Computer-Aided Business Model Design

There is a lack of dedicated tools for business model design at a strategic level. However, in today's economic world the need to be able to quickly reinvent a company's business model is essential to stay competitive. This research focused on identifying the functionalities that are necessary in a computer-aided design (CAD) tool for the design of business models in a strategic context. Using design science research methodology a series of techniques and prototypes have been designed and evaluated to offer solutions to the problem. The work is a collection of articles which can be grouped into three parts: First establishing the context of how the Business Model Canvas (BMC) is used to design business models and explore the way in which CAD can contribute to the design activity. The second part extends on this by proposing new technics and tools which support elicitation, evaluation (assessment) and evolution of business models design with CAD. This includes features such as multi-color tagging to easily connect elements, rules to validate coherence of business models and features that are adapted to the correct business model proficiency level of its users. A new way to describe and visualize multiple versions of a business model and thereby help in addressing the business model as a dynamic object was also researched. The third part explores extensions to the business model canvas such as an intermediary model which helps IT alignment by connecting business model and enterprise architecture. And a business model pattern for privacy in a mobile environment, using privacy as a key value proposition. The prototyped techniques and proposition for using CAD tools in business model modeling will allow commercial CAD developers to create tools that are better suited to the needs of practitioners.

Understanding diffusion MR imaging techniques: from scalar diffusion-weighted imaging to diffusion tensor imaging and beyond.

The complex structural organization of the white matter of the brain can be depicted in vivo in great detail with advanced diffusion magnetic resonance (MR) imaging schemes. Diffusion MR imaging techniques are increasingly varied, from the simplest and most commonly used technique-the mapping of apparent diffusion coefficient values-to the more complex, such as diffusion tensor imaging, q-ball imaging, diffusion spectrum imaging, and tractography. The type of structural information obtained differs according to the technique used. To fully understand how diffusion MR imaging works, it is helpful to be familiar with the physical principles of water diffusion in the brain and the conceptual basis of each imaging technique. Knowledge of the technique-specific requirements with regard to hardware and acquisition time, as well as the advantages, limitations, and potential interpretation pitfalls of each technique, is especially useful.

Validation of tissue modelization and classification techniques in T1-weighted MR brain images

We propose a deep study on tissue modelization andclassification Techniques on T1-weighted MR images. Threeapproaches have been taken into account to perform thisvalidation study. Two of them are based on FiniteGaussian Mixture (FGM) model. The first one consists onlyin pure gaussian distributions (FGM-EM). The second oneuses a different model for partial volume (PV) (FGM-GA).The third one is based on a Hidden Markov Random Field(HMRF) model. All methods have been tested on a DigitalBrain Phantom image considered as the ground truth. Noiseand intensity non-uniformities have been added tosimulate real image conditions. Also the effect of ananisotropic filter is considered. Results demonstratethat methods relying in both intensity and spatialinformation are in general more robust to noise andinhomogeneities. However, in some cases there is nosignificant differences between all presented methods.

Coscheduling techniques and monitoring tools for non-dedicated cluster computing

Our efforts are directed towards the understanding of the coscheduling mechanism in a NOW system when a parallel job is executed jointly with local workloads, balancing parallel performance against the local interactive response. Explicit and implicit coscheduling techniques in a PVM-Linux NOW (or cluster) have been implemented. Furthermore, dynamic coscheduling remains an open question when parallel jobs are executed in a non-dedicated Cluster. A basis model for dynamic coscheduling in Cluster systems is presented in this paper. Also, one dynamic coscheduling algorithm for this model is proposed. The applicability of this algorithm has been proved and its performance analyzed by simulation. Finally, a new tool (named Monito) for monitoring the different queues of messages in such an environments is presented. The main aim of implementing this facility is to provide a mean of capturing the bottlenecks and overheads of the communication system in a PVM-Linux cluster.

Microcalcification evaluation in computer assisted diagnosis for digital mammography

In order to develop applications for z;isual interpretation of medical images, the early detection and evaluation of microcalcifications in digital mammograms is verg important since their presence is oftenassociated with a high incidence of breast cancers. Accurate classification into benign and malignant groups would help improve diagnostic sensitivity as well as reduce the number of unnecessa y biopsies. The challenge here is the selection of the useful features to distinguish benign from malignant micro calcifications. Our purpose in this work is to analyse a microcalcification evaluation method based on a set of shapebased features extracted from the digitised mammography. The segmentation of the microcalcificationsis performed using a fixed-tolerance region growing method to extract boundaries of calcifications with manually selected seed pixels. Taking into account that shapes and sizes of clustered microcalcificationshave been associated with a high risk of carcinoma based on digerent subjective measures, such as whether or not the calcifications are irregular, linear, vermiform, branched, rounded or ring like, our efforts were addressed to obtain a feature set related to the shape. The identification of the pammeters concerning the malignant character of the microcalcifications was performed on a set of 146 mammograms with their real diagnosis known in advance from biopsies. This allowed identifying the following shape-based parameters as the relevant ones: Number of clusters, Number of holes, Area, Feret elongation, Roughness, and Elongation. Further experiments on a set of 70 new mammogmms showed that the performance of the classification scheme is close to the mean performance of three expert radiologists, which allows to consider the proposed method for assisting the diagnosis and encourages to continue the investigation in the senseof adding new features not only related to the shape

Computational Techniques for Spectral Image Analysis

Multispectral images are becoming more common in the field of remote sensing, computer vision, and industrial applications. Due to the high accuracy of the multispectral information, it can be used as an important quality factor in the inspection of industrial products. Recently, the development on multispectral imaging systems and the computational analysis on the multispectral images have been the focus of a growing interest. In this thesis, three areas of multispectral image analysis are considered. First, a method for analyzing multispectral textured images was developed. The method is based on a spectral cooccurrence matrix, which contains information of the joint distribution of spectral classes in a spectral domain. Next, a procedure for estimating the illumination spectrum of the color images was developed. Proposed method can be used, for example, in color constancy, color correction, and in the content based search from color image databases. Finally, color filters for the optical pattern recognition were designed, and a prototype of a spectral vision system was constructed. The spectral vision system can be used to acquire a low dimensional component image set for the two dimensional spectral image reconstruction. The data obtained by the spectral vision system is small and therefore convenient for storing and transmitting a spectral image.

Brain-Computer Interfaces, Virtual Reality, and Videogames

Major challenges must be tackled for brain-computer interfaces to mature into an established communications medium for VR applications, which will range from basic neuroscience studies to developing optimal peripherals and mental gamepads and more efficient brain-signal processing techniques.

Measuring higher order optical aberrations of the human eye: techniques and applications

In the present paper we discuss the development of "wave-front", an instrument for determining the lower and higher optical aberrations of the human eye. We also discuss the advantages that such instrumentation and techniques might bring to the ophthalmology professional of the 21st century. By shining a small light spot on the retina of subjects and observing the light that is reflected back from within the eye, we are able to quantitatively determine the amount of lower order aberrations (astigmatism, myopia, hyperopia) and higher order aberrations (coma, spherical aberration, etc.). We have measured artificial eyes with calibrated ametropia ranging from +5 to -5 D, with and without 2 D astigmatism with axis at 45º and 90º. We used a device known as the Hartmann-Shack (HS) sensor, originally developed for measuring the optical aberrations of optical instruments and general refracting surfaces in astronomical telescopes. The HS sensor sends information to a computer software for decomposition of wave-front aberrations into a set of Zernike polynomials. These polynomials have special mathematical properties and are more suitable in this case than the traditional Seidel polynomials. We have demonstrated that this technique is more precise than conventional autorefraction, with a root mean square error (RMSE) of less than 0.1 µm for a 4-mm diameter pupil. In terms of dioptric power this represents an RMSE error of less than 0.04 D and 5º for the axis. This precision is sufficient for customized corneal ablations, among other applications.

Novel Interaction Techniques for Mobile Augmented Reality applications. A Systematic Literature Review

This study reviews the research on interaction techniques and methods that could be applied in mobile augmented reality scenarios. The review is focused on themost recent advances and considers especially the use of head-mounted displays. Inthe review process, we have followed a systematic approach, which makes the reviewtransparent, repeatable, and less prone to human errors than if it was conducted in amore traditional manner. The main research subjects covered in the review are headorientation and gaze-tracking, gestures and body part-tracking, and multimodality– as far as the subjects are related to human-computer interaction. Besides these,also a number of other areas of interest will be discussed.

Étude empirique des commentaires et application des techniques de résumé par extraction pour la redocumentation

La documentation des programmes aide les développeurs à mieux comprendre le code source pendant les tâches de maintenance. Toutefois, la documentation n’est pas toujours disponible ou elle peut être de mauvaise qualité. Le recours à la redocumentation s’avère ainsi nécessaire. Dans ce contexte, nous proposons de faire la redocumentation en générant des commentaires par application de techniques de résumé par extraction. Pour mener à bien cette tâche, nous avons commencé par faire une étude empirique pour étudier les aspects quantitatifs et qualitatifs des commentaires. En particulier, nous nous sommes intéressés à l’étude de la distribution des commentaires par rapport aux différents types d’instructions et à la fréquence de documentation de chaque type. Aussi, nous avons proposé une taxonomie de commentaires pour classer les commentaires selon leur contenu et leur qualité. Suite aux résultats de l’étude empirique, nous avons décidé de résumer les classes Java par extraction des commentaires des méthodes/constructeurs. Nous avons défini plusieurs heuristiques pour déterminer les commentaires les plus pertinents à l’extraction. Ensuite, nous avons appliqué ces heuristiques sur les classes Java de trois projets pour en générer les résumés. Enfin, nous avons comparé les résumés produits (les commentaires produits) à des résumés références (les commentaires originaux) en utilisant la métrique ROUGE.

Deep learning of representations and its application to computer vision

L’objectif de cette thèse par articles est de présenter modestement quelques étapes du parcours qui mènera (on espère) à une solution générale du problème de l’intelligence artificielle. Cette thèse contient quatre articles qui présentent chacun une différente nouvelle méthode d’inférence perceptive en utilisant l’apprentissage machine et, plus particulièrement, les réseaux neuronaux profonds. Chacun de ces documents met en évidence l’utilité de sa méthode proposée dans le cadre d’une tâche de vision par ordinateur. Ces méthodes sont applicables dans un contexte plus général, et dans certains cas elles on tété appliquées ailleurs, mais ceci ne sera pas abordé dans le contexte de cette de thèse. Dans le premier article, nous présentons deux nouveaux algorithmes d’inférence variationelle pour le modèle génératif d’images appelé codage parcimonieux “spike- and-slab” (CPSS). Ces méthodes d’inférence plus rapides nous permettent d’utiliser des modèles CPSS de tailles beaucoup plus grandes qu’auparavant. Nous démontrons qu’elles sont meilleures pour extraire des détecteur de caractéristiques quand très peu d’exemples étiquetés sont disponibles pour l’entraînement. Partant d’un modèle CPSS, nous construisons ensuite une architecture profonde, la machine de Boltzmann profonde partiellement dirigée (MBP-PD). Ce modèle a été conçu de manière à simplifier d’entraînement des machines de Boltzmann profondes qui nécessitent normalement une phase de pré-entraînement glouton pour chaque couche. Ce problème est réglé dans une certaine mesure, mais le coût d’inférence dans le nouveau modèle est relativement trop élevé pour permettre de l’utiliser de manière pratique. Dans le deuxième article, nous revenons au problème d’entraînement joint de machines de Boltzmann profondes. Cette fois, au lieu de changer de famille de modèles, nous introduisons un nouveau critère d’entraînement qui donne naissance aux machines de Boltzmann profondes à multiples prédictions (MBP-MP). Les MBP-MP sont entraînables en une seule étape et ont un meilleur taux de succès en classification que les MBP classiques. Elles s’entraînent aussi avec des méthodes variationelles standard au lieu de nécessiter un classificateur discriminant pour obtenir un bon taux de succès en classification. Par contre, un des inconvénients de tels modèles est leur incapacité de générer deséchantillons, mais ceci n’est pas trop grave puisque la performance de classification des machines de Boltzmann profondes n’est plus une priorité étant donné les dernières avancées en apprentissage supervisé. Malgré cela, les MBP-MP demeurent intéressantes parce qu’elles sont capable d’accomplir certaines tâches que des modèles purement supervisés ne peuvent pas faire, telles que celle de classifier des données incomplètes ou encore celle de combler intelligemment l’information manquante dans ces données incomplètes. Le travail présenté dans cette thèse s’est déroulé au milieu d’une période de transformations importantes du domaine de l’apprentissage à réseaux neuronaux profonds qui a été déclenchée par la découverte de l’algorithme de “dropout” par Geoffrey Hinton. Dropout rend possible un entraînement purement supervisé d’architectures de propagation unidirectionnel sans être exposé au danger de sur- entraînement. Le troisième article présenté dans cette thèse introduit une nouvelle fonction d’activation spécialement con ̧cue pour aller avec l’algorithme de Dropout. Cette fonction d’activation, appelée maxout, permet l’utilisation de aggrégation multi-canal dans un contexte d’apprentissage purement supervisé. Nous démontrons comment plusieurs tâches de reconnaissance d’objets sont mieux accomplies par l’utilisation de maxout. Pour terminer, sont présentons un vrai cas d’utilisation dans l’industrie pour la transcription d’adresses de maisons à plusieurs chiffres. En combinant maxout avec une nouvelle sorte de couche de sortie pour des réseaux neuronaux de convolution, nous démontrons qu’il est possible d’atteindre un taux de succès comparable à celui des humains sur un ensemble de données coriace constitué de photos prises par les voitures de Google. Ce système a été déployé avec succès chez Google pour lire environ cent million d’adresses de maisons.

Fractal based techniques for classification of mammograms and identification of microcalcifications

After skin cancer, breast cancer accounts for the second greatest number of cancer diagnoses in women. Currently the etiologies of breast cancer are unknown, and there is no generally accepted therapy for preventing it. Therefore, the best way to improve the prognosis for breast cancer is early detection and treatment. Computer aided detection systems (CAD) for detecting masses or micro-calcifications in mammograms have already been used and proven to be a potentially powerful tool , so the radiologists are attracted by the effectiveness of clinical application of CAD systems. Fractal geometry is well suited for describing the complex physiological structures that defy the traditional Euclidean geometry, which is based on smooth shapes. The major contribution of this research include the development of • A new fractal feature to accurately classify mammograms into normal and normal (i)With masses (benign or malignant) (ii) with microcalcifications (benign or malignant) • A novel fast fractal modeling method to identify the presence of microcalcifications by fractal modeling of mammograms and then subtracting the modeled image from the original mammogram. The performances of these methods were evaluated using different standard statistical analysis methods. The results obtained indicate that the developed methods are highly beneficial for assisting radiologists in making diagnostic decisions. The mammograms for the study were obtained from the two online databases namely, MIAS (Mammographic Image Analysis Society) and DDSM (Digital Database for Screening Mammography.

Statistical Machine Learning Techniques for the Prediction of Learning Disabilities in School-Age Children

Learning Disability (LD) is a general term that describes specific kinds of learning problems. It is a neurological condition that affects a child's brain and impairs his ability to carry out one or many specific tasks. The learning disabled children are neither slow nor mentally retarded. This disorder can make it problematic for a child to learn as quickly or in the same way as some child who isn't affected by a learning disability. An affected child can have normal or above average intelligence. They may have difficulty paying attention, with reading or letter recognition, or with mathematics. It does not mean that children who have learning disabilities are less intelligent. In fact, many children who have learning disabilities are more intelligent than an average child. Learning disabilities vary from child to child. One child with LD may not have the same kind of learning problems as another child with LD. There is no cure for learning disabilities and they are life-long. However, children with LD can be high achievers and can be taught ways to get around the learning disability. In this research work, data mining using machine learning techniques are used to analyze the symptoms of LD, establish interrelationships between them and evaluate the relative importance of these symptoms. To increase the diagnostic accuracy of learning disability prediction, a knowledge based tool based on statistical machine learning or data mining techniques, with high accuracy,according to the knowledge obtained from the clinical information, is proposed. The basic idea of the developed knowledge based tool is to increase the accuracy of the learning disability assessment and reduce the time used for the same. Different statistical machine learning techniques in data mining are used in the study. Identifying the important parameters of LD prediction using the data mining techniques, identifying the hidden relationship between the symptoms of LD and estimating the relative significance of each symptoms of LD are also the parts of the objectives of this research work. The developed tool has many advantages compared to the traditional methods of using check lists in determination of learning disabilities. For improving the performance of various classifiers, we developed some preprocessing methods for the LD prediction system. A new system based on fuzzy and rough set models are also developed for LD prediction. Here also the importance of pre-processing is studied. A Graphical User Interface (GUI) is designed for developing an integrated knowledge based tool for prediction of LD as well as its degree. The designed tool stores the details of the children in the student database and retrieves their LD report as and when required. The present study undoubtedly proves the effectiveness of the tool developed based on various machine learning techniques. It also identifies the important parameters of LD and accurately predicts the learning disability in school age children. This thesis makes several major contributions in technical, general and social areas. The results are found very beneficial to the parents, teachers and the institutions. They are able to diagnose the child’s problem at an early stage and can go for the proper treatments/counseling at the correct time so as to avoid the academic and social losses.