检索结果-内蒙古大学图书馆

Trends in Material Science and Inventive Materials (ICTMIM), International Conference on

作者： U.V. Anbazhagu A. Alice Blessie R. Santhana Krishnan G. Yamini J. Relin Francis Raj P. Sundaravadivel Department of Computing Technologies School of Computing College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Government College of Engineering Tirunelveli India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmhadevi India Department of English Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Artificial Intelligence and Machine Learning Saveetha Engineering College Chennai India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Wildfires pose a significant threat to ecosystems, biodiversity, and human settlements, with climate change and deforestation exacerbating the frequency and intensity. Conventional forest fire detection methods, including satellite-based monitoring and ground surveillance, suffer from limitations such as delayed detection, high false alarm rates, and dependency on manual intervention. Existing sensor-based detection systems often lack integration with intelligent decision-making frameworks, leading to inefficient fire prevention strategies. The absence of real-time processing and predictive capabilities further reduces the effectiveness of current methodologies in mitigating wildfire risks. This work presents an IoT-based deep learning approach utilizing Convolutional Neural Networks (CNNs) for real-time forest fire detection and prevention. Data is collected from satellite images, drone feeds, and IoT sensors, including temperature, humidity, gas concentration, and infrared readings. Advanced data preprocessing techniques, including image augmentation, normalization, and feature extraction, enhance the robustness of the model. A CNN-based classification model is implemented to analyze fire patterns and assess risk levels. The system is trained using sensor data and image datasets, ensuring high detection accuracy with minimal false positives. The key features of this methodology include real-time wildfire detection, automated risk assessment, and deployment on IoT edge devices for immediate decision-making. The integration of sensor-driven insights with deep learning improves early detection capabilities while reducing reliance on manual surveillance. Efficient data handling and cloud-based alert mechanisms enable proactive measures against fire outbreaks. The proposed system enhances wildfire monitoring by ensuring fast response times, improved accuracy, and scalable deployment in fire-prone regions.

关键词： Deep learning Wildfires Accuracy Prevention and mitigation Surveillance Decision making Manuals Real-time systems Satellite images Time factors Climate change Fires detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Low False-Alarm Active Sonar detection under Strong Reverberation

Low False-Alarm Active Sonar Detection under Strong Reverber...

引用

IEEE/OES China Ocean Acoustics (COA)

作者： Li Sibo Guo Rui Zhang Dianlun Li Yujuan Hou Xiaoqian Wang Shengfeng Science and Technology on Underwater Acoustic Laboratory/ Technology R&D Center Harbin Engineering University / Haiying Enterprise Group Co. Ltd Harbin/Wuxi China Technology R&D Center Haiying Enterprise Group Co. Ltd Wuxi China Science and Technology on Underwater Acoustic Laboratory Harbin Engineering University Harbin China

ISBN: (数字)9798350340297

ISBN: (纸本)9798350340303

In active low-frequency and high-power sonar systems, target detection must overcome strong reverberation. Active sonar reverberation interference strongly fluctuates with distance and exhibits significant temporal and spatial variations. Active sonar reverberation is a typical nonstationary background. Complex changes in reverberation directly affect the target detection performance of active sonar systems. The major difficulty associated with current detection algorithms lies in autonomous detection, particularly in terms of the adaptability of detection algorithms to complex background interference. Accurately performing dynamic background estimation, suppressing interference, controlling false alarms, and highlighting weak targets are the focus of object detection. This paper proposes an active sonar target detection method driven by a combination of data and models. The proposed method can achieve target detection under strong reverberation interference with low sidelobe false alarms and high robustness.

关键词： Target tracking Target recognition Sonar Object detection Interference Robustness Data models Reverberation detection algorithms Sonar detection

来源：评论

学校读者我要写书评

暂无评论

Constellation-Based detection for Frequency Spread OFDM Underlay

Constellation-Based Detection for Frequency Spread OFDM Unde...

引用

MILCOM, Military Communications Conference

作者： Xiang Cheng Daniel J. Jakubisin Hanchao Yang Kumar Sai Bondada Nishith Tripathi Yaling Yang Gustave Anderson Jeffrey H. Reed Bradley Department of ECE Virginia Tech Wireless@VT Blacksburg VA Virginia Tech National Security Institute Blacksburg VA Lockheed Martin Cherry Hill NJ

ISBN: (数字)9798350374230

ISBN: (纸本)9798350374247

In this paper, we present a novel constellation-based detection algorithm designed to identify frequency spread OFDM underlay signals in dynamic and complex wireless environments. Our algorithm leverages the distinct patterns introduced by underlay signals in the constellation diagram to achieve effective detection. We conduct comprehensive simulations to evaluate the detection performance. Additionally, we compare the proposed algorithm with the traditional energy detection method. Our simulation results demonstrate that the constellation-based algorithm provides superior robustness and accuracy, particularly in scenarios with high Doppler shifts and varying transmission power levels. This work highlights the algorithm’s potential for enhancing underlay signal detection in modern wireless communication systems.

关键词： Wireless communication Doppler shift Constellation diagram Accuracy OFDM Heuristic algorithms Simulation detection algorithms Signal detection Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Modified CA-CFAR Multi-human detection Algorithm in Complex Environment Using Radar

A Modified CA-CFAR Multi-human Detection Algorithm in Comple...

引用

Electronic Engineering and Information Systems (EEISS), International Conference on

作者： Zhihuan Liang Yanghao Jin Buge Liang Jinjun Mo School of Information and Communication Guilin University of Electronic Technology Guilin China Academy of Advanced Interdisciplinary Research Xidian University Xi'an Shaanxi School of Automation Central South University Changsha China

ISBN: (数字)9798350351033

ISBN: (纸本)9798350351040

With a rather strong environment clutter and multi-target interference, while indoor monitoring using UWB radar in complex scenarios, the current CA-CFAR algorithm would inevitably introduce the variance peaks leading to the false detection results in multi-target detection. This paper proposed a Modified CA-CFAR based on the Sliding Window DC Removal and Adaptive Threshold method, using Sliding Window DC Removal to eliminate the static environment clutter to avoid the previous variance peaks involved by replacing the MTI and achieving the Adaptive Threshold through echo statistic estimation to reduce the false detection results. The effectiveness of the proposed algorithm has been verified through comparative analysis based on radar-measured data.

关键词： Accuracy Radar detection Estimation Object detection Clutter detection algorithms Ultra wideband radar

来源：评论

学校读者我要写书评

暂无评论

A Novel Lightweight Disease detection Algorithm Used in Ground-Penetrating-Radar

A Novel Lightweight Disease Detection Algorithm Used in Grou...

引用

Annual Conference of Industrial Electronics Society

作者： Huanming Gan Hongjin Hu Guang-Zhong Cao Yu Lei Yanliang Du Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China National Key Laboratory of Green and Long-Life Road Engineering in Extreme Environment (Shenzhen) College of Civil and Transportation Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

To solve the problems of excessive parameters in deep learning models of Ground Penetrating Radar (GPR) disease detection, this paper proposes a lightweight disease detection algorithm based on YOLOv8. A lightweight model is obtained by replacing its backbone network with the GhostHGNetV2 network. The SimAM attention mechanism module is used to improve the ability to perceive different levels of feature representation. Additionally, the WIOU is used as the loss function to improve the convergence and accuracy of the algorithm detection performance. Experimental results demonstrate that the proposed algorithm reduces the parameters of original networks by 25.3%, model size by 28.8%, and computational complexity (GFLOPs) by 20.3%. The effectiveness of the proposed lightweight disease detection algorithm is verified.

关键词： Industrial electronics Accuracy Attention mechanisms Ground penetrating radar Object detection Feature extraction detection algorithms Robots Diseases Convergence

来源：评论

学校读者我要写书评

暂无评论

Uncovering Local Hierarchical Overlapping Communities at Scale

引用

IEEE TRANSACTIONS ON BIG DATA 2022年第2期8卷 432-445页

作者： Liakos, Panagiotis Ntoulas, Alexandros Delis, Alex Univ Athens Athens 15703 Greece New York Univ Abu Dhabi Abu Dhabi U Arab Emirates

Real-life systems involving interacting objects are typically modeled as graphs and can often grow very large in size. Revealing the community structure of such systems is crucial in helping us better understand their complex nature. However, the ever-increasing size of real-world graphs and our evolving perception of what a community is, make the task of community detection very challenging. A critical relevant challenge is the discovery of the possibly overlapping communities of a given node in a billion-node graph. This problem is very common in modern large social networks like Facebook and LinkedIn. In this work, we propose a scalable local community detection approach to efficiently unfold the communities of individual target nodes in a given network. Our goal is to reveal the clusters formed around nodes (e.g., users) by leveraging the relations within all different contexts these nodes participate in. Our approach, termed Local Dispersion-aware Link Communities or LDLC, considers the similarity of pairs of links in the graph as well as the extent of their participation in multiple contexts. Then, we determine the order in which we should group the pairs of links so that we form meaningful hierarchical communities. We are not affected by constraints existing in previous techniques such as the need for several seed nodes or the need to collapse multiple overlapping communities to a single community. Our experimental evaluation using ground-truth communities for a wide range of large real-world networks shows that our LDLC algorithm significantly outperforms state-of-the-art methods on both accuracy and efficiency. Moreover, we show that LDLC uncovers very effectively the hierarchical structure of overlapping communities by producing detailed dendrograms.

关键词： Dispersion Big Data Task analysis detection algorithms Facebook Complex systems Community detection complex networks hierarchical communities dispersion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Malware Family detection

Deep Learning Models for Malware Family Detection

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Jenna Snead Krishnendu Ghosh Department of Computer Science College of Charleston South Carolina USA

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

Malware attacks have been rising, and the response for detection and mitigation have fallen short to counter the threats. The advances in artificial intelligence have not yielded a comprehensive solution in early detection of mal ware and its variants, making this a critical gap. Our work leverages on the biology-inspired analysis of malware trace sequences and clustering based on trace similarity computation. The malware traces extracted from the community detection algorithms are assumed to represent malware families precisely. The deep learning framework uses the most prototypical features from the extracted traces for prediction of mal ware families. In this work, deep learning models in the form of artificial neural networks (ANNs) are evaluated and experimental results are presented. The results elucidate the deep learning framework for malware family detection across different variations of detection and training splits.

关键词： Deep learning Training Prevention and mitigation Digital forensics Artificial neural networks Feature extraction Malware Phylogeny Security detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Recognition Algorithm Based on Improved Real-Time detection Transformer

Traffic Sign Recognition Algorithm Based on Improved Real-Ti...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International Conference on

作者： Rui Zhang Minhan Zhang School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

Accurate detection of traffic signs is of great significance in the fields of road safety, intelligent transportation, and autonomous driving. This paper proposes the MY-DETR traffic sign detection method, which incorporates three innovative modules: EDB-SOP, AIFI-HiLo, and Inner-IoU. The EDB-SOP enhances robustness to small targets, occlusion, and complex backgrounds through multi-branch feature extraction and spatial optimization pooling technology. The AIFI-HiLo module integrates low-frequency and high-frequency attention mechanisms, optimizing the processing of multi-scale and multi-frequency features, and improving detection accuracy and robustness. The Inner-IoU loss function focuses on the inner overlapping area of the bounding box, improving the accuracy of traditional IoU in cases of low overlap. Experimental results show that MY-DETR significantly outperforms some mainstream algorithms on multiple traffic sign datasets, especially in terms of m $A$ P50 and mAP50-95, providing a more efficient and accurate traffic sign detection solution for complex scenarios.

关键词： Accuracy Transportation Focusing Feature extraction Transformers Robustness Real-time systems Road safety detection algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

FD-YOLOv8:An Improved Fire detection Model Base on YOLOv8n

FD-YOLOv8:An Improved Fire Detection Model Base on YOLOv8n

引用

Advanced algorithms and Control Engineering (ICAACE), International Conference on

作者： Longxiang Li Zhe Liu Yangbo Ruan Beimin Chen School of Artificial Intelligence Jianghan University WuHan China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Fire detection technology plays a crucial role in the field of fire safety. However, traditional fire alarms driven by smoke detectors often fail to report fires in a timely and effective manner. To cope with these challenges, We proposed an improved fire detection algorithm FD-YOLOv8 based on YOLOv8n. In this study, we introduced the OCA positive traffic attention mechanism to optimize the Bottleneck layer, enhancing the model's accuracy in object detection. Additionally, we integrated GSConv, an efficient lightweight convolution, to design an improved C2f-OGBlock module, further enhancing the model's detection capability while reducing parameters and computational costs. Furthermore, we incorporated a highly efficient feature enhancement algorithm, HIFA, into the model, significantly improving its feature extraction capabilities. We compared the improved YOLOv8 model with existing models. Experimental results demonstrate that our improved model achieves superior detection performance, with mAP@50 increasing by 3.2% and mAP@50:90 improving by 1.2% compared to the original model.

关键词： Attention mechanisms Accuracy Computational modeling Object detection Visual systems Feature extraction Scattering parameters detection algorithms Smoke detectors Fire safety

来源：评论

学校读者我要写书评

暂无评论

Research on Road Disease detection Algorithm Based on Improved YOLOv5s

Research on Road Disease Detection Algorithm Based on Improv...

引用

Electronics and Communication, Network and Computer Technology (ECNCT), International Conference on

作者： Xili Yang Hu Sheng Na Geng Wenqiang Li Unit: School of Computer and Communication Engineering Dalian Jiaotong University Dalian Liaoning China

ISBN: (数字)9798350366143

ISBN: (纸本)9798350366150

Addressing the issues of low detection efficiency and high subjectivity in traditional pavement disease detection methods, this study leverages deep learning algorithms in object detection to enhance detection accuracy while maintaining real-time responsiveness. We introduce a pavement disease detection algorithm, YOLOv5s-MBD, which enhances YOLOv5s. Initially, we replace the original CIoU Loss with MPDIoU Loss as the regression loss function, maximizing the DIoU value to improve the network's learning of the position and shape of bounding boxes. Subsequently, we integrate a BiFPN weighted bidirectional pyramid structure, enabling more comprehensive and efficient information propagation across multiple scales, thereby enhancing detection performance at different scales. Lastly, we introduce a decoupled head into the detection head of YOLOv5s to better utilize semantic information between low-level and high-level features, thus enhancing detection accuracy and network convergence speed. The results of the experiment demonstrate that the YOLOv5s-MBD algorithm has improved the mAP @ 0.5 for disease recognition by 5.6%, and 1.6% respectively compared to YOLOv3, YOLOv4, YOLOv5s, and YOLOv8 on the GRDDC2020 dataset, and the recognition accuracy and recall rate have also been improved to varying degrees.

关键词： YOLO Accuracy Head Shape Roads Semantics Real-time systems Neck detection algorithms Diseases

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：