检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Bhuiyan, Md Abdullahil Baki Abdullah, Hasan Muhammad Arman, Shifat E. Rahman, Sayed Saminur Al Mahmud, Kaies Department of Plant Pathology Bangabandhu Sheikh Mujibur Rahman Agricultural University Gazipur1706 Bangladesh GIS and Remote Sensing Lab Department of Agroforestry and Environment Bangabandhu Sheikh Mujibur Rahman Agricultural University Gazipur1706 Bangladesh Department of Robotics and Mechatronics Engineering University of Dhaka Dhaka1000 Bangladesh Department of Computer Science and Engineering APJ Abdul Kalam Technological University Kerala695016 India

All over the world, bananas are one of the most common fruits. It accounts for nearly 16% of global fruit production. However, every year, a large amount of banana yield losses occur due to different diseases of the banana leaf. It is essential to identify these diseases at an early stage in order to increase banana production. A visual inspection is the most common method of identifying banana leaf diseases. With visual inspection, errors are common, time is a factor, and expertise is required. This study showed how deep learning and Bayesian optimization could effectively diagnose banana leaf diseases from images without any human intervention. We collected the data from various locations in Bangladesh. The dataset consists of images of three banana leaf diseases: leaf blight, Sigatoka, and Cordana. Our proposed BananaSqueezeNet model performed exceptionally well in diagnosing banana leaf diseases from the images with an overall accuracy of 0.9625, precision of 0.9653, recall of 0.9625, specificity of 0.9875, F1-score of 0.9617, and MCC of 0.9513. The BananaSqueezeNet model outperforms three other convolutional neural networks, EfficientNetB0, MobileNetV3, and ResNet-101. BananaSqueezeNet will enable banana growers to detect banana diseases early, and we hope that it will ultimately lead to an increase in banana production in Bangladesh and around the world. © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Four-dimensional Integral Model of Dry Friction on the Example of Wheel Movement

引用

Journal of Physics: Conference Series 2021年第1期2096卷

作者： M S Salimov G R Saypulaev I V Merkuriev Department of Robotics mechatronics dynamics and strength of machines National Research University "Moscow Power Engineering Institute" Moscow Russia

A four-dimensional model of dry friction in the interaction of a solid wheel and a horizontal rough surface is investigated. It is assumed that there is no separation between the wheel and the horizontal surface. The movement of the body occurs in conditions of combined dynamics, when in addition to the sliding movement, the body participates in spinning and rolling. The equation of motion of the wheel is compiled using the Appel equation. The resulting model of sliding, spinning, and rolling friction is given for the case where the contact area is a circle. The cumbersome integral expressions were replaced by fractional-linear Pade approximations. Pade approximations accurately describe the behavior of the components of the friction model. A mathematical model is proposed that describes the simultaneous sliding, spinning and rolling of a solid wheel. The dependences of the parallel and perpendicular components of the friction force and the torque of the spinning friction were ploted with respect to the parameter that characterizes the movement of the wheel. Comparisons of the integral friction model and the model based on Pade approximations are presented. The results of the comparison showed a qualitative correspondence of the models. After obtaining the equation of motion, the simulation of motion at a constant control torque of the wheel is carried out. The graphs allow you to match the logical behavior of the wheel movement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Appraisal in to the Effects of Partial Shading on an Urban Photovoltaic System Using the Internet of Things

An Appraisal in to the Effects of Partial Shading on an Urba...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Lakshmana Phaneendra Maguluri S Farook Saravanan R Ashutosh Dixit K.P. Aishwarya JoshuvaArockia Dhanraj Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Electrical and Electronics Engineering School of Engineering Mohan Babu University Tirupathi Andhra Pradesh India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India Department of Electrical Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Information Technology Panimalar Engineering College Chennai Tamil Nadu India Department of Mechatronics Engineering Centre for Automation and Robotics (ANRO) Hindustan Institute of Technology and Science Chennai Tamil Nadu India

Partial shadowing of a solar array is known to decrease the array's output power. Unfortunately, it is not always possible to calculate the exact degree of decrease in energy output from the darkened region alone. In this study, the process of partial PV shadowing on multiple PV cells by using IoT wired in series and/or parallel, with and without bypass diodes, is elucidated. A layperson interested in learning how a certain shading geometry affects a PV system may benefit from this study, which is provided in clear language. Commercial 100 W panel and 10 kW PV array data are used to show the study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Planning for Autonomous Underwater Vehicles Performing Information Gathering Tasks in Large Subsea Environments

Online Planning for Autonomous Underwater Vehicles Performin...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Harun Yetkin James McMahon Nicholay Topin Artur Wolek Zachary Waters Daniel J. Stilwell Department of Mechatronics Engineering Bartin University Turkey Code 7130 US Naval Research Laboratory Washington DC USA University of Maryland College Park MD USA Center for Marine Autonomy and Robotics at Virginia Tech Bartın University Turkey US Naval Research Laboratory Washington DC USA Bradley Department of Electrical and Computer Engineering Virginia Tech Blacksburg VA USA

We present an anytime Monte Carlo tree search (MCTS) algorithm to generate real-time, near-optimal search paths in large subsea environments. The MCTS planner continuously builds a tree of the search space until either the allowed time per move is reached or the budget constraint for the search mission is met. In order to improve the performance of the MCTS planner, we propose a novel heuristic action selection policy to determine the value of a leaf node. The proposed heuristic is tailored to problems where making a turn incurs a higher cost than moving straight, such as the case on autonomous underwater vehicles. Through extensive simulations, we show that our heuristic yields a significant performance improvement over a lawnmover path planner - a commonly employed approach in subsea search applications - and over a simple MCTS planner where actions are selected uniformly at random. In our numerical illustrations, we use a real data set abstracted from sonar measurements acquired from the Boston Harbor.

关键词： Search problems Planning Robot sensing systems Real-time systems Monte Carlo methods Cost function Sonar

来源：评论

学校读者我要写书评

暂无评论

Cross-sectional imaging of C. elegans by SEM-CT using Environmental SEM for nanomanipulation

Cross-sectional imaging of C. elegans by SEM-CT using Enviro...

引用

IEEE Conference on Nanotechnology

作者： Masahiro Nakajima Masaru Takeuchi Naoki Hisamoto Toshio Fukuda Yasuhisa Hasegawa Qiang Huang Center For Micro-nano Mechatronics Nagoya University Nagoya Aichi Japan Department of Micro-Nano Systems Engineering Nagoya University Nagoya Aichi Japan Division of Biological Science Nagoya University Nagoya Aichi Japan Institute for Advanced Research Nagoya University Nagoya Aichi Japan Intelligent Robotics Institute Beijing Institute of Technology Faculty of Science and Engineering Meijo University Nagoya Aichi Japan

A novel technique was presented for a cross-sectional imaging of Caenorhabditis elegans (C. elegans) by Scanning Electron Microscope - Computed Tomography (SEM-CT) using Environmental-SEM (E-SEM) for nanomanipulation applications. In our previous works, a nanorobotic manipulation system was established inside the E-SEM for water-contained samples including biological organism with a real-time high resolution observation. However, the SEM image is two dimensional (2D) and surficial information from the secondly electrons. Hence, it is not able to evaluate the targeted structure inside the sample. In this research, we presented the cross-sectional observation of the sample by SEM-CT system which is used the X-ray generated by the electron beam of SEM. To improve the signal-to-noise ratio of CT imaging, we evaluated the following ways, 1) apertures for X-ray before/after irradiating the sample, 2) adjustment of emission currents of the electron beam, 3) iteration processing of captured images. To reduce the damage of C. elegans during observation, a method was used to immerse the C. elegans by a liquid oil. The proposed 3D imaging technique is useful to evaluate the 3D manipulation of the C. elegans, such as nano-injection application with functional micro-nano beads inside the C. elegans.

关键词： Nanobioscience X-ray imaging Apertures Scanning electron microscopy Electron beams

来源：评论

学校读者我要写书评

暂无评论

The reliability analysis for some subassemblies in the structure of 060-DA diesel-electric locomotive

引用

IOP Conference Series: Materials Science and engineering 2018年第6期444卷

作者： M Alexandrov V Goanţă M Mareş D Apostol I Blanari Mechanical Engineering Mechatronics and Robotics Department 'Gheorghe Asachi' Technical University of Iasi Romania CFR Iasi maintenance department

The increasing complexity of technical systems, together with their increasingly important functions, determines the continuously growing importance of reliability studies. The working regime parameters are more and more intense, the operating conditions are more and more complex, leading to the need of a large scale automation of production processes, and also of their control, including the use of some powerful process computers. Industrial products, mechanical equipment and devices, various machine components, and so on, they can all be regarded as basic units with autonomous operation, embedded in complex aggregates or installations. The 060-DA diesel-electric locomotive is SUCH a complex set of components and subassemblies, working together, so that any accidental failure of a basic constituent could lead to a total or partial decommissioning of the locomotive, or to its incorrect operation. The subject of the present paper is a reliability analysis for the most important components and subassemblies from the structure of 060-DA diesel-electric locomotive.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing UAV Autonomous Navigation in Indoor Environments Using Reinforcement Learning and Convolutional Neural Networks

Enhancing UAV Autonomous Navigation in Indoor Environments U...

引用

International Symposium on Intelligent Systems and Informatics (SISY)

作者： Homayoun Safarpour Motealegh Mahalegi Amirfarhad Farhadi György Molnár Eniko Nagy Obuda University Institute of Mechatronics and Vehicle Engineering Budapest Hungary Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Apaczai Csere Janos Faculty of Humanities Education and Social Sciences Kando Kalman Faculty of Electrical Engineering Budapest Obuda University Hungary Szechenyi University Gyor Hungary Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty of Informatics Obuda University Budapest Hungary

ISBN: (数字)9798350385601

ISBN: (纸本)9798350385618

In recent years, the number of unmanned aerial vehicle (UAV) applications has increased. However, navigating them indoors is still tricky because no GPS signals are available, and the obstacles constantly change. This study exploits the collaboration between convolutional neural networks (CNNs) and reinforcement learning (RL) to overcome these challenges, improving the level of independence of UAVs in indoor settings. We present a new technique known as potential-based reward shaping, which directly incorporates expert knowledge into the reinforcement learning framework. This technique efficiently addresses the problem of sparse rewards that often hinder learning in conventional RL configurations. In addition, we have created a reflective reinforcement learning agent that systematically assesses its actions to prioritize those that result in the most substantial enhancements. We have extensively evaluated the performance of our method with the High-Definition Indoor Navigation (HDIN) dataset to show that our method continuously outperformed current non-introspective RL techniques in terms of decision-making speed and navigation accuracy in this evaluation. The results show that this new CNN-RL combination is feasible and suggests a scalable method for complex indoor navigation problems.

关键词： Indoor navigation Refining Reinforcement learning Autonomous aerial vehicles Indoor environment Convolutional neural networks Intelligent systems Informatics Autonomous robots Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Assymetry of coupling between the P3 and P4 electroencephalographic leads during the motions 3

Assymetry of coupling between the P3 and P4 electroencephalo...

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Khorev, Vladimir Zhuravlev, Maksim Borovkova, Ekaterina Ishbulatov, Yuri Gridnev, Vladimir Karavaev, Anatoly Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia Department of Open Systems Physics Saratov State University Russia Department of Dynamic Modeling and Biomedical Engineering Saratov State University Saratov Russia Saratov State University Saratov Branch Institute of RadioEngineering and Electronics Russian Academy of Sciences Saratov State Medical University Named after V. I. Razumovsky Saratov Russia Department of Innovative Cardiological Information Technology Institute of Cardiological Research Saratov State Medical University Saratov Russia Saratov Branch Institute of RadioEngineering and Elecrronics Russian Academy of Sciences Russia

Based on the coupling analysis we analyze electroencephalograms (EEGs) acquired in untrained humans (operators) during real and imaginary movements, and show a difference between the related EEG signals and the record... 详细信息

ISBN: (纸本)9781728124704

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Passivity based Stability Analysis of Disturbance Observer based Trajectory Tracking Control of Nonholonomic Wheeled Mobile Robot

A Passivity based Stability Analysis of Disturbance Observer...

引用

2010 IEEE/ASME international conference on advanced intelligent mechatronics (AIM 2010)

作者： Mohammad Noorbad Alireza Mohammad Shahri Khoshnam Shojaei Behzad Tabibian Electrical Engineering Department Mechatronics and Robotics Research Laboratory Electronic Research Center Iran University of Science and Technology Tehran Iran Computer Engineering Department Iran University of Science and Technology Tehran Iran

This paper proposes a disturbance observer (DOB) algorithm to solve the trajectory tracking problem of a nonholonomic WMR in presence of external disturbances. To obtain a high performance trajectory tracking controller, a computed torque controller (CTC) is integrated into a kinematic controller by back-stepping technique. The disturbance observer as a part of the proposed controller estimates the external disturbances and cancel-out them. By decoupling the estimation errors from disturbances and its passivity property, it is demonstrated that the overall closed-loop system is asymptotically stable. Simulation results show that the performance of the CTC is significantly improved and the DOB achieves good ability of disturbance attenuation.

关键词： Computed Torque Control Disturbance Observer Nonholonomic WMR Weakly Strictly Passive

来源：评论

学校读者我要写书评

暂无评论

A Soft Robotic System Imitating the Multimodal Sensory Mechanism of Human Fingers for Intelligent Grasping and Recognition

SSRN

引用

SSRN 2024年

作者： Xu, Jinsui Xu, Boyi Zhan, Hao Xie, Zhijie Tian, Zhen Lu, Yifan Wang, Zheping Yue, Honghao Yang, Fei South China University of Technology China State Key Laboratory of Robotics and System School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China Wu Xianming School of Intelligent Engineering South China University of Technology Guangzhou510641 China College of Mechanical and Electrical Engineering Northeast Forestry University Harbin150042 China Science and Technology on Space Physics Laboratory China Academy of Launch Vehicle Technology Beijing100000 China

The sensory function is crucial for achieving precise feedback control and environmental interaction in soft robots. Therefore, the multimodal sensory capabilities that mimic human fingers have always been a research hotspot. This study proposes a design method for a soft robotic gripper that can emulate the multimodal perception mechanism of human fingers and achieve high-precision recognition of grasped objects using machine learning algorithms. In addition, a finger texture structure inspired by human fingerprints is designed using a negative pressure-induced buckling method to enhance the soft gripper's ability to perceive minute surface textures. Inspired by slow adapting (SA) receptors and fast adapting (FA) receptors of human fingers, this study designs a capacitive curvature sensor (CS) and a triboelectric texture sensor (TS) to detect the size, material, and texture of objects. Furthermore, a non-contact medium identification sensor (MIS), having a sensitivity of more than 1300 times higher compared to the traditional MISs, is fabricated using the principle of electromagnetic resonance. It is shown that by employing a deep learning-based multi-channel feature fusion network, the soft grasping system with multimodal sensing can achieve an object recognition accuracy of 98.43%. This work provides an innovative approach for the application of soft robots in various fields, such as logistics sorting and food safety. © 2024, The Authors. All rights reserved.

关键词： Textures

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：