Filters








9,200 Hits in 3.2 sec

Evolving granular classification neural networks

Daniel F. Leite, Pyramo Costa, Fernando Gomide
2009 2009 International Joint Conference on Neural Networks  
The objective of this study is to introduce the concept of evolving granular neural networks (eGNN) and to develop a framework of information granulation and its role in the online design of neural networks  ...  The suggested eGNN are neural models supported by granule-based learning algorithms whose aim is to tackle classification problems in continuously changing environments. eGNN are constructed from streams  ...  A novel evolving granular neural network, eGNN, was suggested as a mechanism to develop evolving models of systems.  ... 
doi:10.1109/ijcnn.2009.5178895 dblp:conf/ijcnn/LeiteCG09 fatcat:57zfif4yencdtfkgpoayt5ed3e

Comparison of Evolving Granular Classifiers applied to Anomaly Detection for Predictive Maintenance in Computing Centers [article]

Leticia Decker, Daniel Leite, Fabio Viola, Daniele Bonacorsi
2020 arXiv   pre-print
Granular Neural Network (eGNN), to model and monitor logging activity rate.  ...  We formulated a 4-class online anomaly classification problem, and employed time windows between landmarks and two granular computing methods, namely, Fuzzy-set-Based evolving Modeling (FBeM) and evolving  ...  A Fuzzy-Set-Based evolving Model (FBeM) [11] and an evolving Granular Neural Network (eGNN) [12] are developed from a stream of data dynamically extracted from time windows.  ... 
arXiv:2005.04156v1 fatcat:r4pcx6xjwfh33l36wix3wcbm74

Evolving granular neural network for fuzzy time series forecasting

Daniel Leite, Pyramo Costa, Fernando Gomide
2012 The 2012 International Joint Conference on Neural Networks (IJCNN)  
This paper introduces a granular neural network framework for evolving fuzzy system modeling from fuzzy data streams.  ...  The evolving granular neural network (eGNN) efficiently handles concept changes, distinctive events of nonstationary environments. eGNN constructs interpretable multi-sized local models using fuzzy neural  ...  Refer to [15] for the pioneering work in granular non-evolving neural networks, [16] - [17] for regression and semi-supervised classification applications of eGNN, and [18] - [19] for related  ... 
doi:10.1109/ijcnn.2012.6252382 dblp:conf/ijcnn/LeiteCG12 fatcat:q4h23y3zxvak7g3ml5pxmrvs7u

A study of granular computing in the agenda of growth of artificial neural networks

Mingli Song, Yongbin Wang
2016 Granular Computing  
This study aims to give useful insight into the capability of granular neural networks.  ...  Granular neural networks are being used in areas of knowledge discovery, pattern recognition, etc.  ...  of black box neural network models; (2) online processing of granular data streams; (3) trading off precision and interpretability; and (4) handling of large volume of data in evolving classification  ... 
doi:10.1007/s41066-016-0020-7 fatcat:ktzklzy4ujbdvdezp5jx5khzri

Recent developments in natural computation

JingTao Yao, Qingfu Zhang, Jingsheng Lei
2009 Neurocomputing  
The first one applies a single pair of neural networks while the second one uses an ensemble of pairs of neural networks for the binary classification.  ...  neural network.  ...  by using three sub-BP neural networks.  ... 
doi:10.1016/j.neucom.2009.02.014 fatcat:rpxm46eqbfbyfoxi3dmzffukvq

Design of English Teaching Sharing System Combining Internet of Things and Memory Mechanism

Jie Guo, Kuruva Lakshmanna
2022 Wireless Communications and Mobile Computing  
Then, the information fusion is thoroughly analyzed resulting in the proposal of a multisource and multigranularity information fusion method based on a neural network.  ...  In the era of Internet of Everything, English teaching has evolved continuously undergoing radical changes.  ...  The information fusion method based on neural network mainly makes use of neural network's powerful classification learning ability.  ... 
doi:10.1155/2022/2712199 fatcat:hyan5xrvzna5len2q4d3vol674

Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey [article]

Joakim Skarding, Bogdan Gabrys, Katarzyna Musial
2020 arXiv   pre-print
Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification  ...  Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks.  ...  Node Temporal granularity Node dynamics Link duration Precise dynamic network term 1 Discrete Node static Evolving Discrete node static evolving network 2 Temporal Discrete node static temporal  ... 
arXiv:2005.07496v1 fatcat:ditdpefszzd6bfh4enbcdkztna

A Review on Evolving Interval and Fuzzy Granular Systems

Daniel Leite, Pyramo Costa Jr., Fernando Gomide
2016 Learning and Nonlinear Models  
Evolving granular systems extend evolving intelligent systems allowing data, variables and parameters to be granules (intervals and fuzzy sets).  ...  We briefly summarize the main historical landmarks of evolving intelligent systems leading to the state of the art.  ...  The fuzzy min-max neural network (GFMM) [51] is a generalization of the fuzzy min-max clustering and classification neural networks [80] .  ... 
doi:10.21528/lnlm-vol14-no2-art3 fatcat:mw4xwirbsbg3ln2fciuovvlg6u

Use Of Radial Basis Function Neural Network For Bearing Pressure Prediction Of Strip Footing On Reinforced Granular Bed Overlying Weak Soil

K. Srinath Shetty, R. Shivashankar, Rashmi P. Shetty
2012 Zenodo  
In this context, this paper uses radial basis function neural network (RBFNN) for predicting the bearing pressure of strip footing on reinforced granular bed overlying weak soil.  ...  The inputs for the neural network models included plate width, thickness of granular bed and number of layers of reinforcements, settlement ratio, water content, dry density, cohesion and angle of friction  ...  Radial basis function neural networks (RBFNN) are a relatively new class of neural networks, which have been used in classification or regression problems.  ... 
doi:10.5281/zenodo.1057144 fatcat:ybrkwztwbfatffu2gjfuip7vzm

LuNet: A Deep Neural Network for Network Intrusion Detection [article]

Peilun Wu, Hui Guo
2019 arXiv   pre-print
In LuNet, the convolutional neural network (CNN) and the recurrent neural network (RNN) learn input traffic data in sync with a gradually increasing granularity such that both spatial and temporal features  ...  In this paper, we consider the existence of spatial and temporal features in the network traffic data and propose a hierarchical CNN+RNN neural network, LuNet.  ...  Furthermore, to obtain a fully representative normal traffic profile for a dynamically evolving and expanding network is unlikely possible.  ... 
arXiv:1909.10031v2 fatcat:3527fd7v5vgtzky5tdxlbus7zq

GRANULAR NETWORK TRAFFIC CLASSIFICATION FOR STREAMING TRAFFIC USING INCREMENTAL LEARNING AND CLASSIFIER CHAIN

Faiz Zaki, Firdaus Afifi, Abdullah Gani, Nor Badrul Anuar
2022 Malaysian Journal of Computer Science  
Accordingly, granular network traffic classification quickly rises as an essential technology due to its ability to provide high network visibility.  ...  Granular network traffic classification categorizes traffic into detailed classes like application names and services.  ...  In [30] , the authors proposed using a convolutional neural network (CNN) to classify streaming traffic.  ... 
doi:10.22452/mjcs.vol35no3.5 fatcat:dnnz4cg5wfa7nkkb7sjkmyaxcq

Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey

Joakim Skardinga, Bogdan Gabrys, Katarzyna Musial
2021 IEEE Access  
Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification  ...  Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks.  ...  node-static temporal network 7 Node-dynamic Evolving Continuous node-dynamic evolving network 8 Temporal Continuous node-dynamic temporal network TABLE 3 : 3 Dimension Network types Temporal granularity  ... 
doi:10.1109/access.2021.3082932 fatcat:4pbp2kn6ovf65pnm5pbv7idpim

An Effective Multi-Resolution Hierarchical Granular Representation based Classifier using General Fuzzy Min-Max Neural Network

Thanh Tung Khuat, Fang Chen, Bogdan Gabrys
2019 IEEE transactions on fuzzy systems  
networks and common machine learning algorithms.  ...  conducted comprehensively on both synthetic and real datasets indicated the efficiency of our method in terms of training time and predictive performance in comparison to other types of fuzzy min-max neural  ...  There are many studies on ECG heartbeat classification such as deep residual convolution neural network [37] , a 9-layer deep convolutional neural network on the augmentation of the original data [38  ... 
doi:10.1109/tfuzz.2019.2956917 fatcat:aa4jcwqtzfghlpuncwgruvskfe

Table of Contents

2020 IEEE transactions on fuzzy systems  
Keller 1897 An Improved Fuzzy Min-Max Neural Network for Data Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Meena 2009 Global Synchronization of Fuzzy Memristive Neural Networks With Discrete and Distributed Delays . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tfuzz.2020.3015631 fatcat:wcjbxzkl6fa4bb6rfmn3laz6ui

Fusing diagnostic information without a priori performance knowledge

M. Garbiras, K. Goebel
2000 Proceedings of the Third International Conference on Information Fusion  
In response, a fusion process, using a set of neural networks, was developed to distinguish recognizable patterns from the output of the individual diagnostic tools.  ...  Neural Network (NN1): The second subsystem is a neural network that was trained on binary classes.  ...  The fact that this network was able to recognize "no_wear" was the reason its classification rating went up, but overall the system lost the ability to model the system performance with the same granularity  ... 
doi:10.1109/ific.2000.862710 fatcat:rwginep3zjhpzogr5vryimb2sm
« Previous Showing results 1 — 15 out of 9,200 results