检索结果-内蒙古大学图书馆

Squid-inspired and wirelessly controllable display for active camouflage in aquatic-environment

npj Flexible Electronics 2024年第1期8卷 900-909页

作者： Doyoung Kim Seung Won Seon Minkyung Shin Jihwan Kim Bogeun Kim Janghoon Joo Sang Uk Park Wooseok Kim Hee Kyu Lee Byeong Woon Lee Se Gi Lee Su Eon Lee Ji-Hun Seo Seung Ho Han Bong Hoon Kim Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan University2066Seobu-roJangan-guSuwon 16419Republic of Korea Department of Smart Wearable Engineering Soongsil UniversitySeoul 06978Republic of Korea Electronic Convergence Materials and Devices Research Center Korea Electronics Technology Institute(KETI)Seongnam 13509Republic of Korea Department of Materials Science and Engineering Korea UniversitySeoul 02841Republic of Korea Department of Robotics and Mechatronics Engineering DGISTDaegu 42988Republic of Korea

Achieving optimal camouflage in an aquatic environment necessitates the ability to modulate transmittance in response to the surrounding obscurity and potential *** adaptation involves a dynamic transition from transparency to a deep-blue color,especially in low-light or dark *** a strategy promotes a seamless assimilation with the surroundings,enabling the absorption of searchlights and,subsequently,diminishing the risk of detection by ***,the presence of sophisticated mechanisms that facilitates stable and efficient control of transmittance is imperative,enabling smooth transition between transparent and deep-blue hues within the aquatic *** study presents nature-inspired programmable camouflage system that integrates an electrochromic display as the primary transmittance change element and a wireless base module for power and data *** technology offers a robust and flexible construction,ensuring stable operation as demonstrated through mechanical-fatigue experiments and quantitative simulation.A custom circuit and a power-control software package enable active control of multiple electrochromic displays while submerged in water.

关键词： transparency submerged lights

来源：评论

学校读者我要写书评

暂无评论

Increasing the robustness of computer networks by using hybrid centralized-distributed topology

Increasing the robustness of computer networks by using hybr...

引用

International Computer Sciences and Information Technologies (CSIT)

作者： Alexander Skvorchevsky Scientific Institution “Research Center of Robotics Mechatronics and Production Informatization” LLC Kharkiv Ukraine

ISBN: (纸本)9798350334326

The paper presents the results of the structural synthesis of the hybrid centralized-distributed system of data generation, transferring, storing and restoration. A system of data generation, transferring, storing and restoration is proposed, which includes peripheral nodes made with the possibility of data generation and storing and their subsequent transferring via communication lines to a central node for storage. Each of the peripheral nodes is additionally connected with each other peripheral node by communication lines, and communication lines provide the ability to transfer data, generated in each of the peripheral nodes, for storage on one or several other peripheral nodes and the ability to transfer data to one of the peripheral nodes and to restore data on it in case of the central node loss. A method using the specified system is also proposed. The study objectives are to provide a stability high level of the system and method of generation, transferring, storing and restoration data to data loss, including possibly the holistic body of data, with data loss at the central and one or more peripheral nodes of the system while reducing risk of unauthorised access to data and level of energy consumption. The objectives of the study are achieved by the fact that the pairwise peripheral nodes connect with all other peripheral nodes via communication lines, while the simultaneous connection of all peripheral nodes with the central node via communication lines allows ensuring the integrity of data available in the data generation and storing system in case of complete data loss on the central node and one or more peripheral nodes with a limited number of data copies generated in each of the nodes. Research results can be used in database management systems, server network topology, cryptocurrencies, the financial and banking sectors’ information systems, objects and processes automatic control systems, etc. In addition, the results of the study can be used in the

关键词： Missiles Network topology Process control Banking Database systems Topology Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Features of the resting-state functional network in patients with major depressive disorder: mutual information analysis in fMRI data 7

Features of the resting-state functional network in patients...

引用

7th Scientific School: Dynamics of Complex Networks and their Applications, DCNA 2023

作者： Khorev, Vladimir Kurkin, Semen Paunova, Rositsa Stoyanov, Drozdstoy Innopolis University Center for Technologies in Robotics and Mechatronics Components Innopolis Russia Immanuel Kant Baltic Federal University Baltic Center for Artificial Intelligence and Neurotechnology Kaliningrad Russia Samara State Medical University Neurosciences Research Institute Samara Russia Plovdiv Medical University Plovdiv Bulgaria

ISBN: (纸本)9798350305746

In this work, we conducted the analysis of the functional magnetic resonance imaging data in healthy subjects and patients with major depressive disorder that were obtained during experimental research when subjects were resting. The signals that have undergone preprocessing and filtration were used to find the functional connectivity between the brain regions. Results demonstrate significant changes between functional connections based on the mutual information measure. We obtained five significantly changed connections, four of which increased more in cotrol group over patients. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Regularization Strength Impact on Neural Network Ensembles 22

Regularization Strength Impact on Neural Network Ensembles

引用

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Cedrique Rovile Njieutcheu Tassi Anko Börner Rudolph Triebel German Aerospace Center (DLR) Institute of Optical Sensor Systems Germany German Aerospace Center (DLR) Institute of Robotics and Mechatronics Germany

ISBN: (纸本)9781450398336

In the last decade, several approaches have been proposed for regularizing deeper and wider neural networks (NNs), which is of importance in areas like image classification. It is now common practice to incorporate several regularization approaches in the training procedure of NNs. However, the impact of regularization strength on the properties of an ensemble of NNs remains unclear. For this reason, the study empirically compared the impact of NNs built based on two different regularization strengths (weak regularization (WR) and strong regularization (SR)) on the properties of an ensemble, such as the magnitude of logits, classification accuracy, calibration error, and ability to separate true predictions (TPs) and false predictions (FPs). The comparison was based on results from different experiments conducted on three different models, datasets, and architectures. Experimental results show that the increase in regularization strength 1) reduces the magnitude of logits; 2) can increase or decrease the classification accuracy depending on the dataset and/or architecture; 3) increases the calibration error; and 4) can improve or harm the separability between TPs and FPs depending on the dataset, architecture, model type and/or FP type.

关键词： Calibration error Quality of uncertainty Ensemble Regularization strength Mixture of Monte Carlo Dropout (MMCD) Separating true predictions (TPs) and false predictions (FPs) Monte Carlo Dropout (MCD)

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Router of Machine and Artificial Intelligence Learning for the Expansion of Agriculture's Manufacturing Sector 3

Computational Intelligence Router of Machine and Artificial ...

引用

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Raman, Ramakrishnan Alanya-Beltran, Joel Akram, Shaik Vaseem Shah, Heli Sanjay, P.C. Ponnusamy, R. Symbiosis Institute of Business Management Pune Maharashtra Pune India Universidad Tecnológica Del Perú Peru Uttaranchal University Uttaranchal Institute of Technology India Parul University Mechatronics & Robotics Pit India India Chennai Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798350399264

The economic sector includes agriculture as a major player. Around the world, the primary issue and hot topic is agriculture automation. As a result of the population boom, there is a huge increase in the need for both jobs and food. Farmers employed traditional techniques, which included insufficient to meet these needs. This led to the introduction of new automated techniques. These innovative techniques supplied the world's food needs while giving billions of people access to jobs. An agricultural revolution has been sparked by artificial intelligence. With the use of this technology, crop yields are now more resistant to many conditions like population increase, climate change, job troubles, and food security concerns. The primary goal of this study is to evaluate the numerous ways artificial intelligence is being used in agriculture, including the use of sensors and other tools built into drones and robots for weeding, spraying, and irrigation. The excessive use of pesticides, herbicides, water, and other resources is reduced by these technologies, and the soil fertility is maintained. They also aid in the effective use of labor, which raises productivity and quality. In order to provide a concise summary of the current state of agricultural automation, including the use of drones and robots for weeding, this study analyses the research of several researchers. Along with two automated weeding strategies, the various ways of soil water sensing are described. This study discusses the use of drones as well as the numerous spraying and crop monitoring techniques that may be utilized with them. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

mechatronics Design and Bio-Motion Simulation of Trans-radial Arm Prosthesis Controlled by EMG Signals

Mechatronics Design and Bio-Motion Simulation of Trans-radia...

引用

Colombian Caribbean Conference (C3), IEEE

作者： Diego A. Zavala Molina Ricardo J. Silva Cabrejos José Cornejo Margarita Murillo Manrique Ricardo Rodríguez Ricardo Palomares Professional School of Mechatronics Engineering Universidad Ricardo Palma Lima Peru Universidad Tecnológica del Perú Lima Peru Research Group of Robotics and Mechatronics (GI-ROMA) Universidad Ricardo Palma Lima Peru

According to the National Institute of Statistics and Informatics (INEI), 32 % of the population in the country have some type of motor disability, which includes difficulty in carrying out activities of daily living using the upper extremities. This research proposes the design and simulation of an upper extremity prosthesis controlled by electromyography signals for a patient with a trans-radial amputation. The cover of the prosthesis was made of ABS plastic and its CAD design was made with SolidWorks software. A compartment in the forearm was considered for the placement of the battery and the electronic system in the hand. The EMAXX ES8MA II and TOWER MG995 servomotors were used to load a mass of 2.3 kg of the forearm and hand assembly and a mechanical system to reach the 10 N.m necessary to move the fingers of the hand. The Von Mises stress analysis was carried out by applying a torque of 50 N.m in the coupling of the forearm-hand system. The CoppeliaSim software was used to simulate the movement of the prosthesis with the dimensions extracted from a volunteer patient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-based Methods for Object Recognition with High-Resolution Tactile Sensors

arXiv

引用

arXiv 2023年

作者： Gandarias, Juan M. García-Cerezo, Alfonso J. Gómez-De-Gabriel, Jesús M. Robotics and Mechatronics Group Systems Engineering and Automation Department University of Málaga Escuela de Ingenierías Industriales Málaga Spain

Novel high-resolution pressure-sensor arrays allow treating pressure readings as standard images. Computer vision algorithms and methods such as Convolutional Neural Networks (CNN) can be used to identify contact objects. In this paper, a high-resolution tactile sensor has been attached to a robotic end-effector to identify contacted objects. Two CNN-based approaches have been employed to classify pressure images. These methods include a transfer learning approach using a pre-trained CNN on an RGB-images dataset and a custom-made CNN (TactNet) trained from scratch with tactile information. The transfer learning approach can be carried out by retraining the classification layers of the network or replacing these layers with an SVM. Overall, 11 configurations based on these methods have been tested: 8 transfer learning-based, and 3 TactNet-based. Moreover, a study of the performance of the methods and a comparative discussion with the current state-of-the-art on tactile object recognition is presented. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

MMX Locomotion Subsystem: mechanics for extraterrestrial low gravity drive

MMX Locomotion Subsystem: mechanics for extraterrestrial low...

引用

IEEE Conference on Aerospace

作者： Viktor Langofer Ralph Bayer Alexander Kolb Kaname Sasaki German Aerospace Center (DLR) Institute of Robotics and Mechatronics Weßling German Aerospace Center (DLR) Institute of Space Systems Bremen

The advent of exploring low-gravity environments gives the opportunity to land rovers on celestial bodies without any landing platform and perform manipulative tasks under mostly unknown conditions. In addition to common loads, for example vibration, operation and thermal loads, the rover will face also impact loads during touchdown. This circumstance re-quires additional mechanisms to protect exposed parts, like the legs and wheels of a rover. Previous research attaches the wheels to the rover body or the landing platform through cup-cone interfaces at the wheel hub, which leads to unfavorable force distribution at the wheel rim in certain load cases, especially if the wheel represents the first point of contact during touchdown. This paper gives a detailed description in the mechanical design and testing of the locomotion subsystem (LSS) of the Martian Moons eXploration (MMX) rover. As the rover will fall to the moon Phobos unprotected and without any landing platform, the exposed locomotion subsystem has a high probability of being the initial contact point at touchdown. Besides the driv-etrains and thermal hardware, a novel hold down and release mechanism (HDRM) will be introduced as an integral part of the locomotion subsystem. The HDRM is realized using three support structures at the wheel rim and one fixation in the wheel axis. In this way, the exposed locomotion subsystem will be stabilized in described load cases, since each support structure forms a closed kinematic loop with the wheel and the central fixation in stowed configuration. This approach leads to vibration and impact resistant behavior.

关键词： Vibrations Legged locomotion Mars Moon Wheels Kinematics Hardware

来源：评论

学校读者我要写书评

暂无评论

A Data-Centric Approach for Object Recognition in Hemispherical Camera Images

A Data-Centric Approach for Object Recognition in Hemispheri...

引用

Annual Conference of Industrial Electronics Society

作者： Zarema Balgabekova Muslim Alaran Huseyin Atakan Varol Inst. of Smart Systems and AI Nazarbayev University Astana Kazakhstan Dept. of Robotics and Mechatronics Nazarbayev University Astana Kazakhstan

Object recognition is a machine learning problem that involves the correct classification and localization of objects in an image. Object recognition has found wide applications in Industry 4.0, surveillance, and autonomous driving. Prominent datasets such as Pascal VOC, ImageNet, and MS COCO have further spurred advances in object recognition. However, the images in these datasets were captured using ordinary perspective lenses. Unlike ordinary cameras, fisheye or hemispherical cameras have a wide FoV reaching 180°. Due to this property, they can acquire wide panoramic images, thus, capturing more objects in a scene as compared to ordinary perspective lenses. In this work, we provide the first benchmark testing dataset of real fisheye images containing commonly-occurring objects in the human environment obtained with hemispherical cameras. The dataset comprises 1,000 images containing 39 classes with a total number of 14,218 object instances. We trained the YOLOv7 model on the original MS COCO and transformed FisheyeCOCO datasets and tested the obtained models with our dataset. The results indicate that training the model on the combination of original and transformed datasets improves the performance by 2.5% compared to using these datasets separately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-layer Disturbance Observer-based Wheel Speed Control for Electric Vehicles

Multi-layer Disturbance Observer-based Wheel Speed Control f...

引用

Annual Conference of Industrial Electronics Society

作者： Yussuf Shakhin Ahmad Bala Alhassan Binh-Minh Nguyen Ton Duc Do Dept. of Robotics and Mechatronics School of Engineering and Digital Science (SEDS) Nazarbayev University Astana Kazakhstan Dept. of Advanced Energy The University of Tokyo Tokyo Japan

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

As the adoption of electric vehicles (EVs) increases globally, there is a need to provide effective control for the safety and stability of the vehicles. In this paper, a cascade observer-based wheel speed control of an EV is proposed. The scheme uses three-loop cascade observers to estimate the wheel speed, which is often difficult to measure and critical for the EV’s control. The study only uses the measurement of the motor speed and torque to estimate the wheel speed from the observation of the total disturbances acting on the EV. A PID control is then designed for the control of the wheel speed using the estimated speed. The effectiveness of the designed observers and the wheel speed control is investigated using Matlab simulation under the influence of parametric uncertainties and external disturbance.

关键词： Torque Uncertainty Simulation Velocity control Wheels Motors Electric vehicles Stability analysis Safety Torque measurement

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：