检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Artificial Intelligence and Green Energy, ICAIGE 2024

作者： Guerfel, Mohamed Abdelwahed, Imen Ben Jaffel, Ines Bouzrara, Kais Higher Institute of Applied Sciences and Technology of Sousse University of Sousse Electronics department Tunisia National Engineering School of Monastir University of Monastir Laboratory of Automatic Control Signal and Image Processing Tunisia Higher Institute of Applied Sciences and Technology of Kairouan University of Kairouan Tunisia

ISBN: (纸本)9798350389838

This paper explores the application of genetic algorithms to optimize ARX-Laguerre model parameters. It outlines the ARX-Laguerre modeling process and genetic algorithm principles. A fitness function is chosen and the impact of noise on it is addressed. A new methodology for optimizing Laguerre poles using genetic algorithms is proposed. It is used in modeling a real 2-Degree-of-Freedom helicopter offering valuable insights for real-world applications. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

引用

Journal of engineering and Applied Science 2023年第1期70卷 56页

作者： Attouri, Khadija Dhibi, Khaled Mansouri, Majdi Hajji, Mansour Bouzrara, Kais Nounou, Hazem Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine1200 Tunisia Chemical Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Electrical and Computer Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Monastir5019 Tunisia

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%). © 2023, This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimal Operation of Centralized Battery Swap Charging System with Photovoltaic

引用

Journal of Modern Power Systems and Clean Energy 2022年第1期10卷 149-162页

作者： Yuanzheng Li Yihan Cai Tianyang Zhao Yun Liu Jian Wang Lei Wu Yong Zhao School of Artificial Intelligence and Automation Ministry of Education Key Laboratory of Image Processing and Intelligence ControlHuazhong University of Science and TechnologyWuhanChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore College of Mechatronics and Control Engineering Shenzhen UniversityShenzhenChina Department of Electrical&Computer Engineering Stevens Institute of TechnologyHobokenUSA

Electric vehicles(EVs)are widely deployed throughout the world,and photovoltaic(PV)charging stations have emerged for satisfying the charging demands of EV *** paper proposes a multi-objective optimal operation method for the centralized battery swap charging system(CBSCS),in order to enhance the economic efficiency while reducing its adverse effects on power *** proposed method involves a multi-objective optimization scheduling model,which minimizes the total operation cost and smoothes load fluctuations,***,we modify a recently proposed multi-objective optimization algorithm of non-sorting genetic algorithm III(NSGA-III)for solving this scheduling ***,simulation studies verify the effectiveness of the proposed multi-objective operation method.

关键词： Multi-objective optimization electric vehicle battery swap charging system scheduling photovoltaic

来源：评论

学校读者我要写书评

暂无评论

Deeper Bidirectional Neural Networks with Generalized Non-Vanishing Hidden Neurons

Deeper Bidirectional Neural Networks with Generalized Non-Va...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

The new NoVa hidden neurons have outperformed ReLU hidden neurons in deep classifiers on some large image test sets. The NoVa or nonvanishing logistic neuron additively perturbs the sigmoidal activation function so that its derivative is not zero. This helps avoid or delay the problem of vanishing gradients. We here extend the NoVa to the generalized perturbed logistic neuron and compare it to ReLU and several other hidden neurons on large image test sets that include CIFAR-100 and Caltech-256. Generalized NoVa classifiers allow deeper networks with better classification on the large datasets. This deep benefit holds for ordinary unidirectional backpropagation. It also holds for the more efficient bidirectional backpropagation that trains in both the forward and backward directions.

关键词： Backpropagation Training Neurons Machine learning Delays Biological neural networks Logistics

来源：评论

学校读者我要写书评

暂无评论

Selective User Forwarded Cell-Free Massive Mimo with Quantized Symbols

Selective User Forwarded Cell-Free Massive Mimo with Quantiz...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Maria Francis K. V. S Hari Department of Electrical Communication Engineering Statistical Signal Processing Lab Indian Institute of Science Bangalore India

We consider the uplink of a Selective User-Forwarded Cell-free massive MIMO (SUF-CF-mMIMO) system, where each access point (AP) forwards the received symbols of only a selected subset of users to the centralized processing unit (CPU) for coherent combining. SUF-CF-mMIMO gives significant savings in fronthaul signaling compared to the conventional CF-mMIMO. This paper investigates the uplink performance of SUF-CF-mMIMO with one-bit quantized symbols sent over the fronthaul to the CPU by each AP. Novel expressions for spectral efficiency (SE) are derived for the uplink in the presence of quantization distortion. Simulation results show that SUF-CF-mMIMO is more robust to quantization effects compared to the conventional CF-mMIMO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pyramidal deep neural network for classification of retinal OCT images

Pyramidal deep neural network for classification of retinal ...

引用

Iranian Conference of Biomedical engineering (ICBME)

作者： Mohammad Almasganj Emad Fatemizadeh Department of Electrical Engineering Biomedical Signal and Image Processing Laboratory (BiSIPL) Sharif University of Technology Tehran Iran

Retinal optical coherence tomography (OCT) images are widely used to diagnose and grade macular diseases, such as age-related macular degeneration (AMD). However, manual interpretation of OCT images is time-consuming and subjective. Therefore, automated and accurate classification of OCT images is essential for assisting ophthalmologists in clinical decision-making. This paper proposes a pyramidal deep neural network that can diagnose normal and two types of AMD (dry and wet) in OCT images. Our network leverages features from different scales of a pre-trained convolutional neural network (CNN) and integrates them with two advanced versions of feature pyramid networks: bidirectional feature pyramid network (BiFPN) and path aggregation network (PANet). We evaluate our network on the NEH dataset and compare it with its predecessor. Our results show that our BiFPN-VGG16 and PAN-VGG16 models achieve accuracies of 94.S% and 95.0%, respectively, which are 2.8 to 3% higher than the previous models. Our approach demonstrates the potential of multi-scale feature networks for OCT image classification and can serve as an auxiliary diagnostic tool for ophthalmologists.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence System for Emotion Recognition and Text Analytics

Artificial Intelligence System for Emotion Recognition and T...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Chaudhari, Namrata Agarwal, Reshu Narwade, Meghna Yu, Xinrui Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

Harnessing the power of emotional intelligence by analyzing a person's behavioral and linguistic skills can help humans improve their approach to social interactions. In this paper, we propose an artificial intelligence-based stand-alone system that will allow us to classify and analyze facial expressions in real-time and perform sentiment analysis by examining the body of the text (extracted from audio) to understand the opinion expressed by it. This helps us provide a deeper understanding of how humans really feel at a given time. The proposed system uses a deep neural network (DNN) for classifying eight basic emotions based on features extracted from facial expressions and uses pretrained sentiment analysis tools to quantify text (extracted from audio) based on polarity. The system is implemented by extracting the audio and visual cues from real-time scenarios and using these extracted cues to perform facial expression recognition and text sentiment analysis. The integrated system extracts video and audio simultaneously with a frame rate of 4-5 fps. The facial emotion detection system successfully detects facial expressions of faces detected in real-time video with an accuracy of about 86.75%. The speech extracted is converted to text, cleaned, and processed to determine if the attitude of the speaker in a given situation is positive, negative, or neutral. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High Precision Analog Gauge Reader Using Optical Flow and Computer Vision

High Precision Analog Gauge Reader Using Optical Flow and Co...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Chavan, Shruti Yu, Xinrui Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Department of Electrical and Computer Engineering Research Laboratory ChicagoIL United States

ISBN: (纸本)9781665480093

This paper aims at developing algorithms to automate the process of reading analog gauges at different operational industries, healthcare sector and automobiles using Artificial Intelligence (AI) techniques. Proposed algorithms start with video stabilization using optical flow followed by image processing which performs segmentation using HSV color space and morphological operations. Next, Hough transform is applied to determine the dial region and pointer. Using the coordinates locating the pointer in the frame, angle made with minimum valued scale mark is calculated using trigonometry and evaluated reading is displayed in the form of text and a progress bar. The proposed algorithms for Analog Gauge Reader (AGR) is executed using open-source libraries such as OpenCV, NumPy, PIL with Python programming and it is developed in the PyCharm environment. The experimental results show significant decrease in the error with the introduction of image preprocessing and the generalizability of the algorithm to different types of analog gauges captured in different conditions of illuminance. The accuracy and precision of the algorithms is 99% to 100% in the experimental studies. © 2022 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Soccer Player Recognition using Artificial Intelligence and Computer Vision

Soccer Player Recognition using Artificial Intelligence and ...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Diop, Charles-Alexandre Pelloux, Baptiste Yu, Xinrui Yi, Won-Jae Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Research Laboratory Department of Electrical and Computer Engineering ChicagoIL United States

ISBN: (纸本)9781665480093

Groundbreaking features and functionalities are available in sports broadcasting programs, specifically in soccer games, such as post-game analysis, tracking of players, tracking of the ball, and associated teams' and players' statistical information. However, viewers don't have control to choose which features to view on-demand and aren't able to interact with any of these functionalities. Our system aims for the fundamental system of an on-demand viewer-driven application that would be able to track players on the field, identify formation changes, follow team strategy changes, and gather all statistical information of the player and the team on a single screen. In order to realize such an application, we focus on developing a method to track players on the field using multiple Artificial Intelligence (AI) and computer vision techniques where our application employs facial recognition and jersey number recognition algorithms. As a live soccer game broadcast would have various camera views of the players, our custom-made database contains captured images from different scenarios of camera views such as different angles and zooms of the player and is used to train the model using Convolutional Neural Network (CNN). Our system is scalable to different types of sports, such as basketball, baseball, volleyball, and more where players have their numbers on their jerseys and would be feasible to apply our system since soccer involves more players on the field than other sports games. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Acoustic User Authentication with Smartphones

Acoustic User Authentication with Smartphones

引用

IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems, COMCAS

作者： Neta Gevirtzer Ofir Ben Yosef Alon Eilam Signal and Image Processing Laboratory (SIPL) Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering Technion - Israel Institute of Technology Technion City Haifa Israel

ISBN: (数字)9798350348187

ISBN: (纸本)9798350348194

This paper describes a work on an acoustic user authentication system using smartphones. The system implements two-factor authentication for Windows workstations, where the authentication procedure, including locking and unlocking the workstation is transparent to the user. Since workstations and smartphones have built-in microphones and speakers, the system does not require additional hardware. The uniqueness of the solution is being based on acoustic signals. These signals are transmitted by the user's smartphone and received by the workstation microphone. The system is “pure play acoustic” since no wiring or radio transmission is used. The system configuration supports multiple users in the same area. Eavesdropping prevention is provided by sequentially generated random one-time keys. Acoustic communication can be applied either in the audible range or beyond the human hearing range depending on the sampling rate of the smartphone and the workstation.

关键词： Microwave antennas Wiring Prevention and mitigation Authentication Auditory system Microwave communication Acoustics

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：