检索结果-内蒙古大学图书馆

6th IEEE Information Technology, Networking, Electronic and automation Control Conference, ITNEC 2023

作者： Zhang, Tao Hu, Mingming Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China University of Chinese Academy of Sciences Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang Institute of Automation Shenyang China Center for Clinical Studies Data Management Department Beijing China

ISBN: (纸本)9781665460033

Contrastive learning is a self-supervised learning method used to learn the general features of a dataset without labels by letting the model learn which data points are similar or different. It constructs labeled samples through data augmentation. Therefore, the core and difficulty of self-supervised contrastive learning are to construct high-quality contrastive samples, especially negative sample pairs. In this paper, a cluster-based contrast sample selection method is proposed, which selects the positive contrast samples from the same cluster and the negative contrast samples from different clusters. By minimizing the forward contrast sample loss and maximizing the reverse sample loss, the deep representation clustering result of the image is obtained. The experimental results show the excellence and adaptability of the algorithm. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Location Optimization of 3D Printing Filament in the Waveguide to Decrease Mismatch Uncertainty 5

Location Optimization of 3D Printing Filament in the Wavegui...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Zaichenko, Olga Hapon, Nataliia Khoroshailo, Iurii Oleksandrov, Yuriy Shtanko, Valentyna Maksym, Korbetskyi Department of Design and Operation of Electronic Devices Kharkiv National University of Radioelectronics Ukraine Department of Computer-Integrated Technologies Automation and Robotics Kharkiv National University of Radioelectronics Ukraine Philosophy Department Kharkiv National University of Radioelectronics Ukraine

ISBN: (纸本)9798350384499

-The 3D printing filament non destructive testing and measurement of parameters can be carried out using microwave devices at the microwave frequency range. As it is known, vector network analyzers for measurement parameters can be replaced by cheaper devices, scalar network analyzers or six-port reflectometers, one of them is a multiprobe microwave multimeter. The optimization of filament location in the multiprobe microwave multimeter is considered in the report. The location of filament that leads to mismatch uncertainty decreasing is in the circular polarization plane of rectangular waveguide. ©2024 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Chest X-ray Based Pulmonary Disease Classification Using Transfer Learning and CNN

Chest X-ray Based Pulmonary Disease Classification Using Tra...

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Madhu R. Koravanavar Rakesh P. Tapaskar Department of Automation and Robotics KLE Technological University Hubballi Karnataka India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

Pneumonia and Tuberculosis (TB) are the life threatening diseases caused by viral or bacterial infection of the lungs and leads to the severe abnormality of the lungs. Pneumonia infected people, who have direct contact with those having TB are at the highest risk of contracting pulmonary pneumonia tuberculosis. Early diagnosis of the pneumonia avoids the development of TB in the lungs by infection. Therefore, early diagnosis of the diseases results in successful treatment of the disease caused to the patient. Chest X-ray is the most commonly used medical imaging technique to identify the pulmonary diseases. However, lack of radiologists and pulmonologists reduces the applicability of the technique. To overcome such issues, non clinical methods such as machine learning and deep learning techniques plays a vital role in classification of pulmonary diseases. In this work, classification and prediction of pulmonary diseases using Transfer learning and CNN is proposed. The experimentation is performed by using Chest X-ray database for the classification of two types of diseases namely Pneumonia and Tuberculosis further also identify the normal lung. The proposed work is faster and employs multi-class classifier viz. transfer learning and CNN for the lung diseases classification. The MobilenetV2 transfer learning technique outer performs than convolutional neural networks. The MobilenetV2 achieved a promising performance with an accuracy of 97%.

关键词： Deep learning Pneumonia Accuracy Microorganisms Tuberculosis Transfer learning Lung

来源：评论

学校读者我要写书评

暂无评论

Research of Control Methods of a Spherical Parallel Mechanism Using Intelligent Data Processing 5

Research of Control Methods of a Spherical Parallel Mechanis...

引用

5th IEEE International Conference on Modern Electrical and Energy System, MEES 2023

作者： Derkachenko, A. Polyvoda, O. Lebedenko, Yu. Kalinina, K. Kherson National Technical University Automation Robotics and Mechatronics Department Kherson Ukraine Kyiv National University of Technologies and Design Information and Computer Technologies Department Kyiv Ukraine

ISBN: (纸本)9798350359787

The work is devoted to the research and development of a software and hardware platform based on control methods of a spherical parallel mechanism (SPM) with tracking of changes in the position of a human head with the help of a camera and a computer using intelligent data *** article explores the relevance and advantages of SPMs, emphasizing their high precision, enhanced mobility, reliability, and lightweight design. The paper deals with an important aspect of controlling SPMs, which directly influences their performance. The control methods for SPMs vary based on the specific tasks and operational requirements, such as actuator-based control, sensor-based control, closed-loop control, and adaptive control are *** research additionally investigates the problems of forming tasks for SPMs and the need for improved methods, especially for applications involving human-robot interaction, dangerous works, and camera positioning tasks. To resolve these problems, the study proposed a software-hardware platform that remotely controls SPMs by tracking changes in the position of the human head using a camera and a computer. By employing OpenCV and Dilb libraries for face recognition and control point tracking, the proposed platform enables intuitive and clear control of the *** article presents the mathematical operations involved in calculating the rotation angles of the SPM based on the tracked human head movements. The obtained rotation angles serve as inputs for the servomotors, allowing precise control over the mechanism's *** results of the study demonstrate the effectiveness of the proposed software-hardware platform in controlling the SPM based on human head movements. The platform's ability to accurately track and convert head movements into servo rotation values enables remote and intuitive control of the SPM, making it a promising direction for future research in the field of robotics and automation. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

High-Performance Admittance Control of An Industrial Robot Via Disturbance Observer 48

High-Performance Admittance Control of An Industrial Robot V...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Samuel, Kangwagye Haninger, Kevin Oh, Sehoon Dgist Department of Robotics and Mechatronics Engineering Daegu Korea Republic of Fraunhofer Ipk Department of Automation Berlin Germany

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Safe physical interaction using admittance control on an industrial robot with inner-loop motion control remains challenging. This is partly due to the low intrinsic admittance and stability issues from inner-loop motion control limitations (e.g. bandwidth). To increase the admittance at an interaction point with the user/environment, this paper proposes a robust admittance control architecture. A disturbance observer (DOB) is used to improve effective inner-loop motion control, suppressing the effects of velocity disturbances. The DOB uses the robot's closed-loop task space velocity control as the nominal model, compensating disturbances between the commanded robot velocity and realized robot velocity output. An admittance controller uses measured force to generate robot velocity commands. Detailed analyses are carried out to theoretically evaluate the proposed control system. Experiments conducted on a COMAU RACER-7-1.4 industrial robot verify the effectiveness of the proposed admittance control scheme and stability in environmental contact. Moreover, the proposed method is simple to implement on the existing robot system. © 2022 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Humanitarian Technology (HT) Workshop

Humanitarian Technology (HT) Workshop

引用

IEEE International Conference on Signal and Image Processing Applications (ICSIPA)

作者： Shaikh A. Fattah Department of EEE and Director Institute of Robotics and Automation BUET Dhaka Bangladesh

ISBN: (数字)9798350352368

ISBN: (纸本)9798350352375

Humanitarian technology encompasses a wide range of areas aimed at addressing humanitarian challenges to meet the needs of a particular community. The main objective of this workshop is to illustrate the key factors behind designing HT projects utilizing signal processing techniques. Unlike conventional project design, the HT projects need to address various challenges of the local community. Hence, it is very important to properly understand the needs, maximize community engagement with proper stakeholder mapping. Some major signal processing applications in humanitarian technology will be explained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of Computer Vision and 4DOF SCARA Robot Arm for Tomato Sorting

Integration of Computer Vision and 4DOF SCARA Robot Arm for ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Shilpa Tanvashi C B Kolanur P Shri Aakash Tejas Muchchandi Hrithik Dhongadi Akarsh Hirennavar Sanket Aralgundagi Vaibhav Shreyakar Department of Automation and Robotics KLE Technological University Hubballi Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Automating fruit recognition and classification is an important computer vision application that can improve efficiency and consistency in the fruit industry. Manual sorting methods based on visual inspection are tedious, time-consuming, and prone to inconsistencies. This work presents the design and deployment of an automated tomato sorting system that integrates computer vision and robotics. The system classifies tomatoes into three maturity stages (Green, Half-ripe, Ripe) based on color using the YOLOv5 deep learning algorithm. A SCARA robot is used for picking and placing the sorted tomatoes into respective bins. The system demonstrates a fast inference time of 22.31 milliseconds for tomato detection and can sort three tomatoes of different maturity classes in approximately 1.2 seconds on average. This consistent and efficient sorting is based on objective color criteria rather than manual visual inspection. The system can help improve product quality, reduce labor costs, and increase throughput in tomato processing facilities. The approach can be extended to sorting other fruits and vegetables based on color attributes.

关键词： YOLO Computer vision Visualization Service robots Color Manuals Inspection Throughput Quality assessment Sorting

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of artificial neural network for forecasting of fracture toughness of concrete specimens

引用

Asian Journal of Civil Engineering 2024年第6期25卷 4697-4712页

作者： Pathak, Sudhanshu S. Vesmawala, Gaurang R. Mane, Sachin J. Sarnobat, Sandeep S. Department of Civil Engineering D Y Patil College of Engineering Akurdi Pune India Department of Civil Engineering Sardar Vallabhbhai National Institute of Technology Gujarat Surat India Department of Robotics and Automation D Y Patil College of Engineering Akurdi Pune India

Since fracture energy and fracture toughness are directly linked to failure behavior, crack initiation and propagation assumes a significant importance in the study of fracture mechanics. The current study attempts to develop a prediction model for fracture toughness by employing artificial neural network (ANN). Data sets of previous research work obtained from 210 fracture tests have been used to train, test and validate the ANN Model. Experimental results are further used check the feasibility of the model. The test specimen were concrete beams made using Nano TiO₂ (1, 2, 3 and 4%) and ground granulated blast furnace slag (30%). Compressive strength, maximum aggregate size and water to cement ratio are used as input parameters while fracture toughness, tensile strength, Compressive strength and flexure strength are the measured outputs for experimentation. The experimental results indicate the fracture toughness, tensile strength, compressive strength increase with the increase in the NT percentage by 46.15, 10.22, 16.07 and 14.83% respectively. The ANN predicted values of fracture toughness are in good agreement with the experimental results. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Artificial neural network Fracture toughness Ground granulated blast furnace slag Nano TiO2

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Speed Limiter for Enhanced Safety and Efficiency in Electric Vehicles

Adaptive Dynamic Speed Limiter for Enhanced Safety and Effic...

引用

IEEE International Conference on System, Computation, automation and Networking (ICSCAN)

作者： D. Dharani B. Pradaap H. Hemavandhana V. Mohan Raja Department of Robotics and Automation Manakula Vinayagar Institute of Technology Pondicherry India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

Electric Vehicles (EVs) have revolutionized transportation, providing eco-friendly alternatives to traditional internal combustion engine vehicles. As the number of Electric Vehicles on the road increases, there is a critical need for systems that ensure both safety and operational efficiency. The proposed Adaptive Dynamic Speed Limiter system adjusts a vehicle's speed dynamically based on external control signals transmitted wirelessly. The system uses a transmitter to send predefined commands corresponding to different speed levels or stop conditions. A receiver integrated into the EV decodes these signals and modifies the vehicle's motor speed accordingly. An LCD provides real-time feedback to the driver and displays the vehicle's current status. The adaptive dynamic model ensures compliance with traffic regulations, reduces energy consumption, and enhances safety for both drivers and pedestrians. By integrating advanced control mechanisms, the project contributes to developing smarter, safer EVs.

关键词： Adaptive systems Transmitters Roads Receivers Electric vehicles Regulation Real-time systems Safety Vehicle dynamics Vehicles

来源：评论

学校读者我要写书评

暂无评论

Query Attack by Multi-Identity Surrogates

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 684-697页

作者： Chen, Sizhe Huang, Zhehao Tao, Qinghua Huang, Xiaolin Department of Automation and Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China ESAT-STADIUS Katholieke Universiteit Leuven Leuven3000 Belgium

Deep neural networks (DNNs) are acknowledged as vulnerable to adversarial attacks while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable adversarial examples (AEs) because of their gradient similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the prediction similarity (PS), to filter out inefficient queries by surrogates without querying the victim. To jointly utilize and also optimize surrogates' GS and PS, we develop QueryNet, a unified attack framework that can significantly reduce queries. QueryNet creatively attacks by multi-identity surrogates, i.e., crafts several AEs for one sample by different surrogates and also uses surrogates to decide on the most promising AE for the query. After that, the victim's query feedback is accumulated to optimize not only surrogates' parameters but also their architectures, enhancing both the GS and the PS. Although QueryNet has no access to pretrained surrogates' prior, it reduces queries by averagely about an order of magnitude compared to alternatives within an acceptable time, according to our comprehensive experiments: 11 victims (including two commercial models) on MNIST/CIFAR10/ImageNet, allowing only 8-b image queries, and no access to the victim's training data. The code is available at https://***/Sizhe-Chen/QueryNet. © 2023 IEEE.

关键词： Deep neural networks

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：