Incorporating complex cells into neural networks for pattern classification

Dans le domaine des neurosciences computationnelles, l'hypothèse a été émise que le système visuel, depuis la rétine et jusqu'au cortex visuel primaire au moins, ajuste continuellement un modèle probabiliste avec des variables latentes, à son flux de perceptions. Ni le modèle exact, ni la méthode exacte utilisée pour l'ajustement ne sont connus, mais les algorithmes existants qui permettent l'ajustement de tels modèles ont besoin de faire une estimation conditionnelle des variables latentes. Cela nous peut nous aider à comprendre pourquoi le système visuel pourrait ajuster un tel modèle; si le modèle est approprié, ces estimé conditionnels peuvent aussi former une excellente représentation, qui permettent d'analyser le contenu sémantique des images perçues. Le travail présenté ici utilise la performance en classification d'images (discrimination entre des types d'objets communs) comme base pour comparer des modèles du système visuel, et des algorithmes pour ajuster ces modèles (vus comme des densités de probabilité) à des images. Cette thèse (a) montre que des modèles basés sur les cellules complexes de l'aire visuelle V1 généralisent mieux à partir d'exemples d'entraînement étiquetés que les réseaux de neurones conventionnels, dont les unités cachées sont plus semblables aux cellules simples de V1; (b) présente une nouvelle interprétation des modèles du système visuels basés sur des cellules complexes, comme distributions de probabilités, ainsi que de nouveaux algorithmes pour les ajuster à des données; et (c) montre que ces modèles forment des représentations qui sont meilleures pour la classification d'images, après avoir été entraînés comme des modèles de probabilités. Deux innovations techniques additionnelles, qui ont rendu ce travail possible, sont également décrites : un algorithme de recherche aléatoire pour sélectionner des hyper-paramètres, et un compilateur pour des expressions mathématiques matricielles, qui peut optimiser ces expressions pour processeur central (CPU) et graphique (GPU).

L’évolution de la motivation pour les mathématiques au second cycle du secondaire selon la séquence scolaire et le sexe

De nombreuses études sur l’évolution de la motivation pour les mathématiques sont disponibles et il existe également plusieurs recherches qui se sont penchées sur la question de la différence motivationnelle entre les filles et les garçons. Cependant, aucune étude n’a tenu compte de la séquence scolaire des élèves en mathématiques pour comprendre le changement motivationnel vécu pendant le second cycle du secondaire, alors que le classement en différentes séquences est subi par tous au secondaire au Québec. Le but principal de cette étude est de documenter l’évolution de la motivation pour les mathématiques des élèves du second cycle du secondaire en considérant leur séquence de formation scolaire et leur sexe. Les élèves ont été classés dans deux séquences, soit celle des mathématiques de niveau de base (416-514) et une autre de niveau de mathématiques avancé (436-536). Trois mille quatre cent quarante élèves (1864 filles et 1576 garçons) provenant de 30 écoles secondaires publiques francophones de la grande région de Montréal ont répondu à cinq reprises à un questionnaire à items auto-révélés portant sur les variables motivationnelles suivantes : le sentiment de compétence, l’anxiété de performance, la perception de l’utilité des mathématiques, l’intérêt pour les mathématiques et les buts d’accomplissement. Ces élèves étaient inscrits en 3e année du secondaire à la première année de l’étude. Ils ont ensuite été suivis en 4e et 5e année du secondaire. Les résultats des analyses à niveaux multiples indiquent que la motivation scolaire des élèves est généralement en baisse au second cycle du secondaire. Cependant, cette diminution est particulièrement criante pour les élèves inscrits dans les séquences de mathématiques avancées. En somme, les résultats indiquent que les élèves inscrits dans les séquences avancées montrent des diminutions importantes de leur sentiment de compétence au second cycle du secondaire. Leur anxiété de performance est en hausse à la fin du secondaire et l’intérêt et la perception de l’utilité des mathématiques chutent pour l’ensemble des élèves. Les buts de maîtrise-approche sont également en baisse pour tous et les élèves des séquences de base maintiennent généralement des niveaux plus faibles. Une diminution des buts de performance-approche est aussi retrouvée, mais cette dernière n’atteint que les élèves dans les séquences de formation avancées. Des hausses importantes des buts d’évitement du travail sont retrouvées pour les élèves des séquences de mathématiques avancées à la fin du secondaire. Ainsi, les élèves des séquences de mathématiques avancées enregistrent la plus forte baisse motivationnelle pendant le second cycle du secondaire bien qu’ils obtiennent généralement des scores supérieurs aux élèves des séquences de base. Ces derniers maintiennent généralement leur niveau motivationnel. La différence motivationnelle entre les filles et les garçons ne sont pas souvent significatives, malgré le fait que les filles maintiennent généralement un niveau motivationnel inférieur à celui des garçons, et ce, par rapport à leur séquence de formation respective. En somme, les résultats de la présente étude indiquent que la diminution de la motivation au second cycle du secondaire pour les mathématiques touche principalement les élèves des séquences avancées. Il paraît ainsi pertinent de considérer la séquence scolaire dans les études sur l’évolution de la motivation, du moins en mathématiques. Il semble particulièrement important d’ajuster les interventions pédagogiques proposées aux élèves des séquences avancées afin de faciliter leur transition en mathématiques de quatrième secondaire.

Contextualizing discretion : micro-dynamics of Canada’s refugee determination system

À une époque où l'immigration internationale est de plus en plus difficile et sélective, le statut de réfugié constitue un bien public précieux qui permet à certains non-citoyens l'accès et l'appartenance au pays hôte. Reposant sur le jugement discrétionnaire du décideur, le statut de réfugié n’est accordé qu’aux demandeurs qui établissent une crainte bien fondée de persécution en cas de retour dans leur pays d'origine. Au Canada, le plus important tribunal administratif indépendant, la Commission de l'immigration et du statut de réfugié du Canada (CISR), est chargé d’entendre les demandeurs d'asile et de rendre des décisions de statut de réfugié. Cette thèse cherche à comprendre les disparités dans le taux d’octroi du statut de réfugié entre les décideurs de la CISR qui sont politiquement nommés. Au regard du manque de recherches empiriques sur la manière avec laquelle le Canada alloue les possibilités d’entrée et le statut juridique pour les non-citoyens, il était nécessaire de lever le voile sur le fonctionnement de l’administration sur cette question. En explorant la prise de décision relative aux réfugiés à partir d'une perspective de Street Level Bureaucracy Theory (SLBT) et une méthodologie ethnographique qui combine l'observation directe, les entretiens semi-structurés et l'analyse de documents, l'étude a d'abord cherché à comprendre si la variation dans le taux d’octroi du statut était le résultat de différences dans les pratiques et le raisonnement discrétionnaires du décideur et ensuite à retracer les facteurs organisationnels qui alimentent les différences. Dans la lignée des travaux de SLBT qui documentent la façon dont la situation de travail structure la discrétion et l’importance des perceptions individuelles dans la prise de décision, cette étude met en exergue les différences de fond parmi les décideurs concernant les routines de travail, la conception des demandeurs d’asile, et la meilleure façon de mener leur travail. L’analyse montre comment les décideurs appliquent différentes approches lors des audiences, allant de l’interrogatoire rigide à l’entrevue plus flexible. En dépit des contraintes organisationnelles qui pèsent sur les décideurs pour accroître la cohérence et l’efficacité, l’importance de l’évaluation de la crédibilité ainsi que l’invisibilité de l’espace de décision laissent suffisamment de marge pour l’exercice d’un pouvoir discrétionnaire. Même dans les environnements comme les tribunaux administratifs où la surabondance des règles limite fortement la discrétion, la prise de décision est loin d’être synonyme d’adhésion aux principes de neutralité et hiérarchie. La discrétion est plutôt imbriquée dans le contexte de routines d'interaction, de la situation de travail, de l’adhésion aux règles et du droit. Même dans les organisations qui institutionnalisent et uniformisent la formation et communiquent de façon claire leurs demandes aux décideurs, le caractère discrétionnaire de la décision est par la nature difficile, voire impossible, à contrôler et discipliner. Lorsqu'ils sont confrontés à l'ambiguïté des objectifs et aux exigences qui s’opposent à leur pouvoir discrétionnaire, les décideurs réinterprètent la définition de leur travail et banalisent leurs pratiques. Ils formulent une routine de rencontre qui est acceptable sur le plan organisationnel pour évaluer les demandeurs face à eux. Cette thèse montre comment les demandeurs, leurs témoignages et leurs preuves sont traités d’une manière inégale et comment ces traitements se répercutent sur la décision des réfugiés.

Scoliosis curve type classification from 3D trunk image

Adolescent idiopathic scoliosis (AIS) is a deformity of the spine manifested by asymmetry and deformities of the external surface of the trunk. Classification of scoliosis deformities according to curve type is used to plan management of scoliosis patients. Currently, scoliosis curve type is determined based on X-ray exam. However, cumulative exposure to X-rays radiation significantly increases the risk for certain cancer. In this paper, we propose a robust system that can classify the scoliosis curve type from non invasive acquisition of 3D trunk surface of the patients. The 3D image of the trunk is divided into patches and local geometric descriptors characterizing the surface of the back are computed from each patch and forming the features. We perform the reduction of the dimensionality by using Principal Component Analysis and 53 components were retained. In this work a multi-class classifier is built with Least-squares support vector machine (LS-SVM) which is a kernel classifier. For this study, a new kernel was designed in order to achieve a robust classifier in comparison with polynomial and Gaussian kernel. The proposed system was validated using data of 103 patients with different scoliosis curve types diagnosed and classified by an orthopedic surgeon from the X-ray images. The average rate of successful classification was 93.3% with a better rate of prediction for the major thoracic and lumbar/thoracolumbar types.

Realisation of a Target Classifier For Noise Sources in the Ocean

This thesis addresses one of the emerging topics in Sonar Signal Processing.,viz.the implementation of a target classifier for the noise sources in the ocean, as the operator assisted classification turns out to be tedious,laborious and time consuming.In the work reported in this thesis,various judiciously chosen components of the feature vector are used for realizing the newly proposed Hierarchical Target Trimming Model.The performance of the proposed classifier has been compared with the Euclidean distance and Fuzzy K-Nearest Neighbour Model classifiers and is found to have better success rates.The procedures for generating the Target Feature Record or the Feature vector from the spectral,cepstral and bispectral features have also been suggested.The Feature vector ,so generated from the noise data waveform is compared with the feature vectors available in the knowledge base and the most matching pattern is identified,for the purpose of target classification.In an attempt to improve the success rate of the Feature Vector based classifier,the proposed system has been augmented with the HMM based Classifier.Institutions where both the classifier decisions disagree,a contention resolving mechanism built around the DUET algorithm has been suggested.

An evaluation of Primary health care system in Kerala

The thesis entitled An Evaluation of Primary Health Care System in Kerala. The present study is intended to examine the working of primary health care system and its impact on the health status of people. The hypothesis tested in the thesis includes, a. The changes in the health profile require reallocation of resources of primary health care system, b. Rate of utilization depends on the quality of services provided by primary health centers, and c. There is a significant decline in the operational efficiency of the primary health care system. The major elements of primary health care stated in the report of AlmaAta International Conference on Primary Health Care (WHO, 1994)” is studied on the basis of the classification of the elements in to three: Preventive, Promotive, and Curative measures. Preventive measures include Maternal and Child Health Care including family Planning. Provision of water and sanitation is reviewed under promotive measures. Curative measures are studied using the disease profile of the study area. Collection of primary data was done through a sample survey, using pre-tested interview schedule of households of the study area. Multi stage random sampling design was used for selecting the sample. The design of the present study is both descriptive and analytical in nature. As far as the analytical tools are concerned, growth index, percentages, ratios, rates, time series analysis, analysis of variance, chi square test, Z test were used for analyzing the data. Present study revealed that no one in these areas was covered under any type of health insurance. Conclusion states that considering the present changes in the health profile, traditional pattern of resource allocation should be altered to meet the urgent health care needs of the people. Preventive and promotive measures like health education for giving awareness among people to change health habits, diet pattern, life style etc. are to be developed. Proper diagnosis and treatment of the disease at the beginning of the stage itself may help to cure majority of disease. For that, Public health policy must ensure the primary health care as enunciated at Alma- Ata international Conference. At the same time Public health is not to be treated as the sole responsibility of the government. Active community participation is an essential means to attain the goals.

“Improved Feature Extraction and Classification Techniques for Multispectral Brain Magnetic Resonance Images”

Magnetic Resonance Imaging (MRI) is a multi sequence medical imaging technique in which stacks of images are acquired with different tissue contrasts. Simultaneous observation and quantitative analysis of normal brain tissues and small abnormalities from these large numbers of different sequences is a great challenge in clinical applications. Multispectral MRI analysis can simplify the job considerably by combining unlimited number of available co-registered sequences in a single suite. However, poor performance of the multispectral system with conventional image classification and segmentation methods makes it inappropriate for clinical analysis. Recent works in multispectral brain MRI analysis attempted to resolve this issue by improved feature extraction approaches, such as transform based methods, fuzzy approaches, algebraic techniques and so forth. Transform based feature extraction methods like Independent Component Analysis (ICA) and its extensions have been effectively used in recent studies to improve the performance of multispectral brain MRI analysis. However, these global transforms were found to be inefficient and inconsistent in identifying less frequently occurred features like small lesions, from large amount of MR data. The present thesis focuses on the improvement in ICA based feature extraction techniques to enhance the performance of multispectral brain MRI analysis. Methods using spectral clustering and wavelet transforms are proposed to resolve the inefficiency of ICA in identifying small abnormalities, and problems due to ICA over-completeness. Effectiveness of the new methods in brain tissue classification and segmentation is confirmed by a detailed quantitative and qualitative analysis with synthetic and clinical, normal and abnormal, data. In comparison to conventional classification techniques, proposed algorithms provide better performance in classification of normal brain tissues and significant small abnormalities.

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

Process profiling using frequencies of system calls

In this paper we discuss our research in developing general and systematic method for anomaly detection. The key ideas are to represent normal program behaviour using system call frequencies and to incorporate probabilistic techniques for classification to detect anomalies and intrusions. Using experiments on the sendmail system call data, we demonstrate that we can construct concise and accurate classifiers to detect anomalies. We provide an overview of the approach that we have implemented

Anomaly Detection Using System Call Sequence Sets.

This paper discusses our research in developing a generalized and systematic method for anomaly detection. The key ideas are to represent normal program behaviour using system call frequencies and to incorporate probabilistic techniques for classification to detect anomalies and intrusions. Using experiments on the sendmail system call data, we demonstrate that concise and accurate classifiers can be constructed to detect anomalies. An overview of the approach that we have implemented is provided.

Effectiveness Of Feature Detection Operators On The Performance Of Iris Biometric Recognition System

Iris Recognition is a highly efficient biometric identification system with great possibilities for future in the security systems area.Its robustness and unobtrusiveness, as opposed tomost of the currently deployed systems, make it a good candidate to replace most of thesecurity systems around. By making use of the distinctiveness of iris patterns, iris recognition systems obtain a unique mapping for each person. Identification of this person is possible by applying appropriate matching algorithm.In this paper, Daugman’s Rubber Sheet model is employed for irisnormalization and unwrapping, descriptive statistical analysis of different feature detection operators is performed, features extracted is encoded using Haar wavelets and for classification hammingdistance as a matching algorithm is used. The system was tested on the UBIRIS database. The edge detection algorithm, Canny, is found to be the best one to extract most of the iris texture. The success rate of feature detection using canny is 81%, False Accept Rate is 9% and False Reject Rate is 10%.

Underwater Target Localization, Tracking and Classification

Underwater target localization and tracking attracts tremendous research interest due to various impediments to the estimation task caused by the noisy ocean environment. This thesis envisages the implementation of a prototype automated system for underwater target localization, tracking and classification using passive listening buoy systems and target identification techniques. An autonomous three buoy system has been developed and field trials have been conducted successfully. Inaccuracies in the localization results, due to changes in the environmental parameters, measurement errors and theoretical approximations are refined using the Kalman filter approach. Simulation studies have been conducted for the tracking of targets with different scenarios even under maneuvering situations. This system can as well be used for classifying the unknown targets by extracting the features of the noise emanations from the targets.

A System for Offline Recognition of Handwritten Characters in Malayalam Script

In this paper, we propose a handwritten character recognition system for Malayalam language. The feature extraction phase consists of gradient and curvature calculation and dimensionality reduction using Principal Component Analysis. Directional information from the arc tangent of gradient is used as gradient feature. Strength of gradient in curvature direction is used as the curvature feature. The proposed system uses a combination of gradient and curvature feature in reduced dimension as the feature vector. For classification, discriminative power of Support Vector Machine (SVM) is evaluated. The results reveal that SVM with Radial Basis Function (RBF) kernel yield the best performance with 96.28% and 97.96% of accuracy in two different datasets. This is the highest accuracy ever reported on these datasets

Brain Tissue Classification from Multispectral MRI by Wavelet based Principal Component Analysis

In this paper, we propose a multispectral analysis system using wavelet based Principal Component Analysis (PCA), to improve the brain tissue classification from MRI images. Global transforms like PCA often neglects significant small abnormality details, while dealing with a massive amount of multispectral data. In order to resolve this issue, input dataset is expanded by detail coefficients from multisignal wavelet analysis. Then, PCA is applied on the new dataset to perform feature analysis. Finally, an unsupervised classification with Fuzzy C-Means clustering algorithm is used to measure the improvement in reproducibility and accuracy of the results. A detailed comparative analysis of classified tissues with those from conventional PCA is also carried out. Proposed method yielded good improvement in classification of small abnormalities with high sensitivity/accuracy values, 98.9/98.3, for clinical analysis. Experimental results from synthetic and clinical data recommend the new method as a promising approach in brain tissue analysis.

Development of Hierarchical Clustering Techniques for Gridded Data from Mixed Data Sequences

Knowledge discovery in databases is the non-trivial process of identifying valid, novel potentially useful and ultimately understandable patterns from data. The term Data mining refers to the process which does the exploratory analysis on the data and builds some model on the data. To infer patterns from data, data mining involves different approaches like association rule mining, classification techniques or clustering techniques. Among the many data mining techniques, clustering plays a major role, since it helps to group the related data for assessing properties and drawing conclusions. Most of the clustering algorithms act on a dataset with uniform format, since the similarity or dissimilarity between the data points is a significant factor in finding out the clusters. If a dataset consists of mixed attributes, i.e. a combination of numerical and categorical variables, a preferred approach is to convert different formats into a uniform format. The research study explores the various techniques to convert the mixed data sets to a numerical equivalent, so as to make it equipped for applying the statistical and similar algorithms. The results of clustering mixed category data after conversion to numeric data type have been demonstrated using a crime data set. The thesis also proposes an extension to the well known algorithm for handling mixed data types, to deal with data sets having only categorical data. The proposed conversion has been validated on a data set corresponding to breast cancer. Moreover, another issue with the clustering process is the visualization of output. Different geometric techniques like scatter plot, or projection plots are available, but none of the techniques display the result projecting the whole database but rather demonstrate attribute-pair wise analysis