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.

The berth allocation problem at port terminals : a column generation framework

Le problème d'allocation de postes d'amarrage (PAPA) est l'un des principaux problèmes de décision aux terminaux portuaires qui a été largement étudié. Dans des recherches antérieures, le PAPA a été reformulé comme étant un problème de partitionnement généralisé (PPG) et résolu en utilisant un solveur standard. Les affectations (colonnes) ont été générées a priori de manière statique et fournies comme entrée au modèle %d'optimisation. Cette méthode est capable de fournir une solution optimale au problème pour des instances de tailles moyennes. Cependant, son inconvénient principal est l'explosion du nombre d'affectations avec l'augmentation de la taille du problème, qui fait en sorte que le solveur d'optimisation se trouve à court de mémoire. Dans ce mémoire, nous nous intéressons aux limites de la reformulation PPG. Nous présentons un cadre de génération de colonnes où les affectations sont générées de manière dynamique pour résoudre les grandes instances du PAPA. Nous proposons un algorithme de génération de colonnes qui peut être facilement adapté pour résoudre toutes les variantes du PAPA en se basant sur différents attributs spatiaux et temporels. Nous avons testé notre méthode sur un modèle d'allocation dans lequel les postes d'amarrage sont considérés discrets, l'arrivée des navires est dynamique et finalement les temps de manutention dépendent des postes d'amarrage où les bateaux vont être amarrés. Les résultats expérimentaux des tests sur un ensemble d'instances artificielles indiquent que la méthode proposée permet de fournir une solution optimale ou proche de l'optimalité même pour des problème de très grandes tailles en seulement quelques minutes.

Non invasive classification system of scoliosis curve types using least-squares support vector machines

Objective To determine scoliosis curve types using non invasive surface acquisition, without prior knowledge from X-ray data. Methods Classification of scoliosis deformities according to curve type is used in the clinical management of scoliotic patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of the 3D back surface of the patients. The 3D image of the surface of the trunk is divided into patches and local geometric descriptors characterizing the back surface are computed from each patch and constitute the features. We reduce the dimensionality by using principal component analysis and retain 53 components using an overlap criterion combined with the total variance in the observed variables. In this work, a multi-class classifier is built with least-squares support vector machines (LS-SVM). The original LS-SVM formulation was modified by weighting the positive and negative samples differently and a new kernel was designed in order to achieve a robust classifier. The proposed system is validated using data from 165 patients with different scoliosis curve types. The results of our non invasive classification were compared with those obtained by an expert using X-ray images. Results The average rate of successful classification was computed using a leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. As for the correct classification rates per class, we obtained 96%, 84% and 97% for the thoracic, double major and lumbar/thoracolumbar curve types, respectively. Conclusion This study shows that it is possible to find a relationship between the internal deformity and the back surface deformity in scoliosis with machine learning methods. The proposed system uses non invasive surface acquisition, which is safe for the patient as it involves no radiation. Also, the design of a specific kernel improved classification performance.

An Alternative Approach To Computer System Security Monitoring And Enhancement Through System Call Sequence Analysis

Modern computer systems are plagued with stability and security problems: applications lose data, web servers are hacked, and systems crash under heavy load. Many of these problems or anomalies arise from rare program behavior caused by attacks or errors. A substantial percentage of the web-based attacks are due to buffer overflows. Many methods have been devised to detect and prevent anomalous situations that arise from buffer overflows. The current state-of-art of anomaly detection systems is relatively primitive and mainly depend on static code checking to take care of buffer overflow attacks. For protection, Stack Guards and I-leap Guards are also used in wide varieties.This dissertation proposes an anomaly detection system, based on frequencies of system calls in the system call trace. System call traces represented as frequency sequences are profiled using sequence sets. A sequence set is identified by the starting sequence and frequencies of specific system calls. The deviations of the current input sequence from the corresponding normal profile in the frequency pattern of system calls is computed and expressed as an anomaly score. A simple Bayesian model is used for an accurate detection.Experimental results are reported which show that frequency of system calls represented using sequence sets, captures the normal behavior of programs under normal conditions of usage. This captured behavior allows the system to detect anomalies with a low rate of false positives. Data are presented which show that Bayesian Network on frequency variations responds effectively to induced buffer overflows. It can also help administrators to detect deviations in program flow introduced due to errors.

Journal Productivity in Fishery Science - An Informetric Analysis

This thesis Entitled Journal productivity in fishery science an informetric analysis.The analyses and formulating results of the study, the format of the thesis was determined. The thesis is divided into different chapters mentioned below. Chapter 1 gives an overview on the topic of research. Introduction gives the relevance of topic, define the problem, objectives of the study, hypothesis, methods of data collection, analysis and layout of the thesis. Chapter 2 provides a detailed account of the subject Fishery science and its development. A comprehensive outline is given along with definition, scope, classification, development and sources of information.Method of study used in this research and its literature review form the content of this chapter. Chapter 4 Details of the method adopted for collecting samples for the study, data collection and organization of the data are given. The methods are based on availability of data, period and objectives of the research undertaken.The description, analyses and the results of the study are covered in this chapter.

A study of the information seeking bebavior of science and technology teachers and researchers of Cocbin University of Science and Technology and University of Kerala in the cbanged library environment

Information communication technology (IC T) has invariably brought about fundamental changes in the way in which libraries gather. preserve and disseminate information. The study was carried out with an aim to estimate and compare the information seeking behaviour (ISB) of the academics of two prominent universities of Kerala in the context of advancements achieved through ICT. The study was motivated by the fast changing scenario of libraries with the proliferation of many high tech products and services. The main purpose of the study was to identify the chief source of information of the academics, and also to examine academics preference upon the form and format of information source. The study also tries to estimate the adequacy of the resources and services currently provided by the libraries.The questionnaire was the central instrument for data collection. An almost census method was adopted for data collection engaging various methods and tools for eliciting data.The total population of the study was 957, out of which questionnaire was distributed to 859 academics. 646 academics responded to the survey, of which 564 of them were sound responses. Data was coded and analysed using Statistical Package for Social Sciences (SPSS) software and also with the help of Microsofl Excel package. Various statistical techniques were engaged to analyse data. A paradigm shift is evident by the fact that academies push themselves towards information in internet i.e. they prefer electronic source to traditional source and the very shift is coupled itself with e-seeking of information. The study reveals that ISB of the academics is influenced priman'ly by personal factors and comparative analysis shows that the ISB ofthc academics is similar in both universities. The productivity of the academics was tested to dig up any relation with respect to their ISB, and it is found that productivity of the academics is extensively related with their ISB. Study also reveals that the users ofthe library are satisfied with the services provided but not with the sources and in conjunction, study also recommends ways and means to improve the existing library system.

Design And Development Of A Named Entity Based Question Answering System For Malayalam Language

This is a Named Entity Based Question Answering System for Malayalam Language. Although a vast amount of information is available today in digital form, no effective information access mechanism exists to provide humans with convenient information access. Information Retrieval and Question Answering systems are the two mechanisms available now for information access. Information systems typically return a long list of documents in response to a user’s query which are to be skimmed by the user to determine whether they contain an answer. But a Question Answering System allows the user to state his/her information need as a natural language question and receives most appropriate answer in a word or a sentence or a paragraph. This system is based on Named Entity Tagging and Question Classification. Document tagging extracts useful information from the documents which will be used in finding the answer to the question. Question Classification extracts useful information from the question to determine the type of the question and the way in which the question is to be answered. Various Machine Learning methods are used to tag the documents. Rule-Based Approach is used for Question Classification. Malayalam belongs to the Dravidian family of languages and is one of the four major languages of this family. It is one of the 22 Scheduled Languages of India with official language status in the state of Kerala. It is spoken by 40 million people. Malayalam is a morphologically rich agglutinative language and relatively of free word order. Also Malayalam has a productive morphology that allows the creation of complex words which are often highly ambiguous. Document tagging tools such as Parts-of-Speech Tagger, Phrase Chunker, Named Entity Tagger, and Compound Word Splitter are developed as a part of this research work. No such tools were available for Malayalam language. Finite State Transducer, High Order Conditional Random Field, Artificial Immunity System Principles, and Support Vector Machines are the techniques used for the design of these document preprocessing tools. This research work describes how the Named Entity is used to represent the documents. Single sentence questions are used to test the system. Overall Precision and Recall obtained are 88.5% and 85.9% respectively. This work can be extended in several directions. The coverage of non-factoid questions can be increased and also it can be extended to include open domain applications. Reference Resolution and Word Sense Disambiguation techniques are suggested as the future enhancements

Computational models for the prediction of severe thunderstorms over east indian region

Thunderstorm is one of the most spectacular weather phenomena in the atmosphere. Many parts over the Indian region experience thunderstorms at higher frequency during pre-monsoon months (March- May), when the atmosphere is highly unstable because of high temperatures prevailing at lower levels. Most dominant feature of the weather during the pre-monsoon season over the eastern Indo-Gangetic plain and northeast India is the outburst of severe local convective storms, commonly known as ‘Nor’wester’ or ‘Kalbaishakhi’. The severe thunderstorms associated with thunder, squall line, lightning and hail cause extensive losses in agriculture, damage to structure and also loss of life. The casualty due to lightning associated with thunderstorms in this region is the highest in the world. The highest numbers of aviation hazards are reported during occurrence of these thunderstorms. In India, 72% of tornadoes are associated with this thunderstorm.

Design and Development of a Frame Based MT System for English-to-ISL

This paper presents the design and development of a frame based approach for speech to sign language machine translation system in the domain of railways and banking. This work aims to utilize the capability of Artificial intelligence for the improvement of physically challenged, deaf-mute people. Our work concentrates on the sign language used by the deaf community of Indian subcontinent which is called Indian Sign Language (ISL). Input to the system is the clerk’s speech and the output of this system is a 3D virtual human character playing the signs for the uttered phrases. The system builds up 3D animation from pre-recorded motion capture data. Our work proposes to build a Malayalam to ISL

Agent Based Evacuation Simulation Using Leader-Follower Model

Agent based simulation is a widely developing area in artificial intelligence.The simulation studies are extensively used in different areas of disaster management. This work deals with the study of an agent based evacuation simulation which is being done to handle the various evacuation behaviors.Various emergent behaviors of agents are addressed here. Dynamic grouping behaviors of agents are studied. Collision detection and obstacle avoidances are also incorporated in this approach.Evacuation is studied with single exits and multiple exits and efficiency is measured in terms of evacuation rate, collision rate etc.Net logo is the tool used which helps in the efficient modeling of scenarios in evacuation

Single Frame Image Super Resolution Using Learned Directionlets

In this paper, a new directionally adaptive, learning based, single image super resolution method using multiple direction wavelet transform, called Directionlets is presented. This method uses directionlets to effectively capture directional features and to extract edge information along different directions of a set of available high resolution images .This information is used as the training set for super resolving a low resolution input image and the Directionlet coefficients at finer scales of its high-resolution image are learned locally from this training set and the inverse Directionlet transform recovers the super-resolved high resolution image. The simulation results showed that the proposed approach outperforms standard interpolation techniques like Cubic spline interpolation as well as standard Wavelet-based learning, both visually and in terms of the mean squared error (mse) values. This method gives good result with aliased images also.

Framework for middleware executed on mobile devices

Die ubiquitäre Datenverarbeitung ist ein attraktives Forschungsgebiet des vergangenen und aktuellen Jahrzehnts. Es handelt von unaufdringlicher Unterstützung von Menschen in ihren alltäglichen Aufgaben durch Rechner. Diese Unterstützung wird durch die Allgegenwärtigkeit von Rechnern ermöglicht die sich spontan zu verteilten Kommunikationsnetzwerken zusammen finden, um Informationen auszutauschen und zu verarbeiten. Umgebende Intelligenz ist eine Anwendung der ubiquitären Datenverarbeitung und eine strategische Forschungsrichtung der Information Society Technology der Europäischen Union. Das Ziel der umbebenden Intelligenz ist komfortableres und sichereres Leben. Verteilte Kommunikationsnetzwerke für die ubiquitäre Datenverarbeitung charakterisieren sich durch Heterogenität der verwendeten Rechner. Diese reichen von Kleinstrechnern, eingebettet in Gegenstände des täglichen Gebrauchs, bis hin zu leistungsfähigen Großrechnern. Die Rechner verbinden sich spontan über kabellose Netzwerktechnologien wie wireless local area networks (WLAN), Bluetooth, oder UMTS. Die Heterogenität verkompliziert die Entwicklung und den Aufbau von verteilten Kommunikationsnetzwerken. Middleware ist eine Software Technologie um Komplexität durch Abstraktion zu einer homogenen Schicht zu reduzieren. Middleware bietet eine einheitliche Sicht auf die durch sie abstrahierten Ressourcen, Funktionalitäten, und Rechner. Verteilte Kommunikationsnetzwerke für die ubiquitäre Datenverarbeitung sind durch die spontane Verbindung von Rechnern gekennzeichnet. Klassische Middleware geht davon aus, dass Rechner dauerhaft miteinander in Kommunikationsbeziehungen stehen. Das Konzept der dienstorienterten Architektur ermöglicht die Entwicklung von Middleware die auch spontane Verbindungen zwischen Rechnern erlaubt. Die Funktionalität von Middleware ist dabei durch Dienste realisiert, die unabhängige Software-Einheiten darstellen. Das Wireless World Research Forum beschreibt Dienste die zukünftige Middleware beinhalten sollte. Diese Dienste werden von einer Ausführungsumgebung beherbergt. Jedoch gibt es noch keine Definitionen wie sich eine solche Ausführungsumgebung ausprägen und welchen Funktionsumfang sie haben muss. Diese Arbeit trägt zu Aspekten der Middleware-Entwicklung für verteilte Kommunikationsnetzwerke in der ubiquitären Datenverarbeitung bei. Der Schwerpunkt liegt auf Middleware und Grundlagentechnologien. Die Beiträge liegen als Konzepte und Ideen für die Entwicklung von Middleware vor. Sie decken die Bereiche Dienstfindung, Dienstaktualisierung, sowie Verträge zwischen Diensten ab. Sie sind in einem Rahmenwerk bereit gestellt, welches auf die Entwicklung von Middleware optimiert ist. Dieses Rahmenwerk, Framework for Applications in Mobile Environments (FAME²) genannt, beinhaltet Richtlinien, eine Definition einer Ausführungsumgebung, sowie Unterstützung für verschiedene Zugriffskontrollmechanismen um Middleware vor unerlaubter Benutzung zu schützen. Das Leistungsspektrum der Ausführungsumgebung von FAME² umfasst: • minimale Ressourcenbenutzung, um auch auf Rechnern mit wenigen Ressourcen, wie z.B. Mobiltelefone und Kleinstrechnern, nutzbar zu sein • Unterstützung für die Anpassung von Middleware durch Änderung der enthaltenen Dienste während die Middleware ausgeführt wird • eine offene Schnittstelle um praktisch jede existierende Lösung für das Finden von Diensten zu verwenden • und eine Möglichkeit der Aktualisierung von Diensten zu deren Laufzeit um damit Fehlerbereinigende, optimierende, und anpassende Wartungsarbeiten an Diensten durchführen zu können Eine begleitende Arbeit ist das Extensible Constraint Framework (ECF), welches Design by Contract (DbC) im Rahmen von FAME² nutzbar macht. DbC ist eine Technologie um Verträge zwischen Diensten zu formulieren und damit die Qualität von Software zu erhöhen. ECF erlaubt das aushandeln sowie die Optimierung von solchen Verträgen.

Evolving Distributed Algorithms with Genetic Programming

Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility. Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions. The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior. In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers. Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.

Why are There so Few Female Computer Scientists?

This report examines why women pursue careers in computer science and related fields far less frequently than men do. In 1990, only 13% of PhDs in computer science went to women, and only 7.8% of computer science professors were female. Causes include the different ways in which boys and girls are raised, the stereotypes of female engineers, subtle biases that females face, problems resulting from working in predominantly male environments, and sexual biases in language. A theme of the report is that women's underrepresentation is not primarily due to direct discrimination but to subconscious behavior that perpetuates the status quo.

Infohabitants: laboratori per la simulació d’ infohabitants com agents recomanadors (SIRA)

L’ objectiu del projecte és la implementació d’un simulador de sistema de recomanació que permeti estudiar algoritmes de dissociació entre agent-recomanador i usuari, combinant-los amb diverses tècniques de recomanació i fent servir infohabitants com Agents Recomanadors i veure com treballen en un sistema recomanador