检索结果-内蒙古大学图书馆

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Junfu Wang Yawen Li Meiyu Liang Ang Li Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing School of Economics and Management Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781665456579

Existing studies for representation learning of homogeneous information networks cannot be applicable to academic heterogeneous information networks (HINs) with multi-type nodes and multi-relationships because of the lack of ability to issue heterogeneity. Meanwhile, due to the closeness and blocking of businesses among different enterprises, there is a serious phenomenon of data islands. To solve the above challenges, we proposed an academic heterogeneous information network embedding representation learning method based on federated learning (FedAHE), which utilizes node attention and meta path attention mechanism to learn low-dimensional, dense and real-valued vector representations while preserving the rich topological information and meta-path-based semantic information of nodes in network. Moreover, we combined federated learning with the representation learning of academic HINs and put forward a federal training mechanism based on dynamic weighted aggregation of parameters (FedDWA) to optimize the node embeddings of HINs. Through sufficient experiments, the efficiency, accuracy and feasibility of our proposed framework are demonstrated.

关键词： Representation learning Training Cloud computing Federated learning Semantics Intelligent systems Business

来源：评论

学校读者我要写书评

暂无评论

Design of a Lower Limb Exoskeleton Rehabilitation Robot System Based on Forward Dynamics Simulation

Design of a Lower Limb Exoskeleton Rehabilitation Robot Syst...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Yudong Fang Yuefei Wang Liucun Zhu Zhen Liu Lei Shi Muxin Du Jianchu Lin School of Mechanical and Marine Engineering Beibu Gulf University Qinzhou China Sentinel Institute of Science and Technology Beibu Gulf University Qinzhou China Nagasaki Institute of Applied Science Nagasaki Japan Guangzhou Shiyuan Electronic Technology Company Limited Guangzhou China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai'an China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Lower limb exoskeleton rehabilitation robots can effectively improve the rehabilitation of stroke patients and can substantially reduce the workload of rehabilitation therapists and improve work efficiency. In this paper, we propose a method to investigate the influence of muscle groups on the hip joint during the gait cycle through kinetic modeling simulation. The method is validated using electromyographic signals (EMG). The patients are treated according to their gait characteristics. Simulation with OpenSim; optimisation by Scone controller; joint motion change curves were analysed by Matlab simulation to verify the correctness of the mathematical model, and the simulation showed excellent following effect. The feasibility of the theory is verified, and a new scheme is proposed for the treatment of stroke patients.

关键词： Limbs Exoskeletons Stroke (medical condition) Muscles Assistive robots Mathematical models Kinetic theory MATLAB Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

DDA: A Dynamic Difficulty-aware Data Augmenter for Image Super-resolution

DDA: A Dynamic Difficulty-aware Data Augmenter for Image Sup...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xinyi Zhang Tao Dai Bin Chen Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University College of Computer Science and Software Engineering Shenzhen University Harbin Institute of Technology Shenzhen Peng Cheng Laboratory Research Center of Artificial Intelligence

Deep neural networks (DNNs) have been recently widely used in image super-resolution (SR) and have achieved remarkable performance. However, most existing methods focus on elaborate network design, while rarely considering the training strategy, which affects the model performance and training efficiency. In practice, most SR methods still train the networks with the commonly-used data augmentation (e.g., random crop and sampling), which is shown to converge slowly for deep SR networks. To address this issue, in this paper, we propose a dynamic difficulty-aware data augmenter, named DDA, by considering the restoration difficulty and distribution of input patches. Our DDA mainly consists of difficulty-aware divider, dynamic sampler, and adaptive re-weighter. Specifically, our DDA first uses the difficulty-aware divider to divide the input image into small over-lapping patches, followed by classification into $N$ different classes based on the restoration difficulty. Next, dynamic sampler samples the training patches from each class with probability based on training loss. Furthermore, to remedy the imbalance of training patches between different classes, adaptive re-weighter updates the weight of each training patch according to the accumulated training loss. Extensive experiments demonstrate the effectiveness of our DDA on different SR methods by improving training efficiency and model performance across a wide range of scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated information mining in hazardous chemical accident reporting: An improved deep learning approach

引用

Journal of Loss Prevention in the Process Industries 2025年 97卷

作者： Zhao, Kai Wan, Lining Lu, Xilei Zhao, Jun Chen, Fei He, Miao Gao, Jinhao Wang, Qibo Zhang, Linlin Zhang, Li School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Uygur Autonomous Region Academy of Safety Science and Technology Urumqi830011 China Xinjiang Yihua Chemical Co. Changji Hui Autonomous Prefecture 831100 China School of Chemical Engineering and Technology Xinjiang University Urumqi830017 China School of Software Xinjiang University Urumqi830000 China

Mining and accumulating lessons learned from incident reports, accurately identifying and extracting accident knowledge, can help managers recognize patterns, analyze common attributes, and thus prevent the recurrence of similar incidents. Due to the limitations of unstructured or semi-structured text records, current hazardous chemical accident research heavily relies on expert evaluations, often resulting in inefficiency, lack of intelligence, and subjectivity. To overcome this limitation, we propose an accident analysis framework that combines deep learning-based Named Entity Recognition (NER) and topic mining algorithms. First, we employ a RoBERTa-BiLSTM-Attention-CRF method based on a pre-trained model to automatically recognize and extract information from accident reports according to predefined accident entities. Second, we construct a dictionary specific to the hazardous chemicals domain and apply the Latent Dirichlet Allocation (LDA) model to analyze the causes of accidents within the "CAUSE" entity, thereby deriving the hazardous themes implied in the accidents. Finally, we validate the model on a self-constructed hazardous chemical named entity recognition incident report dataset (HCNER). The research findings indicate that the methodology proposed in this study effectively addresses the challenges associated with dispersed textual information, specialized terminology, and data formatting in the digital processing of hazardous chemical incidents. This advancement propels the development within the domain of hazardous chemical safety management and serves as a viable approach for investigating the causes of such incidents. © 2025 Elsevier Ltd

关键词： Chemical hazards

来源：评论

学校读者我要写书评

暂无评论

A Virtual Farm Tour for Public Education about Dairy Industry

A Virtual Farm Tour for Public Education about Dairy Industr...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Anh Nguyen Emma Windfeld Michael Francis Guillaume Lhermie Kangsoo Kim Department of Computer Science University of Calgary The Simpson Centre The School of Public Policy University of Calgary Department of Electrical and Software Engineering University of Calgary The Simpson Centre Faculty of Veterinary Medicine University of Calgary

In this paper, we present an immersive virtual farm simulation developed to provide realistic on-farm experiences to the public. Users could visit the virtual farm, walk through various sites where dairy cows are raised, and learn how the dairy products are produced through the virtual experience. Public users' responses about the virtual experience were collected in various measures, e.g., user experience and learning efficacy, via showcases at local libraries. We present preliminary results regarding the potential of the simulation as an effective agricultural education, and discuss our future plans.

关键词： Industries Solid modeling Three-dimensional displays Dairy products Conferences Virtual reality User interfaces

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

Adaptive Sparse Convolutional Networks with Global Context E...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Bowei Du Yecheng Huang Jiaxin Chen Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse convolution, which proves effective in balancing the accuracy and efficiency. Nevertheless, it suffers from inadequate integration of contextual information of tiny objects as well as clumsy control of the mask ratio in the presence of foreground with varying scales. To address the issues above, we propose a novel global context-enhanced adaptive sparse convolutional network (CEASC). It first develops a context-enhanced group normalization (CE-GN) layer, by replacing the statistics based on sparsely sampled features with the global contextual ones, and then designs an adaptive multi-layer masking strategy to generate optimal mask ratios at distinct scales for compact foreground coverage, promoting both the accuracy and efficiency. Extensive experimental results on two major benchmarks, i.e. VisDrone and UAVDT, demonstrate that CEASC remarkably reduces the GFLOPs and accelerates the inference procedure when plugging into the typical state-of-the-art detection frameworks (e.g. RetinaNet and GFL V1) with competitive performance. Code is available at https://***/Cuogeihong/CEASC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Natural Language Explanation for Autonomous Navigation

Natural Language Explanation for Autonomous Navigation

引用

Conference on Digital Avionics Systems (DASC)

作者： Lena Trigg Brandon Morgan Alexander Stringer Lacey Schley Dean F. Hougen School of Computer Science University of Oklahoma Norman Oklahoma USA 76 Software Engineering Group United States Air Force Oklahoma City Oklahoma USA Oklahoma Aerospace Defense Innovation Institute University of Oklahoma Norman Oklahoma USA

ISBN: (数字)9798350349610

ISBN: (纸本)9798350349627

Navigating an aircraft is a complicated problem as it requires analyzing extensive operational data to identify an optimal and safe path. Recently, many studies have employed deep reinforcement learning (DRL) to address the navigation problem, and it has been demonstrated to be a powerful tool for addressing these kinds of problems. Despite being a promising tool, the opaque nature of the reasoning mechanisms of DRL methods make them difficult to troubleshoot performance issues and fosters mistrust, thereby constraining their application in critical scenarios. This deficiency necessitates the need for the development of explanation methods aimed at clarifying the reasoning processes of DRL models for users. Additionally, governments around the world are beginning to require the inclusion of such explanation methods in autonomous systems used for safety critical applications. In this paper, we propose NavChat, an explanation framework designed to justify the trajectory suggested by a trained DRL model for an efficient and safe path in an unknown environment. NavChat is a post-hoc approach that leverages SHapley Additive exPlanations (SHAP), a Large Language Model (LLM), and prompt engineering to generate natural language explanations. Using SHAP, we identify the most important features that affect the agent's decision. The LLM provides natural language explanations which facilitate faster comprehension and more lucidity for non-expert users in comparison with visual explanations. We compare the explanations provided by NavChat for various prompts and then evaluate the accuracy and consistency of its explanations via a user study. This method facilitates understanding of the decisions made by the automated navigation model and communicates the reasoning process.

关键词： Visualization Large language models Natural languages Government Deep reinforcement learning Cognition Aircraft navigation Trajectory Safety Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning-Based Method for Real-Time Face Spoof Detection

SSRN

引用

SSRN 2023年

作者： Malik, Muhammad Amir Mazhar, Tehseen Haq, Inayatul Shahzad, Tariq Ghadi, Yazeed Yaseen Mallek, Fatma Hamam, Habib Department of Computer Science and Software Engineering International Islamic Unversity Islamabad44000 Pakistan Department of Computer Science Virtual University of Pakistan Lahore55150 Pakistan School of Information Engineering Zhengzhou University Zhengzhou450001 China Department of Computer Sciences COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan Department of Computer Science and Software Engineering Al Ain University Abu Dhabi15322 United Arab Emirates Faculty of Engineering University of de Moncton MonctonNBE1A3E9 Canada National College Of Business Administration & Economics Canada

This research aims to improve the detection accuracy of face spoof recognition systems by employing a hybrid model of machine learning and computer vision-based approaches. Differences, including Decision Tree, Nave Bayes, K-nearest Neighbor, Support Vector Machine, Convolutional Neural Network (CCN), and Recurrent Neural Networks are used for face spoof detection. For face spoof detection, the proposed model is a hybrid variant of the CNN-based classifier used in the proposed face spoof detection model. This study improves real-time face fake detection using machine learning and computer vision. The proposed system is based on a CNN-based classification approach with optimized hyper parameters that detect real-time face spoofing attacks using print, video, and repeat attacks, improving detection accuracy. IDIAP, USSA & and MSFD datasets are used in the simulation;the proposed model has achieved a maximum accuracy of 87.5%. a high sensitivity score of 92.45%,. © 2023, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Rocket Sensor Data Prediction Based on LSTM with Attention Mechanism 2

Rocket Sensor Data Prediction Based on LSTM with Attention M...

引用

2nd IEEE International Conference on Big Data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2021

作者： Liao, Guorui Yang, Wei Wang, Kun He, Ruimeng You, Tao Launching Test and Control Xichang Satellite Launch Center Xichang China System Software Engineering China Academy of Launch Vehicle Technology Beijing China Northwestern Polytechnical University School of Software Xi'an China Northwestern Polytechnical University School of Computer Science Xi'an China

ISBN: (纸本)9780738131221

Accurately predicting the sensor data of the rocket in the future for a period of time from historical rocket sensor data is of great significance to make corresponding control adjustments in time and prevent major danger. Traditional linear models are difficult to solve multi-variable or multi-input problems, while neural networks such as LSTM are skilled at handling multivariable problems. This feature makes it helpful to solve time series prediction problems. This paper proposes a method for rocket sensor data prediction, which uses the attention mechanism and recurrent neural network to predict. It is verified that the average absolute error of this method for rocket sensor data prediction is only 1.38%, and it has strong applicability and accuracy in predicting the rocket attitude. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

SCALABLE EDGE BLOCKING ALGORITHMS FOR DEFENDING ACTIVE DIRECTORY STYLE ATTACK GRAPHS :A PREPRINT

arXiv

引用

arXiv 2022年

作者： Guo, Mingyu Ward, Max Neumann, Aneta Neumann, Frank Nguyen, Hung School of Computer Science University of Adelaide Australia School of Physics Maths and Computing Computer Science and Software Engineering University of Western Australia Australia Department of Molecular and Cellular Biology Harvard University CambridgeMA United States

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment naturally describes an attack graph where nodes represent computers/accounts/security groups, and edges represent existing accesses/known exploits that allow the attacker to gain access from one node to another. Motivated by practical AD use cases, we study a Stackelberg game between one attacker and one defender. There are multiple entry nodes for the attacker to choose from and there is a single target (Domain Admin). Every edge has a failure rate. The attacker chooses the attack path with the maximum success rate. The defender can block a limited number of edges (i.e., revoke accesses) from a set of blockable edges, limited by budget. The defender’s aim is to minimize the attacker’s success rate. We exploit the tree-likeness of practical AD graphs to design scalable algorithms. We propose two novel methods that combine theoretical fixed parameter analysis and practical optimisation techniques. For graphs with small tree widths, we propose a tree decomposition based dynamic program. We then propose a general method for converting tree decomposition based dynamic programs to reinforcement learning environments, which leads to an anytime algorithm that scales better, but loses the optimality guarantee. For graphs with small numbers of non-splitting paths (a parameter we invent specifically for AD graphs), we propose a kernelization technique that significantly downsizes the model, which is then solved via mixed-integer programming. Experimentally, our algorithms scale to handle synthetic AD graphs with tens of thousands of nodes. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：