2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)最新文献

Communication Encryption Scheme of 5G Power Trading Private Network Based on Dynamic Key 基于动态密钥的5G电力交易专用网通信加密方案

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00020

Rui Zhou, Yiyang Song, Ying Xu

{"title":"Communication Encryption Scheme of 5G Power Trading Private Network Based on Dynamic Key","authors":"Rui Zhou, Yiyang Song, Ying Xu","doi":"10.1109/EPCE58798.2023.00020","DOIUrl":"https://doi.org/10.1109/EPCE58798.2023.00020","url":null,"abstract":"Security has been the primary concern for the 5G power trading private network, which involves a large amount of power trading information. The communication must be encrypted to prevent the leakage of important information. The communication encryption scheme for 5G power trading private network should meet the characteristics of small communication overhead, low storage space requirement and strong resistance to attack. Based on these characteristics, the dynamic key-based encryption scheme is designed. To ensure the security and reduce the computation overhead, the optimized symmetric encryption algorithm is used to update the shared key. And the dynamic key generation method is improved by adding random numbers to solve the problem that the correct transmission of the data link does not have true randomness. The encryption mode used can generate dynamic keys directly and synchronously at both ends of the communication, reducing the overhead of key exchange and eliminating the need for trusted third parties. The algorithm is also analyzed for security and efficiency and compared with other algorithms. The experimental results show that the improved algorithm enhances security with guaranteed efficiency.","PeriodicalId":355442,"journal":{"name":"2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122559925","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}

引用次数: 0

A Left Ventricle Segmentation Based on Boundary Weighted Loss and Residual Feature Aggregation 基于边界加权损失和残差特征聚集的左心室分割方法

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00010

Kaiyu Wang, Yameng Han, Sixing Yin, Yining Wang, Shufang Li

{"title":"A Left Ventricle Segmentation Based on Boundary Weighted Loss and Residual Feature Aggregation","authors":"Kaiyu Wang, Yameng Han, Sixing Yin, Yining Wang, Shufang Li","doi":"10.1109/EPCE58798.2023.00010","DOIUrl":"https://doi.org/10.1109/EPCE58798.2023.00010","url":null,"abstract":"Assessing the left ventricle in cardiac magnetic resonance imaging (MRI) through segmentation plays a crucial role in the diagnosis of cardiac diseases for cardiologists. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. This paper proposes a method for automatically outing the left ventricle, namely a left ventricle segmentation algorithm based on boundary weighted loss and residual feature aggregation (RFA). The proposed method is based on the U-Net model, where normal convolutions of the encoder and decoder are replaced with a residual feature aggregation (RFA) module for more efficient feature extraction. At the same time, we add a series of cascaded dilated convolutions in the middle part of the encoder and decoder to expand the receptive field. In addition, we design a boundary weighted loss function, which can effectively address poor segmentation results caused by blurred/incomplete edges of the target object, or high proximity between the target object and others. Through experimental verification, it is proved that the proposed model and the carefully designed loss function both contribute to segmentation performance.","PeriodicalId":355442,"journal":{"name":"2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127711602","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}

引用次数: 0

Adaptive Large-Scale Multi-Objective Evolutionary Optimization Based on Reference Solution Guidance 基于参考解引导的自适应大规模多目标进化优化

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00014

Xin Yuan, Xiongtao Zhang

引用次数: 0

Prediction of Wind Turbine Blade Icing Based on LSTM-SVM 基于LSTM-SVM的风电叶片结冰预测

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00037

Mengchao Ren, Weilong Wang, Yunqi Bian, Hongxia Cai

{"title":"Prediction of Wind Turbine Blade Icing Based on LSTM-SVM","authors":"Mengchao Ren, Weilong Wang, Yunqi Bian, Hongxia Cai","doi":"10.1109/EPCE58798.2023.00037","DOIUrl":"https://doi.org/10.1109/EPCE58798.2023.00037","url":null,"abstract":"As one of the important parts of wind turbines, icing of wind turbine blade will lead to loss of power generation, and even cause blade to break and injure workers in severe cases. Therefore, the prediction of blade icing has always been the focus of the wind power industry. To solve the problem, this paper proposes a wind turbine blade icing prediction model based on LSTM-SVM. Firstly, we analyzed the time series data of a wind farm and the mechanism of blade icing to obtain the features sensitive to wind turbine blade icing. Then, the LSTM is used to predict these feature parameters for future moments. Finally, an SVM model was employed to diagnose the icing status of wind turbine blades based on the predicted feature parameters, thus achieving the prediction of blade icing. The model was verified by experimental data and was able to accurately predict whether the wind turbine blade would icing or not. Compared with traditional algorithms, it can predict the icing status of wind turbine blade in advance and has more accurate prediction results, making it more suitable for practical applications of blade icing prediction.","PeriodicalId":355442,"journal":{"name":"2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114355203","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}

引用次数: 0

Assessment of a Multi-Step LSTM-based Ensemble Strategy for Short-term Grid Modal Parameters Forecast 基于lstm的多步网格模态参数短期预测集成策略评估

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/epce58798.2023.00017

C. Olivieri, Francesco De Paulis, G. Giannuzzi

引用次数: 0

Design of balanced bicycle system based on anti-integral saturation and incomplete differential PID algorithm 基于反积分饱和和不完全微分PID算法的平衡自行车系统设计

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/epce58798.2023.00025

Yujie Huang, Xuehan Zhou, ZhongJie Liang, Qin Qin

引用次数: 0

Power Optimisation for a Verifiably Secure Separation Kernel 可验证的安全分离内核的电源优化

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/epce58798.2023.00036

A. Kammeyer, Jan C. Nordholz

引用次数: 0

DeepWise Cyber Teen Guardian: Protecting Internet Environment via a Novel Automatic Adversarial Samples Detection System Based on Revised Neural Network DeepWise网络青少年守护者:基于修正神经网络的新型自动对抗样本检测系统保护网络环境

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00022

Yi-Hsien Lin

{"title":"DeepWise Cyber Teen Guardian: Protecting Internet Environment via a Novel Automatic Adversarial Samples Detection System Based on Revised Neural Network","authors":"Yi-Hsien Lin","doi":"10.1109/EPCE58798.2023.00022","DOIUrl":"https://doi.org/10.1109/EPCE58798.2023.00022","url":null,"abstract":"In order to assist teenagers to surf the internet healthily, there are image filters based on image recognition neural networks removing inappropriate content, but image filters are vulnerable to attack by adversarial samples, which are generated by adding well-crafted noise to an image, making the filter consider an inappropriate image as appropriate. In order to defend against adversarial attacks, various adversarial detection algorithms are designed. The state-of-the-art detector enjoys a promising detection performance, but it suffers from high computational overhead. In this work, DeepWise is proposed, which records the mean and covariance for each class of images at each recording layer of the neural network during training. The input image’s mean and covariance at each layer and the network’s classification of the image are also recorded. Then, the Mahalanobis distance is calculated between the distributions of input image and the training images at each layer based on the network’s prediction. A linear regressor takes these distances as input, and determines whether the input image is an adversarial sample or not. DeepWise achieves a computational saving ranging from 39.77% to 87.98% for datasets SVHN, CIFAR- 10, and CIFAR-100 on the image recognition model ResNet-34 and DenseNet-3 while preserving a comparable AUROC to the existing state-of-the-art method.","PeriodicalId":355442,"journal":{"name":"2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129947933","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}

引用次数: 0

An improved Tibetan speaker recognition method based on ResNet 一种改进的基于ResNet的藏语说话人识别方法

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/epce58798.2023.00015

Zhenye Gan, Jincheng Li, Ziqian Qu, Yue Yu

引用次数: 0

Authenticity and uncertainty analysis of enterprise carbon verification data 企业碳核查数据的真实性与不确定度分析

2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE) Pub Date : 2023-04-01 DOI: 10.1109/EPCE58798.2023.00018

Zhang Bo, Lv Bin, Duan Yuqing, Tang Liang, You Jia

{"title":"Authenticity and uncertainty analysis of enterprise carbon verification data","authors":"Zhang Bo, Lv Bin, Duan Yuqing, Tang Liang, You Jia","doi":"10.1109/EPCE58798.2023.00018","DOIUrl":"https://doi.org/10.1109/EPCE58798.2023.00018","url":null,"abstract":"At present, in the process of carbon trading in China, there is an illegal phenomenon that practitioners use various means to falsify and tamper with data results, deliberately exaggerate carbon emissions reductions to obtain additional government incentives. Therefore, this paper will use the energy balance table to calculate carbon, and analyze the impact of calorific value, carbon content, carbon oxidation rate and power emission factors on the total carbon emissions by establishing equations. The results show that the changes of calorific value, carbon content and carbon oxidation rate have a significant impact on the calculation of total carbon emissions, while the impact of power emission factors is not significant. Therefore, in order to obtain accurate emission data based on the energy balance table, we must first adjust the energy balance table, and then improve the geographical and temporal boundaries of carbon emissions and the authenticity of data processing methods according to specific regional differences, carry out in-depth discussion on the uncertainty calculation method of China's carbon verification method, and analyze the comparison of Wilcoxon's sign rank test for the authenticity of data. Finally, the effectiveness and feasibility of the method described in this paper are verified by analyzing the carbon emission data of a chemical enterprise.","PeriodicalId":355442,"journal":{"name":"2023 2nd Asia Conference on Electrical, Power and Computer Engineering (EPCE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133821433","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}

引用次数: 0