检索结果-内蒙古大学图书馆

Out-of-Distribution Detection Algorithms for Robust Insect Classification

Plant Phenomics 2024年第2期6卷 433-444页

作者： Mojdeh Saadati Aditya Balu Shivani Chiranjeevi Talukder Zaki Jubery Asheesh K.Singh Soumik Sarkar Arti Singh Baskar Ganapathysubramanian Department of Computer Science Iowa State UniversityAmesIAUSA Department of Mechanical Engineering Iowa State UniversityAmesIAUSA Department of Agronomy Iowa State UniversityAmesIAUSA

Plants encounter a variety of beneficial and harmful insects during their growth *** identification(i.e.,detecting insects'presence)and classification(i.e.,determining the type or class)of these insect species is critical for implementing prompt and suitable mitigation *** timely actions carry substantial economic and environmental *** learning-based approaches have produced models with good insect classification *** aim to implement identification and classification models in agriculture,facing challenges when input images markedly deviate from the training distribution(e.g.,images like vehicles,humans,or a blurred image or insect class that is not yet trained on).

关键词： distribution robust detection algorithms classification insect

来源：评论

学校读者我要写书评

暂无评论

Warehouse Drone Inventory Management System Using OpenCV 25

Warehouse Drone Inventory Management System Using OpenCV

引用

25th International Seminar on Intelligent Technology and Its Applications, ISITIA 2024

作者： Afandi, Muzakki Dewi, Tiara Kusuma Widianingrum, Sinta Farizki, Muhammad Aldrifa Athhar Endrasari, Fitri Saptaji, Kushendarsyah Hadisujoto, Ignatius Budi Sutanto Djamari, Djati Wibowo Sampoerna University Computer Science Jakarta Indonesia Sampoerna University Mechanical Engineering Jakarta Indonesia

ISBN: (纸本)9798350378573

This research investigates the application of drone technology for enhancing inventory management efficiency. Utilizing DJI Tello Drones with integrated cameras, controlled via a Wi-Fi connection, and supported by OpenCV software on a PC, this study evaluates the effectiveness of drones in capturing and processing warehouse inventory data. The captured video feeds are analyzed for detection and recognition, with the results integrated into a real-time database. The study uses three ranges of 20 m, 50 m, and 100 m for the distance between the drone and the receiver device to analyze the distance factor affecting the latency. It is found that lower range between the drone and the receiver device results in better latency level. The experiment is conducted using the 20m distance for reduced latency. Experimental results demonstrate that drones can significantly reduce the time required for inventory tasks, with a recorded time of 2 minutes to document 16 items, compared to 15 minutes for manual checks. Additionally, the drones maintained a high detection accuracy, with an average successful detection distance of 0.55 meters for 8x8 cm QR codes. These findings substantiate the potential of drones and computer vision technology to optimize warehouse operations and supply chain management by increasing inventory accuracy, reducing labor costs, and improving responsiveness. This research contributes to the advancement of drone-enabled solutions across various industries, offering a pathway towards more efficient and agile inventory management practices. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Design of electric powertrains to achieve NVH performance using autoencoders and a physical meaningful latent space

引用

Neural Computing and Applications 2025年第16期37卷 10287-10308页

作者： Ricardo Souza, Marcos Offner, Guenter Soltoggio, Andrea Mohammadpour, Mahdi Theodossiades, Stephanos Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University Loughborough United Kingdom AVL List GmbH Graz Austria Computer Science Department School of Science Loughborough University Loughborough United Kingdom

One of the fundamental differences in the perception of electric (e-) vehicles is how their radiated noise is perceived with respect to classic internal combustion engines. Even though e-vehicles are usually quieter, the tonal content of the radiated noise can be more annoying. This paper proposes a novel approach that starts from the assumed radiated noise spectrum profile as input to a neural network that can return powertrain design parameters that would lead to generation of that specific noise profile. The proposed network acts as an autoencoder where the latent space is forced to have a physical meaning. As diverse combinations of powertrain parameters can result in similar noise profiles, a variational autoencoder is used to learn a structured latent representation, ensuring continuity and smooth transitions between possible solutions. The network predictions are validated against results of a three-dimensional CAE e-powertrain model. Overall, the mean absolute error is around 5 dBA for this feasibility study, which aims to demonstrate the concept. This work takes an inverse approach to the optimisation problem by starting from the user-perceived noise to predict the parameters required to achieve that. Although this study focuses solely on gear teeth microgeometry changes and bearing preloads, additional powertrain parameters could be incorporated as needed. © The Author(s) 2025.

关键词： Internal combustion engines

来源：评论

学校读者我要写书评

暂无评论

Model-Free Safety Critical Model Predictive Control for Mobile Robot in Dynamic Environments

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Nguyen, Minh-Nhat Van, Mien McIlvanna, Stephen Sun, Yuzhu Close, Jack Olayemi, Kabirat Jin, Yan School of Electronics Electrical Engineering and Computer Science Queen's University Belfast Belfast United Kingdom School of Mechanical and Aerospace Engineering Queen's University Belfast Belfast United Kingdom

Within the context of Nonlinear Model Predictive Control (NMPC) design for autonomous mobile robots, which face challenges such as parametric uncertainty and measurement inaccuracies, focusing on dynamic modelling and parameter identification becomes crucial. This paper presents a novel safety-critical control framework for a mobile robot system that utilises NMPC with a prediction model derived entirely from noisy measurement data. The Sparse Identification of Nonlinear Dynamics (SINDY) is employed to predict the system's state under actuation effects. Meanwhile, the Control Barrier Function (CBF) is integrated into the NMPC as a safety-critical constraint, ensuring obstacle avoidance even when the robot's planned path is significantly distant from these obstacles. The closed-loop system demonstrates Input-to-State Stability (ISS) with respect to the prediction error of the learned model. The proposed framework undergoes exhaustive analysis in three stages, training, prediction, and control, across varying noise levels in the state data. Additionally, validation in Matlab and Gazebo illustrates that the NMPC-SINDY-CBF approach enables smooth, accurate, collision-free movement, even with measurement noise and short prediction times. Our findings, supported by tests conducted with the Husky A200 robot, confirm the approach's applicability in real-time scenarios. IEEE

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Active thermal balance control for improving orientation error of vertical machine tool spindle

引用

Precision engineering 2024年 88卷 686-698页

作者： Liu, Yu-Chi Liao, Chien-Wei Lee, Ming-Tsang Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung411030 Taiwan Department of Power Mechanical Engineering National Tsing Hua University Hsinchu300044 Taiwan

In this study, a thermal balance control method by local heating on the spindle head structure of a vertical milling machine was proposed to improve the squareness error of the Y-Z plane. Thermal deformation and temperature distribution of the spindle head structure was analyzed to determine the key positions on the structure for prediction and control of the spindle pose. A long short-term memory (LSTM) neural network with time series characteristics was used to build the in-situ spindle tilt error prediction model. The particle swarm optimization algorithm was integrated with a neural network model to dynamically determine and find temperature control targets in local positions on the spindle head. Finally, the temperatures at selected local locations of spindle head was adjusted by elective heating to suppress thermal bending and improve the spindle tilt on the Y-Z plane. The proposed method was verified using a five-axis vertical milling machine. The experimental results showed that the proposed method could effectively maintain the spindle tilt in the Y direction at [10, −10] μrad after long-time operation of the spindle at both 7200 and 12,000 rpm. © 2024 Elsevier Inc.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Machine learning based Development and Evaluation of a Hand Exoskeleton Rehabilitation Robot for Patients with Partial Paralysis 2

Machine learning based Development and Evaluation of a Hand ...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Singh, Durgesh Kumar Srivastava, Anand Prakash Singh, Shivanshu Paliwal, Sanjay Singh, Anupam Singh, Jagendra Hi-Tech Institute of Engineering & Technology Mechanical Engineering Department Ghaziabad India Nitra Technical Campus Department of Computer Science Ghaziabad India R D Engineering College Mechanical Engineering Department Ghaziabad India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798350371055

This work focuses on the estimation of elbow joint angles from electromyography (EMG) signals and investigates the use of machine learning models in rehabilitation robotics. Four distinct machine learning algorithms were tested for their capacity to precisely translate EMG inputs into actuator commands: Artificial Neural Network (ANN), Naive Bayes (NB), Linear Regression (LR), and Decision Trees (DT). The models were trained and tested using a dataset generated by a wireless EMG sensor and motion capture system that recorded the dynamic relationship between elbow movements and related muscle activations. The results show the remarkable 98.7% accuracy of the ANN model, indicating that it can be a valuable tool for real-time rehabilitation robotics applications. Additionally, NB, LR, and DT displayed competitive results that demonstrated their unique capacities to manage a range of sensor inputs. The discussion highlights how important these models' interpretability, computational efficiency, and continuous adaptation are to their successful integration into real-world rehabilitation settings. This work contributes to the field of rehabilitation robotics by applying machine learning models for accurate actuation control based on EMG signals. The findings demonstrate how these models could enhance the accuracy and responsiveness of assistive technology, offering individuals with partial paralysis customized and adaptable rehabilitation regimens. © 2024 IEEE.

关键词： assistive devices electromyography joint angle prediction machine learning Rehabilitation robotics

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Lane Following Network based on Multimodal Sensor Fusion and LiDAR Reconstruction in Extreme Lighting and Snowing Environments 4

Autonomous Vehicle Lane Following Network based on Multimoda...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Padmapriya, J. Meera, V. Murugavalli, S. Karthikeyan, L. Panimalar Engineering College Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai City Campus Chennai India Panimalar Engineering College Department of Mechanical Engineering Chennai India

ISBN: (数字)9798350387063

ISBN: (纸本)9798350387063

The self-driving car industry is gaining attention for its role in motion planning technology. Deep learning approaches have been implemented to plan autonomous vehicles' motion, but their effectiveness depends on the data used in training. Despite advancements, fully autonomous vehicles still face limitations, such as lighting-related issues affecting camera image accuracy, and LiDARs are negatively impacted by challenging weather circumstances like snow in varied snowfall conditions, thus becoming imperative to precisely control the motion of the Autonomous Vehicle. To address this, an architecture based on deep-learning networks is proposed for lane-following on roads, consisting of LiDAR De-snowing, Multi-modal Sensor Fusion, VGG16, and gated recurrent units (GRUs). The Point Reconstruction Network (PR-Net) rebuilds points from neighbors, while the Reconstruction Difficulty Network forecasts reconstruction difficulty. Radar measurements and de-snowed LiDAR point clouds are projected onto the front-view image plane, fed into VGG16 and GRU output layers, and processed into two fully connected layers for steering and speed parameters estimation. © 2024 IEEE.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

Classifying chest x-rays for COVID-19 through transfer learning: a systematic review

引用

Multimedia Tools and Applications 2025年第2期84卷 689-748页

作者： Mallick, Devanshi Singh, Arshdeep Ng, Eddie Yin-Kwee Arora, Vinay Thapar Institute of Engineering & Technology Punjab Patiala India Wipro Limited Gurugram India School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore Singapore Computer Science Engineering Department Thapar Institute of Engineering & Technology Punjab Patiala India

This study makes a comprehensive assessment of the predominant Transfer Learning (TL) techniques employed for the classification of COVID-19 cases in Chest X-rays (CXR) images. The methodologies have been selected on the basis of their merits and demerits, suitability, and possible impact on the development of the region being studied. The study examines the various methods of TL employed in the classification of COVID-19 cases with the objective to gain a deeper understanding about all the aspects of these methodologies. It can be of great significance for the researchers and medical professionals in making well-informed decisions about the implementation of these techniques to improve the precision and effectiveness of COVID-19 diagnosis. The practical consequences of these techniques help in early identification of such cases for having a suitable intervention. As many as 48 studies conducted during the period 2020–2023 have been included in the current research work for having an assessment about the problem under investigation. The study has specifically focused on transfer learning-based models utilized for the identification of COVID-19 through CXR pictures. It highlights the challenges posed by dataset dynamics, methodological variations, and performance metrics of different models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Flexible pressure sensors with ultrahigh stress tolerance enabled by periodic microslits

引用

Microsystems & Nanoengineering 2024年第1期10卷 301-311页

作者： Song Wang Chenying Wang Yifan Zhao Yujing Zhang Yaxin Zhang Xiangyue Xu Qijing Lin Kai Yao Yuheng Wang Feng Han Yu Sun Zhuangde Jiang State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesSchool of Mechanical EngineeringXi’an Jiaotong UniversityXi’anChina State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesSchool of Instrument Science and TechnologyXi’an Jiaotong UniversityXi’anChina The Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingboChina Department of Mechanical and Industrial Engineering University of TorontoTorontoCanada

Stress tolerance plays a vital role in ensuring the effectiveness of piezoresistive sensing films used in flexible pressure ***,existing methods for enhancing stress tolerance employ dome-shaped,wrinkle-shaped,and pyramidal-shaped microstructures in intricate molding and demolding processes,which introduce significant fabrication challenges and limit the sensing *** address these shortcomings,this paper presents periodic microslits in a sensing film made of multiwalled carbon nanotubes and polydimethylsiloxane to realize ultrahigh stress tolerance with a theoretical maximum of 2.477 MPa and a sensitivity of 18.092 kPa−*** periodic microslits permit extensive deformation under high pressure(e.g.,400 kPa)to widen the detection ***,the periodic microslits also enhance the sensitivity based on simultaneously exhibiting multiple synapses within the sensing interface and between the periodic sensing *** proposed solution is verified by experiments using sensors based on the microslit strategy for wind direction detection,robot movement sensing,and human health *** these experiments,vehicle load detection is achieved for ultrahigh pressure sensing under an ultrahigh pressure of over 400 kPa and a ratio of the contact area to the total area of 32.74%.The results indicate that the proposed microslit strategy can achieve ultrahigh stress tolerance while simplifying the fabrication complexity of preparing microstructure sensing films.

关键词： robot shaped stress

来源：评论

学校读者我要写书评

暂无评论

Using FliPSi to Generate Data for Machine Learning Algorithms 28

Using FliPSi to Generate Data for Machine Learning Algorithm...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Liebert, Artur Wittke, Christian Ehrhardt, Jonas Jaufmann, Richard Widulle, Niklas Eilermann, Sebastian Krantz, Maria Niggemann, Oliver Helmut-Schmidt University Computer Science in Mechanical Engineering Hamburg Germany

ISBN: (纸本)9798350339918

Cyber-Physical Production Systems (CPPS) are becoming increasingly important in modern manufacturing, which leads to a growing need for automated anomaly detection, maintenance decision-making, and fault diagnosis. Artificial Intelligence (AI) and Machine Learning (ML) algorithms are often used to perform these tasks. However, there is a shortage of real data sets with fault modes, making it difficult to train ML algorithms. To overcome this problem, we propose the use of the Flexible Production Simulation (FliPSi) to generate simulated data for the development, training and evaluation of ML algorithms. FliPSi is a simulation tool developed in Unity, a game engine, which is used to simulate modular CPPS. It allows the construction of different CPPS, data collection, and generating data which could realistically originate from CPPS. The focus of FliPSi is to generate data for the development, training and testing of anomaly detection and diagnosis algorithms. In this paper, we show that data generated with FliPSi can be used to train ML algorithms, specifically recurrent neural networks (RNNs) and variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), which are specifically designed to process sequential data and that the algorithms trained with these data sets can be employed to detect simulated anomalies. With this, we show that FliPSi can be employed to overcome a blocking issue in using ML algorithms for anomaly detection. © 2023 IEEE.

关键词： Anomaly detection

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：