检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2021

作者： Cai, Hongxia Wang, Cheng Liu, Zhishu Shanghai University Shanghai Key Lab. of Intelligent Mfg. and Robotics School of Mechatronic Engineering and Automation Shanghai China

ISBN: (纸本)9781665428361

Recommendation technologies can help users to solve the problem of information overload. In the academic and educational fields, the application of intelligent recommendation technology has largely improved the effective use of academic resources, especially for researchers whose research tasks are constantly updated by research teams. In this paper, we propose a recommendation method that takes into account the changing stages of researchers' tasks and the needs of researchers' tasks. The recommendation model first considers user task and demand changes over time, introduces the forgetting function based on the Ebbinghaus forgetting curve into user features to create a dynamic user preference matrix, then uses the improved TF-IDF algorithm to extract article features to correlate user task demands with article features to avoid the problem of irrelevance of literature and user tasks, and finally by linear combination of Finally, the similarity between users and the similarity between users and documents is linked to generate a list of document recommendations. The experimental results show that the proposed method can better take into account the phase change of researchers' tasks and the correlation between research tasks and articles, and it is confirmed through experiments that the method has higher recommendation quality than the traditional collaborative filtering method. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Gas Source Localization for UAV Using Infotaxis-Based Three-Dimensional Algorithm and Particle Filtering

Gas Source Localization for UAV Using Infotaxis-Based Three-...

引用

第43届中国控制会议

作者： Duan He Cheng Lei Wang Rong Zhang Yu Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology School of Information Science and Engineering Wuhan University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Unmanned aerial vehicles(UAVs) are extensively utilized in gas source localization tasks due to their payload capacity and maneuverability. This paper presents a UAV gas source localization algorithm that utilizes three-dimensional Infotaxis and particle filter. The algorithm is designed for gas source localization of UAVs in dynamic outdoor airflow *** source localization process comprises UAV search area partitioning, particle filter initialization, observation and update of probability map, entropy calculation and direction selection, particle direction and weight update, and UAV movement. To validate the effectiveness of the algorithm, we build a CFD gas environment and UAV source localization platform, and compare it with traditional Infotaxis-based source localization algorithms. The proposed algorithm based on three-dimensional Infotaxis and particle filter demonstrates higher accuracy.

关键词： infotaxis particle filtering gas source localization olfactory drone path planning

来源：评论

学校读者我要写书评

暂无评论

Truth in the Age of Misinformation: A Dual-Approach Model for Improved Fake News Detection

Truth in the Age of Misinformation: A Dual-Approach Model fo...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Ishan Malik Sanjay Kumar Singh Pranshu Saxena University School of Automation and Robotics Guru Gobind Singh Indraprastha University East Delhi Campus Delhi India Department of Information Technology ABES Engineering College Ghaziabad India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

The inspiration that drives this study is the increase in the prevalence of misinformation, and the need to solve the big challenge of detecting fake news. With the possibility of uncontrolled misinformation disastrously impacting our society, the objective of our study is to make contributions towards the body of knowledge which aims to improve the efficiency and accuracy of current methodologies to detect false information. Although there has been an improvement in the fake news detection systems, their adaptation to real-time applications remains sub-optimal due to the subtle and complex processing involved with handling misinformation. The purpose of this study is to bridge this gap and come up with a better detection model using the Recurrent neural network (RNN) models like Long Short-Term Memory (LSTM) and Bi-directional LSTM (BiLSTM) that will enhance the performance of the existing models, especially in terms of detection accuracy, as the existing systems are weak in the “disagree” category and mostly misclassify it. We use a mix of machine learning algorithms and natural language processing techniques. Integrating LSTM with BiLSTM will analyze textual content at a granular level to find patterns representing fake news. The preliminary results have indicated that our model is performing significantly better than existing ones, with an overall improvement of up to 86.25% in accuracy [15]. However, in the “disagree” category, there are a few challenges faced by the system, reflecting the scope for many improvements in the future. Our research has made a valuable contribution to the knowledge and tools in the area of digital information credibility by providing a strong model that improves detection rates of more subtle cues of misinformation thereby, combating the spread of fake news.

关键词： Training Adaptation models Accuracy Bidirectional long short term memory Real-time systems Natural language processing Reliability Fake news Standards Overfitting

来源：评论

学校读者我要写书评

暂无评论

Intelligent recommendation system based on knowledge graph for scientific research teams 13

Intelligent recommendation system based on knowledge graph f...

引用

13th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2021

作者： Cai, Hongxia Liu, Zhishu Wang, Cheng Shanghai University Shanghai Key Lab. of Intelligent Mfg. and Robotics School of Mechatronic Engineering and Automation Shanghai China

ISBN: (纸本)9781665428361

With the continuous penetration of information technology into scientific research work, information resources with diverse structures have gathered into the scientific research team. Facing the needs of scientific research workers to manage and utilize scientific research resources, we provide a knowledge recommendation platform for university scientific research teams. In the face of multi-source heterogeneous resources in the scientific research field (such as literature data and work record data), we have established a resource knowledge base based on knowledge graph descriptions. In order to realize the effective recommendation of resources, we use the graph neural network model to design a personalized recommendation module while constantly updating our knowledge resources. After actual testing, our resource platform can better knowledge resources and push knowledge content. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

An Intuitive Six-DOF Admittance Control Method for Human-Robot Collaboration

An Intuitive Six-DOF Admittance Control Method for Human-Rob...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yuming Meng Xin Jiang Marten Erik Brelen Yun-Hui Liu School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong HKSAR China Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong HKSAR China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Admittance control is a well-established frame-work for enhancing human-robot collaboration. Although it is widely applied in translational tasks, the a six-degree-of-freedom (6-DOF) admittance control involving the use of a handle in both translational and rotational spaces is rarely addressed in the literature. This paper introduces 6-DOF admittance control method that utilizes a handle equipped with a force/torque sensor mounted on the robotic arm to intuitively farme the operation of the end effector. By transforming the force/torque applied to the handle into the operation of the end-effector while preserving the operator's intent, intuitive 6-DOF admittance control is achieved. To eliminate the operational risks associated with the uncertainty of the hand's contact point on the handle, uncertainty shielding is implemented, ensuring stable force/torque calculations. The effectiveness of the proposed 6-DOF admittance control method is validated through an assembly operation and a specific trajectory operation.

关键词： Uncertainty Biomimetics Human-robot interaction Aerospace electronics Robot sensing systems 6-DOF End effectors Trajectory Admittance control Assembly

来源：评论

学校读者我要写书评

暂无评论

Review of Current Robotic Approaches for Precision Weed Management

引用

Current robotics reports 2022年第3期3卷 139-151页

作者： Wen Zhang Zhonghua Miao Nan Li Chuangxin He Teng Sun Intelligent Equipment and Robotics Lab Department of Automation School of Mechatronic Engineering and Automation Shanghai University Shangda Street No. 99 Baoshan District Shanghai China.

Purpose of Review:The goal of this review is to provide an overview of current robotic approaches to precision weed management. This includes an investigation into applications within this field during the past 5 years, identifying which major technical areas currently preclude more widespread use, and which key topics will drive future development and utilisation. Recent Findings:Studies combining computer vision with traditional machine learning and deep learning are driving progress in weed detection and robotic approaches to mechanical weeding. Integrating key technologies for perception, decision-making, and control, autonomous weeding robots are emerging quickly. These effectively save effort while reducing environmental pollution caused by pesticide use. Summary:This review assesses different weed detection methods and weeder robots used in precision weed management and summarises the trends in this area in recent years. The limitations of current systems are discussed, and ideas for future research directions are proposed.

关键词： Agricultural robotics Deep learning Machine learning Machine vision Precision agriculture Weed detection

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of laser transmission welding of PEEK and CF-PEEK composite pipe fittings

Numerical simulation of laser transmission welding of PEEK a...

引用

2024 8th International Conference on Electrical, Mechanical and Computer engineering (ICEMCE)

作者： Mingqiang Huang Haitao Luo Yuxin Li Yanbin Li School of Mechanical Engineering Shenyang University of Technology Shenyang Liaoning China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Liaoning China

ISBN: (数字)9798331506230

ISBN: (纸本)9798331506247

In order to realize the erection of large structural bodies in space for on-orbit construction, we are looking for the mechanical property parameters in line with the large structural unit body in space. Now based on finite element software for PEEK and CF-PEEK laser transmission welding numerical simulation, study the welding process temperature field, stress field and welding deformation distribution law, after the pre-experiment, from the point of view of numerical simulation of heat transfer to analyze the laser power, spot diameter on the overall impact of the pipe fittings to verify the correctness of the experiment as a whole. The surface of the upper layer of modified transparent PEEK material has no ablation damage, and the average fracture load of the joint in tensile test is 3585 N. The microscopic scale analysis of the three groups of welded pipe fittings is carried out by light microscope scanning, and it is proved that the two materials on the surface of weld fusion area are well fused by the observation of weld morphology with different magnification, and the weld width under the light microscope is compared with that in the simulation to validate the accuracy of the weld model.

关键词： Welding Microscopy Power lasers Fitting Surface morphology Numerical simulation Laser modes Finite element analysis Stress Strain

来源：评论

学校读者我要写书评

暂无评论

Breast Tumor Classification with Fine-Tuned Hyperparameter Training using Deep Learning Models

Breast Tumor Classification with Fine-Tuned Hyperparameter T...

引用

2025 AI-Driven Smart Healthcare for Society 5.0, AdSoc5.0 2025

作者： Maini, Yash Singh, Sanjay Kumar Saxena, Pranshu University School of Automation and Robotics Guru Gobind Singh Indraprastha University East Delhi Campus Surajmal Vihar Delhi110092 India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798331536336

Breast tumor classification plays a crucial role in early detection and treatment planning for breast cancer. In recent years, deep learning models have shown remarkable success in image-based medical diagnosis. This study focuses on improving breast tumor classification using fine-tuned hyperparameter training of deep learning models. By optimizing key parameters such as learning rate, batch size, and network architecture, the classification accuracy of models like ResNet, AlexNet, GoogleNet and VGG is enhanced. The proposed approach leverages advanced techniques such as transfer learning, data augmentation, and hyperparameter optimization algorithms (Bayesian Optimization along with population-based training) to achieve robust performance on breast cancer datasets. The proposed method is able to achieve 98.46% accuracy while classifying breast cancer dataset. Experimental results demonstrate significant improvements in classification accuracy, precision, recall, and F1-score compared to conventional approaches, making the fine-tuned models more suitable for clinical applications. The findings suggest that hyperparameter tuning in deep learning models is critical to improving model performance and generalization in breast tumor classification tasks. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

State estimation with unknown measurement losses: A detector-based approach

引用

Information Sciences 2024年 670卷

作者： Lin, Hong Cai, Chenxiao Lu, Shan Xie, Xiaochen Shi, Peng Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen518055 China School of Automation Nanjing University of Science and Technology Nanjing210094 China School of Mechanical Engineering and Automation Harbin Institute of Technology Guangdong Shenzhen518055 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Guangdong Shenzhen518055 China School of Electrical and Mechanical Engineering the University of Adelaide AdelaideSA5005 Australia

In this paper, we are devoted to solving the problems of designing an estimator, and determining its estimator stability and estimation performance for a system with unknown measurement losses (UML). The solutions to these problems include three steps: first, we design two measurement-loss detectors to detect the measurement losses;Then, we design a detector-based estimator for UML systems. Finally, by analyzing the upper and lower bounds of the covariances of the proposed estimator, we establish a stability condition and determine the estimation performance. Detailed findings and main contributions of this paper are summarized as follows: (i) from the estimator stability perspective, we obtain a necessary and sufficient stability condition. Specifically, the estimator is stable almost surely if and only if the measurement-loss rate is less than a critical value. (ii) From the estimation performance perspective, we prove that under some conditions, the performance of the proposed estimator is almost surely the same as that of the optimal estimator for the system with known measurement losses. © 2024 Elsevier Inc.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Loss Analysis in Spoke Dual-Stator Permanent Magnet Vernier Machine Considering Stator Mutual Effect

Loss Analysis in Spoke Dual-Stator Permanent Magnet Vernier ...

引用

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Wenyuan Mi Jincheng Yu Fei Zhao Zheng Cai Hang Zhao School of Mechanical Engineering and Automation Harbin Institute of Technology (Shenzhen) Shenzhen China Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798350362213

ISBN: (纸本)9798350362220

The phase-shifted spoke array double-stator permanent magnet (DSPM) vernier machine has special merits for its high power factor, while the research on its loss influence principle is limited. In this paper, the mutual effect of stator phase shift on machine loss is revealed by the equivalent circuit based flux-pattern model. By the phase shift, both the ripple and average of the stator analytical air-gap length can be significantly reduced, which is the reason for the reduction of PM loss and rise of iron loss in the PSDSPM machine. And the proposed influence principle is verified by the comparison between PSDSPM and coincident DSPM (CDSPM) machine via finite element analysis (FEA).

关键词： Phased arrays Reactive power Stators Permanent magnets Iron Magnetic analysis Finite element analysis

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：