检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Das, Swagatam Granger, Eric García, Salvador Dept. of Automation Shanghai Jiao Tong University Shanghai China Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata India Dept. of Systems Engineering Ecole de tech-nologie supérieure Université du Québec Montreal Canada Dept. of Computer Science and Artificial Intelligence University of Granada Granada Spain

Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing. However, this hierarchical relationship modeling is computationally expensive, which has limited the wider use of CapsNet despite its potential advantages. The current state of CapsNet models primarily focuses on comparing their performance with capsule baselines, falling short of achieving the same level of proficiency as deep CNN variants in intricate tasks. To address this limitation, we present an efficient approach for learning capsules that surpasses canonical baseline models and even demonstrates superior performance compared to high-performing convolution models. Our contribution can be outlined in two aspects: firstly, we introduce a group of subcapsules onto which an input vector is projected. Subsequently, we present the Hybrid Gromov-Wasserstein framework, which initially quantifies the dissimilarity between the input and the components modeled by the subcapsules, followed by determining their alignment degree through optimal transport. This innovative mechanism capitalizes on new insights into defining alignment between the input and subcapsules, based on the similarity of their respective component distributions. This approach enhances CapsNets’ capacity to learn from intricate, high-dimensional data while retaining their interpretability and hierarchical structure. Our proposed model offers two distinct advantages: (i) its lightweight nature facilitates the application of capsules to more intricate vision tasks, including object detection;(ii) it outperforms baseline approaches in these demanding tasks. Our empirical findings illustrate that Hybrid Gromov-Wasserstein Capsules (HGWCapsules) exhibit enhanced robustness against affine transformations, scale effectively to larger datasets, and surpass CNN and CapsNet models across various vision tasks. © 202

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Implementation of Industrial automation Sustainable Training in Savannakhet University, Laos

Implementation of Industrial Automation Sustainable Training...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Tsvetelina Georgieva Nina Bencheva Plamen Daskalov Hamed Yahoui Sitha Khemmarath Khonesavanh Norasane Lamnguen Chanthanouvong Youlananh Leaunglith Vinai Keovorabouth Automation and Mechatronics Department University of Ruse “Angel Kanchev” Ruse Bulgaria Telecommunications Department University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Mechanical Engineering Automation &Processing Claude Bernard University Lyon 1 Lyon France Faculty of Engineering Savannakhet University Savannakhet Laos Technology computer network Dept. Faculty of Information Technology Savannakhet University Savannakhet Laos Faculty of Information Technology Savannakhet University Savannakhet Laos

The paper presents part of the work fulfilled under the Asean Factori 4.0 Erasmus+ project focused on the implementation of industrial automation in the education in 6 universities from 3 countries in South-East Asia: Thailand, Laos and Cambodia. The implementation of the project tasks, related to increasing the capacity and more precisely to the training of the professors from the Asian Universities is presented. According to the planned activities, professors from the University of Ruse conduct training for teachers from two universities: Chulalongkorn University, Thailand and Savannakhet University, Laos. The phases of training included in the project activities and how many of them have already been implemented are briefly presented. The program and the tasks of the teachers practical training for building the necessary teaching capacity in Savannakhet University and implementation of sustainable training in the field of industrial automation were presented and analyzed. Conclusions and future training of the staff of Asian universities planned under the project are presented in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Training and Adapting Algorithms in Medical with De-Noising EEG

Evaluation of Deep Training and Adapting Algorithms in Medic...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Ali Hadi Abdulwahid Girija Rani Karetla KVB. Ganesh A Suresh Kumar K. Radha K. Shivakumar Control and Automation Engineering Department Engineering Technical College Southern Technical University Basra Iraq School of Computer Data and Mathematical Sciences Western Sydney University Australia KL Business School Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India Department of CSE Graphic Era Deemed to be University Dept. of IT St. Martin's Engineering College Secunderabad Telangana India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

An electroencephalogram that was captured with electrodes placed can easily get contaminated with a variety of artifacts. Here is a comparative of various electroencephalogram (EEG) de-noising techniques. Three alternative techniques are used to eliminate five different kinds of noise, and also the outcomes are evaluated. These three methods are just the Least Mean Square (LMS) technique, the Connected Neural Network, and also the Recursive Least - square (RLS) adaptable algorithm (FCNN). Period charts of the actual EEG signal, the noise EEG signal, and thus the predicted EEG signal are used to display the results. RRMSE and signal- to-noise ratio were utilized to compare the effectiveness of the 3 de-noising strategies in this study. Investigating the model parameters in this case, we discover the FCNN forecasts a better outcome compared to the other two methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion detection in infants using an ensemble classifier with a novel member selection technique

Emotion detection in infants using an ensemble classifier wi...

引用

2020 Summer computer Simulation Conference, SCSC 2020, Held at the 2020 Summer Simulation Multi-Conference, SummerSim 2020

作者： Fahmy, Hesham Ahmed Fahmy, Sherif Fadel Del Barrio García, Alberto A. Juan, Guillermo Botella Dept. of Electronics and Communications Dept. of Computer Engineering Arab Academy for Science Technology and Maritime Transport 2401 Smart Village Campus Giza12577 Egypt Dept. of Computer Architecture and Automation Complutense University of Madrid Ciudad Universitaria C/ Jose Santesmases 9 Madrid28040 Spain

ISBN: (纸本)9781713819462

In this paper, we develop a method for detecting infant emotion from images using machine learning techniques. It is important to develop automatic infant emotion detection algorithms as they can become part of an integrated system that monitors the well-being of infants at home and in institutional settings. In particular, we develop an ensemble classifier that combines the results from diverse individual classifiers to produce better classification results. We present a novel method for selecting members of the ensemble that is based on the Pearson correlation coefficient of the location of the errors in the classifiers. The results show that the ensemble classifier outperforms individual classifiers by at least 1.4 times, and outperforms a state-of-the-art open-source algorithm for adult emotion detection by a larger margin. The results also indicate that Pearson Correlation among classifiers at a certain number of classifier count is a good criterion for selecting ensemble members. ©2020 Society for Modeling & Simulation (SCS) International

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Synchronizing sequences for verification of finite state machines

Synchronizing sequences for verification of finite state mac...

引用

2019 International Conference on Information and Telecommunication Technologies and Radio Electronics, UkrMiCo 2019

作者： Mroshnyk, Maryna Shkil, Olexander Kulak, Elvira Rakhlis, Dariia Pahomov, Yurii Mroshnyk, Anatolii Dept. Specialized Computer Systems Ukrainian State University of Railway Transport Kharkiv Ukraine Dept. Computer Engineering Design Kharkiv National University of Radio Electronics Kharkiv Ukraine Dept. Automation and Control in Technical Systems of the National Technical University Kharkov Polytechnic Institute Kharkiv Ukraine

ISBN: (纸本)9781728126920

The method of detection and localization of design errors in HDL-models of finite state machines with arbitrary output functions was proposed. The diagnostic experiment is carried out bypassing all arcs of the Mealy machine, starting from the initial vertex, including for machines of the "nonexclusive" class. To ensure the return of the machine with a possible design error in the initial state, it is suggested to use synchronizing sequences. Diagnostic experiments were performed in the Active-HDL design environment. © 2019 IEEE

关键词： Diagnistic experiment HDL State diagram State machine Tests Verification Waveform

来源：评论

学校读者我要写书评

暂无评论

Active Disturbance Rejection Control for 3D Crane Systems

引用

Procedia computer Science 2024年 242卷 976-983页

作者： Raul-Cristian Roman Radu-Emil Precup Emil M. Petriu Politehnica University of Timisoara Dept. Automation and Applied Informatics Bd. V. Parvan 2 300223 Timişoara Romania Center for Fundamental and Advanced Tech. Res. Romanian Academy – Timisoara Br. Bd. Mihai Viteazu 24 300223 Timisoara Romania University of Ottawa School of Electrical Engineering and Computer Science 800 King Eduard Ottawa ON K1N 6N5 Canada

Active Disturbance Rejection Control (ADRC) is a data-driven algorithm that offers a promising approach for robust control design. This paper investigates the effectiveness of first-order and second-order ADRC for 3D cranes. To compare the results fairly and reduce the heuristics in parameter tuning, the ADRC parameters were optimally computed via the African Vultures Optimization Algorithm. Both controllers based on ADRC are validated using experiments on a 3D crane laboratory system and their design and performance evaluation are done by minimizing the sum of squared errors. The results demonstrate the robustness of the ADRCs. This comparative analysis highlights the advantages and limitations of both control strategies, providing valuable insights for selecting the appropriate ADRC order for specific applications.

关键词： 3D crane systems ADRC data-driven control optimization

来源：评论

学校读者我要写书评

暂无评论

GWO-based Modeling of an Unstable Transport System 9th

GWO-based Modeling of an Unstable Transport System

引用

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Gale-Cazan, Cristiana-Bogdana Bojan-Dragos, Claudia-Adina Precup, Radu-Emil Roman, Raul-Cristian Petriu, Emil M Szedlak-Stinean, Alexandra-Iulia Politehnica University of Timisoara Dept. Automation and Applied Informatics Bd. V. Parvan 2 Timisoara300223 Romania Center for Fundamental and Advanced Technical Research Romanian Academy Timisoara Branch Bd. Mihai Viteazu 24 Timisoara300223 Romania University of Ottawa School of Electrical Engineering and Computer Science 800 King Eduard OttawaONK1N 6N5 Canada

The goal of this paper is to obtain optimal models of an unstable transport system, which is a nonlinear process represented by the two-wheeled unstable transport system. An optimization problem is defined in order to ideally minimize and practically reduce the differences of the outputs of the real-time laboratory equipment with respect to the outputs of the nonlinear model. The parameters of the nonlinear models are optimally tuned using a recent metaheuristic optimization algorithm, namely the Grey Wolf Optimizer, which solves three optimization problems. A comparison of the responses of the real-time laboratory equipment and the derived optimal nonlinear models is carried out in various simulation scenarios, which are discussed and analyzed. © 2022 The Authors. Published by Elsevier B.V.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Young Driver Gaze (YDGaze): Dataset for driver gaze analysis

Young Driver Gaze (YDGaze): Dataset for driver gaze analysis

引用

Artificial Intelligence of Things (ICAIoT), International Conference on

作者： Süleyman Çeven Ahmet Albayrak Raif Bayır Dept. of Electronics and Automation Tech. Düzce Vocational School Düzce University Düzce Turkey Department of Computer Engineering Faculty of Engineering Düzce University Düzce Turkey Department of Mechatronics Engineering Faculty of Technology Karabük University Karabük Turkey

One of the most important factors in ensuring successful and safe driving in the road traffic network is the driver’s sense of sight. The driver can determine the environmental factors in the traffic with his gaze and can predict the next move after evaluating it with the current driving position. In this process, the focus of the driver’s gaze should be on the area to which the vehicle is heading. Driver eye movements and gaze analysis is a topic that has been intensively studied in recent years in “Intelligent Driver Assistance Systems”. In this study, a data set was prepared with a group of 40 participants between the ages of 18–28 in order to determine which points the driver looked at while driving. The dataset was created by having each participant look at the labeled areas on the vehicle in turn for one minute. Experimental studies lasted approximately 11 days. Approximately 350 hours of work was carried out to prepare the obtained data set.

关键词： Roads Environmental factors Safety Internet of Things Artificial intelligence Vehicles

来源：评论

学校读者我要写书评

暂无评论

Development of CAN and OBD-II Supported Experimental Setup for Vehicle ECU Data Acquisition

Development of CAN and OBD-II Supported Experimental Setup f...

引用

Artificial Intelligence of Things (ICAIoT), International Conference on

Today, CAN Bus protocol is widely used in various technological fields such as industrial, medical or automotive. Data is provided from ECUs and diagnostic codes through the OBD-II system, which is a standard in vehicles. The aim of this study is to develop an experimental setup to analyze driver driving skills based on vehicle data obtained over CAN Bus protocol with an open-source software. In this study, an experimental setup with a PiCAN 2 module and an LCD touch screen compatible with Raspberry Pi 3 Model B+ has been developed. Thanks to the developed experimental setup, it is connected to the vehicle ECU via an OBD-II connector to obtain real-time ECU data of the vehicle. This article presents validation tests to determine the design and construction phases of the system and its functionality as a data logger. Python programming language CAN software library was used on the experimental setup.

关键词： Protocols Software libraries Data acquisition Touch sensitive screens Real-time systems Standards Open source software

来源：评论

学校读者我要写书评

暂无评论

Constructing Multi-granular Knowledge Graph with Structure Similarity and Hierarchical Clustering

Constructing Multi-granular Knowledge Graph with Structure S...

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Ke Yang Jingyun Feng Zhiyu Xi Qiuke Zheng Huan Zhang Wei Deng China Railway Eryuan Engineering Group Co. Ltd. Chengdu China Dept. of Statistics Southern University of Science and Technology Shenzhen China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science and Artificial Intelligence Southwestern University of Finance and Economics Chengdu China School of Statistics Southwestern University of Finance and Economics Chengdu China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350363203

ISBN: (纸本)9798350363210

The structure of knowledge graph is basically flat and lack of hierarchies to make knowledge graph too general to deal with concrete reasoning problems. There are few work about hierarchical knowledge graph. In this paper, the entity and relation combined method is proposed to divide the entities into groups based on structure similarity. The hierarchical cluster method is proposed with the entity and relation combined embedding representation to construct a multi-granular knowledge graph. The experimental results show that the hierarchical division relied on combined embedding are significantly better than those based on the existing entity embedding methods in three evaluation indexes. The combined embedding can capture the structure information which is helpful to hierarchical knowledge graph accurately and reasonably.

关键词： Accuracy Large language models Clustering algorithms Knowledge graphs Cognition Classification algorithms Indexes Informatics

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：