27 research outputs found
GUJARATI HANDWRITTEN NUMERAL OPTICAL CHARACTER THROUGH NEURAL NETWORK AND SKELETONIZATION
Full text linkThis paper deals with an optical character recognition (OCR) system for handwritten Gujarati numbers. One may find so much of work for Indian languages like Hindi, Kannada, Tamil, Bangala, Malayalam, Gurumukhi etc, but Gujarati is a language for which hardly any work is traceable especially for handwritten characters. The features of Gujarati digits are abstracted by four different profiles of digits. Skeletonization and binarization are also done for preprocessing of handwritten numerals before their classification. This work has achieved approximately 80,5% of success rate for Gujarati handwritten digit identification
Control Design for Bounded Partially Controlled TPNs Using Timed Extended Reachability Graphs and MDP
No full text
Solving Finite-Horizon Discounted Non-Stationary MDPS
No full textMarkov Decision Processes (MDPs) are a powerful framework for modeling many real-world problems with finite-horizons that maximize the reward given a sequence of actions. Although many problems such as investment and financial market problems where the value of a reward decreases exponentially with time, require the introduction of interest rates
Phonemes Classification Using the Spectrum
Get PDFIn this work, we present an automatic speech classification system for the Tamazight phonemes. We based on the spectrum presentation of the speech signal to model these phonemes. We have used an oral database of Tamazight phonemes. To test the system’s performances, we calculate the classification rate. The obtained results are satisfactory in comparison with the reference database and the quality of speech files
Control Design for Untimed Petri Nets Using Markov Decision Processes
No full textDesign of control sequences for discrete event systems (DESs) has been presented modelled by untimed Petri nets (PNs). PNs are well-known mathematical and graphical models that are widely used to describe distributed DESs, including choices, synchronizations and parallelisms. The domains of application include, but are not restricted to, manufacturing systems, computer science and transportation networks. We are motivated by the observation that such systems need to plan their production or services. The paper is more particularly concerned with control issues in uncertain environments when unexpected events occur or when control errors disturb the behaviour of the system. To deal with such uncertainties, a new approach based on discrete time Markov decision processes (MDPs) has been proposed that associates the modelling power of PNs with the planning power of MDPs. Finally, the simulation results illustrate the benefit of our method from the computational point of view. (original abstract
A Blind Identification and Equalization for MC-CDMA Transmission Channel using a New of Adaptive Filter Algorithm
Get PDFA review of literature shows that there are a variety of adaptive filters. In this research study, we propose a new type of adaptive filter that increases the diversification used to compensate the channel distortion effect in the MC-CDMA transmission. First, we show expressions of the impulse responses of the filter in the case of a perfect channel. The adaptive filter was simulated was experienced by blind equalization for different cases of Gaussian white noise in the case of an MC-CDMA transmission with orthogonal frequency baseband for mobile radio downlink channel Bran A. Simulation Results of the proposed model shows the performance of the identification and blind equalization algorithm for MC-CDMA transmission chain using IFFT
Using A Fuzzy Number Error Correction Approach to Improve Algorithms in Blind Identification
Get PDFAs part of a detailed study on blind identification of Gaussian channels, the main purpose was to propose an algorithm based on cumulants and fuzzy number approach involved throughout the whole process of identification. Our objective was to compare the new design of the algorithm to the old one using the higher order cumulants, namely Alg1, Algat and the Giannakis algorithm. We were able to demonstrate that the proposed method -fuzzy number error correction- increases the performance of the algorithm by calculating the ratio of squared errors of ALGaT and AlgatF. The method can be applied to any algorithm for more improvement and effinciency
