Feature Selection and Classification Using Age Layered Population Structure Genetic Programming

The curse of dimensionality is a major problem in the fields of machine learning, data mining and knowledge discovery. Exhaustive search for the most optimal subset of relevant features from a high dimensional dataset is NP hard. Sub–optimal population based stochastic algorithms such as GP and GA are good choices for searching through large search spaces, and are usually more feasible than exhaustive and deterministic search algorithms. On the other hand, population based stochastic algorithms often suffer from premature convergence on mediocre sub–optimal solutions. The Age Layered Population Structure (ALPS) is a novel metaheuristic for overcoming the problem of premature convergence in evolutionary algorithms, and for improving search in the fitness landscape. The ALPS paradigm uses an age–measure to control breeding and competition between individuals in the population. This thesis uses a modification of the ALPS GP strategy called Feature Selection ALPS (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS uses a novel frequency count system to rank features in the GP population based on evolved feature frequencies. The ranked features are translated into probabilities, which are used to control evolutionary processes such as terminal–symbol selection for the construction of GP trees/sub-trees. The FSALPS metaheuristic continuously refines the feature subset selection process whiles simultaneously evolving efficient classifiers through a non–converging evolutionary process that favors selection of features with high discrimination of class labels. We investigated and compared the performance of canonical GP, ALPS and FSALPS on high–dimensional benchmark classification datasets, including a hyperspectral image. Using Tukey’s HSD ANOVA test at a 95% confidence interval, ALPS and FSALPS dominated canonical GP in evolving smaller but efficient trees with less bloat expressions. FSALPS significantly outperformed canonical GP and ALPS and some reported feature selection strategies in related literature on dimensionality reduction.

Feature Selection and Classification Using Age Layered Population Structure Genetic Programming

The curse of dimensionality is a major problem in the fields of machine learning, data mining and knowledge discovery. Exhaustive search for the most optimal subset of relevant features from a high dimensional dataset is NP hard. Sub–optimal population based stochastic algorithms such as GP and GA are good choices for searching through large search spaces, and are usually more feasible than exhaustive and determinis- tic search algorithms. On the other hand, population based stochastic algorithms often suffer from premature convergence on mediocre sub–optimal solutions. The Age Layered Population Structure (ALPS) is a novel meta–heuristic for overcoming the problem of premature convergence in evolutionary algorithms, and for improving search in the fitness landscape. The ALPS paradigm uses an age–measure to control breeding and competition between individuals in the population. This thesis uses a modification of the ALPS GP strategy called Feature Selection ALPS (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS uses a novel frequency count system to rank features in the GP population based on evolved feature frequencies. The ranked features are translated into probabilities, which are used to control evolutionary processes such as terminal–symbol selection for the construction of GP trees/sub-trees. The FSALPS meta–heuristic continuously refines the feature subset selection process whiles simultaneously evolving efficient classifiers through a non–converging evolutionary process that favors selection of features with high discrimination of class labels. We investigated and compared the performance of canonical GP, ALPS and FSALPS on high–dimensional benchmark classification datasets, including a hyperspectral image. Using Tukey’s HSD ANOVA test at a 95% confidence interval, ALPS and FSALPS dominated canonical GP in evolving smaller but efficient trees with less bloat expressions. FSALPS significantly outperformed canonical GP and ALPS and some reported feature selection strategies in related literature on dimensionality reduction.

The antecedents to participation in learning activities among support staff at a college in Ontario

Les tendances de la participation à la formation des adultes au Canada n’ont pas évolué depuis des décennies, malgré les nouvelles influences économiques qui ont stimulé l’augmentation et la diversification permanente de la formation des employés et malgré les initiatives plus nombreuses en faveur de l’apprentissage des employés en milieu de travail. Il est donc nécessaire de ne plus se contenter d’étudier les prédicteurs de la formation déjà connus dans les profils des employés et des employeurs. Il est, en revanche, indispensable d’étudier les antécédents de la participation des employés à la formation, y compris les aspects et les étapes du processus qui la précède. Cette étude porte sur les antécédents de la participation des employés aux formations dans un important collège communautaire urbain en Ontario. Afin de préparer le recueil des données, un cadre théorique a été élaboré à partir du concept d’expression de la demande. Ce cadre implique l’existence d’un processus qui comporte plusieurs étapes, au cours desquelles plusieurs intervenants interagissent et dont la formation est susceptible d’être le résultat. Les résultats de l’enquête sur le profil d’apprentissage ont permis de conclure que le comportement des employés et de l’employeur est conforme aux modèles de prédicteurs existants et que les taux et les types de participation étaient similaires aux tendances nationales et internationales. L’analyse des entrevues d’un groupe d’employés atypiques, de leurs superviseurs, ainsi que de représentants du collège et du syndicat, a révélé d’importants thèmes clés : l’expression de la demande n’est pas structurée et elle est communiquée par plusieurs canaux, en excluant parfois les superviseurs. De plus, la place de l’auto évaluation est importante, ainsi que la phase de prise de décision. Ces thèmes ont souligné l’interaction de plusieurs intervenants dans le processus d’expression de la demande d’apprentissage et pendant la prise de décision. L’examen des attentes de chacun de ces intervenants au cours de ce processus nous a permis de découvrir un désir tacite chez les superviseurs et les employés, à savoir que la conversation soit à l’initiative de « l’autre ». Ces thèmes clés ont été ensuite abordés dans une discussion qui a révélé une discordance entre le profil de l’employeur et les profils des employés. Celle-ci se prête à la correction par l’employeur de son profil institutionnel pour l’harmoniser avec le profil dispositionnel des employés et optimiser ainsi vraisemblablement son offre de formation. Ils doivent, pour cela, appliquer un processus plus systématique et plus structuré, doté de meilleurs outils. La discussion a porté finalement sur les effets des motivations économiques sur la participation des employés et a permis de conclure que, bien que les employés ne semblent pas se méfier de l’offre de formation de l’employeur et que celle ci ne semble pas non plus les décourager, des questions de pouvoir sont bel et bien en jeu. Elles se sont principalement manifestées pendant le processus de prise de décision et, à cet égard, les superviseurs comme les employés reconnaissent qu’un processus plus structuré serait bénéfique, puisqu’il atténuerait les problèmes d’asymétrie et d’ambiguïté. Les constatations de cette étude sont pertinentes pour le secteur de la formation des adultes et de la formation en milieu de travail et, plus particulièrement, pour la méthodologie de recherche. Nous avons constaté l’avantage d’une méthodologie à deux volets, à l’écoute de l’employeur et des employés, afin de mieux comprendre la relation entre l’offre de formation et la participation à la formation. La définition des antécédents de la participation sous la forme d’un processus dans lequel plusieurs intervenants remplissent plusieurs rôles a permis de créer un modèle plus détaillé qui servira à la recherche future. Ce dernier a démontré qu’il est indispensable de reconnaître que la prise de décision constitue une étape à part entière, située entre l’expression de la demande et la participation à la formation. Ces constatations ont également révélé qu’il est véritablement indispensable que le secteur de la formation des adultes continue à traiter les questions reliées à la reconnaissance de la formation informelle. Ces conclusions et la discussion sur les constatations clés nous ont inspiré des recommandations à appliquer pour modifier les retombées du processus précédant la participation des employés à la formation. La majorité de ces recommandations ont trait à l’infrastructure de ce processus et ciblent donc principalement l’employeur. Certaines recommandations sont cependant destinées aux syndicats, aux superviseurs et aux employés qui peuvent aider l’employeur à remplir son rôle et favoriser la participation efficace de tous à ce processus. Les recommandations qui précédent impliquent que ce sont les antécédents de la formation qui gagneraient à être plus structurés et non la formation elle même. La structuration de l’infrastructure de l’apprentissage présente cependant des risques à elle seule. En liaison avec ce phénomène, une étude spécifique des effets de la nature, de la qualité et de l’asymétrie de la relation superviseur employé sur la participation des employés à la formation serait bénéfique. Mots clés : formation en entreprise, formation professionnelle continue, antécédents à la participation, employés de soutien

Bodies, stories, cities : learning to read and write (in) Montréal with Gail Scott

Cette lecture, tant critique, comparative, et théorique que pédagogique, s’ancre dans le constat, premièrement, qu’il advient aux étudiantEs en littérature de se (re)poser la question des coûts et complicités qu’apprendre à lire et à écrire présuppose aujourd’hui; deuxièmement, que nos pratiques littéraires se trament au sein de lieux empreints de différences, que l’on peut nommer, selon le contexte, métaphore, récit, ville; et, troisièmement, que les efforts et investissements requis sont tout autant couteux et interminable qu’un plaisir et une nécessité politique. Ces conclusions tendent vers l’abstrait et le théorique, mais le langage en lequel elles sont articulées, langage corporel et urbain, de la dépendance et de la violence, cherche d’autant plus une qualité matérielle et concrète. Or, l’introduction propose un survol des lectures et comparaisons de Heroine de Gail Scott qui centre ce projet; identifie les contextes institutionnels, historiques, et personnels qui risquent, ensuite, de décentrer celui-ci. Le premier chapitre permet de cerner le matérialisme littéraire qui me sert de méthode par laquelle la littérature, à la fois, sollicite et offre une réponse à ces interrogations théoriques. Inspirée de l’œuvre de Gail Scott et Réjean Ducharme, premièrement, et de Walter Benjamin, Elisabeth Grosz, et Pierre Macherey ensuite, ‘matérialisme’ fait référence à cette collection de figures de pratiques littéraires et urbaines qui proviennent, par exemple, de Georges Perec, Michel DeCerteau, Barbara Johnson, et Patricia Smart, et qui invitent ensuite une réflexions sur les relations entre corporalité et narrativité, entre la nécessité et la contingence du littéraire. De plus, une collection de figures d’un Montréal littéraire et d’une cité pédagogique, acquis des œuvres de Zygmunt Bauman, Partricia Godbout, et Lewis Mumford, constitue en effet un vocabulaire nous permettant de mieux découvrir (et donc enseigner) ce que lire et apprendre requiert. Le deuxième chapitre propose une lecture comparée de Heroine et des romans des auteures québécoises Anne Dandurand, Marie Gagnon, et Tess Fragoulis, dans le contexte, premièrement, les débats entourant l’institutionnalisation de la littérature (anglo)Québécoise et, deuxièmement, des questions pédagogiques et politiques plus larges et plus urgentes que nous pose, encore aujourd’hui, cette violence récurrente qui s’acharna, par exemple, sur la Polytechnique en 1989. Or, cette intersection de la violence meurtrière, la pratique littéraire, et la pédagogie qui en résulte se pose et s’articule, encore, par le biais d’une collection de figures de styles. En fait, à travers le roman de Scott et de l’œuvre critique qui en fait la lecture, une série de craques invite à reconnaître Heroine comme étant, ce que j’appelle, un récit de dépendance, au sein duquel se concrétise une temporalité récursive et une logique d’introjection nous permettant de mieux comprendre la violence et, par conséquent, le pouvoir d’une pratique littéraire sur laquelle, ensuite, j’appuie ma pédagogie en devenir. Jetant, finalement, un regard rétrospectif sur l’oeuvre dans son entier, la conclusion de ce projet se tourne aussi vers l’avant, c’est-à-dire, vers ce que mes lectures dites matérialistes de la littérature canadienne et québécoise contribuent à mon enseignement de la langue anglaise en Corée du Sud. C’est dans ce contexte que les propos de Jacques Rancière occasionnent un dernier questionnement quant à l’historique des débats et des structures pédagogiques en Corée, d’une part, et, de l’autre, les conclusions que cette lecture de la fiction théorique de Gail Scott nous livre.

Quantum wire with periodic serial structure

Electron wave motion in a quantum wire with periodic structure is treated by direct solution of the Schrödinger equation as a mode-matching problem. Our method is particularly useful for a wire consisting of several distinct units, where the total transfer matrix for wave propagation is just the product of those for its basic units. It is generally applicable to any linearly connected serial device, and it can be implemented on a small computer. The one-dimensional mesoscopic crystal recently considered by Ulloa, Castaño, and Kirczenow [Phys. Rev. B 41, 12 350 (1990)] is discussed with our method, and is shown to be a strictly one-dimensional problem. Electron motion in the multiple-stub T-shaped potential well considered by Sols et al. [J. Appl. Phys. 66, 3892 (1989)] is also treated. A structure combining features of both of these is investigated

Diurnal Structure of Monsoon Boundary Layer

The characteristics of the monsoon boundary layer are imperative to understand in the perception of the tropical regions. The southwest monsoon is associated with a strong wind in the lower troposphere near 1.5 km and is referred to as Low Level Jet stream (LLJ). The boundary layer structure associated with the LLJ during monsoon can be studied using L-band Ultra High Frequency (UHF) radar. This L-band wind profiler-commonly referred as lower atmospheric wind profiler (LAWP), was installed at NARL, Gadanki. Zonal, meridional and vertical wind components are used to understand the diurnal variation of the wind in the Atmospheric Boundary Layer (ABL) and associated features. From the analysis during non rainy days of the southwest monsoon, it is found that the LLJ has maximum strength during the early morning hours at lower level and the height increases as day progresses. The vertical wind shows the transfer of momentum from the LLJ towards the surface, indicating the sinking motion during the daytime. Vertical gradient of the wind shear shows the intensity of clear air turbulence is moderate and no severe clear air turbulence is noticed during the monsoon period

Femtosecond time-resolved wave packet motion in molecular multiphoton ionization and fragmentation

The dynamics of molecular multiphoton ionization and fragmentation of a diatomic molecule (Na_2) have been studied in molecular beam experiments. Femtosecond laser pulses from an amplified colliding-pulse mode-locked (CPM) ring dye laser are employed to induce and probe the molecular transitions. The final continuum states are analyzed by photoelectron spectroscopy, by ion mass spectrometry and by measuring the kinetic energy of the formed ionic fragments. Pump-probe spectra employing 70-fs laser pulses have been measured to study the time dependence of molecular multiphoton ionization and fragmentation. The oscillatory structure of the transient spectra showing the dynamics on the femtosecond time scale can best be understood in terms of the motion of wave packets in bound molecular potentials. The transient Na_2^+ ionization and the transient Na^+ fragmentation spectra show that contributions from direct photoionization of a singly excited electronic state and from excitation and autoionization of a bound doubly excited molecular state determine the time evolution of molecular multiphoton ionization.

Identification of Problem-based learning components and their effects on graduates' competencies

This study investigated the relationship between higher education and the requirement of the world of work with an emphasis on the effect of problem-based learning (PBL) on graduates' competencies. The implementation of full PBL method is costly (Albanese & Mitchell, 1993; Berkson, 1993; Finucane, Shannon, & McGrath, 2009). However, the implementation of PBL in a less than curriculum-wide mode is more achievable in a broader context (Albanese, 2000). This means higher education institutions implement only a few PBL components in the curriculum. Or a teacher implements a few PBL components at the courses level. For this kind of implementation there is a need to identify PBL components and their effects on particular educational outputs (Hmelo-Silver, 2004; Newman, 2003). So far, however there has been little research about this topic. The main aims of this study were: (1) to identify each of PBL components which were manifested in the development of a valid and reliable PBL implementation questionnaire and (2) to determine the effect of each identified PBL component to specific graduates' competencies. The analysis was based on quantitative data collected in the survey of medicine graduates of Gadjah Mada University, Indonesia. A total of 225 graduates responded to the survey. The result of confirmatory factor analysis (CFA) showed that all individual constructs of PBL and graduates' competencies had acceptable GOFs (Goodness-of-fit). Additionally, the values of the factor loadings (standardize loading estimates), the AVEs (average variance extracted), CRs (construct reliability), and ASVs (average shared squared variance) showed the proof of convergent and discriminant validity. All values indicated valid and reliable measurements. The investigation of the effects of PBL showed that each PBL component had specific effects on graduates' competencies. Interpersonal competencies were affected by Student-centred learning (β = .137; p < .05) and Small group components (β = .078; p < .05). Problem as stimulus affected Leadership (β = .182; p < .01). Real-world problems affected Personal and organisational competencies (β = .140; p < .01) and Interpersonal competencies (β = .114; p < .05). Teacher as facilitator affected Leadership (β = 142; p < .05). Self-directed learning affected Field-related competencies (β = .080; p < .05). These results can help higher education institution and educator to have informed choice about the implementation of PBL components. With this information higher education institutions and educators could fulfil their educational goals and in the same time meet their limited resources. This study seeks to improve prior studies' research method in four major ways: (1) by indentifying PBL components based on theory and empirical data; (2) by using latent variables in the structural equation modelling instead of using a variable as a proxy of a construct; (3) by using CFA to validate the latent structure of the measurement, thus providing better evidence of validity; and (4) by using graduate survey data which is suitable for analysing PBL effects in the frame work of the relationship between higher education and the world of work.

Three-Dimensional Motion Estimation Using Shading Information in Multiple Frames

A new formulation for recovering the structure and motion parameters of a moving patch using both motion and shading information is presented. It is based on a new differential constraint equation (FICE) that links the spatiotemporal gradients of irradiance to the motion and structure parameters and the temporal variations of the surface shading. The FICE separates the contribution to the irradiance spatiotemporal gradients of the gradients due to texture from those due to shading and allows the FICE to be used for textured and textureless surface. The new approach, combining motion and shading information, leads directly to two different contributions: it can compensate for the effects of shading variations in recovering the shape and motion; and it can exploit the shading/illumination effects to recover motion and shape when they cannot be recovered without it. The FICE formulation is also extended to multiple frames.

A Distributed Model for Mobile Robot Environment-Learning and Navigation

A distributed method for mobile robot navigation, spatial learning, and path planning is presented. It is implemented on a sonar-based physical robot, Toto, consisting of three competence layers: 1) Low-level navigation: a collection of reflex-like rules resulting in emergent boundary-tracing. 2) Landmark detection: dynamically extracts landmarks from the robot's motion. 3) Map learning: constructs a distributed map of landmarks. The parallel implementation allows for localization in constant time. Spreading of activation computes both topological and physical shortest paths in linear time. The main issues addressed are: distributed, procedural, and qualitative representation and computation, emergent behaviors, dynamic landmarks, minimized communication.

Geometric Structure of the Adaptive Controller of the Human Arm

The objects with which the hand interacts with may significantly change the dynamics of the arm. How does the brain adapt control of arm movements to this new dynamic? We show that adaptation is via composition of a model of the task's dynamics. By exploring generalization capabilities of this adaptation we infer some of the properties of the computational elements with which the brain formed this model: the elements have broad receptive fields and encode the learned dynamics as a map structured in an intrinsic coordinate system closely related to the geometry of the skeletomusculature. The low--level nature of these elements suggests that they may represent asset of primitives with which a movement is represented in the CNS.

Learning-Based Approach to Estimation of Morphable Model Parameters

We describe the key role played by partial evaluation in the Supercomputing Toolkit, a parallel computing system for scientific applications that effectively exploits the vast amount of parallelism exposed by partial evaluation. The Supercomputing Toolkit parallel processor and its associated partial evaluation-based compiler have been used extensively by scientists at MIT, and have made possible recent results in astrophysics showing that the motion of the planets in our solar system is chaotically unstable.

Global Depth Perception from Familiar Scene Structure

In the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured. The interpretation of shading, edges and junctions may provide a 3D model of the scene but it will not inform about the actual "size" of the space. One possible source of information for absolute depth estimation is the image size of known objects. However, this is computationally complex due to the difficulty of the object recognition process. Here we propose a source of information for absolute depth estimation that does not rely on specific objects: we introduce a procedure for absolute depth estimation based on the recognition of the whole scene. The shape of the space of the scene and the structures present in the scene are strongly related to the scale of observation. We demonstrate that, by recognizing the properties of the structures present in the image, we can infer the scale of the scene, and therefore its absolute mean depth. We illustrate the interest in computing the mean depth of the scene with application to scene recognition and object detection.

Designing context-aware adaptive units of learning based on IMS-LD standard

Learning contents adaptation has been a subject of interest in the research area of the adaptive hypermedia systems. Defining which variables and which standards can be considered to model adaptive content delivery processes is one of the main challenges in pedagogical design over e-learning environments. In this paper some specifications, architectures and technologies that can be used in contents adaptation processes considering characteristics of the context are described and a proposal to integrate some of these characteristics in the design of units of learning using adaptation conditions in a structure of IMS-Learning Design (IMS-LD) is presented. The key contribution of this work is the generation of instructional designs considering the context, which can be used in Learning Management Systems (LMSs) and diverse mobile devices

Recovering Euclidean deformable models from stereo-motion

In this paper we present a novel structure from motion (SfM) approach able to infer 3D deformable models from uncalibrated stereo images. Using a stereo setup dramatically improves the 3D model estimation when the observed 3D shape is mostly deforming without undergoing strong rigid motion. Our approach first calibrates the stereo system automatically and then computes a single metric rigid structure for each frame. Afterwards, these 3D shapes are aligned to a reference view using a RANSAC method in order to compute the mean shape of the object and to select the subset of points on the object which have remained rigid throughout the sequence without deforming. The selected rigid points are then used to compute frame-wise shape registration and to extract the motion parameters robustly from frame to frame. Finally, all this information is used in a global optimization stage with bundle adjustment which allows to refine the frame-wise initial solution and also to recover the non-rigid 3D model. We show results on synthetic and real data that prove the performance of the proposed method even when there is no rigid motion in the original sequence