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 first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possible in a visually simple environment, using a neural network controller with evolved weights. Two retina layouts are tested, each with the same number of inputs: first, a graduated density retina which focuses near the center of...
This paper presents a new way to combine two different approaches of artificial intelligence looking for the best path in a graph, ant colony optimization and Bayesian networks. The main objective is to develop a learning management system which will have the capability of adapting the learning path to the learnerpsilas needs in execution time, taking into account the pedagogical weight of each learning...
e-Learning is a critical support mechanism for industrial and academic organizations to enhance the skills of employees and students and, consequently, the overall competitiveness in the new economy. The remarkable velocity and volatility of modern knowledge require novel learning methods offering additional features as efficiency, task relevance and personalization. The main aim of adaptive eLearning...
This paper proposes a novel feature extraction method for face recognition in the wavelet domain called wavelet projection entropy (WPE). First, the projection entropy features from each wavelet subband are computed along the vertical and horizontal direction after the division. Then information fusion scheme is applied to integrate results obtained from each subband. Experiments show that WPE can...
Studies on chaos synchronization in coupled chaotic circuits are extensively carried out in various fields. In this study, synchronization patterns generated in a ring of cross-coupled chaotic circuits are investigated. Computer simulations show that this coupled system produces several phase patterns.
In recent years, facial expressions of pain have been the focus of considerable behavioral research. Such work has documented that pain expressions, like other affective facial expressions, play an important role in social communication. Enabling computer systems to recognize pain expression from facial images is a challenging research topic. In this paper, we present two systems for pain recognition...
Traditional connectionist models place an emphasis on learned weights. Based on neurobiological evidence, a new approach is developed and experimentally shown to be more robust for disambiguating novel combinations of stimuli. It does not require variable weights and avoids many training related issues. This approach is compared with traditional weight-learning methods. The network is better able...
This paper presents a river flood prediction technique using support vector machine (SVM). We investigated the 2-year data covering 2005 and 2006 and 7 crucial river floods that occurred in the downtown of Chiang Mai, Thailand. Past and current river levels of the 3 gauging stations are utilized as the input data of the SVM models to predict the river levels at the downtown station in 1 hour and 7...
We propose a relational neural network defined as a special instance of the recurrent cascade correlation. The proposed model is designed to deal with classification tasks where classes are organized into generic graphs (e.g. taxonomies, ontologies etc.). The open challenge is to exploit the knowledge encoded in the relationships among the classes. This is particularly useful when there are many classes...
This paper studies application of binary neural networks (BNN) to prediction for spatio-temporal patterns. In the approach, we assume that the objective spatio-temporal patterns can be approximated by a cellular automaton (CA). Teacher signals are extracted from a part of objective pattern and are used for learning of the BNN. The BNN is used to govern dynamics of CA that outputs prediction patterns...
In this paper, we propose a new kernel discriminant analysis using composite vectors (C-KDA). We show that employing composite vectors is similar to using more samples by analysis, which is a great advantage in classification problems when the size of training samples is small. Motivated by this, we apply composite vectors to kernel-based methods, which may have overfitting problems when training...
We propose a feature selection criterion based on kernel discriminant analysis (KDA) for a n-class problem, which finds eigenvectors on which the projected class data are locally maximally separated. The proposed criterion is the sum of the objective function values of KDA associated with the n-1 eigenvectors. The criterion results in calculating the sum of n-1 eigenvalues associated with the eigenvectors...
The operation of V1 simple cells in primates has been traditionally modelled with linear models resembling Gabor filters, whereas the functionality of subsequent visual cortical areas is less well understood. Here we explore the learning of mechanisms for further nonlinear processing by assuming a functional form of a product of two linear filter responses, and estimating a basis for the given visual...
In this work we show that a metaheuristic, the variable neighborhood search (VNS), can be effectively used in order to improve the performance of the hardware-friendly version of the support vector machine (SVM). Our target is the implementation of the feed-forward phase of SVM on resource-limited hardware devices, such as field programmable gate arrays (FPGAs) and digital signal processors (DSPs)...
Since machine learning has become a tool to make more efficient design of sophisticated systems, we present in this paper a novel methodology to create powerful neural network controllers for complex systems while minimising the design effort. Using a robot task as a case study, we have shown that using the feedback from the robot itself, the system can learn from experience, or example provided by...
A nonlinear discrete-time neural observer for the state estimation of a discrete-time induction motor model, in presence of external and internal uncertainties is presented. The observer is based on a discrete-time recurrent high order neural network (RHONN) trained with an extended Kalman filter (EKF)-based algorithm. This observer estimates the state of the unknown discrete-time nonlinear system,...
Entropy partition method for complex system has been applied in many ldnds of fields. In this paper, we improve the calculation of correlative measure for both discrete variables and continuous variables, and apply this method in vascular endothelial dysfunction (ED) discrete data and neuro-endocrine-immune (NEI) continuous data respectively. The partition results show this entropy partition methodpsilas...
Salient objects detection in time sequenced images has a very important role in many applications such as surveillance systems, tracking and recognition systems, scene analysis and so on. This paper presents a novel approach for salient objects detection in time sequenced images. The approach in this paper is based on a visual saliency model which is proposed for analysis in time sequenced images...
In various studies, it has been demonstrated that combining the decisions of multiple classifiers can lead to better recognition results. Plurality voting is one of the most widely used combination strategies. In this paper, we both theoretically and experimentally analyze the performance of a plurality voting-based ensemble classifier. Theoretical expressions for system performance are derived as...
Locally linear embedding heavily depends on whether the neighborhood graph represents the underlying geometry structure of the data manifolds. Inspired from the cognitive law, the relative transformation(RT) and kernel relative transformation (KRT) are proposed. They can improve the distinction between data points and inhibit the impact of noise and sparsity of data, which can be then applied to construct...
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.