Topic
Hybrid neural network
About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: In this paper, a hybrid neural network-flexibility damage index technique was used to predict the severity level and location of damages in a gravity dam in order to estimate the damage.
Abstract: This paper presents a practical procedure based on a hybrid neural network-flexibility damage index technique to predict the severity level and location of damages in a gravity dam. Numeric...
01 Jan 2011
TL;DR: A hybrid neural network/modal method computer-aided design (CAD) tool to the analysis of uniaxial discontinuities in rectangular waveguides that can outperform the classical modal methods in CPU time.
Abstract: We propose a hybrid neural network/modal method computer-aided design (CAD) tool to the analysis of uniaxial discontinuities in rectangular waveguides. The neural network is trained using the continuity conditions of the transverse electric and magnetic fields in the discontinuity plane. Unlike the conventional modal methods, the performances of the proposed neuromodel are controlled by the operator and can outperform the classical modal methods in CPU time. The parallel nature of the proposed hybrid CAD tool makes it an interesting solution for parallel implementation in hardware and software.
26 Oct 1992
TL;DR: A hybrid MTR system composed of ANN and KB classifiers and decision makers, and conventionalsignal processing and probabilistic target track- ing algorithms is developed.
Abstract: In this paper, we present a hybrid artificial neural network (ANN)/knowledge base (KB) system for multi-target recognition (MTR). Specifically, we develop a hybrid MTR archi- tecture composed of ANNand KB classifiers and decision makers, and conventionalsignal processing and probabilistic target track- ing algorithms. Our approach centerson the use of both the on-line classification and parallel processing of neural networks and the formal knowledge and reasoning of domain experts.
Posted Content•
TL;DR: In this article, a hybrid deep learning model known as SzHNN (Schizophrenia Hybrid Neural Network), a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) was proposed.
Abstract: In the field of neuroscience, Brain activity analysis is always considered as an important area. Schizophrenia(Sz) is a brain disorder that severely affects the thinking, behaviour, and feelings of people all around the world. Electroencephalography (EEG) is proved to be an efficient biomarker in Sz detection. EEG is a non-linear time-seriesi signal and utilizing it for investigation is rather crucial due to its non-linear structure. This paper aims to improve the performance of EEG based Sz detection using a deep learning approach. A novel hybrid deep learning model known as SzHNN (Schizophrenia Hybrid Neural Network), a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) has been proposed. CNN network is used for local feature extraction and LSTM has been utilized for classification. The proposed model has been compared with CNN only, LSTM only, and machine learning-based models. All the models have been evaluated on two different datasets wherein Dataset 1 consists of 19 subjects and Dataset 2 consists of 16 subjects. Several experiments have been conducted for the same using various parametric settings on different frequency bands and using different sets of electrodes on the scalp. Based on all the experiments, it is evident that the proposed hybrid model (SzHNN) provides the highest classification accuracy of 99.9% in comparison to other existing models. The proposed model overcomes the influence of different frequency bands and even showed a much better accuracy of 91% with only 5 electrodes. The proposed model is also evaluated on the Internet of Medical Things (IoMT) framework for smart healthcare and remote monitoring applications.
07 Dec 2013
TL;DR: The fundamental equation of brake motor system for soft friction control, and the novel hybrid of radial and sigmoid neural network using mutated particle swarm optimization are presented and the simulation shows the system with swarm intelligence method is practical for improving the braking energy efficiency.
Abstract: Smart brake control of heavy lifting motor, based on nonlinear model, requires one to obtain the instantaneous control parameters, from the trained neural network. This in turn depends on the instantaneous speed interaction with the braking force, through the soft contact. In this paper, we present the nonlinear soft friction identification on the base of stator current with present and its previous values. The fundamental equation of brake motor system for soft friction control, and the novel hybrid of radial and sigmoid neural network using mutated particle swarm optimization are presented. The simulation based on the scaled factory experiment test data shows the system with swarm intelligence method is practical for improving the braking energy efficiency.