检索结果-南通市图书馆

ON LINE MONITORING OF BURNING THROUGH FOR SHORT CIRCUIT CO_2 ARC WELDING BASED ON THE SELF-ORGANIZE FEATURE MAP neural networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2001年第2期14卷 106-110页

作者： Li Di Song Yonglun Ye Feng Mechatronics Engineering Department, South China University of Technology 华南理工大学机电工程系广东广州

A method for automatic detection of burning through of short circuit CO 2 arc welding is presented. It is based on the extraction of arc signal features as well as classification of the obtained features using self organize feature map(SOM) neural networks in order to get the weld quality information, for example, to determine if there is defect in the product. This is important for the on line monitoring of weld quality especially in robotic welding and lay the foundation for the further real time control of weld quality.

关键词： Weld Quality Defect SOM neural networks CO 2 arc welding

neural networks Based Component Content Soft-Sensor in Countercurrent Rare-Earth Extraction

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2003年第6期21卷 691-696页

作者：杨辉谭明皓柴天佑 Research Center of Automation Northeastern University

The equilibrium model for multicomponent rare earth extraction is developed using neural networks, which combined with the material balance model could give online prediction of component content in countercurrent rare earth (extraction) production. Simulation experiments with industrial operation data prove the effectiveness of the hybrid soft-(sensor).

关键词： countercurrent extraction first principle model soft-sensor model neural networks rare earths

A new result on global exponential robust stability of neural networks with time-varying delays

在线全文

学校读者我要写书评

暂无评论

控制理论与应用（英文版） 2009年第3期7卷 315-320页

作者： Jinliang SHAO Tingzhu HUANG School of Applied Mathematics University of Electronic Science and Technology of China Chengdu Sichuan 610054 China

In this paper, the global exponential robust stability of neural networks with ume-varying delays is investigated. By using nonnegative matrix theory and the Halanay inequality, a new sufficient condition for global exponential robust stability is presented. It is shown that the obtained result is different from or improves some existing ones reported in the literatures. Finally, some numerical examples and a simulation are given to show the effectiveness of the obtained result.

关键词： neural networks Time-varying delays Global exponential robust stability

Improved Exponential Stability Criteria for Recurrent neural networks with Time-varying Discrete and Distributed Delays

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2010年第2期7卷 199-204页

作者： Yuan-Yuan Wu Tao Li Yu-Qiang Wu School of Automation Southeast University Nanjing 210096 PRC Department of Information and Communication Nanjing University of Information Science and Technology Nanjing 210044 PRC Institute of Automation Qufu Normal University Qufu 273165 PRC

In this paper, the problem of the global exponential stability analysis is investigated for a class of recurrent neural networks （RNNs） with time-varying discrete and distributed delays. Due to a novel technique when estimating the upper bound of the derivative of Lyapunov functional, we establish new exponential stability criteria in terms of LMIs. It is shown that the obtained criteria can provide less conservative results than some existing ones. Numerical examples are given to show the effectiveness of the proposed results.

关键词： neural networks time-varying delay exponential stability linear matrix inequalities (LMIs).

A novel confidence estimation method for neural networks in multispectral image classification

在线全文

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2009年第4期2卷 343-358页

作者： O.Arslan Geodesy and Photogrammetry Engineering Department Engineering FacultyUniversity of Kocaeli41040Turkey

The Digital Earth concept has attracted much attention recently and this approach uses a variety of earth observation data from the global to the local *** techniques have made much progress technically and the methods used for automatic extraction of geo-ralated information are of importance in Digital Earth *** of these methods,artificial neural networks(ANN)techniques,have been effectively used in classification of remotely sensed *** image classification with ANN has been producing higher or equal mapping accuracies than parametric *** studies have,in fact,shown that there is no discernible difference in classification accuracies between neural and conventional statistical *** well designed and trained neural networks can present a better performance than the standard statistical *** are,as yet,no widely recognised standard methods to implement an optimum *** this point of view it might be beneficial to quantify ANN’s reliability in classification *** measure the reliability of the neural network might be a way of developing to determine suitable network *** date,the problem of confidence estimation of ANN has not been studied in remote sensing studies.A statistical method for quantifying the reliability of a neural network that can be used in image classification is investigated in this *** this purpose the method is to be based on a binomial experimentation concept to establish confidence *** novel method can also be used for the selection of an appropriate network structure for the classification of multispectral *** the main focus of the research is to estimate confidence in ANN,the approach might also be applicable and relevant to Digital Earth technologies.

关键词： digital earth neural networks confidence estimation image classification

Texture image classification with discriminative neural networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第4期2卷 367-377页

作者： Yang Song Qing Li Dagan Feng Ju Jia Zou Weidong Cai School of Information Technologies the University of Sydney School of Computing Engineering and MathematicsWestern Sydney University

Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks(CNN) have emerged as the state-of-the-art: CNN-based features provide a significant performance improvement over previous handcrafted features. In this study, we demonstrate that we can further improve the discriminative power of CNN-based features and achieve more accurate classification of texture images. In particular, we have designed a discriminative neural network-based feature transformation(NFT) method, with which the CNN-based features are transformed to lower dimensionality descriptors based on an ensemble of neural networks optimized for the classification objective. For evaluation, we used three standard benchmark datasets(KTH-TIPS2, FMD, and DTD)for texture image classification. Our experimental results show enhanced classification performance over the state-of-the-art.

关键词： texture classification neural networks feature learning feature transformation

Adaptive synchronization of different kinds of chaotic neural networks

在线全文

学校读者我要写书评

暂无评论

控制理论与应用（英文版） 2008年第2期6卷 201-207页

作者： Huanxin GUAN Zhanshan WANG Huaguang ZHANG School of Information Science and Engineering Northeastern University Shenyang Liaoning 110004 China Department of Continuous Education Shenyang InstitUte of Engineering Shenyang Liaoning 110034 China

The purpose of the paper is to present an adaptive control method for the synchronization of different classes of chaotic neural networks. A new sufficient condition for the global synchronization of two kinds of chaotic neural networks is derived. The proposed control method is efficient for implementing the synchronization when the parameters of the drive system are different from those of the response system. A numerical example is used to demonstrate the validity of the proposed method and the obtained result.

关键词： Chaotic system neural networks Adaptive synchronization Linear matrix inequality

Evaluation tool for the thermal performance of retrofitted buildings using an integrated approach of deep learning artificial neural networks and infrared thermography

在线全文

学校读者我要写书评

暂无评论

能源与人工环境(英文) 2021年第4期2卷 345-365页

作者： Amin Al-Habaibeh Arijit Sen John Chilton Innovative and Sustainable Built Environment Technologies Research Group(iSBET) Nottingham Trent UniversityUK Department of Architecture and Built Environment University of NottinghamUK

In most countries,buildings are responsible for significant energy consumption where space heating and air conditioning is responsible for the majority of this energy *** reduce this massive consumption and decrease carbon emission,thermal insulation of buildings can play an important *** estimation of energy savings following the improvement of a building’s insulation remains a key area of research in order to calculate the cost savings and the payback *** this paper,a case study has been presented where deep retrofitting has been introduced to an existing building to bring it closer to a Passivhaus standard with the introduction of insulation and solar photovoltaic *** thermal performance of the building with its improved insulation has been evaluated using infrared *** intelligence using deep learning neural networks is implemented to predict the thermal performance of the building and the expected energy *** prediction of neural networks is compared with the actual savings calculated using historical weather *** results of the neural network show high accuracy of predicting the actual energy savings with success rate of about 82%when compared with the calculated *** results show that this suggested approach can be used to rapidly predict energy savings from retrofitting of buildings with reasonable accuracy,hence providing a practical rapid tool for the building industry and communities to estimate energy savings.A mathematical model has been also developed which has indicated a life-long monitoring will be needed to precisely estimate the benefits of energy savings in retrofitting due to the change in weather conditions and people’s behaviour.

关键词： Artificial intelligence neural networks Building thermal performance Wall insulation Infrared thermography Deep retrofitting

Hate speech detection in Twitter using hybrid embeddings and improved cuckoo search-based neural networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2020年第4期13卷 485-525页

作者： Femi Emmanuel Ayo Olusegun Folorunso Friday Thomas Ibharalu Idowu Ademola Osinuga Computer Science College of Natural and Applied SciencesMcPherson UniversitySeriki SotayoNigeria Computer Science College of Natural SciencesFederal University of Agriculture AbeokutaAbeokutaNigeria Computer Science Federal University of Agriculture AbeokutaAbeokutaNigeria Mathematics Federal University of Agriculture AbeokutaAbeokutaNigeria

Purpose-Hate speech is an expression of intense *** has become a popular analytical tool for the prediction and monitoring of abusive *** speech detection with social media data has witnessed special research attention in recent studies,hence,the need to design a generic metadata architecture and efficient feature extraction technique to enhance hate speech ***/methodology/approach-This study proposes a hybrid embeddings enhanced with a topic inference method and an improved cuckoo search neural network for hate speech detection in Twitter *** proposed method uses a hybrid embeddings technique that includes Term Frequency-Inverse Document Frequency(TF-IDF)for word-level feature extraction and Long Short Term Memory(LSTM)which is a variant of recurrent neural networks architecture for sentence-level feature *** extracted features from the hybrid embeddings then serve as input into the improved cuckoo search neural network for the prediction of a tweet as hate speech,offensive language or ***-The proposed method showed better results when tested on the collected Twitter datasets compared to other related *** order to validate the performances of the proposed method,t-test and post hoc multiple comparisons were used to compare the significance and means of the proposed method with other related methods for hate speech ***,Paired Sample t-Test was also conducted to validate the performances of the proposed method with other related *** limitations/implications-Finally,the evaluation results showed that the proposed method outperforms other related methods with mean F1-score of ***/value-The main novelty of this study is the use of an automatic topic spotting measure based on na€ıve Bayes model to improve features representation.

关键词： Twitter Hate speech detection Embeddings Cuckoo search neural networks