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

Graph-geometric message passing via a graph convolution transformer for FKP regression

引用

science China(Information sciences) 2024年第12期67卷 176-190页

作者： Huizhi ZHU Wenxia XU Jian HUANG Baocheng YU Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology

In this paper, the forward kinematics problem(FKP) of the Gough-Stewart platform(GSP) with six degrees of freedom(6 DoFs) is estimated via deep learning. We propose a graph convolution transformer model by systematically analyzing some challenges encountered with using deep learning regression on largescale data. We attempt to leverage the graph-geometric message as input and singular value decomposition(SVD) orthogonalization for SO(3) manifold learning. This study is the first in which a robot with a sophisticated closed-loop mechanism is described by a graph structure and a specific deep learning model is proposed to solve the FKP of the GSP. Qualitative and quantitative experiments on our dataset demonstrate that our model is feasible and superior to other methods. Our method can guarantee error percentages of translation and rotation less than 1 mm and 1° of 81.9% and 96.7%, respectively.

关键词： deep learning graph-structured learning graph convolution transformer forward kinematics problem Gough-Stewart platform

来源：评论

学校读者我要写书评

暂无评论

Stochastic Augmented-Based Dual-Teaching for Semi-Supervised Medical Image Segmentation

引用

computers, Materials & Continua 2025年第1期82卷 543-560页

作者： Hengyang Liu Yang Yuan Pengcheng Ren Chengyun Song Fen Luo School of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China College of Artificial Intelligence Chongqing Technology and Business UniversityChongqing400067China

Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution ***,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than *** design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these *** be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled *** introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in *** the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local *** this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation *** two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation *** only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.

关键词： Semi-supervised medical image segmentation contrastive learning stochastic augmented

来源：评论

学校读者我要写书评

暂无评论

A Random Fusion of Mix 3D and Polar Mix to Improve Semantic Segmentation Performance in 3D Lidar Point Cloud

引用

computer Modeling in Engineering & sciences 2024年第7期140卷 845-862页

作者： Bo Liu Li Feng Yufeng Chen School of Computer Science and Engineering Macao University of Science and TechnologyMacao999078China School of Computer Science and Artificial Intelligence Chaohu UniversityChaohu238000China Institute of Vehicle Information Control and Network Technology Hubei University of Automotive TechnologyShiyan442002China

This paper focuses on the effective utilization of data augmentation techniques for 3Dlidar point clouds to enhance the performance of neural network *** point clouds,which represent spatial information through a collection of 3D coordinates,have found wide-ranging *** augmentation has emerged as a potent solution to the challenges posed by limited labeled data and the need to enhance model generalization *** of the existing research is devoted to crafting novel data augmentation methods specifically for 3D lidar point ***,there has been a lack of focus on making the most of the numerous existing augmentation *** this deficiency,this research investigates the possibility of combining two fundamental data augmentation *** paper introduces PolarMix andMix3D,two commonly employed augmentation techniques,and presents a new approach,named *** of using a fixed or predetermined combination of augmentation methods,RandomFusion randomly chooses one method from a pool of options for each instance or *** innovative data augmentation technique randomly augments each point in the point cloud with either PolarMix or *** crux of this strategy is the random choice between PolarMix and Mix3Dfor the augmentation of each point within the point cloud data *** results of the experiments conducted validate the efficacy of the RandomFusion strategy in enhancing the performance of neural network models for 3D lidar point cloud semantic segmentation *** is achieved without compromising computational *** examining the potential of merging different augmentation techniques,the research contributes significantly to a more comprehensive understanding of how to utilize existing augmentation methods for 3D lidar point *** data augmentation technique offers a simple yet effective method to leverage the diversity of augmentation techniques and boost the ro

关键词： 3D lidar point cloud data augmentation RandomFusion semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Weighted Probability Density Estimator with Updated Bandwidths

引用

Journal of Systems science & Complexity 2024年第2期37卷 886-906页

作者： WU Yi YU Wei WANG Xuejun PRAKASA RAO B L S School of Big Data and Artificial Intelligence Chizhou UniversityChizhou 247000China School of Big Data and Statistics Anhui UniversityHefei 230601China CR Rao Advanced Institute of Mathematics Statistics and Computer ScienceHyderabad 500046India

In this paper,the authors study a class of weighted version of probability density *** is shown that the weighted estimator contains some existing estimators of probability density,no matter they are recursive or *** statistical results including weak consistency,strong consistency,rate of strong consistency,and asymptotic normality are established under some mild ***,the random weighted estimator is also *** numerical simulations and a real data analysis are presented to study the numerical performances of the estimators.

关键词： Asymptotic normality consistency numerical simulation probability density real data analysis updated bandwidths weighted estimator

来源：评论

学校读者我要写书评

暂无评论

Collaborative graph contrastive learning for recommendation

引用

Journal of Intelligent and Fuzzy Systems 2025年第1-2期48卷 33-46页

作者： Wei, Tao Yang, Changchun Zheng, Yanqi Zhang, Jingxue School of Computer Science and Artificial Intelligence Aliyun School of Big Data School of Software Changzhou University Jiangsu Changzhou China School of Microelectronics and Control Engineering Changzhou University Jiangsu Changzhou China

Recently, Graph Neural Networks (GNNs) using aggregating neighborhood collaborative information have shown effectiveness in recommendation. However, GNNs-based models suffer from over-smoothing and data sparsity problems. Due to its self-supervised nature, contrastive learning has gained considerable attention in the field of recommendation, aiming at alleviating highly sparse data. Graph contrastive learning models are widely used to learn the consistency of representations by constructing different graph augmentation views. Most current graph augmentation with random perturbation destroy the original graph structure information, which mislead embeddings learning. In this paper, an effective graph contrastive learning paradigm CollaGCL is proposed, which constructs graph augmentation by using singular value decomposition to preserve crucial structure information. CollaGCL enables perturbed views to effectively capture global collaborative information, mitigating the negative impact of graph structural perturbations. To optimize the contrastive learning task, the extracted meta-knowledge was propagate throughout the original graph to learn reliable embedding representations. The self-information learning between views enhances the semantic information of nodes, thus alleviating the problem of over-smoothing. Experimental results on three real-world datasets demonstrate the significant improvement of CollaGCL over state-of-the-art methods. © 2025 – IOS Press. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Cooperative UAV clustering for fair coverage of communication regions

引用

Intelligent and Converged Networks 2025年第1期6卷 1-19页

作者： Jiehong Wu Linpeng Gu Zhongli Jia Jinsong Wu School of Computer Science Shenyang Aerospace UniversityShenyang 110136China School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China

Cooperative unmanned aerial vehicles(UAVs)cluster technology is considered a prospective solution for area coverage problems,enabling network access and emergency communications in remote *** this paper,we investigate how to control UAV cluster to achieve long-term and stable regional coverage while maintaining link connectivity and minimizing energy consumption,given the limited communication range and energy consumption of the UAVs *** this end,we propose a cooperative UAV cluster strategy based on multi-agent deep reinforcement learning(MADRL)to achieve fair coverage of communication regions,which we call MADRL-based cooperative UAV cluster strategy(MADRL-CUCS).Our solution is a centralized training distributed execution architecture and defines a cluster structure for leader UAVs and follower *** the premise of comprehensively considering the maximum coverage,we use a new energy efficiency function to minimize energy consumption,so as to extend the network lifetime of the UAVs cluster *** new fairness index and collision avoidance factor are used to ensure that the UAV cluster achieve effective and secure regional *** adopt depth first search algorithm to check the link connectivity of the UAVs during the coverage *** show that the MADRL-CUCS algorithm outperforms the benchmark algorithm.

关键词： unmanned aerial vehicle(UAV)cluster networks communication coverage multi-agent deep reinforcement learning fairness

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Dynamic Flexible Job Shop Scheduling With Biased Objectives via Multitask Genetic Programming

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年第1期6卷 169-183页

作者： Zhang, Fangfang Shi, Gaofeng Mei, Yi Zhang, Mengjie Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Emerson New Plymouth4310 New Zealand

Dynamic flexible job shop scheduling is an important combinatorial optimization problem that has rich real-world applications such as product processing in manufacturing. Genetic programming has been successfully used to learn scheduling heuristics for dynamic flexible job shop scheduling. Intuitively, users prefer small and effective scheduling heuristics that can not only generate promising schedules but also are computationally efficient and easy to be understood. However, a scheduling heuristic with better effectiveness tends to have a larger size, and the effectiveness of rules and rule size are potentially conflicting objectives. With the traditional dominance relation-based multiobjective algorithms, there is a search bias toward rule size, since rule size is much easier to optimized than effectiveness, and larger rules are easily abandoned, resulting in the loss of effectiveness. To address this issue, this article develops a novel multiobjective genetic programming algorithm that takes size and effectiveness of scheduling heuristics for optimization via multitask learning mechanism. Specifically, we construct two tasks for the multiobjective optimization with biased objectives using different search mechanisms for each task. The focus of the proposed algorithm is to improve the effectiveness of learned small rules by knowledge sharing between constructed tasks which is implemented with the crossover operator. The results show that our proposed algorithm performs significantly better, i.e., with smaller and more effective scheduling heuristics, than the state-of-the-art algorithms in the examined scenarios. By analyzing the population diversity, we find that the proposed algorithm has a good balance between exploration and exploitation during the evolutionary process. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

The Object-Centric Anomaly Detection for Aero-engine Blade 24

The Object-Centric Anomaly Detection for Aero-engine Blade

引用

2nd International Conference on Frontiers of Intelligent Manufacturing and Automation, CFIMA 2024

作者： Lv, Xinwei Chen, Haiyong Qi, Xuan Wang, Yining Li, Dongying Zhang, Xingshun Zhang, Haode School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China

ISBN: (纸本)9798400710681

Industrial Anomaly Detection (IAD) focuses on the real-time identification of various deviations that affect product quality, such as appearance defects, dimensional inaccuracies, or material performance issues. By providing timely corrections, IAD effectively reduces the defect rate and significantly enhances product quality. However, most existing IAD research assumes that training and test data are derived from the same distribution, which often poses challenges in real-world applications. The experimental dataset highlights two major issues: the inconsistency and scale differences of target samples, and the significant distribution shifts in test data caused by variations in illumination, pose, or background, which greatly diminish the effectiveness of traditional IAD methods. To address the anomaly detection challenges posed by distribution shifts. The innovation lies in introducing a dual-view mechanism coupled with an asymmetric masking rate of up to 95%, effectively mitigating dependency on dataset diversity. Additionally, we propose a novel robust AD strategy that involves masking the vast majority of the future frame regions while keeping past frames unchanged. This approach encourages the network to focus on object dynamics, extracting object-centric representations. During training, we adopt an unsupervised approach, aiming to minimize the differences between distributions and among OOD normal samples, to address the diverse distribution shifts and ensure the robustness and accuracy of detection results. © 2024 Copyright held by the owner/author(s).

关键词： Turbomachine blades

来源：评论

学校读者我要写书评

暂无评论

Orbital angular momentum-mediated machine learning for high-accuracy mode-feature encoding

引用

Light(science & Applications) 2024年第3期13卷 466-477页

作者： Xinyuan Fang Xiaonan Hu Baoli Li Hang Su Ke Cheng Haitao Luan Min Gu Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Machine learning with optical neural networks has featured unique advantages of the information processing including high speed,ultrawide bandwidths and low energy consumption because the optical dimensions(time,space,wavelength,and polarization)could be utilized to increase the degree of ***,due to the lack of the capability to extract the information features in the orbital angular momentum(OAM)domain,the theoretically unlimited OAM states have never been exploited to represent the signal of the input/output nodes in the neural network ***,we demonstrate OAM-mediated machine learning with an all-optical convolutional neural network(CNN)based on Laguerre-Gaussian(LG)beam modes with diverse diffraction *** proposed CNN architecture is composed of a trainable OAM mode-dispersion impulse as a convolutional kernel for feature extraction,and deep-learning diffractive layers as a *** resultant OAM mode-dispersion selectivity can be applied in information mode-feature encoding,leading to an accuracy as high as 97.2%for MNIST database through detecting the energy weighting coefficients of the encoded OAM modes,as well as a resistance to eavesdropping in point-to-point free-space ***,through extending the target encoded modes into multiplexed OAM states,we realize all-optical dimension reduction for anomaly detection with an accuracy of 85%.Our work provides a deep insight to the mechanism of machine learning with spatial modes basis,which can be further utilized to improve the performances of various machine-vision tasks by constructing the unsupervised learning-based auto-encoder.

关键词： polarization mode momentum

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：