time, the clustering algorithm is combined with SMOTE algorithm to improve the processing ability of the algorithm for negative samples; On the algorithm level, through the Relief F algorithm, different weight values are given to the preprocessed high-dimensional data, irrelevant and redundant features are eliminated, and high-dimensional data is reduced for dimensionality; Finally, the weighted voting principle is used to further elevate the predictive performance of HF_RF. The experimental results show that compared with the traditional algorithm, the proposed algorithm has higher indicators when dealing with high-dimensional unbalanced data, which proves that the HF_RF proposed in this paper is The correctness of the algorithm and its effectiveness in improving the classification performance of high-dimensional unbalanced data.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130137744","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 Energy -saving algorithm based on wireless sensors based on evolution games","authors":"Weibo Zhao, Yongwen Du, Shuai Li, Ji Ma","doi":"10.1109/ICCECE58074.2023.10135346","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135346","url":null,"abstract":"Aiming at the problem of excessive load and uneven energy consumption in the wireless sensor network, establishing a game model of cluster node cooperation data based on the theory of evolutionary game, and also proposed a wireless sensor network optimal route based on the evolutionary game algorithm. The income function of cluster-head evolutionary game is designed by integrating the energy of nodes and energy consumption of forwarding data and consider the impact of the selfish node on the network performance of the wireless sensor, thereby forming a stable and efficient routing forwarding structure. The simulation experiment shows that the algorithm balances the node load, effectively improves the problem of imbalance in energy in the network, reduces the packet loss rate, and extends the survival time of the network.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117209764","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 Intelligent Control System for Wheeled Drug Spraying Robot","authors":"Shenglong Xu, Yuping Cui","doi":"10.1109/ICCECE58074.2023.10135270","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135270","url":null,"abstract":"Facing the problems of low manual efficiency and great harm to human body in the process of pesticide spraying, this paper puts forward a remote control solution ofof wheeled drug spraying robot, and designs the corresponding intelligent control system. The system takes Siemens S7-1200 PLC as the core controller, takes the touch screen as the man-machine interface, and combines the multi-sensor system to complete the allocation and control of the motor drive unit, so as to realize the functions of advancing, retreating, steering, speed regulating of the wheeled drug spraying robot. In addition, according to the experimental test results, PLC can realize the coordinated control of the drug spraying robot, and the whole system runs smoothly, responds quickly, and its operability and flexibility meet the design requirements, which provides a useful technical reference for realizing the automatic and intelligent operation of pesticide spraying.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131694520","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":"Driving behavior recognition method based on trajectory data detected by millimeter wave radar","authors":"Rui Zhang, Haiqing Liu","doi":"10.1109/ICCECE58074.2023.10135333","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135333","url":null,"abstract":"In this paper, a multi-step vehicle driving behavior recognition method based on roadside millimeter-wave radar detecting trajectory data is proposed. The time and vehicle radial speed in trajectory data are selected as characteristic parameters. By analyzing the characteristic parameters of vehicles, different vehicle driving behaviors are classified. The proposed method marks and judges single driving behaviors, continuous driving behaviors, and complete driving behaviors in the state of RA (rapid acceleration), RD (rapid deceleration), GA (general acceleration), GD (general deceleration), and CS (constant speed) by calculating acceleration, interval time, and duration. The identification of vehicle driving behavior is completed finally. Using the vehicle trajectory data of continuous traffic flow scenarios at urban signal intersections as a sample, the established recognition method is applied for recognition and the results are compared with the actual driving behaviors of the sample. The identification results are consistent with the driving behavior reflected by the sample time-speed variation curves. It shows that the identification method proposed in this paper can effectively identify five types of driving behavior, and the accurate identification results of vehicle driving behavior have significance for traffic safety and traffic congestion improvement decision-making.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130692056","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":"Power data attribution revocation searchable encrypted cloud storage","authors":"Jiawei Li, T. Zhang","doi":"10.1109/ICCECE58074.2023.10135266","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135266","url":null,"abstract":"Grid business data contains a large amount of electricity data customer privacy data, serving more than 1.1 billion people, involving personnel, financial, material, assets and other ten areas of data resources. The existing grid data has the security problem of privacy leakage due to reverse analysis in the process of publishing, and the data permission is difficult to revoke. To address these problems, this paper proposes a CP-ABE (ciphertext policy attribute based encryption) cloud storage scheme with revocable attributes, which can ensure the security of attribute permissions, dynamic change of user attributes and complete protection of user privacy. The paper is based on a subset-covered attribute revocation technique, which generates a corresponding user tree for each user attribute to enable revocation of user attributes without updating the user key after revocation, reducing the corresponding computational overhead. Then, multiple attribute authorisation authorities are used to distribute and manage keys without introducing any other trusted authorities, protecting user privacy and avoiding security issues caused by a single attribute authorisation authority. Finally, a pre-decryption algorithm is designed to reduce the computational overhead of the user when decrypting. The security analysis yields that the scheme has ciphertext privacy and keyword privacy; the performance analysis finds that the scheme has low computation and communication overheads; the experimental analysis reflects that the scheme has low key storage overhead, ciphertext storage overhead and index storage overhead.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114669953","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}