检索结果-内蒙古大学图书馆

Data Science and Information Technology (DSIT), International Conference on

作者： Boya Feng Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350384093

ISBN: (纸本)9798350384109

Community detection is a research focus in the field of complex networks and has wide applications in various domains. However, traditional label propagation algorithms and modularity maximization algorithms often fail to achieve optimal results in many community detection tasks. By observing the characteristics of real-world social networks, this paper proposes a label propagation algorithm based on 2-hop neighbor and weighted path (LPANW) for community detection. The proposed algorithm is compared with three other algorithms on both synthetic networks and real-world datasets, demonstrating better NMI index and robustness.

关键词： Social networking (online) Heuristic algorithms Complex networks Data science Robustness Iterative algorithms Indexes Time complexity Information technology detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Fatigue detection Scheme in Complex Environments Based on rPPG and Dynamic Convolution

Fatigue Detection Scheme in Complex Environments Based on rP...

引用

Artificial Intelligence and Electromechanical Automation (AIEA), International Conference on

作者： Haoming Deng Yubin Chen Qingqing Wu Yue Pan School of Software Nanchang Hangkong University Nanchang China

ISBN: (数字)9798350366174

ISBN: (纸本)9798350366181

Workers who succumb to fatigue not only experience a decline in productivity but are also at an increased risk of accidents. In order to more effectively detect fatigue states within intricate work settings, a novel fatigue detection approach grounded in rPPG technology has been introduced. This approach involves the extraction of rPPG signals from facial videos, followed by the reconstruction of the raw signals through empirical mode decomposition, and subsequently their conversion into two-dimensional time-frequency signals via wavelet transform. Subsequently, a TVCNN-att model is constructed by integrating dynamic convolution techniques and attention mechanisms. The experimental outcomes indicate that the proposed method has yielded satisfactory performance across a range of evaluative metrics.

关键词： Productivity Measurement Time-frequency analysis Continuous wavelet transforms Empirical mode decomposition Convolution Heuristic algorithms Fatigue detection algorithms Videos

来源：评论

学校读者我要写书评

暂无评论

Overhead Power Line detection Based on Curriculum Learning Strategy

Overhead Power Line Detection Based on Curriculum Learning S...

引用

Data Science and Information Technology (DSIT), International Conference on

作者： Zhang Gefei Chen Quan Liu Bingheng Ma Hao Zhang Yihan Cui Zanchen Yang Fan Tong Ying School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing Institute of Technology Nanjing China School of Electrical Power Engineering School of Shen Guorong Nanjing Institute of Technology Nanjing China

ISBN: (数字)9798350384093

ISBN: (纸本)9798350384109

Drone inspection of overhead power lines is a crucial aspect of ensuring electrical safety. Due to the elongated shape of overhead power lines and the complex inspection backgrounds, commonly used detection networks struggle to learn the unique features of these targets. To achieve high-precision detection of overhead power lines, a detection method based on a curriculum learning strategy is proposed. First, multiple target bounding boxes are annotated for individual overhead power lines in aerial images. Next, simulating the human learning process of starting with easier tasks and progressing to more difficult ones, the wavelet-entropy algorithm is used to divide the dataset into simple and complex subsets, allowing the YOLOv5 object detection network to first learn from the simple data and then from the complex data. Finally, a false detection box removal algorithm based on directional gradient statistics is introduced to process the overhead power line images that still contain incorrect identifications after network detection, eliminating the erroneous detection boxes. Experimental results indicate that, under the same network scale, high-precision detection of overhead power lines has been achieved, with an accuracy improvement of 10.8% compared to YOLOv5 based on traditional training strategies, and mAP_0.5 reaching 78.6%. This method effectively detects slender targets like overhead power lines while minimizing background interference, advancing the development of drone-based electrical inspection technology.

关键词： YOLO Training Point cloud compression Accuracy Shape Inspection Real-time systems Reliability detection algorithms Drones

来源：评论

学校读者我要写书评

暂无评论

Ramose RAIM: A Multiple-Failure detection Algorithm Design for Civil Aviation

引用

Chinese Journal of Electronics 2023年第2期19卷 356-359页

作者： Xinyuan Zhang Zhigang Huang Rui Li School of Electronic and Information Engineering Beihang University Beijing China

With the advent of Galileo and Chinese Compass, GNSS navigation technologies will develop rapidly. However, as the number of navigation satellites in view will increase, the fault probability will rise. This paper calculates the multi-fault risk of multi-constellation satellite navigation system in terms of MOPS. It is highlighted that the probability of either one-fault or double-faults is higher than integrity requirement. The paper also describes a snap-shot ramose RAIM technology to protect civil aviation users in multiple-fault case. In this condition, a series of FDE calculation is adopted to separate satellites in sight into several groups. Therefore the problem will transform into several single-fault case, which current RAIM can solve. Simulation results verify that this technique is proper to solve both single-fault and double-fault problem of civil aviation caused by application of multi-constellation GNSS.

关键词： Fault diagnosis Global navigation satellite system Satellites Simulation Transforms detection algorithms Compass

来源：评论

学校读者我要写书评

暂无评论

Strawberry Maturity detection Algorithm Based on Improved YOLOv9

Strawberry Maturity Detection Algorithm Based on Improved YO...

引用

Advances in Electrical Engineering and Computer Applications( AEECA), 2020 IEEE International Conference on

作者： Rong Ye Guoqi Shao Hongrui Zhang Tong Li Quan Gao College of Food Science and Technology Yunnan Agricultural University Kunming China The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province Yunnan Agricultural University Kunming China College of Landscape and Horticulture Yunnan Agricultural University Kunming China College of Big Data Yunnan Agricultural University Kunming China

ISBN: (纸本)9798350355260

Deep learning is a crucial research focus within the realm of artificial intelligence, with its utilization in agriculture becoming more prevalent. Strawberries are one of the most popular fruits, but immature strawberries are difficult to attract consumers. This paper aims to enhance the accuracy of strawberry ripeness detection during the picking process by introducing a strawberry ripeness detection model called YOLOv9-CS. The model integrates Cloformer into the backbone network to improve the fusion effect of texture features among strawberries of the same maturity. Additionally, the inclusion of SeaFormer Block in the neck network enhances the model's ability to perceive target positions, thereby boosting detection accuracy. By utilizing the Focal-EIoU loss function instead of the traditional IoU loss function, the model's robustness and accuracy are further improved. Experimental results on a strawberry dataset demonstrate that the YOLOv9-CS model outperforms the original YOLOv9 model, achieving a 2.47% increase in precision, 4.54% in recall, and 4.16% in mAP, reaching 95.72%, 95.59%, and 96.61% respectively, while maintaining real-time detection capabilities. The proposed model significantly enhances the identification of strawberries at different maturity levels in natural settings, catering to the intelligent and automated requirements of smart agriculture for strawberry picking.

关键词： YOLO Smart agriculture Electrical engineering Accuracy Color Robustness Real-time systems Neck detection algorithms Monitoring

来源：评论

学校读者我要写书评

暂无评论

Lightweight detection Algorithm for Corn Insect Pests Based on Attention Mechanism

Lightweight Detection Algorithm for Corn Insect Pests Based ...

引用

Internet of Things, Automation and Artificial Intelligence (IoTAAI), International Conference on

作者： Haiying Song Yiying Yan Jian Cen Min Xie Zhifeng Li Changhao Guo School of Automation Guangdong Polytechnic Normal University China School of Electricity South China University of Technology China

ISBN: (数字)9798350386974

ISBN: (纸本)9798350386981

The timely and accurate detection of corn pests is of great significance for the prevention and control of corn pest damage. To improve the real-time and precision of corn pest detection, this paper proposes a lightweight YOLOv8s-FS model for corn pest detection. Firstly, the paper introduces an efficient FasterNet network structure into the network architecture, achieving the lightweight of the model. Secondly, a Simple Parameter-Free Attention Module (SimAm) is introduced to build an efficient neck network, which improves the recognition accuracy of the model. Finally, in terms of corn pest detection, compared with the YOLOv8s model, the YOLOv8s-FS model reduces the number of parameters by 25%. The recognition accuracy mAP0.5 is increased by 2%, reaching 89.4%. The YOLOv8s-FS model has the characteristics of being lightweight and high precision, and can accurately identify corn pests.

关键词： Accuracy Attention mechanisms Prevention and mitigation Insects Production Network architecture Real-time systems Neck Internet of Things detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Dual-Channel Input Image Tampering detection for Scientific Papers

Hybrid Dual-Channel Input Image Tampering Detection for Scie...

引用

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Jiayi Shi Haihong E Jianhua Liu Tianyi Hu Xiaodong Qiao Junpeng Ding Jiayu Huang School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Beijing Wanfang Data Co. Ltd. Beijing China

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

With the development of science and technology, the application of digital image processing and artificial intelligence technology is becoming more and more widespread, which makes it easier and more difficult to detect forged academic images, and academic images have become a high incidence of scientific and technological journal paper forgery. To ensure the authenticity of academic images and scientific reproducibility of experiments, we developed a network called MultiScopeNet. It combines RGB and DCT streams, performs multi-resolution fusion at each layer, and can comprehensively analyze spatial and frequency domain features of images. We also created a new dataset based on an existing tamper detection dataset by applying an image complementation model to train and validate our model against academic misconduct of tampering using generatively forged images. MultiScopeNet significantly outperforms existing state-of-the-art models in dealing with image tampering at different resolutions and sizes.

关键词： Training Visualization Frequency-domain analysis Transform coding Transforms Reproducibility of results Discrete cosine transforms detection algorithms Spatial resolution Streams

来源：评论

学校读者我要写书评

暂无评论

Enhancing Traffic Light detection and Classification through Federated Learning

Enhancing Traffic Light Detection and Classification through...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Ioannis V. Vondikakis Ilias E. Panagiotopoulos George J. Dimitrakopoulos Dept. of Informatics and Telematics Harokopio University of Athens (HUA) Athens Greece

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Traffic light detection stands as a pivotal challenge in the realm of connected and automated driving systems and intelligent traffic management. Traffic light detection lies in the real-time and accurate recognition of traffic lights and their states ’go’, ’warning’, ’stop’, ’goLeft’, ’warningLeft’, ’stopLeft’, even under diverse environmental conditions. This paper introduces a synthetic approach for intelligent traffic light detection and classification, namely FL-TLDC, that synergizes federated learning with Fast Region-based Convolutional Neural Networks (Faster R-CNN). The proposed collaborative and decentralised approach allows the collective improvement of traffic light detection algorithms without the need to share sensitive or proprietary data. Simulation results demonstrate that the proposed analysis achieves a high detection performance and provides fast responses.

关键词： Vehicular and wireless technologies Accuracy Federated learning Simulation Collaboration Real-time systems Convolutional neural networks detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Insulator detection Based on Feature-Enhanced Convolution Attention Method

Insulator Detection Based on Feature-Enhanced Convolution At...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Hangfan Dong Jun Feng Yijie Wang Yang Li Yibo Yu Binyu Xiong School of Automation Wuhan University of Technology Wuhan China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

With the purpose of solving the problems of low inspection efficiency and high field inspection danger encountered in current insulator detection, in this paper we propose the Feature-Enhanced Convolution Attention YOLO (F-ECA YOLOv8), an improved YOLOv8 insulator detection algorithm for infrared images. Firstly, the ordinary convolution in C2 is substituted by the Depthwise Separable convolution, improving the target detection accuracy which enhance its adaptive ability and reducing the computational complexity. Next, the Fusion-SE-Coord Attention(F-SCA) module is designed to improve the model's ability to adapt to key features and to capture channel features and spatial features, which is able to fuse global and local information effectively. Finally, WIOU is used to replace the original loss function to further address the issue of the unbalance quality of the sample. Compared to the YOLOv8s,the F-ECA algorithm scored 0.5% and 6.7% higher in mAP@0.5 and mAP@0.5-0.95 separably, indicating that the algorithm can be effectively applied to detect insulators in infrared images in practical scenes.

关键词： YOLO Accuracy Convolution Fuses Energy Internet System integration Inspection Insulators Feature extraction detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Covariance-Based Activity detection Algorithm in Clustered Cell-Free Massive MIMO

Covariance-Based Activity Detection Algorithm in Clustered C...

引用

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

作者： Haowen Ye Ranran Lv Kai Sun Wei Huang School of Electronic Information Engineering Inner Mongolia University Hohhot China

ISBN: (数字)9798350388404

ISBN: (纸本)9798350388411

Massive Machine-Type Communications (mMTC) plays an increasingly important role in future wireless communications, and the use of a large number of low-power devices in conjunction with cell-free massive MIMO networks is a promising enabling technology. In this research, we explore activity detection for Grant-Free Random Access in massive mMTC within a cell-free Massive MIMO network employing distributed antenna arrays. Each active device sends a non-orthogonal pilot sequence to geographically clustered Access Points (APs) using the K-means algorithm. The clustered APs then relay the received signals to the Central Processing Unit (CPU) for collaborative activity detection. Simulation results demonstrate that for extensive coverage areas, the covariance-based activity detection algorithm with K-means clustered APs exhibits reduced complexity and improved activity detection efficiency while maintaining robust performance.

关键词： Wireless communication Simulation Partial transmit sequences Clustering algorithms Massive MIMO Central Processing Unit detection algorithms

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：