检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1513-1528页

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Ma, Xingjun Qi, Peng Ding, Zhijun Jin, Jiong Tongji University School of Computer Science and Technology Shanghai201804 China Ant Group Shanghai200122 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Fudan University School of Computer Science Shanghai200438 China Tongji University Department of Control Science and Engineering Shanghai201804 China Swinburne University of Technology School of Science Computing and Engineering Technologies Melbourne3122 Australia

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this article, we propose a hypergraph learning framework named learning from heterogeneity (LFH) that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterward, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with twelve state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experimental results demonstrate a significant performance gain (an average of 12.9% in node classification and 12.8% in link prediction) compared with recent state-of-the-art methods. © 2020 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge Probabilization in Ensemble Distillation: Improving Accuracy and Uncertainty Quantification for Object Detectors

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 221-233页

作者： Yang, Yang Wang, Chao Gong, Lei Wu, Min Chen, Zhenghua Li, Xiang Chen, Xianglan Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China 138632 Singapore East China Normal University School of Data Science and Engineering Shanghai200062 China

Ensemble object detectors have demonstrated remarkable effectiveness in enhancing prediction accuracy and uncertainty quantification. However, their widespread adoption is hindered by significant computational and storage demands, limiting their feasibility in resource-constrained settings. To overcome this, researchers have focused on distilling the knowledge from ensemble object detectors into a single model. In this article, we introduce probabilization based ensemble distillation (ProbED), an innovative ensemble distillation framework that consolidates knowledge from multiple object detectors into a single, resource-efficient model. Unlike traditional ensemble distillation methods that average the outputs of subteachers, ProbED captures comprehensive outcome distributions from all subteachers, providing a more nuanced approach to knowledge transfer. ProbED employs knowledge probabilization to achieve a sophisticated and refined aggregation of teacher knowledge, including feature knowledge, semantic knowledge, and localization knowledge, resulting in dual improvements in prediction accuracy and uncertainty quantification for the student model. In particular, ProED's novel knowledge probabilization-based approach to aggregating teacher knowledge is inspired by our empirical observations, which demonstrate that knowledge probabilization excels in effectively representing uncertainty, improving prediction, and facilitating robust knowledge transfer. Furthermore, we introduce a random smoothing perturbation technique to modify inputs within ProbED, further enhancing the distillation process. Extensive experiments highlight ProbED's ability to significantly enhance the prediction accuracy and uncertainty quantification of various object detectors, demonstrating its superior performance compared to other state-of-the-art techniques. © 2024 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Design, Simulation, and Field Testing of an Intelligent Control Algorithm Based on Event-Triggered and Nonlinear MPC for USVs

引用

IEEE Internet of Things Journal 2025年第12期12卷 22155-22167页

作者： Hu, Jiabao Yang, Xiaofei Lou, Mengmeng Ye, Hui Shen, Hao Xiang, Zhengrong Jiangsu University of Science and Technology School of Automation Zhenjiang212100 China Anhui University of Technology School of Electrical and Information Engineering Maanshan242032 China Nanjing University of Science and Technology School of Automation Nanjing210094 China

The design, simulation, and testing of intelligent trajectory-tracking control in narrow waters are essential issues for unmanned surface vehicles (USVs). Due to limited actuators, spatial constraints, and obstacles in narrow waters, the reference trajectory for USVs has various curves. This presents significant challenges to the accuracy and computational load of trajectory tracking. Therefore, a novel event-triggered-based nonlinear model predictive control with artificial reference trajectory (ENMPC-ART) method is proposed. The artificial reference decision variables are integrated into the quadratic trajectory planning of reference trajectory and motion control of USVs to reduce the cross-track error. An event-triggered mechanism is designed to improve NMPCs efficiency. Further, a cyber-physical simulation test framework based on virtual reality is designed to verify the algorithms performance and enhance the immersion. Finally, the proposed ENMPC-ART shows significant improvements through virtual simulations and field tests, such as the maximum cross-track error being reduced by 16% and the computation time being reduced by 20.2%. © 2014 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

DAFPN-YOLO: An Improved UAV-Based Object Detection Algorithm Based on YOLOv8s

引用

computers, Materials & Continua 2025年第5期83卷 1929-1949页

作者： Honglin Wang Yaolong 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

UAV-based object detection is rapidly expanding in both civilian and military applications,including security surveillance,disaster assessment,and border ***,challenges such as small objects,occlusions,complex backgrounds,and variable lighting persist due to the unique perspective of UAV *** address these issues,this paper introduces DAFPN-YOLO,an innovative model based on YOLOv8s(You Only Look Once version 8s).Themodel strikes a balance between detection accuracy and speed while reducing parameters,making itwell-suited for multi-object detection tasks from drone perspectives.A key feature of DAFPN-YOLO is the enhanced Drone-AFPN(Adaptive Feature Pyramid Network),which adaptively fuses multi-scale features to optimize feature extraction and enhance spatial and small-object *** leverage Drone-AFPN’smulti-scale capabilities fully,a dedicated 160×160 small-object detection head was added,significantly boosting detection accuracy for small *** the backbone,the C2f_Dual(Cross Stage Partial with Cross-Stage Feature Fusion Dual)module and SPPELAN(Spatial Pyramid Pooling with Enhanced LocalAttentionNetwork)modulewere *** components improve feature extraction and information aggregationwhile reducing parameters and computational complexity,enhancing inference ***,Shape-IoU(Shape Intersection over Union)is used as the loss function for bounding box regression,enabling more precise shape-based object *** results on the VisDrone 2019 dataset demonstrate the effectiveness *** to YOLOv8s,the proposedmodel achieves a 5.4 percentage point increase inmAP@0.5,a 3.8 percentage point improvement in mAP@0.5:0.95,and a 17.2%reduction in parameter *** results highlight DAFPN-YOLO’s advantages in UAV-based object detection,offering valuable insights for applying deep learning to UAV-specific multi-object detection tasks.

关键词： YOLOv8 UAV-based object detection AFPN small-object detection head SPPELAN DualConv loss function

来源：评论

学校读者我要写书评

暂无评论

Mechanical behaviour and acoustic emission characteristics of the reinforced soft muddy rock under various moisture content levels

引用

International Journal of Coal science & technology 2024年第6期11卷 139-157页

作者： Haoyu Rong Wei Wang Guichen Li Guangming Zhao Dongxu Liang Jiahui Xu College of Civil and Transportation Engineering Hohai UniversityNanjingChina School of Mines Key Laboratory of Deep Coal Resource MiningMinistry of Education of ChinaChina University of Mining and TechnologyXuzhouChina School of Safety Science and Engineering Anhui University of Science and TechnologyHuainanChina School of Civil Engineering Xuzhou University of TechnologyXuzhouChina

In order to investigate the failure mechanism of the reinforced muddy soft rock under the influence of the hydration reaction when ground water is present,a series of confined compressive tests and Acoustic Emission(AE)recordings were conducted subject to various moisture content levels and lateral confining *** was found that the failure modes of the reinforced rock specimen were affected by the moisture content level and the lateral stress σ_(2) in a way that the load bearing capacity of the reinforced rock would increase with the lateral stress σ_(2) but decrease as the moisture content *** increase in the moisture content would reduce the extent of the influence of the lateral stress on the load bearing capacity of the reinforced *** addition,much less AE counts were recorded when the moisture content increased indicating that the crack initiation and propagation in this case was easier due to the reduction of the required external input *** increasing moisture content,the failure mode of the specimen gradually changes from sudden and brittle to progressive and ***,the hydration reaction became more significant leading to a complete debonding between the grout and the ***,the reinforcement provided by the rock bolt to the rock became negligible.

关键词： Mudstone Anchorage structure Reinforced rock Hydration Bearing capacity

来源：评论

学校读者我要写书评

暂无评论

SegNet-OPC: A Mask Optimization Framework in VLSI Design FlowBased on Semantic Segmentation Network

引用

Journal of computer science & technology 2025年第2期40卷 500-512页

作者： Hui Xu Pan Qi Fu-Xin Tang Hua-Guo Liang Zheng-Feng Huang School of Computer Science and Engineering Anhui University of Science and TechnologyHuainan 232001China School of Artificial Intelligence Anhui University of Science and TechnologyHuainan 232001China School of Microelectronics Hefei University of TechnologyHefei 230009China

With the continuous decrease in the critical dimensions of integrated circuits, mask optimization has becomethe main challenge in VLSI design. In recent years, thriving machine learning has been gradually introduced in the field ofoptical proximity correction (OPC). Currently, advanced learning-based frameworks have been limited by low mask printability or large computational overhead. To address these limitations, this paper proposes a learning-based frameworknamed SegNet-OPC, which can generate optimized masks from the target layout at shorter training and turnaround timewith higher mask printability. The proposed framework consists of a backbone network and loss terms suitable for maskoptimization tasks, followed by a fine-tuning network. The framework yields remarkable improvements over conventionalmethods, delivering significantly faster turnaround time and superior mask printability and manufacturability. With just1.25 hours of training, the framework achieves comparable mask complexity while surpassing the state-of-the-art methods,achieving a minimum 3% enhancement in mask printability and an impressive 16.7% improvement in mask manufacturability.

关键词： learning-based framework mask optimization mask printability optical proximity correction

来源：评论

学校读者我要写书评

暂无评论

Retaining the self-released chalcogenate at reconstructed cobalt sites by self-transformed carbonate regulation for boosted oxygen evolution

引用

Journal of Energy Chemistry 2024年第10期97卷 46-54,I0002页

作者： Jingxuan Zhao Zhe Xue Qing Wang Xiangyang Li Shoujie Liu Xu Zhao School of Chemical Engineering and Technology Xi'an Jiaotong UniversityXi'an 710049ShaanxiChina Key Laboratoryof Materials Physics Instituteof Solid State PhysicsHefei Institutes of Physical Science(HFIPS)Chinese Academy of SciencesHefei 23031 Anhui China School of Materials Science and Engineering Anhui UniversityHefei 230601AnhuiChina

The in-situ generated oxyanions at electrochemically reconstructed catalysts from metal-based nonoxide compounds have been proven to significantly accelerate oxygen evolution reaction(OER)***,it remains a challenge to retain these self-released oxyanions at reconstructed catalysts,hindering its utilization as a tool to develop efficient OER ***,we demonstrate a versatile selftransformed carbonate regulation strategy to efficiently retain the self-released chalcogenate at Co oxyhydroxides reconstructed from carbon-incorporated Co selenides under OER *** selftransformed CO_(3)^(2-)can induce electron accumulation and narrow d bond at Co sites to facilitate the Co3d-O 2p orbital hybridization between Co sites and SeO_(x)^(2-)for enhanced SeO_(x)^(2-)retention,which can accelerate the rate-limiting step for^(*)OOH formation during *** to CoOOH-SeO_(x)^(2-)with limited SeO_(x)^(2-)residues,CoOOH-CO_(3)^(2-)/SeO_(x)^(2-)with elevated SeO_(x)^(2-)retention by CO_(3)^(2-)regulation exhibited a 5.6-fold increase in current density and a remarkable lower Tafel slope towards *** strategy paves a rational avenue to design efficient catalysts for electrooxidation reactions through finely regulating self-released oxyanions at reconstructed structures.

关键词： Electrochemical reconstruction Chalcogenate retention Carbonate regulation Orbital hybridization Oxygen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Optimization for Traveling Salesman Problem: A Deep Reinforcement Learning Algorithm via Transfer Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 896-908页

作者： Gao, Le-Yang Wang, Rui Jia, Zhao-Hong Liu, Chuang Anhui University School of Computer Science and Technology Hefei230039 China National University of Defense Technology College of System Engineering Changsha410073 China Xiangjiang Laboratory Changsha410205 China Anhui University School of Internet Hefei230039 China

A wide range of real applications can be modelled as the multiobjective traveling salesman problem (MOTSP), one of typical combinatorial optimization problems. Meta-heuristics can be used to address MOTSP. However, due to involving iteratively searching large solution space, they often entail significant computation time. Recently, deep reinforcement learning (DRL) algorithms have been employed in generating approximate optimal solutions to the single objective traveling salesman problems, as well as MOTSPs. This study proposes a multiobjective optimization algorithm based on DRL, called multiobjective pointer network (MOPN), where the input structure of the pointer network is redesigned to be applied to MOTSP. Furthermore, a training strategy utilizing a representative model and transfer learning is introduced to enhance the performance of MOPN. The proposed MOPN is insensitive to problem scale, meaning that a trained MOPN can address MOTSPs with different scales. Compared to meta-heuristics, MOPN takes much less time on forward propagation to obtain the pareto front. To verify the performance of our model, extensive experiments are conducted on three different MOTSPs to compare the MOPN with two state-of-the-art DRL models and two multiobjective meta-heuristics. Experimental results demonstrate that the proposed MOPN obtains the best solution with the least training time among all the compared DRL methods. © 2024 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

DEEPRIDGE: A HOP-LAYER DEEP LEARNING MODEL FOR DETECTING ENERGY RIDGES IN HOIST OPERATION NOISE SPECTROGRAMS

引用

International Journal of Innovative Computing, Information and Control 2025年第2期21卷 307-322页

作者： Meng, Yifan Zhang, Heng Zhang, Xiaoming School of Artificial Intelligence Anhui University of Science & Technology No. 168 Taifeng Street Huainan232000 China School of Electrical and Information Engineering Anhui University of Science & Technology No. 168 Taifeng Street Huainan232000 China

The variation trend of energy ridge in the noise spectrum of mine hoist is an important index of its health state. Due to the interference of background noise, the energy ridges in the hoist spectrum have unclear boundaries and poor continuity, making them hard to separate and analyze. To address this challenge, we propose a new end-to-end training deep neural network that extracts and fuses multi-scale features of spectrographs using multiple encoder-attention module-decoder blocks. The multi-scale features enable the network to capture the energy ridges in the spectrum more accurately and robustly. The small-scale feature map is used for coarse localization, and the large-scale feature map is used for fine refinement. We design and train our network, named DeepRidge, on a noise spectrum dataset of mining hoist collected from a preliminary experiment. We compared DeepRidge with other state-of-the-art methods, and the test results show that DeepRidge achieves better accuracy at smaller parameter sizes, with an average precision (AP) of 0.826. We also conduct experiments to find the optimal network configuration for the energy ridge detection task in the hoist noise spectrum. © 2024, ICIC International. All rights reserved.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZATION RESEARCH OF IMPROVED GENERALIZED NORMAL DISTRIBUTION OPTIMIZATION ALGORITHM IN WSN COVERAGE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2023年第2期85卷 95-110页

作者： Hu, Biling Hou, Mengshu Xie, Fei Liu, Yanan School of Computer science Hefei Normal University China School of Computer Science and Engineering University of Electronic Science and Technology of China China

A coverage control strategy based on an improved generalized normal distribution optimization algorithm is proposed for coverage optimization of sensor networks. Firstly, IGNDO uses a combination of Logistic and Tent chaotic mappings to initialize the original population in the initialization phase;secondly, it uses nonlinear control parameters to adjust the probability of local search and global search being selected in the iterative phase, and perturbs the update of individuals after iterative update with partial Lévy flight to Improve their ability to escape from their local best;Finally, the algorithm’s search ability is further improved by using random regression transgression. In the experimental phase, the improved algorithm is firstly tested with benchmark functions, and secondly IGNDO is employed to sensor network coverage optimization, and the optimal results are obtained in comparison with other optimization algorithms. © 2023, Politechnica university of Bucharest. All rights reserved.

关键词： Wireless sensor networks

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：