732 resultados para Processament de senyals
Resumo:
Aquest projecte es dirigeix a tots aquells docents que gestionen informació d'activitats dinvestigació des de diferents eines tecnològiques i que precisen de connexió a Internet i de diverses Webs. Per centralitzar aquestes dades, neix TeachPro, un software automatitzat que gestiona i emmagatzema informació sobre les activitats de gestió per tal que l'usuari en disposi de manera ràpida i organitzada. Tot això, sense connexió a Internet. Les dades són gestionades mitjançant una interfície a partir de la qual l'usuari podrà consultar, afegir, modificar, o eliminar tota aquella informació que desitgi. Totes aquestes dades seran emmagatzemades en una base de dades local.
Resumo:
La finalitat d'aquest projecte és la creació d'una aplicació web per gestionar una empresa d'autobusos. El resultat que s'obtingui anirà dirigit a Agobe Tours SL. Permetrà reservar places als usuaris i l'administrador podrà gestionar tots els esdeveniments relacionats amb el negoci. Es desenvoluparà de zero per crear una aplicació a mida amb el propòsit de complir els objectius de l'empresa.
Resumo:
L'objectiu d'aquest projecte és definir una metodologia de treball àgil en el manteniment de sistemes CRM basada en la metodologia de desenvolupament de software SCRUM. A partir de l'estudi d'aquesta metodologia i de la definició dels processos de manteniment d'un sistema CRM, el projecte adapta aquests processos i proposa una nova metodologia que millorarà el rendiment, l'eficiència i la satisfacció tant dels equips de treball que participen en l'execució d’aquests processos com dels clients finals.
Resumo:
El Sistema d'Informació de Taxacions de béns immobles és una solució adaptada a les necessitats d'una empresa que vol sortir al mercat venent els seus productes a través d'internet. L'activitat econòmica de l'empresa es basa en la venda d'informació de subhastes i taxacions de béns immobles. El sistema implementat proporciona una eina per gestionar els productes i un canal de venda per internet.
Resumo:
Aquest projecte consisteix en la creació d'una botiga virtual per a l'empresa CREATIFHPROMOS, companyia del sector del reclam publicitari; per a dur a terme aquest projecte, es realitzarà un estudi de les plataformes actuals de comerç electrònic “Open Source” desenvolupades en PHP, per tal de, a partir dels requeriments de l'empresa, seleccionar la més adient per a la seva implantació,i, en cas de ser necessari, desenvolupar nous mòduls i funcionalitats per adaptar als requeriments recollits.
Resumo:
Este proyecto es un estudio que pretende realizar una aplicación dirigida a centros deportivos, implementando a través de BIOMAX el acceso a las instalaciones utilizando tarjetas de proximidad. Además la aplicación permitirá gestionar de forma eficiente a sus socios e instalaciones. De esta manera se consigue automatizar - mejorando en tiempo y calidad -una tarea imprescindible de realizar, control de accesos de forma sencilla y con un mantenimiento fácil por parte de los usuarios que la utilicen. Para ello se utilizará un dispositivo KIMALDI que nos permitirá gestionar el control de accesos
Resumo:
A nonlocal variational formulation for interpolating a sparsel sampled image is introduced in this paper. The proposed variational formulation, originally motivated by image inpainting problems, encouragesthe transfer of information between similar image patches, following the paradigm of exemplar-based methods. Contrary to the classical inpaintingproblem, no complete patches are available from the sparse imagesamples, and the patch similarity criterion has to be redefined as here proposed. Initial experimental results with the proposed framework, at very low sampling densities, are very encouraging. We also explore somedepartures from the variational setting, showing a remarkable ability to recover textures at low sampling densities.
Resumo:
Biometric system performance can be improved by means of data fusion. Several kinds of information can be fused in order to obtain a more accurate classification (identification or verification) of an input sample. In this paper we present a method for computing the weights in a weighted sum fusion for score combinations, by means of a likelihood model. The maximum likelihood estimation is set as a linear programming problem. The scores are derived from a GMM classifier working on a different feature extractor. Our experimental results assesed the robustness of the system in front a changes on time (different sessions) and robustness in front a change of microphone. The improvements obtained were significantly better (error bars of two standard deviations) than a uniform weighted sum or a uniform weighted product or the best single classifier. The proposed method scales computationaly with the number of scores to be fussioned as the simplex method for linear programming.
Resumo:
In this paper we propose the inversion of nonlinear distortions in order to improve the recognition rates of a speaker recognizer system. We study the effect of saturations on the test signals, trying to take into account real situations where the training material has been recorded in a controlled situation but the testing signals present some mismatch with the input signal level (saturations). The experimental results for speaker recognition shows that a combination of several strategies can improve the recognition rates with saturated test sentences from 80% to 89.39%, while the results with clean speech (without saturation) is 87.76% for one microphone, and for speaker identification can reduce the minimum detection cost function with saturated test sentences from 6.42% to 4.15%, while the results with clean speech (without saturation) is 5.74% for one microphone and 7.02% for the other one.
Resumo:
This paper deals with non-linear transformations for improving the performance of an entropy-based voice activity detector (VAD). The idea to use a non-linear transformation has already been applied in the field of speech linear prediction, or linear predictive coding (LPC), based on source separation techniques, where a score function is added to classical equations in order to take into account the true distribution of the signal. We explore the possibility of estimating the entropy of frames after calculating its score function, instead of using original frames. We observe that if the signal is clean, the estimated entropy is essentially the same; if the signal is noisy, however, the frames transformed using the score function may give entropy that is different in voiced frames as compared to nonvoiced ones. Experimental evidence is given to show that this fact enables voice activity detection under high noise, where the simple entropy method fails.
Resumo:
This special issue aims to cover some problems related to non-linear and nonconventional speech processing. The origin of this volume is in the ISCA Tutorial and Research Workshop on Non-Linear Speech Processing, NOLISP’09, held at the Universitat de Vic (Catalonia, Spain) on June 25–27, 2009. The series of NOLISP workshops started in 2003 has become a biannual event whose aim is to discuss alternative techniques for speech processing that, in a sense, do not fit into mainstream approaches. A selected choice of papers based on the presentations delivered at NOLISP’09 has given rise to this issue of Cognitive Computation.
Resumo:
The work presented here is part of a larger study to identify novel technologies and biomarkers for early Alzheimer disease (AD) detection and it focuses on evaluating the suitability of a new approach for early AD diagnosis by non-invasive methods. The purpose is to examine in a pilot study the potential of applying intelligent algorithms to speech features obtained from suspected patients in order to contribute to the improvement of diagnosis of AD and its degree of severity. In this sense, Artificial Neural Networks (ANN) have been used for the automatic classification of the two classes (AD and control subjects). Two human issues have been analyzed for feature selection: Spontaneous Speech and Emotional Response. Not only linear features but also non-linear ones, such as Fractal Dimension, have been explored. The approach is non invasive, low cost and without any side effects. Obtained experimental results were very satisfactory and promising for early diagnosis and classification of AD patients.
Resumo:
Alzheimer's disease is the most prevalent form of progressive degenerative dementia; it has a high socio-economic impact in Western countries. Therefore it is one of the most active research areas today. Alzheimer's is sometimes diagnosed by excluding other dementias, and definitive confirmation is only obtained through a post-mortem study of the brain tissue of the patient. The work presented here is part of a larger study that aims to identify novel technologies and biomarkers for early Alzheimer's disease detection, and it focuses on evaluating the suitability of a new approach for early diagnosis of Alzheimer’s disease by non-invasive methods. The purpose is to examine, in a pilot study, the potential of applying Machine Learning algorithms to speech features obtained from suspected Alzheimer sufferers in order help diagnose this disease and determine its degree of severity. Two human capabilities relevant in communication have been analyzed for feature selection: Spontaneous Speech and Emotional Response. The experimental results obtained were very satisfactory and promising for the early diagnosis and classification of Alzheimer’s disease patients.
Resumo:
In this paper we propose an endpoint detection system based on the use of several features extracted from each speech frame, followed by a robust classifier (i.e Adaboost and Bagging of decision trees, and a multilayer perceptron) and a finite state automata (FSA). We present results for four different classifiers. The FSA module consisted of a 4-state decision logic that filtered false alarms and false positives. We compare the use of four different classifiers in this task. The look ahead of the method that we propose was of 7 frames, which are the number of frames that maximized the accuracy of the system. The system was tested with real signals recorded inside a car, with signal to noise ratio that ranged from 6 dB to 30dB. Finally we present experimental results demonstrating that the system yields robust endpoint detection.
Resumo:
Avui en dia s’ha convertit en una necessitat tenir cura del medi ambient i optimitzar els recursos naturals. En el camp per estalviar energia s’han fet grans progressos i disposem d’un gran ventall de dispositius que ens ajuden i ens faciliten l’optimització del consum d’energia. Però és una realitat que en l’estalvi del consum d’aigua el progrés ha estat molt menor i es limita molt a donar consells i repartir dosificadors d’aigua. Qui no ha vist carrers o jardins o cases inundades amb milers de litres d’aigua? Aquesta realitat m’ha portat a dissenyar i desenvolupar un prototip que em permeti tenir un millor control del consum d’aigua. El prototip, a trets principals, consta d’un sensor, una electrovàlvula i una placa Arduino Atmega. El sensor ens permet mesurar els litres consumits durant un cert període de temps. Passat aquest temps de mostreig es compara els litres consumits amb el consum habitual, en aquell període de temps. En cas de sobrepassar el volum programat es tancarà l’electrovàlvula de forma automàtica i rebrem un SMS al telèfon. L’activació de l’alarma es pot ajustar que sigui al igualar-se els dos valors, litres programats i litres consumits. També es pot programar el percentatge que cal sobrepassar de litres consumits per activar l’alarma, com el temps de mostreig. El fet de poder programar tots aquests valors ens permet fer un ajust ideal per a la instal·lació que es vol tenir controlada. A més, el prototip es pot utilitzar per enviar a la companyia d’aigua el valor del comptador de forma automàtica. D’aquesta forma la companyia d’aigua també optimitza recursos estalviant-se el desplaçament de personal a la instal·lació per fer la lectura corresponent. El prototip està basat amb un Arduino Atmega que ens permet el processament de les dades programades i capturades pel sensor. També s’ha incorporat una pantalla TFT Touch 2’8”, que permet visualitzar i programar els valors d’una forma molt més intuïtiva. Per enviar els SMS s’utilitza una placa d’Arduino Cel·lular Shield - SM5100B, a la qual només cal afegir una targeta SIM. A priori, el prototip té un elevat cost al fabricar una sola unitat i pot semblar poc útil. Però ens pot estalviar alguna sorpresa en les factures d’aigua si tenim una fuita i no ens n’adonem fins a veure el rebut de la companyia. Si es fabriqués a grans quantitats es podria abaratir el preu i fer-lo encara més engrescador.