检索结果-南通市图书馆

Piezoresistive Prediction of CNTs-Embedded Cement Composites via Machine Learning Approaches

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第4期71卷 1503-1519页

作者： Jinho Bang SongEe Park Haemin Jeon School of Civil Engineering Chungbuk National UniversityCheongju28644Korea Department of Civil and Environmental Engineering Hanbat National UniversityDaejeon34158Korea

Conductive cementitious composites are innovated materials that have improved electrical conductivity compared to general types of cement,and are expected to be used in a variety of future infrastructures with unique functionalities such as self-heating,electromagnetic shielding,and *** the present study,machine learning methods that have been recently applied in various fields were proposed for the prediction of piezoelectric characteristics of carbon nanotubes(CNTs)-incorporated cement *** on the resistivity change of CNTs/cement composites according to various water/binder ratios,loading types,and CNT content were considered as training *** data were applied to numerous machine learning techniques including linear regression,decision tree,support vector machine,deep belief network,Gaussian process regression,genetic algorithm,bagging ensemble,random forest ensemble,boosting ensemble,long short-term memory,and gated recurrent units to estimate the time-independent and-dependent electrical properties of conductive cementitious *** comparing and analyzing the computed results of the proposed methods,an optimal algorithm suitable for application to CNTs-embedded cementitious composites was derived.

关键词： Machine learning long short-term memory gated recurrent units nano-composites cement matrix carbon nanotube

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“gated recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

Seasonal electric vehicle forecasting model based on machine learning and deep learning techniques

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2023年第4期14卷 398-414页

作者： Heba-Allah I.El-Azab R.A.Swief Noha H.El-Amary H.K.Temraz Faculty of Engineering Ahram Canadian University(ACU)GizaEgypt Faculty of Engineering Ain Shams UniversityCairo 11517Egypt Arab Academy for Science Technology and Maritime Transport(AASTMT)Cairo 2033Egypt

In this paper,multiple featured machine learning algorithms and deep learning algorithms are applied in fore-casting the electric vehicles charging load profile from real datasets of Spain’s electrical *** study aims to provide realistic datasets of electric vehicle load profiles to cope with the potential increase in electric vehicle penetration taking into consideration the seasonality *** issues are caused by the distribution network of the electricity grid;such as the huge charging power and stochastic charging behaviors of the drivers of electric vehicles due to the mass rollout of electric *** electric vehicles’load profile is necessary to face challenges to solve the problem of the potential mass rollout of electric vehicles ***,Electric vehicle is considered one of the most promising solutions that develops faster than other stochastic renewable solution to reduce greenhouse *** seasonality effect is one of the huge chal-lenges on electrical loads,so it is investigated by creating four separate forecasting networks to increase system accuracy and studying the effect of seasonal factors such as temperature fluctuation in the four seasons affecting the electric vehicles’battery in charging and draining *** factors are affecting the accuracy of the forecasting *** featured algorithms are *** Neural Networks and Adaptive Neuro-Fuzzy Inference Systems are applied as machine learning algorithms,and Long Short-Term Memory and the gated recurrent units are also utilized as deep learning *** gated recurrent units model performs slightly better than the long short-term memory employed on the hourly average daily historical data of charging electric *** the Adaptive Neuro-Fuzzy Inference System gathers both Artificial Neural Network and Fuzzy Inference System advantages.

关键词： Adaptive neuro-fuzzy inference system Deep learning Electric vehicles gated recurrent units Long short-term memory Neural network Short-term load forecasting

Improving Deep Attractor Network by BGRU and GMM for Speech Separation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2021年第3期28卷 90-96页

作者： Rawad Melhem Assef Jafar Riad Hamadeh Higher Institute for Applied Sciences and Technology DamascusSyria

Deep Attractor Network(DANet) is the state-of-the-art technique in speech separation field, which uses Bidirectional Long Short-Term Memory(BLSTM), but the complexity of the DANet model is very high. In this paper, a simplified and powerful DANet model is proposed using Bidirectional gated neural network(BGRU) instead of BLSTM. The Gaussian Mixture Model(GMM) other than the k-means was applied in DANet as a clustering algorithm to reduce the complexity and increase the learning speed and accuracy. The metrics used in this paper are Signal to Distortion Ratio(SDR), Signal to Interference Ratio(SIR), Signal to Artifact Ratio(SAR), and Perceptual Evaluation Speech Quality(PESQ) score. Two speaker mixture datasets from TIMIT corpus were prepared to evaluate the proposed model, and the system achieved 12.3 dB and 2.94 for SDR and PESQ scores respectively, which were better than the original DANet model. Other improvements were 20.7% and 17.9% in the number of parameters and time training respectively. The model was applied on mixed Arabic speech signals and the results were better than that in English.

关键词： attractor network speech separation gated recurrent units

An Evaluation of Deep Learning Models for Classifying Time Series Individual Data Instances

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第11期12卷 187-206页

作者： Joshua A. Blaney Suresh S. Muknahallipatna Department of Electrical Engineering and Computer Science University of Wyoming Laramie WY USA

Deep learning for time series sequence individual data instance classification can revolutionize computer assisted navigation by providing surgeons with accurate, real-time instrument locality through automatic instrument localization. This paper presents an evaluation of Deep Learning models to perform individual data instance classification of time series data. The models explored include convolution and recurrent networks, as well as state-of-the-art residual and inception architectures. The time series data used to evaluate the models consists of depth and force measurements from a drill. Four recurrent neural network models using long short-term memory and gated recurrent units, known as baseline models, and four models using 1D convolution with ResNet and Inception architectures, known as advanced models, were evaluated by determining the data instance membership of the four classes. The four classes represent four distinct regions in a bone traversed by the drill bit during a surgical procedure. First, the time series data is preprocessed, identifying the four classes or regions of the bone. Next, the paper presents a discussion of the network architecture and modifications of both the basic and advanced deep learning models, followed by the training process and hyperparameters tuning. The performance of the models was evaluated using the precision and recall performance parameters. Out of the eight models evaluated, the recurrent neural network with gated recurrent units has the best performance. The paper also demonstrates the importance of the feature depth over the feature force in classifying the data instances, followed by the effects of the imbalanced dataset on the performance of the models.

关键词： recurrent Neural Networks Long Short Term Memory gated recurrent units Residual Networks Inception Networks