检索结果-内蒙古大学图书馆

3rd International conference on Smart Grid and Renewable Energy, SGRE 2022

ISBN: (纸本)9781665479080

The proceedings contain 61 papers. The topics discussed include: simulation platform for power packet distribution;the effect of relay coordination on cost - a sample of a medium voltage feeder;buck-boost resonant Z-source partial power converter;reassessment of bill management by batteries with various TOU tariffs: a pilot project from Turkey;a coplanar waveguide based antenna for partial discharge detection in gas-insulated switchgear;on-grid photovoltaic energy system - a case study;efficient data processing and storage at phasor data concentrators in smart grids;analysis of the view factors in rooftop PV solar;stochastic simulations of the optimal control of a standalone microgrid at the scale of two houses;a MATLAB/Simulink model for electric vehicle with four independent in-wheel drive and steering;modified particle swarm optimization algorithms for solving economic load dispatch;and efficient deep learning based detector for electricity theft generation system attacks in smart grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning based Real-time Stolen Vehicle Detection Model with Improved Precision and Reduced Look Up Time 3

Deep Learning based Real-time Stolen Vehicle Detection Model...

引用

3rd IEEE International conference on intelligent Technologies, CONIT 2023

作者： Shafi, Shaik Pavan Sai Kumar Reddy, T. Silla, Rohan Yasmeen, Musrath B V Raju Institute of Technology Dept of ECE Medak India

ISBN: (纸本)9798350338607

In the recent past, the number of vehicles stolen in India has surged substantially. As per the Acko Vehicle Theft Report, in Delhi-National Capital Region (NCR), for every 12 minute a vehicle is stolen and overall Delhi-NCR accounts for more than 56% of all vehicle thefts in the country. Further, almost 3 lakh automobiles were stolen in the national capital during 2011 and 2020. While Bengaluru, India's second-highest car theft city, accounts for 9% of vehicle theft. There exists plethora of studies for stolen vehicle tracking or detection models. The prior methods employed were time-consuming and inefficient, requiring a lot of human work to go through CCTV video recordings and trace the stolen vehicle. Some models are 96% accurate but are incapable of being employed in real time. Some are inaccurate, yet they are utilized for real-time detection. To overcome this time consuming process, a Deep learning Based Real Time Stolen Vehicle Detection Model is proposed in this paper. Our work aims to reduce the lookup time of the vehicle in CCTV footage besides the several tasks to accomplish, like vehicle and license plate detection, optical character recognition. To achieve this, a deep learning tool known as You Only Look Once (YOLO) v8 algorithm has been used for real-time object recognition in the system. In addition, TensorFlow, an open-source machine learning platform is used for vehicle number plate recognition and for image processing. Using this strategy, we can dramatically shorten the time it takes to find the stolen vehicle. Upon rigorous experiments, results showed that the proposed deep learning based real time framework is viable and can achieve decent detection. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 2020 3rd International conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020

Proceedings - 2020 3rd International Conference on Advanced ...

引用

3rd International conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020

ISBN: (纸本)9781728181431

The proceedings contain 201 papers. The topics discussed include: assessment study of aging life for typical defects in XLPE cable joints;prototype design of landslide forecast system based on Axure;topic analysis of internet public opinion on natural disasters based on time division;research on dynamic detection of geometric parameters of groove rail based on laser triangulation and four-point chord measurement;DCBGCN: an algorithm with high memory and computational efficiency for training deep graph convolutional network;base on the design and implementation of the quality control system of food antioxidant vitamins C;a mobile robot path planning algorithm based on multi-objective optimization;research on property prediction of materials based on machine learning;and Chinese sentence compression algorithm based on deep analysis of sentence hierarchy in multiple application scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Architecture for Production Logistics: The Critical Role of Programmable Logic Controllers (PLCs) 3

Digital Twin Architecture for Production Logistics: The Crit...

引用

3rd International conference on Industry 4.0 and Smart Manufacturing (ISM)

作者： Thurer, Matthias Li, Shan Shan Qu, Ting Jinan Univ Sch Intelligent Syst Sci & Engn Jinan 519000 Guangdong Peoples R China

Digital Twin is a key enabling technology of Industry 4.0, Smart Manufacturing and Made in China 2025, and a broad literature emerged. But existing literature tends to focus on large-scale equipment or large products, often in a fixed position layout. This study argues that this is due to the use of centralized data and system models. It proposes new architectures for digital twins based on local product and resource twins that use digital encapsulated information to create higher level system twins. Using Action Design Research, a first tentative to develop a prototype of this new architecture is presented. A main learning outcome is that the Programmable Logic Controller (PLC) is an essential part of a digital twin implementation, which receives insufficient research attention. The capability of the PLC largely determines the architecture of a digital twin. (C) 2022 The Authors. Published by Elsevier B.V.

关键词： Digital Twin Programmable Logic Controller (PLC) Digital Encapsulated Information Action Design Research Smart Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Design and Research on Visual Recognition System for Fruit Sorting Collaborative Robot 3

Design and Research on Visual Recognition System for Fruit S...

引用

3rd International conference on Networking Systems of AI, INSAI 2023

作者： Ma, Yingchen Zhu, Hanan Jia, Hongli Guo, Chunlai Li, Jiaqi Li, Zhe Harbin Institute of Petroleum College of Intelligent Engineering Harbin China Heilongjiang Agricultural Engineering Vocational College College of Intelligent Engineering Harbin China Harbin Cambridge University IE Technology Research Center Harbin China

ISBN: (纸本)9798350344660

This study aimed to enhance the efficiency and accuracy of fruit sorting through the development of a collaborative robotic vision recognition system based on neural networks. Leveraging convolutional neural networks (CNNs), a substantial dataset of fruit images was collected, preprocessed, and utilized for training. The core algorithm employed was the neural network, particularly effective in pattern recognition and feature extraction. Integration with the control system of collaborative robots allowed real-time fruit identification and analysis using visual sensors during sorting. The system's design considered optimization and acceleration of neural networks, incorporating advanced deep learning techniques like CNNs and recurrent neural networks. This fusion of collaborative robots, neural networks, and visual recognition technologies significantly improved fruit sorting efficiency and accuracy. The automated sorting process achieved through thoughtful system design and optimization reduces labor costs and enhances productivity. Despite notable progress in the design and research of collaborative robotic and neural network-based vision recognition systems, challenges and areas for improvement persist. Future work may involve further optimizing neural network models for increased precision and robustness and refining collaborative robot control strategies for more complex task collaboration. The collaborative robotic and neural network-based vision recognition system opens new possibilities in the field of fruit sorting, propelling the industry towards intelligent and efficient practices, thereby creating greater economic and societal value. © 2023 IEEE.

关键词： Robot vision

来源：评论

学校读者我要写书评

暂无评论

Afault Diagnosis Model of Marine Diesel Engine Lubrication System Based on Improvedextreme learning Machine 3

Afault Diagnosis Model of Marine Diesel Engine Lubrication S...

引用

3rd International Symposium on Resource Exploration and Environmental Science, REES 2019

作者： Zhao, Gang Liu, Zhikun Chen, Long Systems Engineering Research Institute Beijing China

The lubrication system provides lubrication oil to various moving parts in the marine diesel engine. Once faults occurred in lubrication system, it can result in dramatically damage to the diesel engine. Development of fast and accurate fault diagnosis method of lubrication system is therefore highly urged. In this paper, we present a novel intelligent fault diagnosis methodbased on improved extreme learning machine (ELM). Firstly, we use chaotic mapping to enhance capability of the particle swarm optimization (PSO) algorithm;Then, an enhanced PSO algorithm is used to determine initial input weights (connecting input layer nodes and hidden layer nodes) and thresholds of ELM. Finally, we carry out fault diagnosis experiment on the marine diesel engine lubrication system. The experiments demonstrated that the proposed model could achieve more ideal performance. © Published under licence by IOP Publishing Ltd.

关键词： Diesel engines

来源：评论

学校读者我要写书评

暂无评论

Self-calibration of a vision-based sensor network

引用

IMAGE AND VISION COMPUTING 2009年第1-2期27卷 116-130页

作者： Marinakis, Dimitri Dudek, Gregory McGill Univ Ctr Intelligent Machines Montreal PQ H3A 2A7 Canada

When a network of vision-based sensors is emplaced in an environment for applications such as surveillance or monitoring the spatial relationships between the sensing units must be inferred or computed for self-calibration purposes. In this paper we describe a technique to solve one aspect of this self-calibration problem: automatically determining the topology and connectivity information of a network of cameras based on a statistical analysis of observed motion in the environment. While the technique can use labels from reliable cameras systems, the algorithm is powerful enough to function using ambiguous tracking data. The method requires no prior knowledge of the relative locations of the cameras and operates under very weak environmental assumptions. Our approach stochastically samples plausible agent trajectories based on a delay model that allows for transitions to and from sources and sinks in the environment. The technique demonstrates considerable robustness both to sensor error and non-trivial patterns of agent motion. The output of the method is a Markov model describing the behavior of agents in the system and the underlying traffic patterns. The concept is demonstrated with simulation data for systems containing up to 10 agents and verified with experiments conducted on a six camera sensor network. (C) 2006 Elsevier B.V. All rights reserved.

关键词： Sensor networks Perception Self-calibration Topology learning Markov chain monte carlo Expectation maximization

来源：评论

学校读者我要写书评

暂无评论

Public Transportation Prediction with Convolutional Neural Networks 3rd

Public Transportation Prediction with Convolutional Neural N...

引用

3rd European-Alliance-for-Innovation (EAI) International conference on intelligent Transport Systems (INTSYS)

作者： Panovski, Dancho Zaharia, Titus Telecom SudParis UMR CNRS SAMOVAR 5157 IP Paris ARTEMIS Dept Evry France

ISBN: (纸本)9783030388225;9783030388218

Good, efficient and reliable public transportation systems are of crucial importance for all major cities today. In this paper, we propose a concrete solution to a particular problem: improve the prediction of the bus arrival time at each bus stop station on a given itinerary, by taking to account global and local traffic contexts. The main principle consists of modeling the traffic data as an image structure, adapted for applying CNN deep neural networks. The results obtained shows that the proposed approach outperforms traditional machine learning techniques, such as OLS (Ordinary Least Squares) or SVR (Support Vector Regression) with different kernels (RBF or Polynomial), with more than 18% better accuracy prediction, while being computationally faster.

关键词： Machine learning Deep learning Convolutional neural networks Public transportation Traffic prediction Traffic simulation

来源：评论

学校读者我要写书评

暂无评论

Architectural Decorative Image Pattern Recognition in the Context of Iconography for Efficient Information Mining 3

Architectural Decorative Image Pattern Recognition in the Co...

引用

3rd International conference on Sentiment Analysis and Deep learning, ICSADL 2024

作者： Qin, Yu College of Art and Design Guangzhou Panyu Polytechnic Guangzhou City511483 China

ISBN: (纸本)9798350396157

This study addresses the crucial task of architectural decorative image pattern recognition in the context of iconography, with an emphasis on efficient information mining. The proposed research work presents a novel algorithm that combines edge detection, ResNet50, and the triplet attention mechanism for image style analysis. The proposed methodology is organized into comprehensive sections, including a literature review that explores various studies in image pattern recognition. The proposed algorithm focuses on overcoming the challenges faced by existing deep learning methods in capturing aesthetic style features. It introduces a multifaceted self-supervised task and incorporates edge detection using the Canny method, followed by the application of ResNet50 with a triplet attention mechanism. The paper then focuses on the optimization of the network structure for the targeted task of architectural decorative image recognition, introducing a feature embedding encoder (FEE) to effectively handle multi-level structures. In the experimental phase, the proposed model is tested against traditional CNN and FCM models, demonstrating superior performance with recognition accuracy consistently ranging from 97% to 99%. The comparative analysis highlights the effectiveness of the proposed algorithm in achieving high accuracy, positioning it as a promising solution for image recognition tasks. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AraFake: A Deep learning Approach for Arabic Fake News Detection 3

AraFake: A Deep Learning Approach for Arabic Fake News Detec...

引用

3rd International Mobile, intelligent, and Ubiquitous Computing conference, MIUCC 2023

作者： Abd Elminaam, Diaa Salama Abdelaziz, Amr Essam, George Mohamed, Shehab Eldeen Misr International University Faculty of Computer Science Cairo Egypt

ISBN: (纸本)9798350306231

In this digital age, the proliferation of false Arabic news has become prevalent, posing various risks to society. This paper uses Machine learning, Deep learning, and Natural Language Processing techniques to classify Arabic news as fake or real. The spread of such information not only causes harm to the social fabric but undermines the integrity of digital information and creates an environment of hate, mistrust, and deception, weakening the bonds of social trust. This research can help eliminate and flag Arabic news that contains such threats by leveraging modern technologies. The Arabic language is morphologically rich, meaning words can have multiple meanings depending on their inflectional form. Furthermore, Arabic has numerous diacritics, which are small marks that indicate the pronunciation of vowels;this can make it harder to classify Arabic text. However, modern Natural Language Processing techniques provide enough assistance to eliminate these problems. We aim to utilize numerous approaches from Machine earning and Deep learning perspectives. A single data set with various resources was used in the modeling and testing phases with the following ML approaches taken;Logistic Regression (LR), Naive Bayes (NB), k-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Machine (SVM), and Deep learning (DL) approaches;Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), with promising results shown by the DL approach specifically LSTM. In conclusion, this research has shown that LSTM is the most effective method for detecting Arabic fake news, and with further research in the future, it will only improve. © 2023 IEEE.

关键词： Long short-term memory

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：