检索结果-内蒙古大学图书馆

Hierarchical annotation method for metal corrosion detection of power equipment

Journal of Southeast University(English Edition) 2021年第4期37卷 350-355页

作者： Zhang Baili Cao YongZhang Pei Zhang Zhao He Yina Zhong Mingjun School of Computer Science and Engineering Southeast UniversityNanjing 211189China State Key Laboratory of Smart Grid Protection and Control State Grid Electric Power Research InstituteNanjing 211106China NARI Group Corporation Nanjing 211106China Department of Computing Science University of AberdeenAberdeen AB243UEUK

To solve the ambiguity and uncertainty in the labeling process of power equipment corrosion datasets,a novel hierarchical annotation method(HAM)is ***,large boxes are used to label a large area covering the range of corrosion,provided that the area is visually continuous and adjacent to corrosion that cannot be clearly ***,in each labeling box established in the first step,regions with distinct corrosion and relative independence are labeled to form a second layer of nested ***,a series of comparative experiments are conducted with other common annotation methods to validate the effectiveness of *** experimental results show that,with the help of HAM,the recall of YOLOv5 increases from 50.79%to 59.41%;the recall of Faster R-CNN+VGG16 increases from 66.50%to 78.94%;the recall of Faster R-CNN+Res101 increases from 78.32%to 84.61%.Therefore,HAM can effectively improve the detection ability of mainstream models in detecting metal corrosion.

关键词： deep learning Faster R-CNN YOLOv5 object detection hierarchical annotation

来源：评论

学校读者我要写书评

暂无评论

Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2023年

作者： Shi, Zhaoyuan Lu, Huabing Xie, Xianzhong Yang, Helin Huang, Chongwen Cai, Jun Ding, Zhiguo The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing China The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian116024 China Chongqing Key Lab of Computer networks and Communication Technology Chongqing University of Posts and Telecommunications Chongqing China The Department of Information and Communication Engineering School of Informatics Xiamen University Xiamen361005 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada The Department of Electrical Engineering Princeton University PrincetonNJ08544 United States The School of Electrical and Electronic Engineering The University of Manchester Manchester United Kingdom

An active reconfigurable intelligent surface (RIS)-aided multi-user downlink communication system is investigated, where non-orthogonal multiple access (NOMA) is employed to improve spectral efficiency, and the active RIS is powered by energy harvesting (EH). The problem of joint control of the RIS’s amplification matrix and phase shift matrix is formulated to maximize the communication success ratio with considering the quality of service (QoS) requirements of users, dynamic communication state, and dynamic available energy of RIS. To tackle this non-convex problem, a cascaded deep learning algorithm namely long short-term memory-deep deterministic policy gradient (LSTM-DDPG) is designed. First, an advanced LSTM based algorithm is developed to predict users’ dynamic communication state. Then, based on the prediction results, a DDPG based algorithm is proposed to joint control the amplification matrix and phase shift matrix of the RIS. Finally, simulation results verify the accuracy of the prediction of the proposed LSTM algorithm, and demonstrate that the LSTM-DDPG algorithm has a significant advantage over other benchmark algorithms in terms of communication success ratio performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Double Deep Q-learning for Anti-saturation Attack Problem of Warship Group

Double Deep Q-learning for Anti-saturation Attack Problem of...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wei Li Gang Xiong Hao Tao Yunjun Han Fang Wang Xisong Dong Zhen Shen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan China School of Control Science and Engineering (CSE) Shandong University Jinan China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios.

关键词： Industries Heuristic algorithms Digital twin Conferences Knowledge based systems Reinforcement learning Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and Tracking

A Novel Deep Learning Approach Featuring Graph-Based Algorit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Keliang Zhao Jovial Niyogisubizo Linxia Xiao Yi Pan Dongqing Wei Didi Rosiyadi Yanjie Wei Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory of Microbial Metabolism and School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai China Research Center for Artificial Intelligence and Cybersecurity National Research and Innovation Agency Bandung Indonesia

The precise segmentation and tracking of cells in microscopy image sequences play a pivotal role in biomedical research, facilitating the study of tissue, organ, and organism development. However, manual segmentation and tracking of cells is time-consuming and often require professional experiences. Besides, segmenting cells in the images with a low signal-to-noise ratio remains difficult. While deep learning (DL) has become a common method for cell segmentation, few DL- based methods address concurrent cell segmentation and tracking. In this paper, we propose a novel DL approach featuring graph-based tracking for cell segmentation and tracking in microscopy images. We combine Deeplabv3+ for semantic segmentation and ResNet50 for enhanced feature extraction, enabling comprehensive cell detection and instance segmentation. Post-processing, involving non-maxima suppression and outlier detection, refines predictions and produces final segmentation. The tracking method is based on the relative position of graph nodes to track segmented cells, encompassing cell division and apoptosis. We conduct our experiments on the induced pluripotent stem (iPS) cell datasets, and the results show that the segmentation and tracking performance of our method yields superior performance compared to the benchmark models. More specifically, our approach achieved DET values of 0.955 and 0.913, TRA values of 0.951 and 0.906, and SEG values of 0.690 and 0.665 on two iPS dataset videos, respectively. Additionally, the performance assessment encompasses four real microscopy datasets from the Cell Tracking Challenge (CTC). Our method greatly reduces the cost of manual labeling and labor-intensive costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

arXiv

引用

arXiv 2022年

作者： Sun, Li Ye, Junda Peng, Hao Wang, Feiyang Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Computer Science University of Illinois ChicagoIL United States

Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence. On the other hand, continual learners in the literature rely on abundant labels, but labeling graph in practice is particularly hard especially for the continuously emerging graphs on-the-fly. To address the aforementioned challenges, we propose to explore a challenging yet practical problem, the self-supervised continual graph learning in adaptive Riemannian spaces. In this paper, we propose a novel self-supervised Riemannian Graph Continual Learner (RieGrace). In RieGrace, we first design an Adaptive Riemannian GCN (AdaRGCN), a unified GCN coupled with a neural curvature adapter, so that Riemannian space is shaped by the learnt curvature adaptive to each graph. Then, we present a Label-free Lorentz Distillation approach, in which we create teacher-student AdaRGCN for the graph sequence. The student successively performs intra-distillation from itself and inter-distillation from the teacher so as to consolidate knowledge without catastrophic forgetting. In particular, we propose a theoretically grounded Generalized Lorentz Projection for the contrastive distillation in Riemannian space. Extensive experiments on the benchmark datasets show the superiority of RieGrace, and additionally, we investigate on how curvature changes over the graph sequence. © 2022, CC BY-NC-SA.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

arXiv

引用

arXiv 2022年

作者： Liu, Ruiping Yang, Kailun Roitberg, Alina Zhang, Jiaming Peng, Kunyu Liu, Huayao Wang, Yaonan Stiefelhagen, Rainer The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany The School of Robotics The National Engineering Laboratory of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The Institute for Artificial Intelligence The University of Stuttgart Stuttgart70569 Germany The Institute for Visual Computing ETH Zurich Zurich8092 Switzerland NIO Shanghai201804 China

Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computational costs and prolonged training durations. To lift this constraint, we look at efficient semantic segmentation from a perspective of comprehensive knowledge distillation and aim to bridge the gap between multi-source knowledge extractions and transformer-specific patch embeddings. We put forward the Transformer-based Knowledge Distillation (TransKD) framework which learns compact student transformers by distilling both feature maps and patch embeddings of large teacher transformers, bypassing the long pre-training process and reducing the FLOPs by >85.0%. Specifically, we propose two fundamental modules to realize feature map distillation and patch embedding distillation, respectively: (1) Cross Selective Fusion (CSF) enables knowledge transfer between cross-stage features via channel attention and feature map distillation within hierarchical transformers;(2) Patch Embedding Alignment (PEA) performs dimensional transformation within the patchifying process to facilitate the patch embedding distillation. Furthermore, we introduce two optimization modules to enhance the patch embedding distillation from different perspectives: (1) Global-Local Context Mixer (GL-Mixer) extracts both global and local information of a representative embedding;(2) Embedding Assistant (EA) acts as an embedding method to seamlessly bridge teacher and student models with the teacher’s number of channels. Experiments on Cityscapes, ACDC, NYUv2, and Pascal VOC2012 datasets show that TransKD outperforms state-of-the-art distillation frameworks and rivals the time-consuming pre-training method. The source code is publicly available at https://***/RuipingL/TransKD. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Novel Scheme Towards Interfacial Charge Transfer between Znin2s4 and Biobr for Efficient Photocatalytic Removal of Organics and Chromium (Vi) from Water

SSRN

引用

SSRN 2022年

作者： He, Zuming Yang, Hanpei Sunarso, Jaka Wong, Ngie Hing Huang, Zhengyi Xia, Yongmei Wang, Yong Su, Jiangbin Wang, Lina Kang, Li Key Laboratory of Integrated Regulation and Resource Development on Shallow Lakes Ministry of Education College of Environment Hohai University Nanjing210098 China Huaide School Changzhou University Jingjiang214500 China School of Microelectronics and Control Engineering Changzhou University Changzhou213164 China Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga Sarawak Kuching93350 Malaysia School of Materials and Engineering Jiangsu University of Technology Changzhou213001 China School of Pharmaceutical and Materials Engineering Taizhou University Jiaojiang318000 China

Construction of Z-scheme heterostructure is an effective strategy to enhance the charge carriers' separation. However, successfully achieving this on the defect heterojunction to improve the photocatalytic activity remains challenging. This work successfully obtained sulfur vacancy in the ZnIn2S4/BiOBr (SZIS/BOB) heterojunction composites with S-O covalent bonding using a hydrothermal method. As a result, they exhibited superior photocatalytic and stability performance. The optimized SZIS/BOB-10 exhibited excellent rhodamine B degradation (95.2%) and chromium (VI) reduction (97.8%) within 100 minutes under visible light. The enhanced composites with S-vacancies, S-O bond, and internal electric field induced the Z-scheme charge transfer mechanism. We had verified this mechanism based on the surface photovoltage spectra, electron spin response spectra, and density functional theory calculations. This work not only provides valuable insights into designing photocatalysts with a direct Z scheme heterostructure but also delineates a promising strategy for developing efficient photocatalysts to degrade organic pollutants. © 2022, The Authors. All rights reserved.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Optimal Minimum Energy Path Planning of Mobile Robot Based on Improved WOA-GA with Hybrid Strategy for Community-Centric Application

Optimal Minimum Energy Path Planning of Mobile Robot Based o...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jiang Du Zhou Da-Lin Li Gong-Fa Lu Bao-Li Yun Jun-Tong Liu Ying Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan China School of Computing University of Portsmouth Portsmouth UK Hubei key laboratory of hydroelectric machinery design & maintenance China Three Gorges University Yichang China Key Laboratory of Mechanical Transmission and Manufacturing Engineering of Hubei Province Wuhan University of Science and Technology Wuhan China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan China Institute of Semiconductors Chinese Academy of Sciences Beijing China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan China

The path planning of mobile robots is investigated to minimize energy loss in intelligent manufacturing. To achieve optimal energy consumption planning, this paper proposes a hybrid strategy that enhances the whale optimization algorithm (WOA) and the genetic algorithm (GA). The WOA-GA algorithm combines their respective advantages and effectively mitigates premature convergence exhibited by the standard traditional algorithm. To enhance the global and local search capabilities of the standard WOA, we employ adaptive weighting and a Cauchy mutation strategy. Additionally, we introduce an adaptive crossover mutation probability and an elite strategy to mitigate the detrimental effects of the genetic algorithm's evolutionary operation in the late iterations, thereby improving its performance. This paper compares the performance of the standard GA, the standard WOA-GA algorithm, and the enhanced WOA-GA algorithm. The experimental results demonstrate that the enhanced WOA-GA algorithm can achieve optimal energy-efficient path planning using the hybrid strategy. The average energy consumption of the enhanced WOA-GA algorithm can be reduced by 30%, while the maximum energy consumption can be reduced by 47%. The results confirm the effectiveness and feasibility of the proposed method in enhancing the level of green manufacturing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-term Wind Power Predication Based on Feature engineering and SOA-SVM 5

Short-term Wind Power Predication Based on Feature Engineeri...

引用

5th IEEE Conference on Energy Internet and Energy System Integration, EI2 2021

作者： Zhang, Wenfeng Yan, Renwu Yu, Ning Liu, Yunzhang Zhang, Yang College of Electronic Electrical and Physics FuJian University of Technology Fuzhou350118 China College of Electronic Electrical and Physics Fujian Provincial University Fuzhou350118 China Engineering Research Center for Smart Grid Simulation Analysis and Integrated Control FuJian University of Technology Fuzhou350118 China Department of Computing Sciences SUNY Brockport BrockportNY14420 United States College of Electronic EFuJian University of Tlectrical and Physics Echnology Fuzhou350118 China

ISBN: (纸本)9781665434256

Contraposing to the issues of strong randomness, large volatility, and high prediction error of wind power, this paper proposes a short-term wind power prediction method based on feature engineering and support vector machine optimized by the seagull optimization algorithm (ISOA-SVM). First, in feature engineering, the abnormal values are preprocessed and utilizing the Pearson correlation coefficient (PCC) method to analyze the correlation between wind power and every feature. On this basis, a set of new features are constructed. Then, in the construction of the combined model, the seagull optimization algorithm is utilized to optimize the parameters of the support vector machine, so as to realize the complementary advantages of the optimization characteristics of the seagull algorithm and the support vector machine in simplifying the high-dimensional space complexity problems. Finally, the short-term wind power prediction model is constructed based on the ISOA-SVM model. The emulation experiment is carried out with the relevant measurement data of a wind power field. The results show that, in relation to other models, the proposed ISOA-SVM model has more excellent precision and dependability of short-term wind power prediction, which provides a certain reference for power dispatching. © 2021 IEEE

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Spectrometric Characterization of Suspension Liquid and Light Extinction Model Update

SSRN

引用

SSRN 2022年

作者： Liu, Sheng Shen, Yang Gao, Zihui Gao, Hongwen School of Computer Science and Technology Huaibei Normal University Huaibei235000 China State Key Laboratory of Enviromental Pollution Control and Resource Reuse Tongji University Shanghai200092 China Shanghai GreenEmpire Environmental Science and Technology Corporation Shanghai200092 China Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior Huaibei235000 China

On the basis of the classical light scattering models, the light extinction model is the first to establish as [[EQUATION]] (, N and γ – average diameter in μm, number and relative refractive index of the suspending particles, λ , A and δ – incident light wavelength in μm, absorbance and optical path in cm of the suspension liquid) by spectrometric characterization of ten standard suspension liquids. It has been used to determine the suspending particles in the calcium oxalate, Formazine, soil, milk and sewage suspension water samples. As the result, the light extinction model method brought out less than 12% error of and 18% error of the suspending particles’ quality by comparing with the conventional methods. It provides a simple and reliable spectroptometric determination of a suspension liquid. Also, it is very potential to in-situ monitor the growth and working state of the suspending particles using in synthesis of materials, culture of cells, treatment of wastewater and safety of drinking water and foods. © 2022, The Authors. All rights reserved.

关键词： Suspensions (fluids)

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：