Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Estudo da implementação do Warehouse Management System em uma empresa produtora de embreagens

In the supply chain management there are several risk factors that must be mitigated to increase the flow of production and as a possible solution the literature cites the implementation of a warehouse management system, but this subject is few explored. This thesis has as main objective the study of the implementation of a warehouse management system in a company from the automotive sector that produces clutches. As results, are shown data of the characterization of items; as well as data and comparisons between disruptions in production reports due to lack of material before and after the implementation of WMS and is presented the result of a questionnaire applied to the involved on the implementation of the system, the results were associated with the risk factors on the implementation of the system studied on the literature review, and enumeration of the results that are not associated with any factors previously studied. And finally, the study is concluded and are recommended future studies related to the theme

A mixed model QTL analysis for sugarcane multiple-harvest-location trial data

Sugarcane-breeding programs take at least 12 years to develop new commercial cultivars. Molecular markers offer a possibility to study the genetic architecture of quantitative traits in sugarcane, and they may be used in marker-assisted selection to speed up artificial selection. Although the performance of sugarcane progenies in breeding programs are commonly evaluated across a range of locations and harvest years, many of the QTL detection methods ignore two- and three-way interactions between QTL, harvest, and location. In this work, a strategy for QTL detection in multi-harvest-location trial data, based on interval mapping and mixed models, is proposed and applied to map QTL effects on a segregating progeny from a biparental cross of pre-commercial Brazilian cultivars, evaluated at two locations and three consecutive harvest years for cane yield (tonnes per hectare), sugar yield (tonnes per hectare), fiber percent, and sucrose content. In the mixed model, we have included appropriate (co)variance structures for modeling heterogeneity and correlation of genetic effects and non-genetic residual effects. Forty-six QTLs were found: 13 QTLs for cane yield, 14 for sugar yield, 11 for fiber percent, and 8 for sucrose content. In addition, QTL by harvest, QTL by location, and QTL by harvest by location interaction effects were significant for all evaluated traits (30 QTLs showed some interaction, and 16 none). Our results contribute to a better understanding of the genetic architecture of complex traits related to biomass production and sucrose content in sugarcane.

Network-based high level data classification

Traditional supervised data classification considers only physical features (e. g., distance or similarity) of the input data. Here, this type of learning is called low level classification. On the other hand, the human (animal) brain performs both low and high orders of learning and it has facility in identifying patterns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is, here, referred to as high level classification. In this paper, we propose a hybrid classification technique that combines both types of learning. The low level term can be implemented by any classification technique, while the high level term is realized by the extraction of features of the underlying network constructed from the input data. Thus, the former classifies the test instances by their physical features or class topologies, while the latter measures the compliance of the test instances to the pattern formation of the data. Our study shows that the proposed technique not only can realize classification according to the pattern formation, but also is able to improve the performance of traditional classification techniques. Furthermore, as the class configuration's complexity increases, such as the mixture among different classes, a larger portion of the high level term is required to get correct classification. This feature confirms that the high level classification has a special importance in complex situations of classification. Finally, we show how the proposed technique can be employed in a real-world application, where it is capable of identifying variations and distortions of handwritten digit images. As a result, it supplies an improvement in the overall pattern recognition rate.

Query Player : a component for Triskel architecture

[ES] Uno de los cinco componentes de la arquitectura triskel,  una base de datos NoSQL que trata de dar solución al problema de Big data de la web semántica, el  gran número de identificadores de recursos que se necesitarían debido al creciente número de sitios web, concretamente el motor de gestión de ejecución de patrones basados en tripletas y en la tecnología RDF. Se encarga de recoger la petición de consulta por parte del intérprete, analizar los patrones que intervienen en la consulta en busca de dependencias explotables entre ellos, y así poder realizar la consulta con mayor rapidez además de ir resolviendo los diferentes patrones contra el almacenamiento, un TripleStore, y devolver el resultado de la petición en una tabla.

Sparql Interpreter : a component for Triskel architecture

[ES] SPARQL Interpreter es uno de los cinco componentes de la Arquitectura Triskel, una arquitectura de software para una base de datos NoSQL que intenta aportar una solución al problema de Big Data en la web semántica. Este componente da solución al problema de la comunicación entre el lenguaje y el motor, interpretando las consultas que se realicen contra el almacenamiento en lenguaje SPARQL y generando una estructura de datos que los componentes inferiores puedan leer y ejecutar.

Molecular architecture of fur binding to iron-induced and - repressed genes in Helicobacter pylori

The ferric uptake regulator protein Fur regulates iron-dependent gene expression in bacteria. In the human pathogen Helicobacter pylori, Fur has been shown to regulate iron-induced and iron-repressed genes. Herein we investigate the molecular mechanisms that control this differential iron-responsive Fur regulation. Hydroxyl radical footprinting showed that Fur has different binding architectures, which characterize distinct operator typologies. On operators recognized with higher affinity by holo-Fur, the protein binds to a continuous AT-rich stretch of about 20 bp, displaying an extended protection pattern. This is indicative of protein wrapping around the DNA helix. DNA binding interference assays with the minor groove binding drug distamycin A, point out that the recognition of the holo-operators occurs through the minor groove of the DNA. By contrast, on the apo-operators, Fur binds primarily to thymine dimers within a newly identified TCATTn10TT consensus element, indicative of Fur binding to one side of the DNA, in the major groove of the double helix. Reconstitution of the TCATTn10TT motif within a holo-operator results in a feature binding swap from an holo-Fur- to an apo-Fur-recognized operator, affecting both affinity and binding architecture of Fur, and conferring apo-Fur repression features in vivo. Size exclusion chromatography indicated that Fur is a dimer in solution. However, in the presence of divalent metal ions the protein is able to multimerize. Accordingly, apo-Fur binds DNA as a dimer in gel shift assays, while in presence of iron, higher order complexes are formed. Stoichiometric Ferguson analysis indicates that these complexes correspond to one or two Fur tetramers, each bound to an operator element. Together these data suggest that the apo- and holo-Fur repression mechanisms apparently rely on two distinctive modes of operator-recognition, involving respectively the readout of a specific nucleotide consensus motif in the major groove for apo-operators, and the recognition of AT-rich stretches in the minor groove for holo-operators, whereas the iron-responsive binding affinity is controlled through metal-dependent shaping of the protein structure in order to match preferentially the major or the minor groove.

Innovative architecture of on-board and on-ground radio systems for space communication

The radio communication system is one of the most critical system of the overall satellite platform: it often represents the only way of communication, between a spacecraft and the Ground Segment or among a constellation of satellites. This thesis focuses on specific innovative architectures for on-board and on-ground radio systems. In particular, this work is an integral part of a space program started in 2004 at the University of Bologna, Forlì campus, which led to the completion of the microsatellite ALMASat-1, successfully launched on-board the VEGA maiden flight. The success of this program led to the development of a second microsatellite, named ALMASat-EO, a three-axis stabilized microsatellite able to capture images of the Earth surface. Therefore, the first objective of this study was focused on the investigation of an innovative, efficient and low cost architecture for on-board radio communication systems. The TT&C system and the high data rate transmitter for images downlink design and realization are thoroughly described in this work, together with the development of the embedded hardware and the adopted antenna systems. Moreover, considering the increasing interest in the development of constellations of microsatellite, in particular those flying in close formations, a careful analysis has been carried out for the development of innovative communication protocols for inter-satellite links. Furthermore, in order to investigate the system aspects of space communications, a study has been carried out at ESOC having as objective the design, implementation and test of two experimental devices for the enhancement of the ESA GS. Thus, a significant portion of this thesis is dedicated to the description of the results of a method for improving the phase stability of GS radio frequency equipments by means of real-time phase compensation and a new way to perform two antennas arraying tracking using already existing ESA tracking stations facilities.

Design and implementation of a testbed for data distribution management

Data Distribution Management (DDM) is a core part of High Level Architecture standard, as its goal is to optimize the resources used by simulation environments to exchange data. It has to filter and match the set of information generated during a simulation, so that each federate, that is a simulation entity, only receives the information it needs. It is important that this is done quickly and to the best in order to get better performances and avoiding the transmission of irrelevant data, otherwise network resources may saturate quickly. The main topic of this thesis is the implementation of a super partes DDM testbed. It evaluates the goodness of DDM approaches, of all kinds. In fact it supports both region and grid based approaches, and it may support other different methods still unknown too. It uses three factors to rank them: execution time, memory and distance from the optimal solution. A prearranged set of instances is already available, but we also allow the creation of instances with user-provided parameters. This is how this thesis is structured. We start introducing what DDM and HLA are and what do they do in details. Then in the first chapter we describe the state of the art, providing an overview of the most well known resolution approaches and the pseudocode of the most interesting ones. The third chapter describes how the testbed we implemented is structured. In the fourth chapter we expose and compare the results we got from the execution of four approaches we have implemented. The result of the work described in this thesis can be downloaded on sourceforge using the following link: https://sourceforge.net/projects/ddmtestbed/. It is licensed under the GNU General Public License version 3.0 (GPLv3).

Software tools and efficient algorithms for the feature detection, feature tracking, event localization, and visualization of large sets of atmospheric data

Data sets describing the state of the earth's atmosphere are of great importance in the atmospheric sciences. Over the last decades, the quality and sheer amount of the available data increased significantly, resulting in a rising demand for new tools capable of handling and analysing these large, multidimensional sets of atmospheric data. The interdisciplinary work presented in this thesis covers the development and the application of practical software tools and efficient algorithms from the field of computer science, aiming at the goal of enabling atmospheric scientists to analyse and to gain new insights from these large data sets. For this purpose, our tools combine novel techniques with well-established methods from different areas such as scientific visualization and data segmentation. In this thesis, three practical tools are presented. Two of these tools are software systems (Insight and IWAL) for different types of processing and interactive visualization of data, the third tool is an efficient algorithm for data segmentation implemented as part of Insight.Insight is a toolkit for the interactive, three-dimensional visualization and processing of large sets of atmospheric data, originally developed as a testing environment for the novel segmentation algorithm. It provides a dynamic system for combining at runtime data from different sources, a variety of different data processing algorithms, and several visualization techniques. Its modular architecture and flexible scripting support led to additional applications of the software, from which two examples are presented: the usage of Insight as a WMS (web map service) server, and the automatic production of a sequence of images for the visualization of cyclone simulations. The core application of Insight is the provision of the novel segmentation algorithm for the efficient detection and tracking of 3D features in large sets of atmospheric data, as well as for the precise localization of the occurring genesis, lysis, merging and splitting events. Data segmentation usually leads to a significant reduction of the size of the considered data. This enables a practical visualization of the data, statistical analyses of the features and their events, and the manual or automatic detection of interesting situations for subsequent detailed investigation. The concepts of the novel algorithm, its technical realization, and several extensions for avoiding under- and over-segmentation are discussed. As example applications, this thesis covers the setup and the results of the segmentation of upper-tropospheric jet streams and cyclones as full 3D objects. Finally, IWAL is presented, which is a web application for providing an easy interactive access to meteorological data visualizations, primarily aimed at students. As a web application, the needs to retrieve all input data sets and to install and handle complex visualization tools on a local machine are avoided. The main challenge in the provision of customizable visualizations to large numbers of simultaneous users was to find an acceptable trade-off between the available visualization options and the performance of the application. Besides the implementational details, benchmarks and the results of a user survey are presented.

Implementazione ed analisi di un framework basato su Cloud per la valutazione di algoritmi di data Distribution Management

Il Data Distribution Management (DDM) è un componente dello standard High Level Architecture. Il suo compito è quello di rilevare le sovrapposizioni tra update e subscription extent in modo efficiente. All'interno di questa tesi si discute la necessità di avere un framework e per quali motivi è stato implementato. Il testing di algoritmi per un confronto equo, librerie per facilitare la realizzazione di algoritmi, automatizzazione della fase di compilazione, sono motivi che sono stati fondamentali per iniziare la realizzazione framework. Il motivo portante è stato che esplorando articoli scientifici sul DDM e sui vari algoritmi si è notato che in ogni articolo si creavano dei dati appositi per fare dei test. L'obiettivo di questo framework è anche quello di riuscire a confrontare gli algoritmi con un insieme di dati coerente. Si è deciso di testare il framework sul Cloud per avere un confronto più affidabile tra esecuzioni di utenti diversi. Si sono presi in considerazione due dei servizi più utilizzati: Amazon AWS EC2 e Google App Engine. Sono stati mostrati i vantaggi e gli svantaggi dell'uno e dell'altro e il motivo per cui si è scelto di utilizzare Google App Engine. Si sono sviluppati quattro algoritmi: Brute Force, Binary Partition, Improved Sort, Interval Tree Matching. Sono stati svolti dei test sul tempo di esecuzione e sulla memoria di picco utilizzata. Dai risultati si evince che l'Interval Tree Matching e l'Improved Sort sono i più efficienti. Tutti i test sono stati svolti sulle versioni sequenziali degli algoritmi e che quindi ci può essere un riduzione nel tempo di esecuzione per l'algoritmo Interval Tree Matching.

Data dissemination over complex networks through gossip

This thesis offers a practical and theoretical evaluations about gossip-epidemic algorithms, comparing those most common in the literature with new proposed algorithms and analyzing their behavior. Tests have been executed using one hundred graphs that has been randomly generated by Large Unstructured NEtwork Simulator (LUNES), a simulation software provided by Parallel and Distributed Simulation Research Group (PADS), of the Department of Computer Science, Università di Bologna and simulated using Advanced RTI System (ARTÌS), based on the High Level Architecture standard. Literatures algorithms have been analyzed and taken as base for new algorithms.

TARWIS - A Testbed Management Architecture for Wireless Sensor Network Testbeds

With research on Wireless Sensor Networks (WSNs) becoming more and more mature in the past five years, researchers from universities all over the world have set up testbeds of wireless sensor networks, in most cases to test and evaluate the real-world behavior of developed WSN protocol mechanisms. Although these testbeds differ heavily in the employed sensor node types and the general architectural set up, they all have similar requirements with respect to management and scheduling functionalities: as every shared resource, a testbed requires a notion of users, resource reservation features, support for reprogramming and reconfiguration of the nodes, provisions to debug and remotely reset sensor nodes in case of node failures, as well as a solution for collecting and storing experimental data. The TARWIS management architecture presented in this paper targets at providing these functionalities independent from node type and node operating system. TARWIS has been designed as a re-usable management solution for research and/or educational oriented research testbeds of wireless sensor networks, relieving researchers intending to deploy a testbed from the burden to implement their own scheduling and testbed management solutions from scratch.

System Architecture of a Mixed Reality Framework

In this paper the software architecture of a framework which simplifies the development of applications in the area of Virtual and Augmented Reality is presented. It is based on VRML/X3D to enable rendering of audio-visual information. We extended our VRML rendering system by a device management system that is based on the concept of a data-flow graph. The aim of the system is to create Mixed Reality (MR) applications simply by plugging together small prefabricated software components, instead of compiling monolithic C++ applications. The flexibility and the advantages of the presented framework are explained on the basis of an exemplary implementation of a classic Augmented Realityapplication and its extension to a collaborative remote expert scenario.