Configuration et exploitation d'une machine émotionnelle

Dans ce travail, nous explorons la faisabilité de doter les machines de la capacité de prédire, dans un contexte d'interaction homme-machine (IHM), l'émotion d'un utilisateur, ainsi que son intensité, de manière instantanée pour une grande variété de situations. Plus spécifiquement, une application a été développée, appelée machine émotionnelle, capable de «comprendre» la signification d'une situation en se basant sur le modèle théorique d'évaluation de l'émotion Ortony, Clore et Collins (OCC). Cette machine est apte, également, à prédire les réactions émotionnelles des utilisateurs, en combinant des versions améliorées des k plus proches voisins et des réseaux de neurones. Une procédure empirique a été réalisée pour l'acquisition des données. Ces dernières ont fourni une connaissance consistante aux algorithmes d'apprentissage choisis et ont permis de tester la performance de la machine. Les résultats obtenus montrent que la machine émotionnelle proposée est capable de produire de bonnes prédictions. Une telle réalisation pourrait encourager son utilisation future dans des domaines exploitant la reconnaissance automatique de l'émotion.

Apprentissage des réseaux de neurones profonds et applications en traitement automatique de la langue naturelle

En apprentissage automatique, domaine qui consiste à utiliser des données pour apprendre une solution aux problèmes que nous voulons confier à la machine, le modèle des Réseaux de Neurones Artificiels (ANN) est un outil précieux. Il a été inventé voilà maintenant près de soixante ans, et pourtant, il est encore de nos jours le sujet d'une recherche active. Récemment, avec l'apprentissage profond, il a en effet permis d'améliorer l'état de l'art dans de nombreux champs d'applications comme la vision par ordinateur, le traitement de la parole et le traitement des langues naturelles. La quantité toujours grandissante de données disponibles et les améliorations du matériel informatique ont permis de faciliter l'apprentissage de modèles à haute capacité comme les ANNs profonds. Cependant, des difficultés inhérentes à l'entraînement de tels modèles, comme les minima locaux, ont encore un impact important. L'apprentissage profond vise donc à trouver des solutions, en régularisant ou en facilitant l'optimisation. Le pré-entraînnement non-supervisé, ou la technique du ``Dropout'', en sont des exemples. Les deux premiers travaux présentés dans cette thèse suivent cette ligne de recherche. Le premier étudie les problèmes de gradients diminuants/explosants dans les architectures profondes. Il montre que des choix simples, comme la fonction d'activation ou l'initialisation des poids du réseaux, ont une grande influence. Nous proposons l'initialisation normalisée pour faciliter l'apprentissage. Le second se focalise sur le choix de la fonction d'activation et présente le rectifieur, ou unité rectificatrice linéaire. Cette étude a été la première à mettre l'accent sur les fonctions d'activations linéaires par morceaux pour les réseaux de neurones profonds en apprentissage supervisé. Aujourd'hui, ce type de fonction d'activation est une composante essentielle des réseaux de neurones profonds. Les deux derniers travaux présentés se concentrent sur les applications des ANNs en traitement des langues naturelles. Le premier aborde le sujet de l'adaptation de domaine pour l'analyse de sentiment, en utilisant des Auto-Encodeurs Débruitants. Celui-ci est encore l'état de l'art de nos jours. Le second traite de l'apprentissage de données multi-relationnelles avec un modèle à base d'énergie, pouvant être utilisé pour la tâche de désambiguation de sens.

Development of a Biometric Personal Authentication System Based on Fingerprint and Speech

Biometrics deals with the physiological and behavioral characteristics of an individual to establish identity. Fingerprint based authentication is the most advanced biometric authentication technology. The minutiae based fingerprint identification method offer reasonable identification rate. The feature minutiae map consists of about 70-100 minutia points and matching accuracy is dropping down while the size of database is growing up. Hence it is inevitable to make the size of the fingerprint feature code to be as smaller as possible so that identification may be much easier. In this research, a novel global singularity based fingerprint representation is proposed. Fingerprint baseline, which is the line between distal and intermediate phalangeal joint line in the fingerprint, is taken as the reference line. A polygon is formed with the singularities and the fingerprint baseline. The feature vectors are the polygonal angle, sides, area, type and the ridge counts in between the singularities. 100% recognition rate is achieved in this method. The method is compared with the conventional minutiae based recognition method in terms of computation time, receiver operator characteristics (ROC) and the feature vector length. Speech is a behavioural biometric modality and can be used for identification of a speaker. In this work, MFCC of text dependant speeches are computed and clustered using k-means algorithm. A backpropagation based Artificial Neural Network is trained to identify the clustered speech code. The performance of the neural network classifier is compared with the VQ based Euclidean minimum classifier. Biometric systems that use a single modality are usually affected by problems like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks. Multifinger feature level fusion based fingerprint recognition is developed and the performances are measured in terms of the ROC curve. Score level fusion of fingerprint and speech based recognition system is done and 100% accuracy is achieved for a considerable range of matching threshold

Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

A Comparative Study of Wavelet Based Feature Extraction Techniques in Recognizing Isolated Spoken Words

Speech is a natural mode of communication for people and speech recognition is an intensive area of research due to its versatile applications. This paper presents a comparative study of various feature extraction methods based on wavelets for recognizing isolated spoken words. Isolated words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. This work includes two speech recognition methods. First one is a hybrid approach with Discrete Wavelet Transforms and Artificial Neural Networks and the second method uses a combination of Wavelet Packet Decomposition and Artificial Neural Networks. Features are extracted by using Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Training, testing and pattern recognition are performed using Artificial Neural Networks (ANN). The proposed method is implemented for 50 speakers uttering 20 isolated words each. The experimental results obtained show the efficiency of these techniques in recognizing speech

PERFORMANCE OF DIFFERENT CLASSIFIERS IN SPEECH RECOGNITION

Speech is the most natural means of communication among human beings and speech processing and recognition are intensive areas of research for the last five decades. Since speech recognition is a pattern recognition problem, classification is an important part of any speech recognition system. In this work, a speech recognition system is developed for recognizing speaker independent spoken digits in Malayalam. Voice signals are sampled directly from the microphone. The proposed method is implemented for 1000 speakers uttering 10 digits each. Since the speech signals are affected by background noise, the signals are tuned by removing the noise from it using wavelet denoising method based on Soft Thresholding. Here, the features from the signals are extracted using Discrete Wavelet Transforms (DWT) because they are well suitable for processing non-stationary signals like speech. This is due to their multi- resolutional, multi-scale analysis characteristics. Speech recognition is a multiclass classification problem. So, the feature vector set obtained are classified using three classifiers namely, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Naive Bayes classifiers which are capable of handling multiclasses. During classification stage, the input feature vector data is trained using information relating to known patterns and then they are tested using the test data set. The performances of all these classifiers are evaluated based on recognition accuracy. All the three methods produced good recognition accuracy. DWT and ANN produced a recognition accuracy of 89%, SVM and DWT combination produced an accuracy of 86.6% and Naive Bayes and DWT combination produced an accuracy of 83.5%. ANN is found to be better among the three methods.

On-Line Handwritten Character Recognition using Kohonen Networks

This paper presents an efficient Online Handwritten character Recognition System for Malayalam Characters (OHR-M) using Kohonen network. It would help in recognizing Malayalam text entered using pen-like devices. It will be more natural and efficient way for users to enter text using a pen than keyboard and mouse. To identify the difference between similar characters in Malayalam a novel feature extraction method has been adopted-a combination of context bitmap and normalized (x, y) coordinates. The system reported an accuracy of 88.75% which is writer independent with a recognition time of 15-32 milliseconds

Using self organizing maps on compositional data

Self-organizing maps (Kohonen 1997) is a type of artificial neural network developed to explore patterns in high-dimensional multivariate data. The conventional version of the algorithm involves the use of Euclidean metric in the process of adaptation of the model vectors, thus rendering in theory a whole methodology incompatible with non-Euclidean geometries. In this contribution we explore the two main aspects of the problem: 1. Whether the conventional approach using Euclidean metric can shed valid results with compositional data. 2. If a modification of the conventional approach replacing vectorial sum and scalar multiplication by the canonical operators in the simplex (i.e. perturbation and powering) can converge to an adequate solution. Preliminary tests showed that both methodologies can be used on compositional data. However, the modified version of the algorithm performs poorer than the conventional version, in particular, when the data is pathological. Moreover, the conventional ap- proach converges faster to a solution, when data is \well-behaved". Key words: Self Organizing Map; Artificial Neural networks; Compositional data

Los conceptos de salud financiera, riesgo y epidemiología en los estados financieros de las compañías del sector de extracción de petróleo crudo y gas natural en Colombia

El presente proyecto tiene como objeto identificar cuáles son los conceptos de salud, enfermedad, epidemiología y riesgo aplicables a las empresas del sector de extracción de petróleo y gas natural en Colombia. Dado, el bajo nivel de predicción de los análisis financieros tradicionales y su insuficiencia, en términos de inversión y toma de decisiones a largo plazo, además de no considerar variables como el riesgo y las expectativas de futuro, surge la necesidad de abordar diferentes perspectivas y modelos integradores. Esta apreciación es pertinente dentro del sector de extracción de petróleo y gas natural, debido a la creciente inversión extranjera que ha reportado, US$2.862 millones en el 2010, cifra mayor a diez veces su valor en el año 2003. Así pues, se podrían desarrollar modelos multi-dimensional, con base en los conceptos de salud financiera, epidemiológicos y estadísticos. El termino de salud y su adopción en el sector empresarial, resulta útil y mantiene una coherencia conceptual, evidenciando una presencia de diferentes subsistemas o factores interactuantes e interconectados. Es necesario mencionar también, que un modelo multidimensional (multi-stage) debe tener en cuenta el riesgo y el análisis epidemiológico ha demostrado ser útil al momento de determinarlo e integrarlo en el sistema junto a otros conceptos, como la razón de riesgo y riesgo relativo. Esto se analizará mediante un estudio teórico-conceptual, que complementa un estudio previo, para contribuir al proyecto de finanzas corporativas de la línea de investigación en Gerencia.

Prevalencia de neumoconiosis y su relación con medidas de higiene y seguridad industrial y niveles ambientales de carbón en minería subterránea en el departamento de Cundinamarca - Colombia, 2015

Introducción: La exposición en minas subterráneas a altos niveles de polvo de carbón está relacionada con patologías pulmonares. Objetivo: Determinar la prevalencia de neumoconiosis, medidas de higiene y seguridad industrial y su relación con niveles ambientales de carbón en trabajadores de minas de socavón en Cundinamarca. Materiales y Métodos: Estudio de corte transversal, en 215 trabajadores seleccionados mediante muestreo probabilístico estratificado con asignación proporcional. Se realizaron monitoreos ambientales, radiografías de tórax y encuestas con variables sociodemográficas y laborales. Se emplearon medidas de tendencia central y dispersión y la prueba de independencia ji-cuadrado de Pearson o pruebas exactas, con el fin de establecer las asociaciones. Resultados: El 99,5% de la población perteneció al género masculino, el 36,7% tenía entre 41-50 años, con un promedio de años de trabajo de 21,70 ± 9,99. La prevalencia de neumoconiosis fue de 42,3% y la mediana de la concentración de polvo de carbón bituminoso fue de 2,329670 mg/m3. El índice de riesgo de polvo de carbón presentó diferencias significativas en las categorías de bajo (p=0,0001) y medio (p=0,0186) con la prevalencia de neumoconiosis. El 84,2% reporto no usar mascarilla. No se presentan diferencias entre los niveles de carbón (p=0,194) con la prevalencia de neumoconiosis. Conclusiones: Se encontró una prevalencia de neumoconiosis de 42,3% en Cundinamarca. Se requiere contar con medidas de higiene y seguridad industrial efectivas para controlar el riesgo al que están expuestos los mineros de carbón por la inhalación de polvo de carbón.

A review and classification of the existing models of cyanobacteria

Bloom-forming and toxin-producing cyanobacteria remain a persistent nuisance across the world. Modelling of cyanobacteria in freshwaters is an important tool for understanding their population dynamics and predicting bloom occurrence in lakes and rivers. In this paper existing key models of cyanobacteria are reviewed, evaluated and classified. Two major groups emerge: deterministic mathematical and artificial neural network models. Mathematical models can be further subcategorized into those models concerned with impounded water bodies and those concerned with rivers. Most existing models focus on a single aspect such as the growth of transport mechanisms, but there are a few models which couple both.

Biogenic nitric oxide emissions from soils: impact on NOx and ozone over West Africa during AMMA (African Monsoon Multidisciplinary Analysis) - observational study

Chemical and meteorological parameters measured on board the Facility for Airborne Atmospheric Measurements (FAAM) BAe 146 Atmospheric Research Aircraft during the African Monsoon Multidisciplinary Analysis (AMMA) campaign are presented to show the impact of NOx emissions from recently wetted soils in West Africa. NO emissions from soils have been previously observed in many geographical areas with different types of soil/vegetation cover during small scale studies and have been inferred at large scales from satellite measurements of NOx. This study is the first dedicated to showing the emissions of NOx at an intermediate scale between local surface sites and continental satellite measurements. The measurements reveal pronounced mesoscale variations in NOx concentrations closely linked to spatial patterns of antecedent rainfall. Fluxes required to maintain the NOx concentrations observed by the BAe-146 in a number of cases studies and for a range of assumed OH concentrations (1×106 to 1×107 molecules cm−3) are calculated to be in the range 8.4 to 36.1 ng N m−2 s−1. These values are comparable to the range of fluxes from 0.5 to 28 ng N m−2 s−1 reported from small scale field studies in a variety of non-nutrient rich tropical and sub-tropical locations reported in the review of Davidson and Kingerlee (1997). The fluxes calculated in the present study have been scaled up to cover the area of the Sahel bounded by 10 to 20 N and 10 E to 20 W giving an estimated emission of 0.03 to 0.30 Tg N from this area for July and August 2006. The observed chemical data also suggest that the NOx emitted from soils is taking part in ozone formation as ozone concentrations exhibit similar fine scale structure to the NOx, with enhancements over the wet soils. Such variability can not be explained on the basis of transport from other areas. Delon et al. (2008) is a companion paper to this one which models the impact of soil NOx emissions on the NOx and ozone concentration over West Africa during AMMA. It employs an artificial neural network to define the emissions of NOx from soils, integrated into a coupled chemistry-dynamics model. The results are compared to the observed data presented in this paper. Here we compare fluxes deduced from the observed data with the model-derived values from Delon et al. (2008).

Benchmarking consensus model quality assessment for protein fold recognition

Background: Selecting the highest quality 3D model of a protein structure from a number of alternatives remains an important challenge in the field of structural bioinformatics. Many Model Quality Assessment Programs (MQAPs) have been developed which adopt various strategies in order to tackle this problem, ranging from the so called "true" MQAPs capable of producing a single energy score based on a single model, to methods which rely on structural comparisons of multiple models or additional information from meta-servers. However, it is clear that no current method can separate the highest accuracy models from the lowest consistently. In this paper, a number of the top performing MQAP methods are benchmarked in the context of the potential value that they add to protein fold recognition. Two novel methods are also described: ModSSEA, which based on the alignment of predicted secondary structure elements and ModFOLD which combines several true MQAP methods using an artificial neural network. Results: The ModSSEA method is found to be an effective model quality assessment program for ranking multiple models from many servers, however further accuracy can be gained by using the consensus approach of ModFOLD. The ModFOLD method is shown to significantly outperform the true MQAPs tested and is competitive with methods which make use of clustering or additional information from multiple servers. Several of the true MQAPs are also shown to add value to most individual fold recognition servers by improving model selection, when applied as a post filter in order to re-rank models. Conclusion: MQAPs should be benchmarked appropriately for the practical context in which they are intended to be used. Clustering based methods are the top performing MQAPs where many models are available from many servers; however, they often do not add value to individual fold recognition servers when limited models are available. Conversely, the true MQAP methods tested can often be used as effective post filters for re-ranking few models from individual fold recognition servers and further improvements can be achieved using a consensus of these methods.

A fuzzy multi-criteria decision approach for enhanced auto-tracking of seismic events

The main activity carried out by the geophysicist when interpreting seismic data, in terms of both importance and time spent is tracking (or picking) seismic events. in practice, this activity turns out to be rather challenging, particularly when the targeted event is interrupted by discontinuities such as geological faults or exhibits lateral changes in seismic character. In recent years, several automated schemes, known as auto-trackers, have been developed to assist the interpreter in this tedious and time-consuming task. The automatic tracking tool available in modem interpretation software packages often employs artificial neural networks (ANN's) to identify seismic picks belonging to target events through a pattern recognition process. The ability of ANNs to track horizons across discontinuities largely depends on how reliably data patterns characterise these horizons. While seismic attributes are commonly used to characterise amplitude peaks forming a seismic horizon, some researchers in the field claim that inherent seismic information is lost in the attribute extraction process and advocate instead the use of raw data (amplitude samples). This paper investigates the performance of ANNs using either characterisation methods, and demonstrates how the complementarity of both seismic attributes and raw data can be exploited in conjunction with other geological information in a fuzzy inference system (FIS) to achieve an enhanced auto-tracking performance.

Communicating neurons: a connectionist spiking neuron implementation of stochastic diffusion search

An information processing paradigm in the brain is proposed, instantiated in an artificial neural network using biologically motivated temporal encoding. The network will locate within the external world stimulus, the target memory, defined by a specific pattern of micro-features. The proposed network is robust and efficient. Akin in operation to the swarm intelligence paradigm, stochastic diffusion search, it will find the best-fit to the memory with linear time complexity. information multiplexing enables neurons to process knowledge as 'tokens' rather than 'types'. The network illustrates possible emergence of cognitive processing from low level interactions such as memory retrieval based on partial matching. (C) 2007 Elsevier B.V. All rights reserved.