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.
A Neuro-Adaptive Internal Model-based Control (NAIMC), using the Fast Clustered Radial Basis Function Network (FCRBFN) equipped by the Stochastic Gradient Descent (SGD) learning algorithm is proposed to control the nonlinear plant with slow dynamics. As a first step in this design approach, the classical feedback controller is applied to improve the overall dynamic characteristics of the obtained...
The research aims to design and implement an automatic speech recognition and synthesis system. A TMS320C6713 DSK Board manufactured by Texas Instrument (TI) is adopted as the system operation platform to support independent development, and the MATLAB software is adopted as the operation platform of the speech synthesis system. Moreover, the two platforms are integrated by a human machine interface...
In this paper, the problem of missing diacritic marks in most of dialectal Arabic written resources is addressed. Our aim is to implement a scalable and extensible platform for automatically retrieving the diacritic marks for undiacritized dialectal Arabic texts. Different rule-based and statistical techniques are proposed. These include: morphological analyzer-based, maximum likelihood estimate,...
An unprecedented growth in data generation is taking place. Data about larger dynamic systems is being accumulated, capturing finer granularity events, and thus processing requirements are increasingly approaching real-time. To keep up, data-analytics pipelines need to be viable at massive scale, and switch away from static, offline scenarios to support fully online analysis of dynamic systems. This...
This paper investigates a new voice conversion technique using phone-aware Long Short-Term Memory Recurrent Neural Networks (LSTM-RNNs). Most existing voice conversion methods, including Joint Density Gaussian Mixture Models (JDGMMs), Deep Neural Networks (DNNs) and Bidirectional Long Short-Term Memory Recurrent Neural Networks (BLSTM-RNNs), only take acoustic information of speech as features to...
Online kernel-based dictionary learning (DL) algorithms are considered, which perform DL on training data lifted to a high-dimensional feature space via a nonlinear mapping. Compared to batch versions, online algorithms require low computational complexity, essential for processing the Big Data, based on the stochastic gradient descent method. However, as with any kernel-based learning algorithms,...
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...
This work describes the Dynse framework, which uses dynamic selection of classifiers to deal with concept drift. Basically, classifiers trained on new supervised batches available over time are add to a pool, from which is elected a custom ensemble for each test instance during the classification time. The Dynse framework is highly customizable, and can be adapted to use any method for dynamic selection...
Amidst the rising impact of machine learning and the popularity of deep neural networks, learning theory is not a solved problem. With the emergence of neuromorphic computing as a means of addressing the von Neumann bottleneck, it is not simply a matter of employing existing algorithms on new hardware technology, but rather richer theory is needed to guide advances. In particular, there is a need...
In order to identify a large number of very similar objects, a novel recognition approach is proposed by mean of combination of two dynamic grouping algorithms, the visual processing mechanism, PCA and multi-pathway SVM. The samples have been segmented to appropriate groups by grouping features, and then features with rotation invariance and translation invariance of each group are extracted. Finally,...
Heuristic search is considered state-of-the-art for classical planning. However, the performance of search heuristics varies significantly from problem to problem and no single heuristic is superior to all others. As a result, it is highly desirable to identify and utilize the best available heuristic for a particular planning problem. This paper presents a novel approach for planning that monitors...
A novel method for nonlinear stochastic time-varying systems identification based on multi-dimensional Taylor network with optimal structure is proposed. In this paper, the connection weight coefficients of multi-dimensional Taylor network are regarded as the time-varying parameters, which are trained by the variable forgetting factor recursive least squares algorithm, to reflect the input-output...
In this paper, we study a new problem of continuous learning from doubly-streaming data where both data volume and feature space increase over time. We refer to the doubly-streaming data as trapezoidal data streams and the corresponding learning problem as online learning from trapezoidal data streams. The problem is challenging because both data volume and data dimension increase over time, and existing...
Software Cost Estimations (SCEs) are tools that used for the software elements classification with number of factors for overall cost estimation. For example resource availability, milestones, deadlines, skill sets, onshore/offshore ratio, knowledge transition etc. Software cost estimations is one of the efficient way to estimate software product's cost with higher accuracy considering the best quality...
We consider the problem of automatic construction of algorithms for recognition of abnormal behavior segments in phase trajectories of dynamic systems. The recognition algorithm is trained on a set of trajectories containing normal and abnormal behavior of the system. The exact position of segments corresponding to abnormal behavior in the trajectories of the training set is unknown. To construct...
This article presents a method for predicting contour error using artificial neural networks. Contour error is defined as the minimum distance between actual position and reference toolpath and is commonly used to measure machining precision of Computerized Numerically Controlled (CNC) machine tools. Offline trained Nonlinear Autoregressive networks with exogenous inputs (NARX) are used to predict...
Existing intelligent theoretical line losses calculation methods that prevalent on worse line calculation error, are all based on single learning algorithm. In order to overcome this defect, a novel intelligent calculation method based on boosting algorithm is proposed. In this calculation method, the theoretical line losses calculation is abstracted into function fitting problem, in addition, the...
In this paper, we introduce an Asynchronous Multiview Learning (AML) approach to allow accurate transfer of activity classification models across asynchronous sensor views. Our study is motivated by the highly dynamic nature of health monitoring using wearable sensors. Such dynamics include changes in sensing platform (e.g., sensor upgrade) and platform settings (e.g., sampling frequency, on-body...
Restricted Boltzmann Machine (RBM) has been successfully applied to many different machine learning and pattern recognition problems. Usually, fixed learning rate (FLR) is used for training RBM. However, the reconstruction error (RCERR) with FLR may not be declined each iteration, which will result in a slow convergence speed. In this paper, we propose a method to dynamically choose the learning rate...
Extreme learning machine (ELM) for single-hidden-layer feedforward neural networks has been widely used in classification and regression for its fast learning speed. However, a single ELM suffers from problems of stability and overfitting. Ensemble approach can effectively resolve these problems. This paper proposes a selective ensemble learning algorithm based on differential evolution (DE) for classification...
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.