检索结果-内蒙古大学图书馆

A deep learning-based model for automated STN localization using local field potentials in Parkinson’s disease

Soft Computing 2025年第4期29卷 2343-2362页

作者： Hosny, Mohamed Naeem, Mohamed A. Zhu, Minwei Gao, Wenpeng Elshenhab, Ahmed M. Fu, Yili Department of Electrical Engineering Benha Faculty of Engineering Benha University Benha Egypt State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150080 China Department of Mechatronics and Robotics Engineering Faculty of Engineering South Valley University Qena Egypt First Affiliated Hospital Harbin Medical University Harbin150001 China School of Life Science and Technology Harbin Institute of Technology Harbin150080 China Department of Mathematics Faculty of Science Mansoura University Mansoura35516 Egypt

Accurate identification of the subthalamic nucleus (STN) borders is time-consuming, relying heavily on the neurosurgeon expertise in manually interpreting the electrophysiological signals. Local field potentials (LFPs) have garnered imperative attention due to their strong correlation with the STN. However, existing detection models often face challenges with high computational complexity, hyperparameter optimization and lack of explainability, making them unreliable for clinicians. Therefore, this study introduces an explanatory framework using convolutional neural networks (CNN) for detecting the STN region from LFPs. Continuous wavelet transform is employed to convert LFPs signals into scalogram images, which are then processed by sixteen CNN models. We evaluated our framework by examining the impact of various limiting factors on the classification performance, including model size, learning rate (LR), optimizers and data scaling. Deep features are extracted from the top-performing CNN architectures to capture rich representations of the scalograms. These features are then fused and classified using k-nearest neighbour algorithm. Gradient-weighted class activation mapping is used to explain the decisions made by the proposed model. Our approach achieved an accuracy of 99.61%, outperforming individual CNN models for STN localization. The experimental results revealed that CNN models, embedded with additional hyperparameters and layers, generally outperformed smaller models. Besides, low LR significantly enhanced the performance compared to high LR. Moreover, features extracted from untuned networks produced lower performance than tuned networks. The proposed system could revolutionize deep brain stimulation surgery by increasing efficiency and reducing reliance on clinician expertise for STN detection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

General Optimal Trajectory Planning:Enabling Autonomous Vehicles with the Principle of Least Action

引用

Engineering 2024年第2期33卷 63-76页

作者： Heye Huang Yicong Liu Jinxin Liu Qisong Yang Jianqiang Wang David Abbink Arkady Zgonnikov School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China Department of Cognitive Robotics Faculty of MechanicalMaritime and Materials Engineering(3mE)Delft University of TechnologyDelft 2628Netherlands Department of Software Technology Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyDelft 2628Netherlands Xi’an Institute of High-Technology Xi’an 710051China

This study presents a general optimal trajectory planning(GOTP)framework for autonomous vehicles(AVs)that can effectively avoid obstacles and guide AVs to complete driving tasks safely and ***,we employ the fifth-order Bezier curve to generate and smooth the reference path along the road *** coordinates are then transformed to achieve the curvature continuity of the generated *** the road constraints and vehicle dynamics,limited polynomial candidate trajectories are generated and smoothed in a curvilinear coordinate ***,in selecting the optimal trajectory,we develop a unified and auto-tune objective function based on the principle of least action by employing AVs to simulate drivers’behavior and summarizing their manipulation characteristics of“seeking benefits and avoiding losses.”Finally,by integrating the idea of receding-horizon optimization,the proposed framework is achieved by considering dynamic multi-performance objectives and selecting trajectories that satisfy feasibility,optimality,and *** simulations and experiments are performed,and the results demonstrate the framework’s feasibility and effectiveness,which avoids both dynamic and static obstacles and applies to various scenarios with multi-source interactive traffic ***,we prove that the proposed method can guarantee real-time planning and safety requirements compared to drivers’manipulation.

关键词： Autonomous vehicle Trajectory planning Multi-performance objectives Principle of least action

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Modelling and Safety Assurance of an Agriculture Robot Providing Light-Treatment 19

Probabilistic Modelling and Safety Assurance of an Agricultu...

引用

19th IEEE International Conference on Automation science and Engineering, CASE 2023

作者： Adam, Mustafa Ye, Kangfeng Anisi, David A. Cavalcanti, Ana Woodcock, Jim Morris, Robert Robotics Group Faculty of Science & Technology Norway University of York Dept. of Computer Science United Kingdom Faculty of Engineering and Science Dept. of Mechatronics Norway Saga Robotics As Norway

ISBN: (纸本)9798350320695

Continued adoption of agricultural robots postulates the farmer's trust in the reliability, robustness and safety of the new technology. This motivates our work on safety assurance of agricultural robots, particularly their ability to detect, track and avoid obstacles and humans. This paper considers a probabilistic modelling and risk analysis framework for use in the early development phases. Starting off with hazard identification and a risk assessment matrix, the behaviour of the mobile robot platform, sensor and perception system, and any humans present are captured using three state machines. An auto-generated probabilistic model is then solved and analysed using the probabilistic model checker PRISM. The result provides unique insight into fundamental development and engineering aspects by quantifying the effect of the risk mitigation actions and risk reduction associated with distinct design concepts. These include implications of adopting a higher performance and more expensive Object Detection System or opting for a more elaborate warning system to increase human awareness. Although this paper mainly focuses on the initial concept-development phase, the proposed safety-assurance framework can also be used during implementation, and subsequent deployment and operation phases. © 2023 IEEE.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

Smart IoT platform for Big Data analysis in predictive maintenance 24

Smart IoT platform for Big Data analysis in predictive maint...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Przepiora, Jan Balazy, Patryk Ksiazek, Piotr Knap, Pawel Paslawski, Pawel Pietrzak, Michal AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Kraków Poland

ISBN: (纸本)9798350310221

A smart IoT platform for big data analysis in predictive maintenance can help achieve goals of predictive maintenance by collection, processing, and analysis of data from various sensors. This platform can use machine learning algorithms and other advanced techniques to identify patterns and trends that can be used to predict when equipment is likely to fail, allowing maintenance teams to take proactive action to prevent those failures from occurring. © 2023 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

A preliminary measurement verification of sound power level emitted by biomimetic drone propellers inspired by an owl's feather 24

A preliminary measurement verification of sound power level ...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Ksiazek, Piotr Lalik, Krzysztof Paslawski, Pawel Pietrzak, Michal Przejczowski, Pawel Przepiora, Jan AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Kraków Poland

ISBN: (纸本)9798350310221

The research issue addressed in the project is to investigate methods of reducing acoustic emissions of unmanned aerial vehicle propellers. S.O.W.A (Silent Observer of the Wild Animals) is an arrangement that mimics the structure of an owl's feathers. Rotor blades based on owl feathers have been constructed to suppress the noise produced during flight. Acoustic emissions, were measured with accordance to ISO 3741:2010. Sound power level of different design variants was discussed. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Target Detection and Tracking of Survey Robots Using Multimodal Internet of Things Sensor data Fusion Using YOLOv5 2

Target Detection and Tracking of Survey Robots Using Multimo...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Ye, Chengjing Wu, Miaoyong Yang, Yefen Zhang, Ke Bu, Xinhua Huang, Miaomiao Guangdong Polytechnic of Science and Technology Faculty of Robotics Guangdong Zhuhai China Guangdong Polytechnic of Science and Technology Computer Engineering Technical College Guangdong Zhuhai China Faculty of Architectural Engineering Guangdong Polytechnic of Science and Technology Guangdong Zhuhai China

ISBN: (纸本)9798350382952

In recent years, due to the rapid development of computer vision technology, real-time detection and tracking of objects using computer vision has become a hot topic. Object detection mainly consists of two parts: object segmentation and object recognition, that is, object acquisition. Accurate detection of targets is the key to achieving high-precision and high-efficiency tracking. Based on the above discussion, this article explored the target detection and tracking of survey robots using the multimodal Internet of Things (IoT) sensor data fusion of YOLOv5, and compared and analyzed the performance of direct frame difference method, traditional ORB method, and the algorithm in this paper through experiments. The results indicated that the accuracy and recall of the robot image object detection algorithm proposed in this paper were both above 90%, and higher than other algorithms, indicating that the algorithm has extremely high accuracy in object detection. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Recent Research on Variants of the Location Routing Problem

引用

Journal of Japan Industrial Management Association 2022年第2期73卷 75-91页

作者： Hosoda, Junko Irohara, Takashi Control and Robotics Innovation Center Hitachi Ltd Japan Faculty of Science and Technology Sophia University Japan

The location routing problem (LRP) is an important focus in logistics that has been studied extensively since the 1970s. Within the past five years, improvements in computer performance and an enhanced emphasis on logistics has led to consideration of LRP variants. Given this context, a survey of LRP studies published between 2015 and 2020 was conducted. Two key trends were found in the literature: 1) The number of studies on LRP variants has rapidly increased, and 2) the constraints on LRP variants have become more complicated as they are applied to solve social issues. In the future, it is very likely that the number of LRP applications will be expanded, and more variants will be proposed. © 2022 Japan Industrial Management Association. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF WIND TURBINE ACOUSTIC SIGNALS IN TERMS OF DETECTING AMPLITUDE MODULATION AND FREQUENCY DEVIATION 10

ANALYSIS OF WIND TURBINE ACOUSTIC SIGNALS IN TERMS OF DETECT...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Czapla, Marcjanna Wszolek, Tadeusz Department of Mechanics and Vibroacoustic Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Poland

ISBN: (纸本)9788888942674

The phenomenon of amplitude modulation has been subject of numerous scientific studies [1-4]. However, the problem remains of determining the depth of AM's impact on the increase in annoyance of wind turbine noise. The results of this research showing the characteristic features and depth of AM in different frequency bands. In addition, it has been shown that, in the recorded results, modulation (deviation) of the frequency of the modulated band occurs simultaneously with amplitude modulation. Cyclical changes in the density distribution of spectra in time and space have been demonstrated. Examples have been presented show that defined metrics to determine the variability of modulation frequency depending on the observer's position relative to the signal source. One such parameter that can demonstrate objective frequency offset is the popular shimmer indicator. © 2023 First author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Identify the objective parameters of direct communication between PLC and MS SQL server 24

Identify the objective parameters of direct communication be...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Flaga, Stanislaw Majcher, Maciej AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Process Control Krakow Poland

ISBN: (纸本)9798350310221

When building digital twins of existing technical solutions, we need a large amount of data on the parameters of their operation under various conditions. The source of data on the values of process variables at the lowest level is control devices - most often PLCs. There are many ways to acquire the qualities of process variables available from the PLC level. Increasingly, OPC UA is replacing the OPC model, and the OPC UA server is increasingly a functionality of the PLC CPU. The Industrial Internet of Things IIoT is used in companies moving toward Factory 4.0. Data from controllers can be acquired using high-level languages such as C++, C# or Python. Libraries often made available under an open-source license are used for this. For example, you can find commercial libraries for communication between PLCs of selected manufacturers and MySQL servers. Siemens provides a library for communication between S7-1200/1500 controllers and MS SQL server. The author has yet to find an exhaustive analysis of such a solution. In the literature, there need to be more studies of experiments describing the performance of query generation and execution and the impact of the library on PLC performance. The article presents the results of an experimental study of this issue. © 2023 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Research study of image classification algorithms based on Convolutional Neural Networks 24

Research study of image classification algorithms based on C...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Nawrocka, Agata Nawrocki, Marcin Kot, Andrzej AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Process Control Krakow Poland

ISBN: (纸本)9798350310221

The beginning of the paper introduces the idea of neural networks by presenting the neuron models and artificial neural networks. Next, the flow of operations used in the development of convolutional neural networks is presented, as well as an overview of popular architectures used in model development. After introducing the theoretical issues, a project using the EfficientNet architecture to recognize medical images taken by MRI is presented. The project describes: the selection and parameters of the MRI image database representing different types of brain tumors, the process of implementation and appropriate modification of the EfficientNet architecture used to classify images, the presentation of the results of learning the convolutional neural network and the images that highlight on the basis of which area the convolutional neural network classifies images. © 2023 IEEE.

关键词： Convolutional 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：