The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Meta-cognition with self-regulated learning equips a machine learning algorithm to make judicious decisions about every sample in the training data set. Due to this capability, meta-cognitive machine learning algorithms exhibit better generalization behavior. In the past, numerous works have focused on studying the effect on meta-cognition for learning patterns from data in a supervised fashion. In...
Spectral band power features are one of the most widely used features in the studies of electroencephalogram (EEG)-based emotion recognition. The power spectral density of EEG signals is partitioned into different bands such as delta, theta, alpha and beta band etc. Though based on neuroscientific findings, the partition of frequency bands is somewhat on an ad-hoc basis, and the definition of frequency...
There are many attempts that utilize deep learning methods to solve the problem of classification in remote sensing images. Convolutional Neural Networks (CNN) have made very good performance for various visual tasks, and marked their important place in all deep learning models. However, for some classification tasks of remote sensing images, CNN could not demonstrate their full potential because...
Nowadays, systems providing user-oriented services often demonstrate periodic patterns due to the repetitive behaviors from people's daily routines. The monitoring data of such systems are time series of observations that record observed system status at sampled times during each day. The periodic feature and multidimensional character of such monitoring data can be well utilized by anomaly detection...
In modern design of power electronic converters, reliability of DC-link capacitors is an essential aspect to be considered. The industrial field have been attracted to the monitoring of their health condition and the estimation of their ageing process status. The existing condition monitoring methods suffer from shortcomings such as, low estimation accuracy, extra hardware, and increased cost. Therefore,...
The deep neural network (DNN) that models characteristics of general blood test (GBT) results was used in clinical opinions generation. The DNN that generates clinical opinions has the complex structure, which causes overfitting problem. The relatively small size of medical dataset also contributes to the occurrence of overfitting. In order to deal with overfitting, we apply two techniques that solve...
How to accurately estimate facial age is a difficult problem due to insufficiency of training data. In this paper, an effective approach is proposed to estimate facial age by means of extreme learning machine (ELM). In the proposed method, a set of features is randomly selected from the original features to consist of a feature subspace. Given an initial weight matrix, the training samples within...
Adding context information into recurrent neural network language models (RNNLMs) have been investigated recently to improve the effectiveness of learning RNNLM. Conventionally, a fast approximate topic representation for a block of words was proposed by using corpus-based topic distribution of word incorporating latent Dirichlet allocation (LDA) model. It is then updated for each subsequent word...
We modeled in this paper the variation of wind speed as a renewable energy in Mediterranean Sea of Libya (North of Africa) using an artificial neural network (ANN). We developed multi-layer, feed-forward, back-propagation artificial neural networks for prediction monthly mean wind speed. The monthly mean wind speed data of 25 cities in Libya were monitored during the period of six years from 2010...
Deep neural network (DNN) acoustic models can be adapted to under-resourced languages by transferring the hidden layers. An analogous transfer problem is popular as few-shot learning to recognise scantily seen objects based on their meaningful attributes. In similar way, this paper proposes a principled way to represent the hidden layers of DNN in terms of attributes shared across languages. The diverse...
It was demonstrated that the standard selection of input weights and biases for Extreme Learning Machine (ELM) may lead to ill-conditioning of the output weights calculation and result in great values of the output weights. Two slight modifications of the standard approach were proposed: i) addition of some distance-based neurons (like Radial Basis Functions — RBF) with centers situated at numerically...
In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier. Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional samples in feature-space. We experimentally evaluate...
In this paper, a progressive learning algorithm for multi-label classification to learn new labels while retaining the knowledge of previous labels is designed. New output neurons corresponding to new labels are added and the neural network connections and parameters are automatically restructured as if the label has been introduced from the beginning. This work is the first of the kind in multi-label...
The imbalanced learning problem is becoming pervasive in today's data mining applications. This problem refers to the uneven distribution of instances among the classes which poses difficulty in the classification of rare instances. Several undersampling as well as oversampling methods were proposed to deal with such imbalance. Many undersampling techniques do not consider distribution of information...
An open world turn based monster battle game was developed in Java using the popular LibGDX game framework applying multiple machine learning algorithms for its mechanics consisting of an ID3 decision tree, perceptron, naïve Bayes classifier and A∗ pathfinding in an attempt to imitate ‘machine intelligence’. A tiled map was used as the game area containing multiple AI agents with different personalities...
Wong et al. [1] proposed a fuzzy extreme learning machine (F-ELM) which possessed advantages of fuzzy inference systems and extreme learning machines. However, the generalization capability and flexibility of F-ELM are restricted by constant rule consequences and the generalized AND operator. Therefore, first-order Takagi-Sugeno-Kang (TSK) type fuzzy rule consequences and a compensatory fuzzy operator...
In this paper, a new online learning algorithm is proposed to learn a data sample in hybrid mode. This new algorithm is developed and referred as Growing and Pruning — Fuzzy ARTMAP-radial basis function (GAP-FAM-RBF) neural network. In this algorithm, fuzzy ARTMAP (FAM) network learns from training samples and radial basis function (RBF) network provides viable solutions. The GAP-FAM-RBF that proposed...
Dog breeds recognition is a typical task of fine-grained image classification, which requires both more training images to describe each dog breed and better models to automatically discriminate different dog breeds. In this paper, we use click-through logs as source data and pre-trained deep convolutional neural network (DCNN) as initial model to build our dog recognizer. To improve recognition accuracy,...
This paper proposes a neural network model and learning algorithm that can be applied to encode words. The model realizes the function of words encoding and decoding which can be applied to text encryption/decryption and word-based compression. The model is based on Deep Belief Networks (DBNs) and it differs from traditional DBNs in that it is asymmetric structured and the output of it is a binary...
In order to extract effective audio feature using autoencoder, different from traditional bottle-neck autoencoder, bottle-body autoencoder is presented in this paper, which is constructed using restricted Boltzmann machine with the same neurons at every layer. Bottle-body feature, which is obtained by using pseudo-inverse method to initialize weights, is applied to audio signal classification. The...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.