检索结果-内蒙古大学图书馆

Robust Indoor Positioning of Automated Guided Vehicles in Internet of Things Networks With Deep Convolution Neural Network Considering Adversarial Attacks

引用

IEEE Transactions on Vehicular Technology 2024年第6期73卷 7748-7757页

作者： Elsisi, Mahmoud Rusidi, Akhmad Lutfi Tran, Minh-Quang Su, Chun-Lien Ali, Mahmoud N. National Kaohsiung University of Science and Technology Department of Electrical Engineering Kaohsiung807618 Taiwan Cairo11629 Egypt National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106 Taiwan Tuetech University Department of Mechanical Engineering Thai Nguyen250000 Viet Nam

The effectiveness of positioning techniques that utilize the receiver signal strength (RSS) is highly dependent on the instability of the received signal strength indicator (RSSI). Up to now, there is no strategy that effectively lowers the influence of such instability on the accuracy of positioning. Moreover, recent studies showed that indoor positioning techniques are vulnerable to noise in RSSI data and cyber-attacks, which make them more expensive. In this study, a new Internet of Things (IoT) paradigm is proposed for the indoor positioning of automated guided vehicles (AGVs) using a deep convolution neural network (CNN). The proposed method handles signal processing by converting the RSSI signal into an image. In which, the 1-D RSSI signal is converted into 2-D image data in order to generate the new features based on continuous wavelet transform (CWT), and then the proposed deep CNN is implemented for the indoor positioning system. The test results show that the proposed model can outperform other state-of-the-art positioning techniques with small position errors. Furthermore, the robustness of the proposed model is validated against various adversarial attacks. In addition, the proposed method can have a lower impact on RSSI change compared with other methods. © 1967-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A gecko-inspired adhesive robotic end effector for critical-contact manipulation

引用

science China(Information sciences) 2022年第8期65卷 120-133页

作者： Zhongyi CHU Jie DENG Lin SU Jing CUI Fuchun SUN School of Instrumentation and Optoelectronic Engineering Beihang University School of Mechanical Engineering and Applied Electronics Beijing University of Technology Department of Computer Science and Technology Tsinghua University

It is an emerging challenge for robots to achieve non-destructive pick-and-place manipulation for delicate objects under low normal preload, i.e., critical-contact manipulation. The prominent on-off controllable property of the gecko-inspired microwedge adhesive makes critical-contact manipulation possible for robotic end effectors. However, it is difficult for end effectors to actuate the micron-scale microwedge adhesive and detect the adhesion state. In this paper, a gecko-inspired adhesive robotic end effector for critical-contact manipulation is proposed, which consists of a half-scissor variable-scale actuator, a 3-axis high-sensitivity isotropic flexible capacitive tactile sensor, and the microwedge adhesive. The half-scissor variable-scale actuator is designed to provide pure large shear loading for the microwedge adhesive at micronscale displacement by merely controlling the normal macro-scale displacement of the actuator. Besides, the3-axis high-sensitivity isotropic flexible capacitive tactile sensor is designed for accurate detection of multiaxis contact forces and the adhesion state between the adhesive and objects to ensure the success of the critical-contact manipulation. The sensor can sense the shear and normal forces by detecting variations of the overlap and distance between electrodes, while the design of the finger-like electrodes improves the sensitivity. In addition, a set of experiments on manipulating objects are implemented and the results show that the proposed robotic end effector can provide pure large shear loading for the microwedge adhesive at micron-scale displacement and can detect the adhesion state between the microwedge adhesive and objects accurately to stably grasp delicate objects in critical-contact condition.

关键词： critical-contact manipulation gecko-inspired microwedge adhesive robotic end effector half-scissor variable-scale actuator tactile sensor

来源：评论

学校读者我要写书评

暂无评论

Obstacle Avoidance for Omnidirectional Mobile Robot Using SLAM

引用

Journal of engineering and science in Medical Diagnostics and Therapy 2023年第1期6卷 011003页

作者： Nandikolla, Vidya K. Ghoslin, Bryan Mechanical Engineering Department College of Engineering and Computer Science California State University Northridge 18111 Nordhoff Street NorthridgeCA91330 United States

In the field of mobile robotics, simultaneous localization and mapping (SLAM) is an algorithmic approach to the computational problem of creating and updating a map of an environment while simultaneously keeping track of where the robot is within the environment. Applications of a SLAM algorithm are important for autonomous mobile systems to traverse an environment while avoiding obstacles and accurately achieving designated goal destinations. This paper presents the design of a SLAM-driven controller for a semi-autonomous omnidirectional mobile robot. Input to the system comes from a brain computer interface in the form of simple driving commands or a goal destination as decided by the user. Due to latency issues of reacting and responding in real-time, the system must safely navigate following the last given commands until it runs out of free space, reaches a goal designation, or receives a new command. The robotic system utilizes a three-wheeled robot kit with an upgraded sensor system. The Intel realsense depth camera D435 and two lidar sensors are utilized to construct a full 360 deg field of view. The SLAM algorithm and system controllers are developed using the robot operating system (ROS). The controllers are developed and tested within Gazebo, which is a physics simulation engine utilized for rapid prototyping. Testing was performed to validate controller performance when given varying commands as well as performing long distance path planning and obstacle avoidance. The system was often capable of achieving its goal destinations with a small error of around 3% or less though the error was found to increase with the more commands the system processed. Copyright © 2023 by ASME.

关键词： Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Through Speech 4th

Emotion Recognition Through Speech

引用

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Shashank, Valandas Sai Bhaskar, Nuthanakanti Srujan Raju, K. Raji Reddy, A. Department of Computer Science and Engineering CMR Technical Campus Hyderabad India Department of Mechanical Engineering CMR Technical Campus Hyderabad India

ISBN: (纸本)9789819994410

Speech is individuals’ primary contact form, and vocabulary is their primary tool. In social connections, emotion is essential. Given that we encounter interaction between humans and machines, it is crucial and difficult to identify the emotions in a speech. The way a person expresses their emotions changes depending on the feeling they are experiencing. When somebody expresses their emotions, each will have a distinctive intensity, pitch, and tone fluctuation that can be put together based on the matter. Therefore, a future objective of computer vision is the identification of spoken emotions. This paper aims to create an intelligent speech that recognizes emotions using a convolutional neural network. Multiple sections are utilized to identify feelings, and a classification algorithm is distinguished between happiness, sadness, anger, and amazement. The machine will transform the mathematical representation of human voice signals, go through its routine, and then show emotion. The data is a spoken specimen, and the Librosa library extracts the attributes from the voice sample. As a research dataset, we are employing the RAVDESS collection. This study demonstrates that all classifications for the data we used have an accuracy level of 68%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Based Smart System for Supply Chain Management 5

Multi-Agent Based Smart System for Supply Chain Management

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Bala, Raj Kumar, Avadhesh Nain, Pawan Kumar Singh Galgotias University Department of Mechanical Engineering Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350383522

The supply chain comprises numerous components/ identities as suppliers, manufacturers, factories, warehouses, distributing agents, etc. These personalities are engaged in delivering raw materials, and components, which are reassembled at the factory to make a final product. With the rising relevance of computer-based communication technologies, communication networks are increasingly vital in supply chain management. Given the aims of the supply chain: to have the appropriate items in the right amounts, at the right location, at the right time, and minimum cost, supply chain management is positioned at the intersection of many professional sectors. This is especially the construction case, as the structure requires its manufacturing the include many industrial items. This study focuses on the continuous development and research activities of MAS (Multi-Agent System) for supply chain management and gives the primary methods to supply chain communications as utilized largely in manufacturing industries. © 2024 IEEE.

关键词： Automated Guided Vehicle Manu-facturing System Material Resource Planning Multi-agent Supply Chain Management

来源：评论

学校读者我要写书评

暂无评论

EVGPT - Fine-Tuned Large Language Model for Electric Vehicle Operational Assistance 4

EVGPT - Fine-Tuned Large Language Model for Electric Vehicle...

引用

4th IEEE International Conference on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET 2024

作者： Kanimozhi, S. Prithvi, G. Barath, M. Vaikash, K.G. Mathew, Abel Manoj Gukhan, V.B.S. School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Mechanical Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331528614

The optimization of electric vehicle (EV) utilization and efficiency is becoming increasingly essential in the ever-changing landscape of sustainable transportation. Consulting user manuals, online resources, and seeking expert advice for EV maintenance and operation is a significant obstacle to productivity. Electric Vehicle GPT (EVGPT) is a specialized Large Language Model (LLM) specifically designed to address queries related to EV maintenance, operation, and troubleshooting, filling the gaps that conventional LLMs may miss. This model serves as a comprehensive digital assistant for technicians, operators, and EV enthusiasts, providing timely and precise information while upholding response quality. This study offers an overview of the EVGPT model architecture and presents an operational evaluation based on its implementation in a specific EV model. ©2024 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Enhanced Security for IOMT Devices: Deep learning Techniques for Network Intrusion Detection 5

Enhanced Security for IOMT Devices: Deep learning Techniques...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Gopala Krishnan, D. Diviya, M. Jyoshika Shri, K. Subramanian, M. Amrita School of Computing Department of Computer Science and Engineering Chennai India St Joseph's College of Engineering Department of Mechanical Engineering Chennai India

ISBN: (纸本)9798350379884

The increasing popularity of Internet of Medical Things (IoMT) devices, like wearable sensors, has greatly improved patient care by allowing continuous monitoring and real-time data transfer to the cloud. However, this progress also raises security concerns, as the data sent from these devices can be at risk of tampering or hacking during transmission. Keeping this sensitive medical data safe is crucial for patient safety. To address these issues, a fused CNN and LSTM are developed to check whether the data from wearable IoMT devices has been altered or attacked during transmission to the cloud. The CNN part of the model helps to pull out important features from the data, while the LSTM part looks for patterns to spot any signs of tampering. The model uses two convolutional layers each of which is followed by a MaxPooling layer. Our model, tested on a large dataset, achieved an accuracy of 97.06%, showing its ability to protect the integrity of transmitted medical data. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-Transformer Model for Efficient Hyperspectral Image Reconstruction 6

A Hybrid CNN-Transformer Model for Efficient Hyperspectral I...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Tian, Fenggang Ma, Long School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China School of Mechanical Engineering Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9798350374315

Recent research in hyperspectral image (HSI) reconstruction mainly emphasizes the development of intricate mappings through using convolutional neural networks (CNNs). Although CNNs excel at capturing local feature information, they struggle to effectively perceive global feature information, resulting in suboptimal reconstruction accuracy. An SRCTNet model was designed to solve the above problem, which integrates CNNs with Transformer modules to efficiently reconstruct HSIs from RGB images. The CNN block utilizes a multi-scale attention mechanism to reuse features and capture multi-level information, while the Transformer block utilizes self-attention mechanism to acquire global information. This fusion maximizes the retention of both local and global representations, ensuring high reconstruction accuracy while balancing computational complexity and expanding the receptive field. Evaluations on the challenging NTIRE2022 dataset show that SRCTNet excels in objective metrics such as mean relative absolute error (MRAE), root mean square error (RMSE), and peak signal-to-noise ratio (PSNR), outperforming six methods. Moreover, our model requires fewer parameters and computational resources, demonstrating its effectiveness and robustness in hyperspectral image reconstruction. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing petroleum logistics with innovative decision support mechanism for fuel tanker selection

引用

Environmental science and Pollution Research 2025年第17期32卷 10910-10928页

作者： Murat, Mirac Seyhan, Mehmet Erdogan, Melike Ayyildiz, Ertugrul Department of Industrial Engineering Karadeniz Technical University Trabzon61080 Turkey Department of Mechanical Engineering Karadeniz Technical University Trabzon61080 Turkey Department of Computer Engineering Duzce University Duzce81620 Turkey College of Science and Engineering Hamad bin Khalifa University Doha Qatar

Transportation of petroleum-based products is a complex and hazardous logistics process. Selecting the appropriate transportation vehicles for this process is crucial for ensuring safety and efficiency. Therefore, prioritizing selection criteria and choosing the most suitable fuel tanker is essential in reducing potential risks and improving overall fleet operations. Given the many types of tankers available for petroleum product transportation, decision-makers should employ a multi-criteria decision-making (MCDM) approach to identify the best option for their specific needs. This study introduces a novel MCDM approach that combines the Weighted Aggregated Sum Product Assessment (WASPAS) and the Criteria Importance through Intercriteria Correlation (CRITIC) in a Fermatean fuzzy (FF) environment, addressing five main criteria and evaluating five fuel tanker alternatives. Using this approach, the research identified and prioritized key criteria for selecting an appropriate tanker model by providing insights into 24 sub-criteria. The results reveal that tanker price emerges as the most important sub-criterion, leading us to determine the M3 tanker model as the most suitable fuel tanker after carefully evaluating all 24 different sub-criteria. The findings can significantly assist petroleum firms in making informed decisions when choosing fuel tankers by considering various technical, operational, comfort, environmental, and economic factors. The results can also be used to inform policy on fuel distribution. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Fleet operations

来源：评论

学校读者我要写书评

暂无评论

A thermal deformation estimation method for high precision machine tool spindles based on the convolutional neural network

引用

Journal of mechanical science and Technology 2023年第6期37卷 3151-3162页

作者： Liao, Chien-Wei Lee, Ming-Tsang Liu, Yu-Chi Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung Taiwan Department of Power Mechanical Engineering National Tsing Hua University Hsinchu Taiwan

The temperature rise of key internal components and ambient temperature changes during machining processes are the main causes of thermal displacement in machine tool spindle. This wastes materials and reduces working efficiency. A highly accurate and robust thermal spindle displacement estimation scheme is proposed in this paper which is based on the convolutional neural network (CNN) technique. Several key signals of specific dimensions related to spindle thermal displacement were first collected as two-dimensional (2D) signal maps. A multi-level feature expression for these 2D signal maps was extracted using convolution and pooling. A relationship between the extracted features and spindle thermal displacement was then learned using the neural architecture of the full connection layer. Optimized hyperparameter settings were determined by design of experiments (DoE) applied to the proposed CNN model. Experimental results showed that the proposed method had better performance than the multiple regression analysis (MLR) or back propagation neural network (BPNN) methods in terms of estimation accuracy and robustness at different spindle speeds. © 2023, The Korean Society of mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

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：