检索结果-内蒙古大学图书馆

Remote Sensing Plateau Forest Segmentation with Boundary Preserving Double Loss Function Collaborative Learning

Journal of New Media 2022年第4期4卷 165-177页

作者： Ying Ma Jiaqi Zhang Pengyu Liu Zhihao Wei Lingfei Zhang Xiaowei Jia School of Physics and Electronic Information Engineering Qinghai Minzu UniversityXining810007China The Information Department Beijing University of TechnologyBeijing100124China Advanced Information Network Beijing Laboratory Beijing100124China Computational Intelligence and Intelligent Systems Beijing key Laboratory Beijing100124China Institute of Remote Sensing and Geographic Information System School of Earth and Space SciencesPeking UniversityBeijing100871China Department of Computer Science University of Pittsburgh15260USA

Plateau forest plays an important role in the high-altitude ecosystem,and contributes to the global carbon *** forest monitoring request in-suit data from field *** recent development of the remote sensing technic,large-scale satellite data become available for surface *** to the various information contained in the remote sensing data,obtain accurate plateau forest segmentation from the remote sensing imagery still remain *** developed deep learning(DL)models such as deep convolutional neural network(CNN)has been widely used in image processing tasks,and shows possibility for remote sensing ***,due to the unique characteristics and growing environment of the plateau forest,generate feature with high robustness needs to design structures with high *** at the problem that the existing deep learning segmentation methods are difficult to generate the accurate boundary of the plateau forest within the satellite imagery,we propose a method of using boundary feature maps for collaborative *** are three improvements in this ***,design a multi input model for plateau forest segmentation,including the boundary feature map as an additional input label to increase the amount of information at the ***,we apply a strong boundary search algorithm to obtain boundary value,and propose a boundary value loss ***,improve the Unet segmentation network and combine dense block to improve the feature reuse ability and reduces the image information loss of the model during *** then demonstrate the utility of our method by detecting plateau forest regions from ZY-3 satellite regarding to Sanjiangyuan nature *** experimental results show that the proposed method can utilize multiple feature information comprehensively which is beneficial to extracting information from boundary,and the detection accuracy is generally higher than several state-of-art algorit

关键词： Remote sensing forest segmentation boundary preserving double loss function

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Approach for Improving Video Transmission Efficiency in WVSN

引用

Journal of Shanghai Jiaotong university(Science) 2020年第5期25卷 600-605页

作者： LIU Min DENG Bin TANG Ying WU Minghu WANG Juan Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System.Hubei University of Technology Wuhan 430068.China Department of Electrical and Computer Engineering.Rowan University GlassboroNJ 08028USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Smart Education Qingdao Academy of Intelligent IndustriesQingdao 266041ShandongChina

The wireless visual sensor network(WVSN)as a new emerged intelligent visual system,has been applied in many video monitoring ***,there is still great challenge because of the limited wireless network *** resolve the problem,we propose a real-time dynamic texture approach which can detect and reduce the temporal redundancy during many successive image ***,an adaptively learning background model is improved to discover successive similar image frames from the inputting video ***,the dynamic texture model based on the singular value decomposition is adopted to distinguish foreground and background element ***,a background discarding strategy based on visual motion coherence is proposed to determine whether each image frame is streamed or *** evaluate the trade-off performance of the proposed method,it is tested on the CDW-2014 dataset,which can accurately detect the first foreground frame when the moving objects of interest appear in the field of view in the most tested dynamic scenes,and the misdetection rate of the undetected foreground frames is near to *** to the original stream,it can reduce the occupied bandwidth a lot and its computational cost is relatively lower than the state-of-the-art methods.

关键词： wireless visual sensor network(WVSN) temporal redundancy foreground background dynamic texture

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Model-Based Sequential Algorithm for Weather-Dependent Probabilistic Power Flow With High Calculation Efficiency

TechRxiv

引用

TechRxiv 2023年

作者： Zhang, Haochen Lin, Xingyu Peng, Sui Tang, Junjie Ponci, Ferdinanda Monti, Antonello Electrical and Computer Engineering Department University of California Los Angeles90095 United States State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing400044 China Grid Planning and Research Center Guangdong Power Grid Corporation CSG Guangzhou510080 China Institute for Automation of Complex Power Systems E.ON Energy Research Center RWTH Aachen University Aachen52074 Germany Digital Energy Fraunhofer FIT Aachen52072 Germany

Recently, a novel power flow model called weather dependent power flow (WDPF) has been proposed to incorporate conductor temperatures in power flow calculation. It is promising to adopt WDPF model in probabilistic analysis since it provides more accurate electrical and thermal states of a power system. However, calculation of the WDPF model is more computationally expensive than that of conventional power flow model, and hence repetitive calculation of the WDPF in probabilistic analysis is quite time-consuming. To overcome this challenge, a surrogate-model-based sequential algorithm is proposed for calculation of the WDPF model with high computational efficiency and good accuracy. Compared to the method that directly learns the whole WDPF model, the proposed method only learns the power flow sub-model whereas applies a linearization method to solve the thermal resistance sub-model. The construction of the proposed method considers the learning difficulty of the sub-model and the whole WDPF model, thus ensuring the high calculation accuracy. This study is the first to conduct a probabilistic power flow analysis based on the WDPF model. Numerical results in the IEEE 30-bus, 57-bus, and 118-bus systems demonstrate the importance of adopting the WDPF model in probabilistic analysis and the efficacy of the proposed method. © 2023, CC BY.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Learning to Branch in Combinatorial Optimization with Graph Pointer Networks

arXiv

引用

arXiv 2023年

作者： Wang, Rui Zhou, Zhiming Zhang, Tao Wang, Ling Xu, Xin Liao, Xiangke Li, Kaiwen The College of Systems Engineering National University of Defense Technology Changsha410073 China The Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKLMSI2T Changsha410073 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Intelligence Science and Technology National University of Defense Technology Changsha410073 China Department of Automation Tsinghua University Beijing100084 China The College of Computer Science and Technology National University of Defense Technology Changsha410073 China

Branch-and-bound is a typical way to solve combinatorial optimization problems. This paper proposes a graph pointer network model for learning the variable selection policy in the branch-and-bound. We extract the graph features, global features and historical features to represent the solver state. The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions. The model is trained to imitate the classic strong branching expert rule by a designed top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. Our approach also outperforms the state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances. Copyright © 2023, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery

arXiv

引用

arXiv 2025年

作者： Li, Yansheng Wu, Yuning Cheng, Gong Tao, Chao Dang, Bo Wang, Yu Zhang, Jiahao Zhang, Chuge Liu, Yiting Tang, Xu Ma, Jiayi Zhang, Yongjun Information and computing science from Shandong University Weihai China Pattern recognition and intelligent system from the Huazhong University of Science and Technology Wuhan China Computer science and technology from Wuhan University Wuhan China Xidian University Xi’an China Pattern recognition and intelligent systems from Northwestern Polytechnical University Xi’an China School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China Institute for Pattern Recognition and Artificial Intelligence Huazhong China University of Science and Technology Remote sensing science and technology from Wuhan University Wuhan China School of Remote Sensing and Information Engineering Wuhan University Wuhan China Electronic circuit and system from Xidian University Xi’an China University of Colorado at Boulder BoulderCO United States Control science and engineering from the Huazhong University of Science and Technology Wuhan China Geodesy and photography from Wuhan University Wuhan China

Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-in-scene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for fine-grained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://***/project/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Learning Convolutional Neural Network Approach for Network Robustness Prediction

arXiv

引用

arXiv 2022年

作者： Lou, Yang Wu, Ruizi Li, Junli Wang, Lin Li, Xiang Chen, Guanrong The Department of Computing and Decision Sciences Lingnan University Hong Kong The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The College of Computer Science Sichuan Normal University Chengdu610066 China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201210 China The Department of Control Science and Engineering Tongji University Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

Network robustness is critical for various societal and industrial networks again malicious attacks. In particular, connectivity robustness and controllability robustness reflect how well a networked system can maintain its connectedness and controllability against destructive attacks, which can be quantified by a sequence of values that record the remaining connectivity and controllability of the network after a sequence of node- or edge-removal attacks. Traditionally, robustness is determined by attack simulations, which are computationally very time-consuming or even practically infeasible. In this paper, an improved method for network robustness prediction is developed based on learning feature representation using convolutional neural network (LFR-CNN). In this scheme, higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction. Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors;2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability;3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations;4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures. © 2022, CC BY.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Unified resilience model using deep learning for assessing power system performance

引用

Heliyon 2025年第4期11卷 e42802页

作者： Artemchuk, Volodymyr Garbuz, Iurii Jamil Alsayaydeh, Jamil Abedalrahim Shkarupylo, Vadym Oliinyk, Andrii Bin Yusof, Mohd Faizal Herawan, Safarudin Gazali Department of Mathematical and Econometric Modelling G.E. Pukhov Institute for Modelling in Energy Engineering of the NAS of Ukraine Kyiv Ukraine Department of Environmental Protection Technologies and Radiation Safety Center for Information-analytical and Technical Support of Nuclear Power Facilities Monitoring of the NAS of Ukraine Kyiv Ukraine Department of Іnformation Systems in Economics Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Department of Computerized Control System National Aviation University Kyiv Ukraine Department of Engineering Technology Fakulti Teknologi Dan Kejuruteraan Elektronik Dan Komputer (FTKEK) Universiti Teknikal Malaysia Melaka (UTeM) Melaka 76100 Malaysia Department of Computer Systems Networks and Cybersecurity of the National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Department of Software Tools Faculty of Computer Science and Technology Zaporizhzhia Polytechnic National University Zaporizhzhia Ukraine Research Section Faculty of Resilience Rabdan Academy Abu Dhabi United Arab Emirates Industrial Engineering Department Faculty of Engineering Bina Nusantara University Jakarta 11480 Indonesia

Energy resilience in renewable energy sources dissemination components such as batteries and inverters is crucial for achieving high operational fidelity. Resilience factors play a vital role in determining the performance of power systems, regardless of their operating environment and interruptions. This article introduces a Unified Resilience Model (URM) using Deep Learning (DL) to enhance power system performance. The proposed model analyzes environmental factors impacting the resilience of batteries and energy storage devices. This deep learning approach trains performance-impacting factors using previously known low resilience drain data. The learning output is utilized to augment various strengthening factors, thereby improving resilience. Drain mitigation and performance improvements are combined for direct impact verification. This process validates the model's fidelity in enhancing power system performance, with a specific focus on the impact of weather factors. © 2025 The Authors

关键词： Deep learning Energy resilience Fidelity Weather impact

来源：评论

学校读者我要写书评

暂无评论

Assessing Time-Optimal Journeys: Combined Routing, Charging and Velocity Strategies for Electric Vehicles

Assessing Time-Optimal Journeys: Combined Routing, Charging ...

引用

2020 Forum on Integrated and Sustainable Transportation systems, FISTS 2020

作者： Cussigh, Maximilian Lochel, Chris Straub, Tobias Hamacher, Thomas Technical University of Munich Chair of Renewable and Sustainable Energy Systems Department of Electrical and Computer Engineering Lichtenbergstraße 4a Garching85748 Germany Technical University of Munich Department of Mathematics Boltzmannstraße 3 Garching85748 Germany Institute of Vehicle System Technology Karlsruhe Institute of Technology Rintheimer Querallee 2 Karlsruhe76131 Germany

ISBN: (数字)9781728195032

ISBN: (纸本)9781728195032

The degree of electrification of vehicle powertrains rose significantly in the last years. For fully electric vehicles particularly longer trips are a problem because of limited range, the necessity to charge and consequently higher travel time. Thus, accurate data on energy consumption, driving and charging options and corresponding routing are critical for long trips. This requires innovations that foster the popularity of battery electric vehicles (BEVs). A combined strategy including route, charging and velocity suggestions can enable seamless use of electric vehicles on long distance trips. Based on a mixed-integer nonlinear program (MINLP) a heuristic approach is shown that calculates route and charger options in heterogeneous networks followed by charging amount and prospective velocities in a time-optimal way. For the comparison of the obtained route-charging-velocity plan, a second dynamic programming (DP) approach is shown. A realistic driving scenario serves for method evaluations. The optimal strategy's aim is a minimum travel time, assuming a predefined final state of charge (SOC). The discussion evaluates both approaches concerning computing time and the obtained results, particularly velocity and charging time. The methods' real-time applicability is shown by calculating optimal strategies. © 2020 IEEE.

关键词： Velocity

来源：评论

学校读者我要写书评

暂无评论

A novel Skin lesion prediction and classification technique: ViT-GradCAM

引用

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI) 2024年第9期30卷 e70040页

作者： Muhammad Shafiq Kapil Aggarwal Jagannathan Jayachandran Gayathri Srinivasan Rajasekhar Boddu Adugna Alemayehu School of Information Engineering Qujing Normal University Qujing China. Key Laboratory of Intelligent Sensor and System Design College of Information Engineering Qujing Normal University Qujing China. Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India. Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Katpadi Vellore India. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India. Department of AIML Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Hyderabad India. Lecturer in Software Engineering Wachemo University Hosaina Ethiopia.

BACKGROUND:Skin cancer is one of the highly occurring diseases in human life. Early detection and treatment are the prime and necessary points to reduce the malignancy of infections. Deep learning techniques are supplementary tools to assist clinical experts in detecting and localizing skin lesions. Vision transformers (ViT) based on image segmentation classification using multiple classes provide fairly accurate detection and are gaining more popularity due to legitimate multiclass prediction capabilities. MATERIALS AND METHODS:In this research, we propose a new ViT Gradient-Weighted Class Activation Mapping (GradCAM) based architecture named ViT-GradCAM for detecting and classifying skin lesions by spreading ratio on the lesion's surface area. The proposed system is trained and validated using a HAM 10000 dataset by studying seven skin lesions. The database comprises 10 015 dermatoscopic images of varied sizes. The data preprocessing and data augmentation techniques are applied to overcome the class imbalance issues and improve the model's performance. RESULT:The proposed algorithm is based on ViT models that classify the dermatoscopic images into seven classes with an accuracy of 97.28%, precision of 98.51, recall of 95.2%, and an F1 score of 94.6, respectively. The proposed ViT-GradCAM obtains better and more accurate detection and classification than other state-of-the-art deep learning-based skin lesion detection models. The architecture of ViT-GradCAM is extensively visualized to highlight the actual pixels in essential regions associated with skin-specific pathologies. CONCLUSION:This research proposes an alternate solution to overcome the challenges of detecting and classifying skin lesions using ViTs and GradCAM, which play a significant role in detecting and classifying skin lesions accurately rather than relying solely on deep learning models.

关键词： Grad‐CAM Multi‐Headed Self attention (MSA) linear patch projection multilayer perceptron (MLP) skin lesion transformer encoder vision transformer (ViT)

来源：评论

学校读者我要写书评

暂无评论

A Compact Low Power AI Module Mounted on Drone for Plant Monitor system 8

A Compact Low Power AI Module Mounted on Drone for Plant Mon...

引用

8th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2019

作者： Kobayashi, Tomoki Yokogawa, Tomoyuki Igawa, Nao Sato, Yoichiro Fujii, Satoshi Arimoto, Kazutami Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Computer Science and System Engineering Okayama Prefectural University Soja Okayama Japan Information and Communication Systems Engineering National Institute of Technology Okinawa College Nago Okinawa Japan

This paper describes the compact and low power AI DNN discriminator which is mounted on the small drone like a hobby type. By adopting this AI module, the effective plant monitoring system using the drone has been ach... 详细信息

ISBN: (纸本)9781728126272

关键词： Energy efficiency

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：