2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)最新文献_第8页

Research on the Application of Long Short-Term Memory Neural Network in Power Load Forecasting 长短期记忆神经网络在电力负荷预测中的应用研究

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176504

Tianyi Hu, Zhen Zhang

引用次数: 0

Local and Global Multimodal Interaction for Image Caption 图像标题的局部和全局多模态交互

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176671

Zhengfa Yu, Kai Fu, Heng Jin, Jianan Bai, Hequn Zhang, Yuanhao Li

引用次数: 0

IGA-BiLSTM: An Improved Method for Network Security Situation Awareness IGA-BiLSTM:一种改进的网络安全态势感知方法

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176577

Chongwei Hong, Y. Qin, Xuwen Qin, Dongcheng Zhang

{"title":"IGA-BiLSTM: An Improved Method for Network Security Situation Awareness","authors":"Chongwei Hong, Y. Qin, Xuwen Qin, Dongcheng Zhang","doi":"10.1109/ICECAI58670.2023.10176577","DOIUrl":"https://doi.org/10.1109/ICECAI58670.2023.10176577","url":null,"abstract":"This paper presents an improved prediction model based on LSTM to solve traditional network security situation perception and prediction problems. Due to the significant advantages of BiLSTM in processing network data with time series characteristics and often related content, this paper will design a prediction model based on the Bi-LTM model. As a neural network model, the setting of LSTM’s superparameters is always a difficult point. On the basis of BiLSTM, this paper improves the original algorithm by using the immune genetic algorithm IGA, which enables the new algorithm to select better parameters and process random data on the basis of processing time series data. In this article, we analyze the UNSW-NB15 intrusion detection dataset, which will be used to train and test our model. Compared with the original LSTM algorithm and Bi LSTM algorithm, the prediction accuracy of the final model is improved. In the binary classification problem, the prediction accuracy has been improved by 1%-2%. In the multi classification problem, the prediction accuracy has improved by up to 3%, while F1 Measure has also improved by 2%. In the recognition of different types of anomalies, the F1-Measure of the IGA-LSTM model also has an improvement of 1%-2%. Finally, for situation prediction, the IGA-LSTM model’s situation curve is closer to the actual situation curve.","PeriodicalId":189631,"journal":{"name":"2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130535243","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 Residual Neural Network-Based Incremental Learning Model for Driver State Perception 基于残差神经网络的驾驶员状态感知增量学习模型

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176412

Jie Cai, Jingming Zhang, Erxin Sun, Jianjun Cai

引用次数: 0

Routing Resource Allocation for FPC in Complex Scenarios 复杂场景下FPC路由资源分配

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176480

Jingxue Xu, Haoying Wu

{"title":"Routing Resource Allocation for FPC in Complex Scenarios","authors":"Jingxue Xu, Haoying Wu","doi":"10.1109/ICECAI58670.2023.10176480","DOIUrl":"https://doi.org/10.1109/ICECAI58670.2023.10176480","url":null,"abstract":"Since the outline of the flexible printed circuit (FPC) is complex and changeable and the pins are densely distributed in some regions of the layout, it is difficult to route all nets completely. In this paper, we propose a partition algorithm for complex FPC to divide the FPC routing problem into escape routing and area routing in order to better allocate the routing resource. Our algorithm is based on constrained Delaunay triangulation (CDT), several techniques are proposed to adapt it to FPC. These techniques are as follows: (1) a pin cluster dendrogram based on FPC outline information, which makes pin clustering result more accurate; (2) a ternary tree based on CDT to determine the escape boundary of each region; (3) an escape-passage-connection model (EPC model) to describe the topological connection relationship; and (4) a global dynamic routing graph based on CDT to calculate the crossing points on the escape boundaries and generate the topological path of each net without congestion. Experimental results on some industrial cases show that our method has great generalization ability, and the routing results are better than those without considering the area partition.","PeriodicalId":189631,"journal":{"name":"2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682687","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

Graph Neural Network Model Based on Layered Converter Aggregation 基于分层转换器聚合的图神经网络模型

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176410

Xinyu Wang

{"title":"Graph Neural Network Model Based on Layered Converter Aggregation","authors":"Xinyu Wang","doi":"10.1109/ICECAI58670.2023.10176410","DOIUrl":"https://doi.org/10.1109/ICECAI58670.2023.10176410","url":null,"abstract":"Graph data is an important data in real society. With the development of neural network technology, graph neural networks are receiving more and more attention. However, the existing methods mostly use adjacency matrix or attention to aggregate the information of surrounding nodes, or use random walk to select neighboring nodes for aggregation, but this aggregation method is too simple and ignores the complexity of the graph structure. At the same time, inputting all the massive graph data into GCN for large-scale matrix operations in the real world requires a lot of computational power, and the attention calculation between multiple nodes also brings a heavy burden to computers, resulting in additional time loss. Based on this, this article proposes a hierarchical transformation aggregation model to aggregate node information by hierarchy and region. To put it simply, we first select nodes in each layer in the way of random walk, and then use GCN to aggregate. After obtaining the node characteristics of each layer, we use the attention mechanism with transformation to aggregate the node characteristics of each layer to obtain the final representation of nodes. Finally, we verify the reliability of the model on multiple datasets.","PeriodicalId":189631,"journal":{"name":"2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)","volume":"211 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133387952","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

Coverage optimization of wireless sensor networks with improved golden jackal optimization 基于改进金豺优化的无线传感器网络覆盖优化

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176640

Junqi Geng, Haihua Wang, Jie Su, Xiaoyu Zheng, Xian Sun, Xu Wu, Yue-Li Zhang

引用次数: 0

Natural and Imperceptible Backdoor Attack against Deep Neural Networks 对深度神经网络的自然和难以察觉的后门攻击

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2023-05-12 DOI: 10.1109/ICECAI58670.2023.10176925

S. Ni, Xin Wang, Yifan Shang, Linji Zhang

{"title":"Natural and Imperceptible Backdoor Attack against Deep Neural Networks","authors":"S. Ni, Xin Wang, Yifan Shang, Linji Zhang","doi":"10.1109/ICECAI58670.2023.10176925","DOIUrl":"https://doi.org/10.1109/ICECAI58670.2023.10176925","url":null,"abstract":"Over the past few years, deep learning has demonstrated impressive performance across a wide range of applications. As the same time, researchers have become increasingly concerned with ensuring the security of deep learning models. Specifically, backdoor attacks have emerged as a significant threat to Deep Learning Model, whereby attackers control the predictions of model by implanting a concealed backdoor into the model. Under this scenario, the backdoored model will appear to make normal predictions on clean images, but will exhibit abnormal behaviors when the trigger is presented. Many existing backdoor attacks utilize a fixed pattern as the trigger, which can be easily detected by defense methods or even humans. Furthermore, existing backdoor attack methods are rarely targeted specifically at the Vision Transformer (ViT) model. Therefore, in this paper, we propose a novel natural backdoor attack method. We exploit natural phenomena to carry out a backdoor attack called the fog backdoor attack, which can utilize fog in the natural world as a trigger to be seamlessly integrated into clean images without being perceived by humans. The generated fog will diffuse over the image, creating a natural-looking effect. In contrast to the fixed and limited triggers produced by other methods, our triggers are more natural and imperceptible. Experimental results demonstrate the effectiveness and robustness of the proposed backdoor attack on different models. Specifically, the attack success rate of the proposed backdoor attack is 98.85% on VGG-16 model, 99.44% on ResNet-18 model and 9S.56% on ViT model, respectively. Furthermore, the proposed attack does not compromise the clean accuracy of the model.","PeriodicalId":189631,"journal":{"name":"2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126883899","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

Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling 基于动态采样的深度层次量化压缩算法

2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) Pub Date : 2022-12-30 DOI: 10.1109/ICECAI58670.2023.10176920

W. Jiang, Gang Liu, Xiaofeng Chen, Yi Zhou

引用次数: 0