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.
The information of electricity demand forecasting is a base for energy generation enterprise to develop electricity supply system. The purpose of this study is to develop a monthly electricity forecasting model in order to predict electricity demand for energy management. The proposed approach to monthly electricity demand time series forecasting model, describes the trend of the electricity demand...
This paper is an attempt to develop a new technology, which is an advancement of the previously published paper [1] for fault diagnosis of multilevel inverter adopting the machine learning and optimization techniques. The advanced machine-learning algorithm called the Optimized Radial Basis Neural Network (ORBNN) method is developed in which the Neural Network uses Radial Basis function as the activation...
Recently, more neuroscience researches focus on the role of dendritic structure during the neural computation. Inspired by the specified topologies of numerous dendritic trees, we proposed a single neural model with a particular dendritic structure. The dendrites are composed of several branches, and these branches correspond to three distributions in coordinate, which are used to classify the training...
We present a novel method for training (evolving) fully convolutional neural networks (CNNs) for deformable object manipulation. Instead of using a weight update rule, we evolve an ensemble of compositional pattern generating networks (CPPNs) by means of a genetic algorithm (GA). These ensembles generate the convolutional kernels that comprise the CNN. This allows the GA to search for fit kernels...
Feature selection algorithms select the most relevant features of a data set to improve the classification performance of the machine learning classifiers trained using the data set. This paper proposes a feature selection algorithm called ultiobjective genetic local search (MOGLS) which integrates a 3-objective genetic algorithm with a local search heuristic to find feature subsets with the maximum...
The recently proposed trainable COSFIRE filters are highly effective in a wide range of computer vision applications, including object recognition, image classification, contour detection and retinal vessel segmentation. A COSFIRE filter is selective for a collection of contour parts in a certain spatial arrangement. These contour parts and their spatial arrangement are determined in an automatic...
We present a novel algorithm for the semantic labeling of photographs shared via social media. Such imagery is diverse, exhibiting high intra-class variation that demands large training data volumes to learn representative classifiers. Unfortunately image annotation at scale is noisy resulting in errors in the training corpus that confound classifier accuracy. We show how evolutionary algorithms may...
Utilization of machine learning algorithms in time-series data analysis is crucial to effective decision making in today's dynamic and competitive environment. One data type of growing interest is the electricity consumer load profile (LP) data. Owing to advances in the smart grid, immense amount of LP data became available to policymakers as potential to improving the electricity sector. Due to the...
The adequate representation of states in the construction of intelligent agents is fundamental for allowing them to achieve a satisfactory performance, principally for those that actuate in a competitive environment that possesses a high state space. One particular type of representation that is very appropriate for these situations is the NetFeatureMap, which describes by means of features the relevant...
On the side of enhancing the execution of skills, specialists in sports are adopting analysis of kinematics to correct actions of an athlete. By means of technological resources used to measure physical variables and to supply relevant data to trainers, results related to improvements on athletes' performance are being achieved. In this context, this work uses the Radial Basis Function Neural Networks...
Artificial immune system (AIS) is considered as an adaptive computational intelligence method that could be used for detecting and preventing current computer network threats. AIS generates Antibodies (self) competent in recognizing Antigen (non-self), which is considered as an anomaly technique. This paper aims to develop artificial immune system (AIS) that consists of two levels. Level one is developed...
Train Location Unit plays a crucial role in train control system, whose reliability is directly related to the safe operation of trains. There are many train positioning methods in public mainly relates to GPS/ Odometer(ODO), which is the direction of the actual demand. In this paper, a fault diagnosis method based on improved HMM(Hidden Markov Model) is studied which the genetic algorithm(GA) is...
Gray-Box Models which combine a phenomenological model with a black box tool are useful for determining the values of not well known parameters of the model. In this work an indirect strategy for training these gray box models using least-square support vector machine and genetic algorithms is presented. The gray box model was tested in a Continuous Stirred Tank Reactor process with good results (Index...
This paper proposes a GA-SVM classification method which is applied to the dynamic evaluation of taekwondo. For classifying a dynamic action, we converted a dynamic action signal to a frequency spectrum signal for analysis. However, the useful features were concentrated in a part of the frequency spectrum, and the useless features led to a decline in accuracy, operation speed, and efficiency of the...
In this paper we are interested in knowing, which features provide useful information for recognizing a gesture or an action, and how the set of selected characteristics impact the accuracy of detection. Then we define a large set of possible features, which are angles calculated from the joints of the skeleton provided by the kinect device. Our contribution is to propose an algorithm: Reduction of...
A software for distributed neural network training is introduced here. The introduced software named NeuralGenesis implements a client — server model for parallel genetic algorithms with custom features such as: an enhanced stopping rule, an advanced mutation scheme and periodical application of a local search procedure. The software is coded in Qt5 for portability reasons and it is freely available...
In this article, we present an application of metaheuristics optimization approaches to improve medical classifier performance. Genetic Algorithm (GA), Simulated Annealing (SA) and Particle Swarm Optimization (PSO) have been applied in conjunction with Least Square Support Vector Machine (LS-SVM) approach to optimize the total misclassification error in term of False Positive and False Negative rates...
The progressive integration of Advanced Driver Assistant Systems (ADAS) into vehicles has contributed significantly to increasing safety and comfort levels of the driver. The need to adapt the vehicle to the preferences and requirements of the driver leads to the development of individualized ADAS. Automatic identification of the driver is a key factor in the design of these systems. In this work,...
Many algorithms are developed to model Genomic Estimated Breeding Value (GEBV). Modeling GEBV evolves a huge size of genotype in both terms of the dimension (columns) and the instances (rows). Good combinations of features help in predicting which phenotype is being represented. Preparing a good training population sample is assumed to be a convenient solution to deal with such complex genotype data...
The major challenge in the design of Interval type-2 fuzzy logic system (IT2FLS) is to determine the optimal parameters for their antecedent and consequent parts. The most frequently used objective function for the design of IT2FLSs is root mean squared error (RMSE). However, other than RMSE, the maximum absolute error (MAE) for each of identification samples is very important. This paper propose...
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.