Search

The paper presents an approach to machine learning involving the use of a hybrid method in Neural ODE. The authors consider a way of the Neural ODE application with an embedded hybrid method for intelligent manipulator control in a non-deterministic environment. To reduce computational resources, the number of layers of the neural network using ODE is reduced, the solution of which is carried out by a hybrid transformation method. The hybrid method includes normalizing the system, linear transformation, and polynomial transformation. Using the hybrid method in Neural ODE can increase the learning and computation speed. The transformation method has high accuracy with low computational complexity of the algorithm. As a result of applying the hybrid method, the original nonlinear system is transformed to a simpler form. To solve the simplified transformed system, the scheme of the numerical Runge-Kutta method of the third order with an adaptive step is used. The results of the computational experiment show an increase in the speed and accuracy of the calculation. The presented approach to implementing the hybrid method in Neural ODE allows faster training of the neural network of the world model on limited data obtained from the real environment. After training on the data generated by the model of the world, a robotic arm always successfully reaches the object during subsequent interaction with the real environment. This solves the problem of the limited ability of the agent to interact when learning with the real environment in robotic systems. [ABSTRACT FROM AUTHOR]

Classification is one of the important tasks in data mining. The probabilistic neural network (PNN) is a well-known and efficient approach for classification. The objective of the work presented in this paper is to build on this approach to develop an effective method for classification problems that can find high-quality solutions (with respect to classification accuracy) at a high convergence speed. To achieve this objective, we propose a method that hybridizes the firefly algorithm with simulated annealing (denoted as SFA), where simulated annealing is applied to control the randomness step inside the firefly algorithm while optimizing the weights of the standard PNN model. We also extend our work by investigating the effectiveness of using Lévy flight within the firefly algorithm (denoted as LFA) to better explore the search space and by integrating SFA with Lévy flight (denoted as LSFA) in order to improve the performance of the PNN. The algorithms were tested on 11 standard benchmark datasets. Experimental results indicate that the LSFA shows better performance than the SFA and LFA. Moreover, when compared with other algorithms in the literature, the LSFA is able to obtain better results in terms of classification accuracy. [ABSTRACT FROM AUTHOR]

Nowadays, many real applications comprise data-sets where the distribution of the classes is significantly different. These data-sets are commonly known as imbalanced data-sets. Traditional classifiers are not able to deal with these kinds of data-sets because they tend to classify only majority classes, obtaining poor results for minority classes. The approaches that have been proposed to address this problem can be categorized into three types: resampling methods, algorithmic adaptations and cost sensitive techniques. Radial Basis Function Networks (RBFNs), artificial neural networks composed of local models or RBFs, have demonstrated their efficiency in different machine learning areas. Centers, widths and output weights for the RBFs must be determined when designing RBFNs. Taking into account the locally tuned response of RBFs, the objective of this paper is to study the influence of global and local paradigms on the weights training phase, within the RBFNs design methodology, for imbalanced data-sets. Least Mean Square and the Singular Value Decomposition have been chosen as representatives of local and global weights training paradigms respectively. These learning algorithms are inserted into classical RBFN design methods that are run on imbalanced data-sets and also on these data-sets preprocessed with re-balance techniques. After applying statistical tests to the results obtained, some guidelines about the RBFN design methodology for imbalanced data-sets are provided. [ABSTRACT FROM AUTHOR]

Multilayer perceptron (MLP) and support vector machine (SVM), two popular learning machines, are increasingly being used as alternatives to classical statistical models for ground-level ozone prediction. However, employing learning machines without sufficient awareness about their limitations can lead to unsatisfactory results in modeling the ozone evolving mechanism, especially during ozone formation episodes. With the spirit of literature review and justification, this paper discusses, with respect to the concerning of ozone prediction, the recently developed algorithms/technologies for treating the most prominent model-performance-degradation limitations. MLP has the “black-box” property, i.e., it hardly provides physical explanation for the trained model, overfitting and local minima problems, and SVM has parameters identification and class imbalance problems. This commentary article aims to stress that the underlying philosophy of using learning machines is by no means as trivial as simply fitting models to the data because it causes difficulties, controversies or unresolved problems. This article also aims to serve as a reference point for further technical readings for experts in relevant fields. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of impact-time-control and proposes a learning-based computational guidance algorithm to solve this problem. The proposed guidance algorithm is developed based on a general prediction-correction concept: the exact time-to-go under proportional navigation guidance with realistic aerodynamic characteristics is estimated by a deep neural network and a biased command to nullify the impact time error is developed by utilizing the emerging reinforcement learning techniques. To deal with the problem of insufficient training data, a transfer-ensemble learning approach is proposed to train the deep neural network. The deep neural network is augmented into the reinforcement learning block to resolve the issue of sparse reward that has been observed in typical reinforcement learning formulation. Extensive numerical simulations are conducted to support the proposed algorithm. [ABSTRACT FROM AUTHOR]

As an essential subproblem in the face recognition field, occluded face recognition has received considerable attention in recent years. However, satisfactory recognition accuracy for occluded faces has not been achieved. Therefore, in order to solve this problem, this paper proposes a convolutional neural network that has multidimensional serial feature extraction modules for occluded faces and uses the deep learning method to improve the recognition rate. In order to improve the expression ability of the network, the method extracts features from two dimensions — space and channel — and built a multidimensional serial feature extraction module. By "multiscale" and "dependence" processing features, the generalization ability was significantly improved. Through the experimental test, the recognition accuracy of the multidimensional feature network (MFNet) reached 90.35%. This accuracy is 17.89% (72.36%) better than that of the traditional algorithm. Meanwhile, compared with other convolutional neural networks, this network has different degrees of improvement, which are 0.68% (ArcFace), 2.14% (Visual Geometry Group Face), and 4.83% (DeepID3). [ABSTRACT FROM AUTHOR]

Abstract: Skin color detection is a popular and useful technique because of its wide range of utilizations both in human computer interaction and content based analysis. Applications such as detecting and tracking of human body parts, face detection and recognition, naked people detection and people retrieval in multimedia databases all benefit from skin detection. Hence finding a proper method for segment the skin-like pixels can solve the presented problems. The Imperialist Competitive Algorithm (ICA) is a new evolutionary algorithm which was recently introduced and has a good performance in some optimization problems. The ICA was inspired by socio-political processes of imperialistic competition of mankind in the real world. In this paper a hybrid ICA-ANN is proposed for solving skin classification. A new algorithm that combines ICA and ANN to solve skin classification has been proposed, and then a hybrid Neural Network (NN)-Imperialist Competitive Algorithm (ICA) is applied to solve the classification problem. In the proposed algorithm, a multi layer perceptron network (MLP) manages the problem’s constraints and an ICA algorithm searches for high quality solutions and minimum cost. The proposed color segmentation algorithm operates directly on RGB color space without the need of color space conversion. Experimental results show that this method can improve the performance of the MLP algorithm significantly. [Copyright &y& Elsevier]

Abstract: A new PID controller for resistant differential control against load disturbance is introduced that can be used for load frequency control (LFC) application. Parameters of the controller have been specified by using imperialist competitive algorithm (ICA). Load disturbance, which is due to continuous and rapid changes of small loads, is always a problem for load frequency control of power systems. This paper introduces a new method to overcome this problem that is based on filtering technique which eliminates the effect of this kind of disturbance. The object is frequency regulation in each area of the power system and decreasing of power transfer between control areas, so the parameters of the proposed controller have been specified in a wide range of load changes by means of ICA to achieve the best dynamic response of frequency. To evaluate the effectiveness of the proposed controller, a three-area power system is simulated in MATLAB/SIMULINK. Each area has different generation units, so utilizes controllers with different parameters. Finally a comparison between the proposed controller and two other prevalent PI controllers, optimized by GA and Neural Networks, has been done which represents advantages of this controller over others. [Copyright &y& Elsevier]

Abstract: For nonlinear processes the classical model predictive control (MPC) algorithm, in which a linear model is used, usually does not give satisfactory closed-loop performance. In such nonlinear cases a suboptimal MPC strategy is typically used in which the nonlinear model is successively linearised on-line for the current operating point and, thanks to linearisation, the control policy is calculated from a quadratic programming problem. Although the suboptimal MPC algorithm frequently gives good results, for some nonlinear processes it would be beneficial to further improve control accuracy. This paper details a computationally efficient nonlinear MPC algorithm in which a neural model is linearised on-line along the predicted trajectory in an iterative way. The algorithm needs solving on-line only a series of quadratic programming problems. Advantages of the discussed algorithm are demonstrated in the control system of a high-purity ethylene–ethane distillation column for which the classical linear MPC algorithm does not work and the classical suboptimal MPC algorithm is slow. It is shown that the discussed algorithm can give practically the same control accuracy as the algorithm with on-line nonlinear optimisation and, at the same time, the algorithm is significantly less computationally demanding. [Copyright &y& Elsevier]