检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Lin, Xinru Shi, Liwei Guo, Shuxiang Beijing Institute of Technology School of Medical Technology Beijing100081 China School of Life Science Beijing Institute of Technology Beijing100081 China Ministry of Industry and Information Technology Key Laboratory of Convergence Medical Engineering System and Healthcare Technology Beijing Institute of Technology Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

With the increased demand for the exploration of the ocean, the focus of research in the field of robotics has changed. Amphibious robots show broad application prospects. In order to design an amphibious robot adapted to multiple environments, a feet-legs device inspired by natatores was designed. Each webbed foot is made up of three sets of four-linked rods that allow the toe bones to fold and shrink, enabling better imitation of the webbed feet motion of natatores paddling. In order to analyse and optimize the mechanical strength of the critical components of the device during operation, static analysis and structural improvements are made to the webbed feet and the roller of the cylindrical cam. The results show that the static strength of improved webbed feet and the cam roller meet the requirements. © 2023 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Improved Deep Matrix Factorization for Signal Recovery in Random Frequency Diversity Array Radar 2

Improved Deep Matrix Factorization for Signal Recovery in Ra...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Guo, Dayan Lin, Zijian Huang, Tianyao Qi, Yue He, Jie Zhang, Xiao-Ping Wang, Xueqian Li, Gang University of Science and Technology Beijing School of Computer & Communication Engineering Beijing China Tsinghua Shenzhen International Graduate School Institute of Data and Information Shenzhen China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9798331515669

Motivated by the success of recent deep learning researches on radar, we consider a deep learning based matrix factorization method for suppressing the high range-angle side-lobes in random frequency diversity array (FDA) radars. While the existing deep matrix factorization approach is designed for real-valued situations and signals of FDA radars are complex-valued cases, we propose two methods to extend the existing approach into complex-valued framework: 1) adjusting the neural network structures and activation functions for complex-valued operations, and 2) constructing a real-valued representation of the original complex-valued input. Simulation results demonstrate that the proposed methods outperform traditional ones in multi-target scenarios. © 2024 IEEE.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Deep Moore-Penrose Inverse Network with Refinement Strategy for One-class Classification

Deep Moore-Penrose Inverse Network with Refinement Strategy ...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Gao, Junna Kong, Dehui Yin, Baocai Lin, Weisi Zhang, Wandong Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Western University Department of Electrical and Computer Engineering London Canada

ISBN: (纸本)9798350337020

Multilayer least-square (LS)-based one-class classification networks (MLS-OCNs) have gained great attention for the purpose of identifying anomalies and outliers. However, many MLS-OCNs encounter the issue of loosely connected feature coding because they use two separate mechanisms for feature encoding and final pattern recognition. This paper proposes a solution to this problem by introducing a multilayer algorithm called deep Moore-Penrose inverse network with refinement (DMPINR). In particular, DMPINR employs an end-to-end learning process based on the Moore-Penrose inverse (MPI) to identify optimal latent space and classify objects simultaneously. To enhance the robustness of representations, the DMPINR technique pulls back the residual error from the output layer to the hidden layers sequentially, recalculating the parameters of these hidden layers using MPI. The experimental results on ten popular OCC datasets demonstrate that the proposed approach outperforms many existing MLS-OCNs in G-Mean and F1 scores. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Landscape Patterns in Mining Cities Influenced by Extraction and Terrain Features

Landscape Patterns in Mining Cities Influenced by Extraction...

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Madhavan, K. Babu, J.Jai Jaganath Karthikeyan, P. Centre for System Design Chennai Institute of Technology Department of Computer Science & Engineering Tamil Nadu Chennai600 069 India Centre for System Design Chennai Institute of Technology Department of Biomedical Engineering Tamil Nadu Chennai600 069 India

ISBN: (纸本)9798350348910

The combined influence of mining activities and the underlying terrain gradient has caused significant transformations in the landscape patterns of mining cities. The natural topography being altered by mining operations can result in a distinct evolution in the spatial arrangement and ecological dynamics of these cities. Spatial heterogeneities are influenced by factors such as extraction techniques, waste disposal methods, and infrastructure development. The inherent terrain gradient heavily influences the distribution of mining sites and urban expansion patterns. This research underscores the intricate interplay between human-induced activities and natural topographical features in shaping the landscape of mining cities. The development of resilient communities in areas that are evolving due to mining requires a clear understanding of these dynamics for sustainable urban planning, environmental conservation, and community development. © 2023 IEEE.

关键词： Waste disposal

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Reinforcement Learning for Intrusion Detection in UAVs

引用

computers, Materials & Continua 2022年第2期70卷 2639-2653页

作者： V.Praveena A.Vijayaraj P.Chinnasamy Ihsan Ali Roobaea Alroobaea Saleh Yahya Alyahyan Muhammad Ahsan Raza Department of Computer Science and Engineering Dr.N.G.P Institute of TechnologyCoimbatore641048India Department of Information Technology Vignan’s Foundation for ScienceTechnology&ResearchGuntur522213India Department of Information Technology Sri Shakthi Institute of Engineering and TechnologyCoimbatore641062India Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science Community College in DwadmiShaqra University11961Saudi Arabia Department of Information Technology Bahauddin Zakariya UniversityMultan60000Pakistan

In recent years,progressive developments have been observed in recent technologies and the production cost has been continuously *** such scenario,Internet of Things(IoT)network which is comprised of a set of Unmanned Aerial Vehicles(UAV),has received more attention from civilian tomilitary *** network security poses a serious challenge to UAV networks whereas the intrusion detection system(IDS)is found to be an effective process to secure the UAV *** IDSs are not adequate to handle the latest computer networks that possess maximumbandwidth and data *** order to improve the detection performance and reduce the false alarms generated by IDS,several researchers have employed Machine Learning(ML)and Deep Learning(DL)algorithms to address the intrusion detection *** this view,the current research article presents a deep reinforcement learning technique,optimized by BlackWidow Optimization(DRL-BWO)algorithm,for UAV *** addition,DRL involves an improved reinforcement learning-based Deep Belief Network(DBN)for intrusion *** parameter optimization of DRL technique,BWO algorithm is *** helps in improving the intrusion detection performance of UAV *** extensive set of experimental analysis was performed to highlight the supremacy of the proposed *** the simulation values,it is evident that the proposed method is appropriate as it attained high precision,recall,F-measure,and accuracy values such as 0.985,0.993,0.988,and 0.989 respectively.

关键词： Intrusion detection UAV networks reinforcement learning deep learning parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Image Transformation Using Generative Adversarial Network 24th

Cross-Modality Image Transformation Using Generative Adversa...

引用

24th Conference on Man-Machine-Environment system engineering, MMESE 2024

作者： Liu, Haoting Yu, Shiqi Hou, Qingwen Chen, Shuai Guo, Kuiyuan Wang, Xu Li, Qing Beijing Engineering Research Center of Industrial Spectrum Imaging School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China CATARC Technology Co. Ltd. Shenzhen518118 China

ISBN: (纸本)9789819771387

A cross-modality image transformation method using the Generative Adversarial Network (GAN) is proposed in this paper. First, the preprocessing methods are performed to the original image data. The computational steps include adjusting image size and suppressing image noises. Second, a kind of GAN is constructed. Both the generator network and discriminator network are created. Third, the GAN is trained and the back propagation optimization is performed continuously. Finally, the trained GAN can be used for data enhancement. To test the effects of computational steps above, the image transformation from the visible light image to other noise-contaminated image is performed. Lots of experiments have illustrated the correctness of our method. © beijing KeCui Man-Machine-Environment system engineering technology Research Academy 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Structure-Aware Conversational Legal Case Retrieval

引用

ACM Transactions on Information systems 2025年第3期43卷 1-28页

作者： Liu, Bulou Hu, Yiran Ai, Qingyao Wu, Yueyue Liu, Yiqun Li, Chenliang Zhang, Fan Shen, Weixing Chen, Chong Tian, Qi Quan Cheng Laboratory Department of Computer Science and Technology Institute for Internet Judiciary Tsinghua University and School of Law Tsinghua University Beijing China School of Cyber Science and Engineering Wuhan University Wuhan China School of Information Management Wuhan University Wuhan China School of Law Tsinghua University Beijing China Huawei Cloud BU Beijing China

Legal case retrieval is an important task in information retrieval that aims to retrieve relevant cases for given query cases. Conversational search paradigms have been shown to improve the search experience in legal case retrieval. However, there are two challenges in applying conversational search to legal scenarios. Firstly, legal search conversations often focus on different parts of legal case documents, but existing models struggle to capture the complex structural information and extract accurate relevance signals. Secondly, collecting large-scale conversational search datasets is costly, making it difficult to build reliable conversational legal case retrieval models. To address these challenges, we propose a Structure-Aware Matching Model (SAMM) for conversational legal case retrieval. SAMM extracts matching signals between conversational utterances and segments of the legal cases to incorporate structural information. We decouple the conversational search task into three subtasks and design pre-training tasks to overcome the lack of training data. Additionally, we create ConvLegal, the largest conversational legal case retrieval dataset to the best of our knowledge, for better evaluation of different methods. We train and evaluate SAMM and baselines on both a public dataset (CLCR) and ConvLegal. Experimental results demonstrate that SAMM outperforms existing models in legal case retrieval and conversational search. © 2025 Copyright held by the owner/author(s).

关键词： Online searching

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multi-Source Domains Adaptation with Locally Topological Persevering

Unsupervised Multi-Source Domains Adaptation with Locally To...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Zhifeng Wang, Lvda Li, Ying Ying, Shihui College of Science Shanghai University Department of Mathematics China Beijing Institute of Computer Technology and Applications China College of Computer Engineering and Science Shanghai University China

ISBN: (纸本)9798350303759

Most existing unsupervised domain adaptation (UDA) methods primarily focus on single-source and single-target domain scenarios, referred to as single-source unsupervised domain adaptation. However, in practical applications, it is often possible to collect labeled data from multiple distinct source domains, which not only differ from the target domain but also exhibit dissimilarities among themselves. As a result, the concept of multi-source unsupervised domain adaptation has emerged. While mainstream UDA techniques aim to align features between two domains, addressing domain shift solely through feature alignment might prove inadequate, potentially undermining the inherent structure of the data. To mitigate this risk, this paper introduces a method called Locally Topology Preserving Multi-Source Unsupervised Domain Adaptation (LTP- MDA). By performing clustering on both source and target data, distinct clusters are formed. During the domain-adaptive feature transformation, this method ensures the preservation of the structural integrity of these clusters throughout the transformation. Additionally, due to the possibility of misclassification during the clustering process, we leverage consistency weights derived from genuine labels in the source domain and pseudo-labels in the target domain to guide the clustering process. Experimental results demonstrate the remarkable performance of our approach across various cross-domain adaptation tasks. We extensively evaluate our method on three benchmark datasets, validating its effectiveness and robustness. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Advancing general robotic manipulation with multimodal foundation models: An embodied AI paradigm

引用

science China(Technological sciences) 2025年第5期68卷 290-292页

作者： Shifeng HUANG He WANG Xing ZHOU Wenkai CHEN Haibin YANG Jianwei ZHANG Department of Mechanical and Aerospace Engineering Hong Kong University of Science and TechnologyHong Kong 999077China Foshan Institute of Intelligent Equipment Technology Foshan 528234China Foshan Huashu Robot Co. Ltd.Foshan 528234China Center on Frontiers of Computing Studies(CFCS) School of Computer SciencePeking UniversityBeijing 100871China Beijing Academy of Artificial Intelligence Beijing 100084China Department of Informatics Universität HamburgHamburg 20146Germany

Can current robotic technologies truly replicate the full scope and intricacies of human labour?In practice,the adoption of robots remains limited,especially in open,unstructured environments commonly encountered in everyday scenarios such as services,healthcare,agriculture,construction,and numerous other *** the perspective of general robotic manipulation,the challenges arise from three factors.(1)High operational barriers:human operators are obliged to master specialized robotic programming languages and gain a deep understanding of the tasks at *** tasks need to be broken down into action-level robotic programs,which results in high labour costs.(2)Limited autonomous task execution:robots lack the capability to independently plan and execute actions required to achieve the target *** limitation renders them unsuitable for deployment in open,unstructured environments that demand sophisticated interaction and seamless collaboration with humans.

关键词： multimodal foundation models autonomous task execution robotic manipulationthe general robotic manipulation robotic programming language embodied AI operational barriers robotic technologies

来源：评论

学校读者我要写书评

暂无评论

Refining Object Localization from Dialogues 1

引用

Chinese Intelligent Automation Conference, CIAC 2023

作者： Kang, Xueze Wu, Lei Lu, Lingyun Liu, Huaping Department of Computer Science and Technology Tsinghua University Beijing China Nanjing Research Institute of Electronic Engineering Nanjing China

ISBN: (数字)9789819961870

ISBN: (纸本)9789819961863

The ability to locate objects accurately is crucial for robots’ application in large-scale environments. However, objects’ location changes constantly in practical scenes, so the robot’s knowledge of objects’ distribution needs to update correspondingly. We propose a method to refine objects’ location from dialogues between humans and robots. When a robot is searching for an object, if the information about the object’s location is insufficient, it constantly raises questions to a human informer until it acquires adequate location information. Furthermore, every possible target object found during the searching process is photographed and sent back to the human informer for judgment. If all possible locations have been searched and the target is not found, the robot requests more specific location information and starts a new search attempt after attaining the information. The interaction process repeats iteratively until the robot finally finds the target. The interactions with humans ensure the success and accuracy of searching. We deploy our method on a mobile robot and conduct language parsing experiment and locating objects experiment to evaluate the performance of our method. Moreover, we compare our method with a one-time message method from a previous work to demonstrate our advantage. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Robot applications

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：