检索结果-内蒙古大学图书馆

YOLO-LFD: A Lightweight and Fast Model for Forest Fire Detection

computers, Materials & Continua 2025年第2期82卷 3399-3417页

作者： Honglin Wang Yangyang Zhang Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Electrical&Computer Engineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA

Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction network. Secondly, we design and implement the Lightweight Faster Implementation of Cross Stage Partial (CSP) Bottleneck with 2 Convolutions (C2f-Light) and the CSP Structure with 3 Compact Inverted Blocks (C3CIB) modules to replace the traditional C3 modules. This optimization enhances deep feature extraction and semantic information processing, thereby significantly increasing inference speed. To enhance the detection capability for small fires, the model employs a Normalized Wasserstein Distance (NWD) loss function, which effectively reduces the missed detection rate and improves the accuracy of detecting small fire sources. Experimental results demonstrate that compared to the baseline YOLOv5s model, the YOLO-LFD model not only increases inference speed by 19.3% but also significantly improves the detection accuracy for small fire targets, with only a 1.6% reduction in overall mean average precision (mAP)@0.5. Through these innovative improvements to YOLOv5s, the YOLO-LFD model achieves a balance between speed and accuracy, making it particularly suitable for real-time detection tasks on mobile and embedded devices.

关键词： Forest fire detection YOLOv5 lightweight small object detection

来源：评论

学校读者我要写书评

暂无评论

Point cloud upsampling generative adversarial network based on residual multi-scale off-set attention

引用

Virtual Reality & Intelligent Hardware 2023年第1期5卷 81-91页

作者： Bin SHEN Li LI Xinrong HU Shengyi GUO Jin HUANG Zhiyao LIANG School of Computer and Artificial Intelligence Wuhan Textile UniversityHubei 430200China School of Computer Science and Engineering Macao University of Science and TechnologyMacao China

Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.

关键词： Point cloud upsampling Generative adversarial network Attention

来源：评论

学校读者我要写书评

暂无评论

Categorisation by Leveraging CNNs and Remote Sensing Satellite Imagery for Crop Analysis in Arid Environments

引用

Remote Sensing in Earth Systems Sciences 2024年第2期7卷 66-79页

作者： Malhan, Anu Chavan, Yogita Rahulsing Swamikan, Brinthakumari Gupta, Megha Varun Bobade, Sunil Department of Artificial Intelligence and Data Science New Horizon Institute of Technology and Management Department of Computer Engineering New Horizon Institute of Technology and Management

The classification of walnuts in the dry areas of Ganquan Township, Awati County, Xinjiang, is investigated in this research using traditional approaches, remote sensing photos taken by satellite, and convolutional neural networks (CNNs). Thorough field sampling and the collecting of Landsat-8 Level-2 data were necessary for correct analysis due to the different environmental features of the research region, which presented major hurdles. Despite some early difficulties, CNN design revisions led to significant gains in classification accuracy. These modifications included AlexNet, VGG, GoogleNet, ResNet, and EfficientNetV2. When compared to more traditional approaches, ResNet and EfficientNetV2 stood up as the most successful models. Nevertheless, challenges including computational complexity and low-resolution imaging highlight the necessity for more research to improve detection efficiency without sacrificing accuracy. The study emphasises the need to keep looking for new ways to analyse and monitor crops, and it suggests that combining remote sensing with advanced machine learning methods could help improve precision agriculture management and increase crop yields in dry areas. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Categorisation of crop Machine learning Precision agriculture Remote sensing Walnut

来源：评论

学校读者我要写书评

暂无评论

A glance at in-context learning

引用

Frontiers of computer Science 2024年第5期18卷 231-232页

作者： Yongliang WU Xu YANG School of Computer Science&Engineering Key Lab of New Generation Artificial Intelligence Technology&Its Interdisciplinary Applications(Ministry of Education)Southeast UniversityNanjing 211189China

The advent of large scale models such as CLIP[1],GPT-2[2],and GPT-3[3]has marked a significant shift in the field of artificial intelligence(AI).Unlike the early days of Al,characterized by the design of distinct models or the utilization of pre-trained models for fine-tuning in specific tasks,these modern models adopt a unified approach.

关键词： such has unified

来源：评论

学校读者我要写书评

暂无评论

A Novel CAPTCHA Recognition System Based on Refined Visual Attention

引用

computers, Materials & Continua 2025年第4期83卷 115-136页

作者： Zaid Derea Beiji Zou Xiaoyan Kui Monir Abdullah Alaa Thobhani Amr Abdussalam School of Computer Science and Engineering Central South UniversityChangsha410083China College of Computer Science and Information Technology Wasit UniversityWasit52001Iraq Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha67714Saudi Arabia Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China

Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell computers and Humans Apart)has emerged as a key strategy for distinguishing human users from automated ***-based CAPTCHAs,designed to be easily decipherable by humans yet challenging for machines,are a common form of this ***,advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising *** our comprehensive investigation into CAPTCHA recognition,we have tailored the renowned UpDown image captioning model specifically for this *** approach innovatively combines an encoder to extract both global and local features,significantly boosting the model’s capability to identify complex details within CAPTCHA *** the decoding phase,we have adopted a refined attention mechanism,integrating enhanced visual attention with dual layers of Long Short-Term Memory(LSTM)networks to elevate CAPTCHA recognition *** rigorous testing across four varied datasets,including those from Weibo,BoC,Gregwar,and Captcha 0.3,demonstrates the versatility and effectiveness of our *** results not only highlight the efficiency of our approach but also offer profound insights into its applicability across different CAPTCHA types,contributing to a deeper understanding of CAPTCHA recognition technology.

关键词： Text-based CAPTCHA recognition refined visual attention web security computer vision

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking Control of Offshore Wind-Photovoltaic Hybrid Power Generation System with Crane-Assisted

引用

computer Modeling in engineering & Sciences 2025年第4期143卷 289-334页

作者： Xiangyang Cao Yaojie Zheng Hanbin Xiao Min Xiao School of Transportation and Logistics Engineering Wuhan University of TechnologyWuhan430063China Sanya Science and Education Innovation Park Wuhan University of TechnologySanya572024China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan430063China

This study investigates the Maximum Power Point Tracking(MPPT)control method of offshore windphotovoltaic hybrid power generation system with offshore crane-assisted.A new algorithm of Global Fast Integral Sliding Mode Control(GFISMC)is proposed based on the tip speed ratio method and sliding mode *** algorithm uses fast integral sliding mode surface and fuzzy fast switching control items to ensure that the offshore wind power generation system can track the maximum power point quickly and with low *** offshore wind power generation system model is presented to verify the algorithm *** offshore off-grid wind-solar hybrid power generation systemis built in MATLAB/*** with other MPPT algorithms,this study has specific quantitative improvements in terms of convergence speed,tracking accuracy or computational ***,the improved algorithm is further analyzed and carried out by using Yuankuan Energy’s ModelingTech semi-physical simulation *** results verify the feasibility and effectiveness of the improved algorithm in the offshore wind-solar hybrid power generation system.

关键词： Offshore wind power generation efficiency maximum power point tracking(MPPT) integral sliding mode control grey wolf optimization algorithm offshore photovoltaic cells

来源：评论

学校读者我要写书评

暂无评论

A New Alliance of Machine Learning and Quantum Computing: Concepts, Attacks, and Challenges in IoT Networks

引用

IEEE Internet of Things Journal 2025年第12期12卷 18865-18886页

作者： Rishiwal, Vinay Agarwal, Udit Yadav, Mano Tanwar, Sudeep Garg, Deepak Guizani, Mohsen MJP Rohilkhand University Department of Computer Science and Information Technology Bareilly243006 India Bareilly College Department of Computer Science Bareilly243005 India Institute of Technology Nirma University Department of Computer Science and Engineering Gujarat 382481 India SR University School of Computer Science and Artificial Intelligence Telangana 506371 India Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Abu Dhabi United Arab Emirates

The Internet of Things (IoT) is a constantly expanding system connecting countless devices for seamless data collection and exchange. This has transformed decision-making with data-driven insights across different domains. However, challenges arise concerning security and computational limitations. To strengthen IoT against cyber threats and optimize resource usage, combining quantum computing (QC) with machine learning (ML) is a promising approach. ML enables computers to learn from data and detect patterns without explicit programming. By leveraging ML algorithms, vast datasets from IoT devices can be analyzed, identifying anomalies and forecasting potential security breaches. Yet, conventional ML algorithms may need help with the complexity and scale of IoT data. QC, based on quantum mechanics, offers unparalleled computational speed and scale. Quantum ML algorithms can quickly analyze IoT datasets, identifying patterns and potential threats. This study examines the ideas behind ML, QC, and their potential collaboration within IoT networks. The research focuses on the possibility of improving the security of IoT networks by integrating QC approaches with ML. It also addresses the challenges and limitations of integrating ML and QC in the context of IoT networks. These obstacles include hardware constraints, algorithm complexities, and the need for specialized knowledge. © 2014 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Systematic Selection of a Suitable Data Imputation Technique Based on Data Characteristics

引用

SN computer Science 2025年第5期6卷 1-19页

作者： Sebastian, Anu Maria Peter, David Artificial Intelligence Lab Department of Computer Science Cochin University of Science and Technology Kerala Cochin India Department of Computer Science and Engineering Indian Institute of Information Technology Kottayam India

Analyzing incomplete data is one of the prime concerns in data analysis. Discarding the missing records or values might result in inaccurate analysis outcomes or loss of helpful information, especially when the size of the data is small. A preferable alternative is to substitute the missing values using imputation such that the substituted values are very close to the actual missing values and this is a challenging task. In spite of the existence of many imputation algorithms, there is no universal imputation algorithm that can yield the best values for imputing all types of datasets. This is mainly because of the dependence of the imputation algorithm on the inherent properties of the data. These properties include type of data distribution, data size, dimensionality, presence of outliers, data dependency among the attributes, and so on. In the literature, there exists no straightforward method for determining a suitable imputation algorithm based on the data characteristics. The existing practice is to conduct exhaustive experimentation using the available imputation techniques with every dataset and this requires a lot of time and effort. Moreover, the current approaches for checking the suitability of imputations cannot be done when the ground truth data is not available. In this paper, we propose a new method for the systematic selection of a suitable imputation algorithm based on the inherent properties of the dataset which eliminates the need for exhaustive experimentation. Our method determines the imputation technique which consistently gives lower errors while imputing datasets with specific properties. Also, our method is particularly useful when the real-world data do not have the ground truth for missing data to check the imputation performance and suitability. Once the suitability of a DI technique is established based on the data properties, this selection will remain valid for another dataset with similar properties. Thus, our method can save time an

关键词： Data analysis Data distribution Data imputation Data preprocessing Imputation performance Machine learning Missing value handling

来源：评论

学校读者我要写书评

暂无评论

Cyclical Training Framework with Graph Feature Optimization for Knowledge Graph Reasoning

引用

computers, Materials & Continua 2025年第5期83卷 1951-1971页

作者： Xiaotong Han Yunqi Jiang Haitao Wang Yuan Tian School of Artificial Intelligence Jilin UniversityChangchun130012China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOEChangchun130012China College of Computer Science and Technology Jilin UniversityChangchun130012China

Knowledge graphs(KGs),which organize real-world knowledge in triples,often suffer from issues of *** address this,multi-hop knowledge graph reasoning(KGR)methods have been proposed for interpretable knowledge graph *** primary approaches to KGR can be broadly classified into two categories:reinforcement learning(RL)-based methods and sequence-to-sequence(seq2seq)-based *** each method has its own distinct advantages,they also come with inherent *** leverage the strengths of each method while addressing their weaknesses,we propose a cyclical training method that alternates for several loops between the seq2seq training phase and the policy-based RL training phase using a transformer ***,a multimodal data encoding(MDE)module is introduced to improve the representation of entities and relations in *** module treats entities and relations as distinct modalities,processing each with a dedicated network specialized for its respective *** then combines the representations of entities and relations in a dynamic and fine-grained manner using a gating *** experimental results from the knowledge graph completion task highlight the effectiveness of the proposed *** five benchmark datasets,our framework achieves an average improvement of 1.7%in the Hits@1 metric and a 0.8%average increase in the Mean Reciprocal Rank(MRR)compared to other strong baseline ***,the maximum improvement in Hits@1 exceeds 4%,further demonstrating the effectiveness of the proposed approach.

关键词： Knowledge graph reinforcement learning transformer

来源：评论

学校读者我要写书评

暂无评论

Infrared polarization reconstruction method for ship target detection with latent low-rank representation and salient region extraction

引用

IEEE Sensors Journal 2025年第12期25卷 22090-22099页

作者： Meng, Xianmeng Fan, Zhiguo Hu, Yunyou Zhang, Yunxiang Zhao, Cailing Hefei University of Technology School of Computer Science and Information Engineering Hefei230022 China Hefei Comprehensive National Science Center Artificial Intelligence Research Institute Hefei230088 China

Infrared imaging detection of ship targets is a challenging task in near-zero contrast conditions, and the infrared polarization imaging technique has the advantage of solving this issue. However, in near-zero contrast conditions, the infrared polarization features of the ship are weak and affected by background noise. In this paper, we propose an infrared polarization reconstruction method with latent low-rank representation (LatLRR) and salient region extraction. Specifically, we employ the LatLRR to represent the Stokes parameter images based on the low-rank characteristic and calculate a low-noise infrared polarization image. Then, we present a fusion method based on the LatLRR to enhance target contrast and use the transition region segmentation approach to extract the salient feature regions. This fusion approach directly performs decomposition, denoising, and fusion on the Stokes images, minimizing noise amplification during polarization information acquisition. Furthermore, the polarization image is reconstructed from the low-noise infrared polarization and fused images with the salient region prior information. We design an infrared polarization imaging system and perform field experiments in near-zero contrast scenes. The experimental results prove the effectiveness of our method. Compared with other methods, our approach can effectively reconstruct weak target polarization features and increase the target contrast. © 2001-2012 IEEE.

关键词： Image segmentation

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：