检索结果-内蒙古大学图书馆

4th International Conference on Communication technology and Information technology, ICCTIT 2024

作者： Bao, Chunhao He, Pengfei Huang, Yong Xu, Lei Yantai University School of Physics and Electronic Information Yantai China Yantai University Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai China Naval Aviation University Yantai China Huaneng Shandong Power generation Co. LTD. Yantai Power Plant Yantai China

ISBN: (纸本)9798331528973

In radar target detection, large targets often mask small targets, and the traditional constant false alarm (CFAR) detection method is difficult to set a suitable threshold and cannot cope with the detection of this type of target well. Aiming at this kind of problem, a residual LSTM detection method based on global channel attention mechanism (Global Channel Attention Mechanism- Long Short Term Memory, GCAMLSTM) is proposed. This method processes the radar echo data, establishes the time-order relationship of the radar signals through the sliding window method, and proposes a new Global Channel Attention Mechanism module according to the characteristics of the time-order signals, so as to extract the target echo features more accurately. The experimental results show that the detection performance of the proposed method is 6.8% higher than that of the traditional CFAR algorithm. It has strong robustness in the above scenario and can achieve effective detection of radar targets. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Dual Aggregation Convolution for Image Super-Resolution

Dual Aggregation Convolution for Image Super-Resolution

引用

Cloud Computing, Big data applications and Software Engineering (CBASE), International Conference on

作者： Zhongxun Wang Zheng Xie School of Physics and Electronic Information Yantai University Shandong China Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University Shandong China

ISBN: (数字)9798331506582

ISBN: (纸本)9798331506599

In recent years, numerous image super-resolution (SR) methods have been introduced, achieving significant advancements. However, many existing methods employ complex, task-specific operations that, while effective, introduce substantial computational overhead when directly stacked, thereby hampering their practical utility. In response, we introduce DACNet, an efficient SR model that innovatively integrates spatial and channel information through a collaborative framework. Specifically, we alternately apply the Aggregation Spatial Convolution Module (ASCM) and the Aggregation Channel Convolution Module (ACCM) to dynamically extract and integrate multi-level features. Furthermore, we employ a Convolution Compensation Module (CCM) to mitigate local pixel forgetting. Our comprehensive experiments demonstrate that DACNet not only achieves superior performance but also maintains minimal computational demands, making it highly effective in resource-constrained environments.

关键词： Cloud computing Convolution Computational modeling Superresolution Collaboration Benchmark testing Feature extraction Big data applications Image reconstruction Software engineering

来源：评论

学校读者我要写书评

暂无评论

Path Tracking Controller Based on Active Front Wheel Steering and Torque Dynamic Allocation

SSRN

引用

SSRN 2024年

作者： He, Pengfei Li, Chenglin Wu, Shie Jia, Juncheng School of Physics and Electronic Information Yantai University Shandong Yantai264005 China Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University Shandong Yantai264005 China

Efficient and stable trajectory tracking control is fundamental for the continuous operation of autonomous vehicles. This paper introduces a path tracking controller based on active front-wheel steering and torque dynamic allocation integrated with model predictive control. By imposing yaw stability constraints on the vehicle and soft constraints on the side slip angle of the tire, it is ensured that the steering angle of the front wheels does not exceed its optimal limit, which could otherwise compromise the vehicle’s ability to follow the intended path. Precise torque allocation control is utilized to prevent tire slip when lateral forces approach their limits. Simulation results under double lane-change maneuvers conducted in Simulink/CarSim demonstrate that the constrained controller significantly enhances lateral tracking, lateral velocity, yaw rate, and front wheel steering precision, thereby ensuring stable vehicle handling during high-speed autonomous driving. © 2024, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Passive radar multi-target detection experimental study at sea

Passive radar multi-target detection experimental study at s...

引用

Computer and Information Processing technology (ISCIPT), International Symposium on

作者： Zaiyuan Wu Jie Song Zhongxun Wang Qian Wang Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology Yantai University School of Physics and Electronic Information Yantai University Yantai China Naval Aviation University Yantai China

ISBN: (数字)9798350388404

ISBN: (纸本)9798350388411

The non-cooperative dual-base radar provides superior performance in terms of safety and robustness of target detection. This paper presents a series of experimental maritime target detections using a passive radar system and the collection of a large amount of data. The first is an introduction to the principle of passive radar and the key technologies involved, the next step is to describe the experimental scenario, finally, the experimental data were used for the plotting of a radar system diagram and the analysis of the resultant graphs. Experimental results showed that the system could succeed in detecting targets at sea.

关键词： Passive radar Radar cross-sections Radar detection Signal processing algorithms Object detection Radar signal processing Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Weak target detection algorithm for passive radar based on deep learning

Weak target detection algorithm for passive radar based on d...

引用

Computer applications and Information technology (ISCAIT), International Symposium on

作者： Qian Wang Zhongxun Wang Jie Song Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University Yantai China School of Physics and Electronic Information Yantai University Yantai China Naval Aviation University Yantai China

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

Aiming at the problem of the degradation of the detection performance of weak targets in the case of low signal-to-noise ratio, a weak target detection network model is proposed. This model converts one-dimensional radar data into two-dimensional image data and processes the images. A weak target detection network model for passive bistatic radar is put forward. The dataset is made by using the PPI (Plan Position Indicator) diagram. Based on the YOLOv8 basic framework, first of all, an attention mechanism module, namely the EffectiveSEModule, is added, which reduces the computational complexity and information loss while maintaining the performance of the model. Secondly, the neck network is replaced with the HSPAN-DySample network. With the help of a series of mechanisms such as its dynamic sampling, feature fusion, and detail enhancement, it can improve the detection ability for small targets. Then, the WIoU dynamic non-monotonic focusing mechanism is used to focus on anchor boxes of ordinary quality, thus improving the overall performance of the detector. Finally, an auxiliary detection head is added, which can better propagate the gradient, accelerate the training process, and prevent the problem of gradient vanishing. In order to verify the effectiveness of the algorithm, ablation experiments and comparative experiments are carried out. The experimental results show that the improved algorithm significantly reduces the situations of false detections and missed detections. The precision is increased to $90.5 \%$, an increase of $4.7 \%$, and the detection ability for weak targets is enhanced.

关键词： Deep learning Training Passive radar Computational modeling Focusing Object detection Bistatic radar Feature extraction Neck Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Cotton Field Pest Recognition Based on Gradient Descent Mechanism and Large Convolutional Kernel Network

Cotton Field Pest Recognition Based on Gradient Descent Mech...

引用

Power Electronics, Computer applications (ICPECA), IEEE International Conference on

作者： Qianlong Liu Pengfei He Zhimin Zhao Chenglin Li School of Physics and Electronic Information Yantai University Yantai China Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology School of Physics and Electronic Information Yantai University Yantai China

To assist farmers in efficiently managing cotton fields in industrial areas, we propose a pest image recognition solution. This solution is based on the GD Mechanism (Gather and Disturb Mechanism) and a large convolutional kernel network. It incorporates the FAM (Feature Alignment Module), IFM (Information Fusion Module), and Inject (Information Injection Module) to align, fuse, and inject features at different hierarchical levels. This enhances the feature fusion capability of the network structure. To boost the model's sensitivity to enlarge the receptive field, we employ the RepLKNet with a large convolutional kernel as an enhancement to the existing small convolutional kernel in the original CNN architecture. Experimental results indicate a significant improvement in recognition accuracy after modifying the model. The optimized model's average precision increases by 2.8%, reaching 96.2%. This provides strong support for preventing and identifying cotton pests at different stages.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experiment Study of Passive Radar Maritime Target Detection Based on Staring Radar

Experiment Study of Passive Radar Maritime Target Detection ...

引用

Computer Science, Electronic Information Engineering and Intelligent Control technology (CEI), IEEE International Conference on

作者： Zaiyuan Wu Jie Song Zhongxun Wang Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University. Yantai University School of Physics and Electronic Information Yantai China Naval Aviation University Yantai China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

This paper introduces the characteristics of passive radar system and staring radar as well as briefly introduces the data processing method, uses gaze radar as a non-cooperative radiation source, carries out a series of maritime target detection experiments, and verifies the experimental results with AIS system. The results show that the passive radar system can accurately get the target speed, distance and other information.

关键词： Passive radar Radar cross-sections Surveillance Radar detection Sea measurements Object detection Interference Sensor systems Marine vehicles Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Passive Radar Weak Target Detection Algorithm Fused with Feature Pyramid Network

Passive Radar Weak Target Detection Algorithm Fused with Fea...

引用

Computer Science, Electronic Information Engineering and Intelligent Control technology (CEI), IEEE International Conference on

作者： Qian Wang Zhongxun Wang Jie Song Zaiyuan Wu Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University Yantai China School of Physics and Electronic Information Yantai University Yantai China Naval Aviation University Yantai China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

Target detection is an important application of passive radar, but due to the non-cooperative characteristics of the radiation source, the target signal-to-noise ratio is too low, and the existing detection algorithms are difficult to effectively detect the target from the echo with low signal-to-noise ratio, and the problem of false detection occurs, which poses a challenge to the weak target detection of passive radar. In order to solve the above problems, the data collected by field passive radar experiments were used to make datasets, and the weak target detection experiments were carried out based on deep learning, and a passive radar weak target detection algorithm based on feature pyramid network was proposed. Firstly, a two-layer routing dynamic sparse attention mechanism is added to provide more flexible computational allocation and content awareness, and secondly, feature fusion is carried out to replace the neck network with a BiFPN network, so that the neural network can better understand and interpret multi-scale information. then, auxiliary detection heads were added to help propagate gradients better, speed up training and prevent gradient disappearance problems. Finally, using the WIoU dynamic non-monotonic focusing mechanism, it is possible to focus on the anchor frame of normal quality and improve the overall performance of the detector. In order to verify the effectiveness of the network, ablation experiments and comparative experiments were carried out. Ablation experiments show that the detection performance is improved after each improvement, the recall and average precision are increased by 3.4% and 4% respectively, and the precision is increased to 89.6% and 3.8% respectively. Experimental results show that the improved algorithm significantly reduces false detection and missed detection in passive radar weak target detection.

关键词： Training Passive radar Heuristic algorithms Neural networks Object detection Feature extraction Dynamic scheduling Routing Resource management Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Improved Gerstner Function Wave Model Based on Elfouhaily Spectrum

Improved Gerstner Function Wave Model Based on Elfouhaily Sp...

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Jianlong Wang Zhongxun Wang Yujie Chen Ketao Ma Laboratory of Smart grid Advanced Technology School of Physics and Electronic Information Yantai University and Shandong Data Open Innovation Application Yantai University Yantai China School of Intelligent Manufacturing Qingdao Huanghai University Qingdao China

ISBN: (数字)9798350354010

ISBN: (纸本)9798350354027

Aiming at the limitations of a single wave simulation approach across various marine environments, and with the aim of enhancing the reliability and realism of wave 3D modelling in different scenarios, this paper proposes a wave formation approach ground on the combination of the Gerstner function and the Elfouhaily wave spectra, which achieves the modelling of waves with different wave strengths, and feasible application of the model to further the reliability and safety of sea surface modelling is also outlined. Firstly, the improved Gerstner's functional equation system is selected as the wave construction model, and it is extended into a three-dimensional form to simulate the details and realism of the waves; secondly, in order to control the wave model and achieve the stochasticity and realism of the waves, the Elfouhaily wave spectra are used to gain the parameters for the control of the wave model, and then to establish the reliable wave simulation model; Finally, wave simulations and model comparisons are carried out with respect to the spectral parameters of multiple wave spectra, and issues related to the safety of ocean engineering applications and offshore activities based on the model are briefly presented. The experimental results show that the proposed method is reliable and practical, with high realism, and is applicable to a variety of wave scenarios, which is of great significance in improving the prognosis and safety assessment of the marine environment.

关键词： Solid modeling Sea surface Three-dimensional displays Surface waves Computational modeling Mathematical models Real-time systems Safety Reliability Prognostics and health management

来源：评论

学校读者我要写书评

暂无评论

Residual LSTM Radar Target Detection Method Based on Global Channel Attention Mechanism

Residual LSTM Radar Target Detection Method Based on Global ...

引用

Communication technology and Information technology (ICCTIT), International Conference on

作者： Chunhao Bao Pengfei He Yong Huang Lei Xu School of Physics and Electronic Information Yantai University Yantai China Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology Yantai University Yantai China Naval Aviation University Yantai China Huaneng Shandong Power generation Co. LTD. Yantai power plant Yantai China

ISBN: (数字)9798331528973

ISBN: (纸本)9798331528980

In radar target detection, large targets often mask small targets, and the traditional constant false alarm (CFAR) detection method is difficult to set a suitable threshold and cannot cope with the detection of this type of target well. Aiming at this kind of problem, a residual LSTM detection method based on global channel attention mechanism (Global Channel Attention Mechanism- Long Short Term Memory, GCAMLSTM) is proposed. This method processes the radar echo data, establishes the time-order relationship of the radar signals through the sliding window method, and proposes a new Global Channel Attention Mechanism module according to the characteristics of the time-order signals, so as to extract the target echo features more accurately. The experimental results show that the detection performance of the proposed method is $\mathbf{6. 8 \%}$ higher than that of the traditional CFAR algorithm. It has strong robustness in the above scenario and can achieve effective detection of radar targets.

关键词： Attention mechanisms Time series analysis Radar detection Radar Object detection Feature extraction Radar signal processing Robustness Long short term memory Monitoring

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：