The use of Deep Belief Networks (DBN) to pretrain Neural Networks has recently led to a resurgence in the use of Artificial Neural Network Hidden Markov Model (ANN/HMM) hybrid systems for Automatic Speech Recognition (ASR). In this paper we report results of a DBN-pretrained context-dependent ANN/HMM system trained on two datasets that are much larger than any reported previously with DBN-pretr...

Transformer incipient fault diagnostic method based on dissolved gas analysis (DGA) using Artificial Neural Networks (ANN) and Neural-Imperialistic Competitive Algorithm (Nero-ICA) hybrid approach is simulated in this paper and the results has been compared with IEC standard. Firstly, dissolved gas analysis method and IEC DGA standard has been presented. In the second step, application of ANN a...

The steady-state stability limit and the system positive damping can be improved by conventional Power System Stabilizer (PSS). However, in order to have abilities such as the online tuning and optimal real-time damping in the entire operating range, robust design of PSS in required. A novel robust PSS design using Artificial Neural Network (ANN) and Imperialist Competitive Algorithm (ICA) for ...

Artificial neural network (ANN) training is one of the major challenges in using a prediction model based on ANN. Gradient based algorithms are the most frequent training algorithms with several drawbacks. The aim of this paper is to present a method for training ANN. The ability of metaheuristics and greedy gradient based algorithms are combined to obtain a hybrid improved opposition based par...

This paper presents a new hybrid automatic learning approach, which combines artificial neural networks (ANN) and regression trees (RT), to perform on-line dynamic security assessment of power systems. In the proposed method, the RT is firstly used to split the vast amount of knowledge data that describes a security problem into several less spread and disjoint problems. Then, an ANN is trained...

Short Term Load Forecasting (STLF) is a power system operating procedures that have an important role in terms of realizing the economic electric production. This research focuses on the application of hybrid PSO-ANN algorithm in STLF. Load data grouped by the type of weekdays and holidays. Consumption of electricity load in West Java Indonesia, used as input to the learning algorithm PSO-ANN. ...

Leaf area index (LAI) is a key parameter used to describe vegetation structures and is widely used in ecosystem biophysical process and vegetation productivity models. Many algorithms have been developed for the estimation of LAI based on remote sensing images. Our goal was to produce accurate and timely predictions of grassland LAI for the meadow steppes of northern China. Here, we compare the...

Seaborne transport forecasting has attracted substantial interest over the years because of providing a useful policy tool for decision-makers. Although various methods have been widely studied, there is still broad debate on accurate models and preprocessing. The current paper aims to point out these issues, as well establish model domestic cargo volumes using SARIMAX, MLP, LSTM NARX SARIMAX-A...

Neuroevolution, the optimisation of artificial neural networks (ANNs) through evolutionary computation, is a promising approach to the synthesis of controllers for autonomous agents. Traditional neuroevolution approaches employ direct encodings, which are limited in their ability to evolve complex or large-scale controllers because each ANN parameter is independently optimised. Indirect encodin...

In the paper, hybrid technique for solving optimal power flow problems that occur in power systems. The proposed hybrid technique is the combination of artificial bee colony (ABC) algorithm and artificial intelligence (AI) technique. The purpose of the ABC algorithm is used to optimize the optimal operating range of generation limits. So, the fuel cost and the emission of the power generation s...