Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Concurrent : Easy to use Python computing environment

Concurrent aims to be a different type of task distribution system compared to what MPI like system do. It adds a simple but powerful application abstraction layer to distribute the logic of an entire application onto a swarm of clusters holding similarities with volunteer computing systems. Traditional task distributed systems will just perform simple tasks onto the distributed system and wait for results. Concurrent goes one step further by letting the tasks and the application decide what to do. The programming paradigm is then totally async without any waits for results and based on notifications once a computation has been performed.

Disseny i implementació d'un clúster high performance computing

Clúster format per una màquina principal HEAD Node més 19 nodes de càlcul de la gama SGI13 Altix14 XE Servers and Clusters, unides en una topologia de màster subordinat, amb un total de 40 processadors Dual Core i aproximadament 160Gb de RAM.

Plataforma "Cloud Computing" per la comunicació entre pares i professors (Saas)

El projecte que es presenta a continuació és el resultat fruit de la detecció d’un problema de comunicació entre les escoles (sobretot de primària) i el pares dels alumnes que hi cursen els estudis, i la necessitat de trobar-hi una solució. Amb aquesta premissa, i tenint en compte que la tecnologia cada vegada ens ofereix més i millors eines per gestionar les nostres necessitats, es porta a terme la construcció d’un servei al núvol (Saas) capaç de cobrir aquestes necessitats i de fer-ho de la manera més senzilla i eficient possible. La plataforma Aula és un servei on tant professors com pares dels alumnes poden comunicar-se i consultar la informació referent als seus alumnes (en el cas del professors), i dels seus fills (en el cas dels pares/tutors). La solució adoptada ha de ser capaç de funcionar sobre qualsevol aparell (ordinador, tablet o mòbil) i en qualsevol lloc on hi hagi connexió a Internet. No s’ha de realitzar cap tipus d’instal·lació un cop el sistema estigui funcionant, i s’hi podran registrar tants centres com siguin necessaris, així com professionals i pares dels alumnes. També s’ha valorat el manteniment mínim del sistema i la seva escalabilitat, per poder fer front a diferents volums de dades. Així doncs, el projecte Aula es presenta com una solució per gestionar el dia a dia dels professors i alumnes, però que no pretén ser substitut de cap altre sistema de gestió que pugui tenir el centre.

Extension and evaluation of JXTA protocols for supporting reliable P2P distributed computing

Peer-reviewed

Computing the diameter of Coxeter groups

This thesis addresses the problem of computing the minimal and maximal diameter of the Cayley graph of Coxeter groups. We first present and assert relevant parts of polytope theory and related Coxeter theory. After this, a method of contracting the orthogonal projections of a polytope from Rd onto R2 and R3, d ¸ 3 is presented. This method is the Equality Set Projection algorithm that requires a constant number of linearprogramming problems per facet of the projection in the absence of degeneracy. The ESP algorithm allows us to compute also projected geometric diameters of high-dimensional polytopes. A representation set of projected polytopes is presented to illustrate the methods adopted in this thesis.

Computing the persistent homology of range images with alpha shapes

Laser scanning is becoming an increasingly popular method for measuring 3D objects in industrial design. Laser scanners produce a cloud of 3D points. For CAD software to be able to use such data, however, this point cloud needs to be turned into a vector format. A popular way to do this is to triangulate the assumed surface of the point cloud using alpha shapes. Alpha shapes start from the convex hull of the point cloud and gradually refine it towards the true surface of the object. Often it is nontrivial to decide when to stop this refinement. One criterion for this is to do so when the homology of the object stops changing. This is known as the persistent homology of the object. The goal of this thesis is to develop a way to compute the homology of a given point cloud when processed with alpha shapes, and to infer from it when the persistent homology has been achieved. Practically, the computation of such a characteristic of the target might be applied to power line tower span analysis.

A hybrid feature selection approach for the early diagnosis of Alzheimer's disease

Objective. Recently, significant advances have been made in the early diagnosis of Alzheimer’s disease from EEG. However, choosing suitable measures is a challenging task. Among other measures, frequency Relative Power and loss of complexity have been used with promising results. In the present study we investigate the early diagnosis of AD using synchrony measures and frequency Relative Power on EEG signals, examining the changes found in different frequency ranges. Approach. We first explore the use of a single feature for computing the classification rate, looking for the best frequency range. Then, we present a multiple feature classification system that outperforms all previous results using a feature selection strategy. These two approaches are tested in two different databases, one containing MCI and healthy subjects (patients age: 71.9 ± 10.2, healthy subjects age: 71.7 ± 8.3), and the other containing Mild AD and healthy subjects (patients age: 77.6 ± 10.0; healthy subjects age: 69.4± 11.5). Main Results. Using a single feature to compute classification rates we achieve a performance of 78.33% for the MCI data set and of 97.56 % for Mild AD. Results are clearly improved using the multiple feature classification, where a classification rate of 95% is found for the MCI data set using 11 features, and 100% for the Mild AD data set using 4 features. Significance. The new features selection method described in this work may be a reliable tool that could help to design a realistic system that does not require prior knowledge of a patient's status. With that aim, we explore the standardization of features for MCI and Mild AD data sets with promising results.

Programa de gestió per la Pastisseria Mas

En els últims anys, el món de la informàtica ha evolucionat d'una manera inimaginable, tan a nivell de Hardware com de Software. Aquesta evolució ha donat lloc a la creació de moltes empreses dedicades a la programació, on una de les seves principals feines ha estat la realització de programes de gestió d'empreses. Moltes vegades, però, els programes estàndards no poden satisfer el total de les necessitats dels clients, sinó algunes d’aquestes i realitzar un programa personalitzat té un cost elevat. En el cas de la Pastisseria Mas de Navàs, una empresa familiar, per poder realitzar les tasques administratives utilitzen fulls de càlcul, concretament el Microsoft Excel, que permet portar els comptes d'una manera més o menys senzilla, ja que només són necessàries unes nocions bàsiques d'informàtica. El mateix passa amb les dades dels proveïdors, que les guarden en una Base de Dades del tipus Microsoft Access. Una altra de les mancances és el tema dels encàrrecs que es fa de manera manual. Per tant, l’objectiu d’aquest projecte, és realitzar un programa que els hi faciliti la seva activitat. Aquest programa els permetrà gestionar les dades que utilitzen, com la informació sobre els clients, personal, comandes... També s’ha desenvolupat una web que permet obtenir informació sobre les comandes que s’han realitzat. Aquesta aplicació està dissenyada per funcionar en l’entorn Windows XP i s’ha desenvolupat amb el compilador de CodeGear Rad Studio, concretament el C++ Builder 2009. A nivell de base de dades, he utilitzat MySQL i en el cas de la pàgina web, PHP i lamateixa base de dades. L’anàlisi i el disseny ha estat fet en UML.

Eficiència energètica aplicada a les instal·lacions de la Universitat de Vic

En termes generals, es pot definir l’Eficiència Energètica com la reducció del consum d’energia mantenint els mateixos serveis energètics, sense disminuir el nostre confort i qualitat de vida, protegint el medi ambient, assegurant el proveïment i fomentant un comportament Sostenible al seu ús. L’objectiu principal d’aquest treball, és reduir el consum d’energia i terme de potència contractat a la Universitat de Vic, aplicant un programa d’estalvi amb mesures correctores en el funcionament de les seves instal·lacions o espais. Per tal de poder arribar a aquest objectiu marcat, prèviament s’ha realitzat un estudi acurat, obtenint tota la informació necessària per poder aplicar les mesures correctores a la bossa més important de consum. Un cop trobada, dur a terme l’estudi de la viabilitat de la inversió de les mesures correctores més eficients, optimitzant els recursos destinats. L’espai on s’ha dut a terme l’estudi, ha estat a l’edifici F del Campus Miramarges, seguint les indicacions d’Arnau Bardolet (Cap de Manteniment de la UVIC). Aquest edifici consta d’un entresol, baixos i quatre plantes. L’equip de mesura que s’ha fet servir per realitzar l’estudi, és de la marca Circutor sèrie AR5-L, aquests equips són programables que mesuren, calculen i emmagatzemen en memòria els principals paràmetres elèctrics en xarxes trifàsiques. Els projectes futurs complementaris que es podrien realitzar a part d’aquest són: instal·lar sensors, instal·lar mòduls convertidors TCP/IP, aprofitar la xarxa intranet i crear un escada amb un sinòptic de control i gestió des d’un punt de treball. Aquest aplicatiu permet visualitzar en una pantalla d’un PC tots els estats dels elements controlats mitjançant un sinòptic (encendre/parar manualment l’enllumenat i endolls de les aules, estat d’enllumenat i endolls de les aules, consums instantanis/acumulats energètics, estat dels passadissos entre altres) i explotar les dades recollides a la base de dades. Cada espai tindria la seva lògica de funcionament automàtic específic. Entre les conclusions més rellevants obtingudes en aquest treball s’observa: · Que és pot reduir la potència contractada a la factura a l’estar per sota de la realment consumida. · Que no hi ha penalitzacions a la factura per consum de reactiva, ja que el compensador funciona correctament. · Que es pot reduir l’horari de l’inici del consum d’energia, ja que no correspon a l’activitat docent. · Els valors de la tensió i freqüència estan dintre de la normalitat. · Els harmònics estan al llindar màxim. Analitzant aquestes conclusions, voldria destacar les mesures correctores més importants que es poden dur a terme: canvi tecnològic a LED, temporitzar automàticament l’encesa i apagada dels fluorescents i equips informàtics de les aules “seguint calendari docent”, instal·lar sensors de moviment amb detecció lumínica als passadissos. Totes les conclusions extretes d’aquest treball, es poden aplicar a tots els edificis de la facultat, prèviament realitzant l’estudi individual de cadascuna, seguint els mateixos criteris per tal d’optimitzar la inversió.

Bag-of-Features Approach to Unsupervised Visual Object Categorisation

The large and growing number of digital images is making manual image search laborious. Only a fraction of the images contain metadata that can be used to search for a particular type of image. Thus, the main research question of this thesis is whether it is possible to learn visual object categories directly from images. Computers process images as long lists of pixels that do not have a clear connection to high-level semantics which could be used in the image search. There are various methods introduced in the literature to extract low-level image features and also approaches to connect these low-level features with high-level semantics. One of these approaches is called Bag-of-Features which is studied in the thesis. In the Bag-of-Features approach, the images are described using a visual codebook. The codebook is built from the descriptions of the image patches using clustering. The images are described by matching descriptions of image patches with the visual codebook and computing the number of matches for each code. In this thesis, unsupervised visual object categorisation using the Bag-of-Features approach is studied. The goal is to find groups of similar images, e.g., images that contain an object from the same category. The standard Bag-of-Features approach is improved by using spatial information and visual saliency. It was found that the performance of the visual object categorisation can be improved by using spatial information of local features to verify the matches. However, this process is computationally heavy, and thus, the number of images must be limited in the spatial matching, for example, by using the Bag-of-Features method as in this study. Different approaches for saliency detection are studied and a new method based on the Hessian-Affine local feature detector is proposed. The new method achieves comparable results with current state-of-the-art. The visual object categorisation performance was improved by using foreground segmentation based on saliency information, especially when the background could be considered as clutter.

SaaS and Public Cloud from Custom Application Provider’s Perspective

The main objective of this master’s thesis is to provide a comprehensive view to cloud computing and SaaS, and analyze how well CADM, a unit of Capgemini Finland Ltd., would fit to the cloud-based SaaS business. Another objective for this thesis is to investigate how public clouds would fit for CADM as a delivery model, if they would provide SaaS applications to their customers. This master’s thesis is executed by investigating characteristics of cloud computing and SaaS especially from application provider point of view. This is done by exploring what kinds of researches and analysis there have been done regarding these two phenomena during past few years. Then CADM’s current business model and operations are analyzed from SaaS’s and public cloud’s perspective. This analyzing part is conducted by using SWOT analysis which is widely used analytical tool when observing company’s strategic position and when figuring out possibilities how to improve company’s operations. The conducted analysis and observations reveals that CADM should pursue SaaS business as it could provide remarkable advantages and strengthen their position in current markets. However, pure SaaS model would not be the optimal solution for CADM because they do not have own product which could be transformed to SaaS model, and they lack of Infrastructure Management ability. Also public cloud would not be the most suitable delivery model for them if providing SaaS services. The main observation of this thesis is that CADM should adopt the SaaS model via Capgemini Immediate offering.

Memristive Computing

Memristive computing refers to the utilization of the memristor, the fourth fundamental passive circuit element, in computational tasks. The existence of the memristor was theoretically predicted in 1971 by Leon O. Chua, but experimentally validated only in 2008 by HP Labs. A memristor is essentially a nonvolatile nanoscale programmable resistor — indeed, memory resistor — whose resistance, or memristance to be precise, is changed by applying a voltage across, or current through, the device. Memristive computing is a new area of research, and many of its fundamental questions still remain open. For example, it is yet unclear which applications would benefit the most from the inherent nonlinear dynamics of memristors. In any case, these dynamics should be exploited to allow memristors to perform computation in a natural way instead of attempting to emulate existing technologies such as CMOS logic. Examples of such methods of computation presented in this thesis are memristive stateful logic operations, memristive multiplication based on the translinear principle, and the exploitation of nonlinear dynamics to construct chaotic memristive circuits. This thesis considers memristive computing at various levels of abstraction. The first part of the thesis analyses the physical properties and the current-voltage behaviour of a single device. The middle part presents memristor programming methods, and describes microcircuits for logic and analog operations. The final chapters discuss memristive computing in largescale applications. In particular, cellular neural networks, and associative memory architectures are proposed as applications that significantly benefit from memristive implementation. The work presents several new results on memristor modeling and programming, memristive logic, analog arithmetic operations on memristors, and applications of memristors. The main conclusion of this thesis is that memristive computing will be advantageous in large-scale, highly parallel mixed-mode processing architectures. This can be justified by the following two arguments. First, since processing can be performed directly within memristive memory architectures, the required circuitry, processing time, and possibly also power consumption can be reduced compared to a conventional CMOS implementation. Second, intrachip communication can be naturally implemented by a memristive crossbar structure.