2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)最新文献_第9页

Disaster Remote Sensing Image Semantic Segmentation model with boundary constraints based on SegNeXt 基于SegNeXt的灾害遥感图像边界约束语义分割模型

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105751

Z. Wang

引用次数: 0

Spectral Feature Selection Via Low Rank Decomposition and Local Preservation 基于低阶分解和局部保存的光谱特征选择

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105729

Luxi Jiang, Xiuhong Chen

{"title":"Spectral Feature Selection Via Low Rank Decomposition and Local Preservation","authors":"Luxi Jiang, Xiuhong Chen","doi":"10.1109/NNICE58320.2023.10105729","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105729","url":null,"abstract":"Feature selection is an important step in data mining and pattern recognition tasks. In unsupervised cases, feature selection becomes more difficult due to the lack of labels in the samples. Therefore, this paper proposes a spectral feature selection (JLRDLP) algorithm that combines low rank decomposition and local preservation. First, the model predicts pseudo-labels using spectral clustering, which jointly learns the cluster labels and feature selection matrix, enabling the algorithm to select more discriminative features. In order to realize the selection of data features, the feature selection matrix is guaranteed to be sparse by $mathbf{L}_{2,1}$ -norm minimization constraint; the projection matrix is decomposed into the product of two low-rank matrices to reveal the global correlation of data features; The idea is to preserve the local geometry of the data when transforming the original data into a low-dimensional space. Finally, the experimental results on multiple real datasets show that the above has better robustness, thus improving the effect of the classification.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115715925","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

Global optimization using a combination of differential evolution and modified Powell method 采用差分进化与改进Powell方法相结合的全局优化方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105732

Zhiping Wang, Fan Zhang, Dongcai Liu, Xiaoting Chen, Jing Yin

引用次数: 0

Computation Offloading and Task Scheduling Based on Improved Integer Particle Swarm Optimization in Fog Computing 基于改进整数粒子群优化的雾计算卸载与任务调度

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105675

Jianjie He, Wenle Bai

引用次数: 0

Mobile Robot Path Planning Based on Improved Ant Colony Algorithm 基于改进蚁群算法的移动机器人路径规划

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105742

Lin Lu, Xinxin Jiang

引用次数: 0

Defect Detection of Photovoltaic Panels Based on Deep Learning 基于深度学习的光伏板缺陷检测

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105789

Haoran Lu, Xuyu Huang, Haoyu Shi, HuaiYu He

引用次数: 0

An intermittent sampling and forwarding interference suppression method based on intra-pulse frequency-time-delay agile waveform 一种基于脉冲内频率时延敏捷波形的间歇采样转发干扰抑制方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105721

Chuang Niu, Qiang Lin, Y. Ma, Min Duan, Heng Zhang

{"title":"An intermittent sampling and forwarding interference suppression method based on intra-pulse frequency-time-delay agile waveform","authors":"Chuang Niu, Qiang Lin, Y. Ma, Min Duan, Heng Zhang","doi":"10.1109/NNICE58320.2023.10105721","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105721","url":null,"abstract":"Intermittent sampling repeater jamming can rapidly and accurately sample and forward radar signals, and make use of the matching filtering characteristics of pulse pressure radar to form a false target group, which seriously affects the detection and tracking of the performance of radar targets. To improve the interference suppression effect under the condition of a high dry-signal ratio, an anti-intermittent sampling and forwarding interference method based on an iterative threshold segmentation algorithm was proposed based on the frequency-time-delay flexible waveform within the pulse. Firstly, the interfered and uninterfered echo signal segments are determined based on the iterative threshold algorithm, and the target position is determined. Then according to the location of the target and the random time delay information judge whether the interference and the target overlap in the time domain. Finally, according to the overlapping condition, the intermittent sampling and forwarding interference are suppressed by combining subpulse filtering and time domain filtering. The simulation results show that the proposed method has good anti-intermittent sampling and forwarding jamming performance under different SNR, JSR, and asynchronous sampling conditions.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117234307","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 New Approach in Discrete Event System by Deep Monte Carlo Tree Search 一种基于深度蒙特卡罗树搜索的离散事件系统新方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105686

Tianxiang Ou, Jianwen Cao, Yanan Lu, Yu-Peng Wang, Xuesong Wu

{"title":"A New Approach in Discrete Event System by Deep Monte Carlo Tree Search","authors":"Tianxiang Ou, Jianwen Cao, Yanan Lu, Yu-Peng Wang, Xuesong Wu","doi":"10.1109/NNICE58320.2023.10105686","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105686","url":null,"abstract":"The decision-making problem is one of core issues in discrete event system, which is often used to describe adversarial complex environment. Aiming at the problem that there exists huge space in this kind of environment, we use Monte Carlo Tree Search (MCTS) as our main search algorithm. One of the key challenges is that, during simulation, it is difficult to accurately predict opponent agents' actions. To deal with this challenge, we propose a deep neural network based on Long Short-Term Memory Network (LSTM), which is trained to predict most possible actions from opponent agents, the prediction is used to guide simulation. We test the performance of our method in the field of autonomous driving (AD), experiments are carried out on the simulation platform CARLA. We design a route containing several dangerous events. Results show that, if the prediction is accurate enough, algorithm using MCTS and deep learning outperforms the one using MCTS only, the former has a higher success rate in avoiding collisions, meanwhile it has a higher average speed.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130442260","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

Underwater Image Enhancement Method Based on CGAN and Parallel Attention Mechanism 基于CGAN和并行注意机制的水下图像增强方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105760

Chi Ma, Le Yang, Hui Hu, Yuenai Chen, Anxu Bu

引用次数: 0

Highly overlapping strawberry leaf detection based on YOLOv5s-MBLS deep learning method 基于YOLOv5s-MBLS深度学习方法的草莓叶片高度重叠检测

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105782

T. Hu, Jun Zhang

{"title":"Highly overlapping strawberry leaf detection based on YOLOv5s-MBLS deep learning method","authors":"T. Hu, Jun Zhang","doi":"10.1109/NNICE58320.2023.10105782","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105782","url":null,"abstract":"In response to the existing object detection algorithms are applied to complex strawberry planting scenes with poor detection accuracy, slow speed and difficult deployment, this paper proposes a lightweight YOLOv5s-MBLS detection algorithm. First of all, replace the CBS module in the YOLOv5 backbone network with the MBL module. The multi-scale convolution kernel of the MBL module can enhance the feature extraction ability of the backbone network while reducing the amounts of parameters and model size. Secondly, SIoU loss function is used to improve model accuracy and model detection speed. Finally, compared with the current popular target detection algorithm, the experimental results show that the the mean average precision (mAP) of YOLOv5s-MBLS algorithm is 1.6% higher than the original algorithm, the model size is reduced by 21.9%, and the average detection speed of each image is only 5.19 ms. Even compared with the latest YOLOv7, the mAP of YOLOv5s-MBLS is also improved by 0.4%, and other indicators are also better than YOLOv7, which proves the effectiveness of the algorithm.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134166341","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