Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-08-09T22:51:25Z No. of bitstreams: 1 CarlosAlbertoDeAlbuquerqueSilva_TESE.pdf: 4568486 bytes, checksum: 5ddf18d55603ffd49ea2899025e1615f (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-08-10T23:15:49Z (GMT) No. of bitstreams: 1 CarlosAlbertoDeAlbuquerqueSilva_TESE.pdf: 4568486 bytes, checksum: 5ddf18d55603ffd49ea2899025e1615f (MD5) / Made available in DSpace on 2016-08-10T23:15:49Z (GMT). No. of bitstreams: 1 CarlosAlbertoDeAlbuquerqueSilva_TESE.pdf: 4568486 bytes, checksum: 5ddf18d55603ffd49ea2899025e1615f (MD5) Previous issue date: 2015-09-04 / Ag?ncia Nacional do Petr?leo - ANP / As Redes Neurais Artificiais (RNAs), que constituem uma das ramifica??es da Intelig?ncia Artificial (IA), est?o sendo empregadas como solu??o para v?rios problemas complexos, existentes nas mais diversas ?reas. Para a solu??o destes problemas torna-se indispens?vel que sua implementa??o seja feita em hardware. Em meio as estrat?gias a serem adotadas e satisfeitas durante a fase de projeto e implementa??o das RNAs em hardware, as conex?es entre os neur?nios s?o as que necessitam de maior aten??o. Recentemente, encontram-se RNAs implementadas tanto em circuitos integrados de aplica??o espec?fica (Application Specific Integrated Circuits - ASIC) quanto em circuitos integrados, configurados pelo usu?rio, a exemplo dos Field Programmable Gate Array (FPGAs), que possuem a capacidade de serem reconfigurados parcialmente, em tempo de execu??o, formando, portanto, um Sistema Parcialmente Reconfigur?vel (SPR), cujo emprego proporciona diversas vantagens, tais como: flexibilidade na implementa??o e redu??o de custos. Tem-se observado um aumento considerado no uso destes dispositivos para a implementa??o de RNAs. Diante do exposto, prop?e-se a implementa??o de uma matriz de neur?nios dinamicamente reconfigur?vel no FPGA Virtex 6 da Xilinx, descrita em linguagem de hardware e que possa absorver projetos baseados em plataforma de sistemas embarcados, dedicados ao controle distribu?do de equipamentos normalmente utilizados na ind?stria. Prop?e-se ainda, que a configura??o das topologias das RNAs que possam vir a ser formadas, seja realizada via software. / The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Submitted by João Arthur Martins (joao.arthur@ufpe.br) on 2015-03-10T18:50:01Z No. of bitstreams: 2 Dissertação Gleydson Vilanova.pdf: 10406213 bytes, checksum: 4161dab35fb90ca62e4ebd0186c0870e (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) / Made available in DSpace on 2015-03-11T17:34:31Z (GMT). No. of bitstreams: 2 Dissertação Gleydson Vilanova.pdf: 10406213 bytes, checksum: 4161dab35fb90ca62e4ebd0186c0870e (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2013 / A presença de textos manuscritos e impressos em um mesmo documento representa um grande desafio para os atuais mecanismos de Reconhecimento Óptico de Caracteres. Uma vez que essas classes de texto possuem suas próprias rotinas de reconhecimento, o uso de técnicas que permitam diferenciação entre elas tornou-se indispensável e o bom funcionamento dessas técnicas depende da escolha de características que melhor representem os elementos de texto sobre os quais os classificadores devem atuar. Considerando que na literatura existe uma grande variedade de características utilizadas para este fim, este trabalho objetiva o desenvolvimento de um método que permita, através de um processo de otimização com Algoritmos Genéticos e a partir de um conjunto inicial de 52 características, a seleção de subconjuntos de melhores características que, além de menores que o conjunto original, possibilitem melhoria dos resultados de classificação. Os experimentos foram realizados com classificadores kNN e Redes Neurais MLP a partir de imagens de palavras segmentadas. O método proposto foi avaliado fazendo uso de uma base de dados pública para textos manuscritos e outra criada especificamente para este trabalho para textos impressos. Os resultados dos experimentos mostram que os objetivos propostos foram alcançados. Os Erros Médios de Classificação foram estatisticamente equivalentes para os dois classificadores e uma melhor performance foi obtida com o kNN. A influência dos diferentes tipos de fontes e estilos utilizados nos textos impressos também foi analisada e mostrou que as fontes que imitam textos manuscritos como a "Lucida Handwriting" e "Comic Sans MS" apresentam maiores ocorrências de erros de classificação. Da mesma forma, a maioria dos erros foi percebida nos textos impressos com estilo itálico.

Made available in DSpace on 2014-06-12T15:59:13Z (GMT). No. of bitstreams: 2 arquivo4980_1.pdf: 1807272 bytes, checksum: abdafe66edec7c505073236b251526d0 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 1999 / Motivados pela demanda do mercado de software musical, bem como pelo interesse científico envolvido no problema de previsão de séries temporais [Weigend, 1993], desenvolvemos um ambiente capaz de realizar previsões de acordes de canções de Jazz em tempo real. Nós propusemos uma arquitetura híbrida original que tem como base uma rede neural MLP-backpropagation atuando de forma concorrente com um rastreador de seqüências repetidas de acordes. A rede neural faz um aprendizado prévio a partir de diversos exemplos de canções, extraindo os padrões curtos de seqüências de acordes típicas. O sistema rastreador funciona capturando em tempo real as repetições (refrões, estrofes, etc.) dentro de uma dada canção, as quais escapariam à rede neural. Trata-se da problemática geral de aprendizado a priori versus aprendizado situado, em tempo real. Com a arquitetura híbrida proposta e uma representação rica do acorde musical, obtivemos resultados muito acima dos registrados na literatura dedicada ao problema

Artificial neural networks have shown great potential and have attracted much research interest. One problem faced when simulating such networks is speed. As the number of neurons increases, the time to simulate and train a network increases dramatically. This makes it difficult to simulate and train a large-scale network system without the support of a high-performance computer system. The solution we present is a "real" parallel system - using a parallel machine to simulate neural networks which are intrinsically parallel applications. SpiNNaker is a scalable massively-parallel computing system under development with the aim of building a general-purpose platform for the parallel simulation of large-scale neural systems. This research investigates how to model large-scale neural networks efficiently on such a parallel machine. While providing increased overall computational power, a parallel architecture introduces a new problem - the increased communication reduces the speedup gains. Modeling schemes, which take into account communication, processing, and storage requirements, are investigated to solve this problem. Since modeling schemes are application-dependent, two different types of neural network are examined - spiking neural networks with spike-time dependent plasticity, and the parallel distributed processing model with the backpropagation learning rule. Different modeling schemes are developed and evaluated for the two types of neural network. The research shows the feasibility of the approach as well as the performance of SpiNNaker as a general-purpose platform for the simulation of neural networks. The linear scalability shown in this architecture provides a path to the further development of parallel solutions for the simulation of extremely large-scale neural networks.

Innovations such as combustion engines, electricity and assembly lines have all had a significant role in manufacturing, where the past three industrial revolutions have changed the way manufacturing is performed. The technical progress within the manufacturing industry continues at a high rate and today's progress can be seen as a part of the fourth industrial revolution. The progress can be exemplified by ”Industrie 4.0”; the German government's vision of future manufacturing. Previous studies have been conducted with the aim of investigating the benefits, progress and relevance of Industry 4.0-technologies. Little emphasis in these studies has been put on differences in implementation and relevance of Industry 4.0-technologies across and within industries. This thesis aims to investigate the adoption of Industry 4.0-technologies among and within selected industries and what types of patterns that exists among them. Using a qualitative multiple case study consisting of firms from Aerospace, Heavy equipment, Automation, Electronics and Motor Vehicle Industry, we gain insight into how leading firms are implementing the technologies. In order to identify the factors determining how Industry 4.0-technologies are implemented and what common themes can be found, we introduce the concept production logic, which is built upon the connection between competitive priorities; quality, flexibility, delivery time, cost efficiency and ergonomics. This thesis has two contributions. In our first contribution, we have categorized technologies within Industry 4.0 into two bundles; the Human-Machine-Interface (HMI) and the connectivity bundle. The HMI bundle includes devices for assisting operators in manufacturing activities, such as touchscreens, augmented reality and collaborative robots. The connectivity-bundle includes systems for connecting devices, collecting and analyzing data from the digitalized factory. The result of this master thesis indicates that depending on a firm’s or industry’s logic of production, the adoption of elements from the technology bundles differ. Firms where flexibility is dominant tend to implement elements from the HMI-bundle to a larger degree. In the other end, firms with few product variations where quality and efficiency dominates the production logic tends to implement elements from the connectivity bundle in order to tightly monitor and improve quality in their assembly. Regardless of production logic, firms are implementing elements from both bundles, but with different composition and applications. The second contribution is within the literature of technological transitions. In this contribution, we have studied the rise and development of the HMI-bundle in the light of Geels (2002) Multi-Level Perspective (MLP). It can be concluded that an increased pressure on the landscape-level in the form of changes in the consumer-market and the attitudes within the labor force has created a gradual spread of the HMI-bundle within industries. The bundles have also been studied through Rogers (1995) five attributes of innovation, where the lack of testability and observability prevents increased application of M2M-interfaces. Concerning Big Data and analytics, the high complexity prevents the technology from being further applied. As the HMI-bundle involves a number of technologies with large differences in properties, it is hard draw any conclusion using the attributes of innovation about what limits their application.

A significant proportion of construction and demolition (C&D) waste is encompassed within the broader category of global waste. The handling of C&D waste is subject to the influence of a tripartite of environmental, social, and economic factors. An extensive comprehension of C&D waste management can be attained by examining the construction industry, waste management, transportation, and non-governmental organisations (NGOs). The escalating aggregate demand and landfill practices significantly threaten developing nations' natural resources, despite the national government's regulatory measures. The present study employed a qualitative research approach and a multi-level perspective (MLP) framework to investigate the various actors, factors, and levels that impact the management of C&D waste. The present analysis relates independently to investigating lock-in determinants, encompassing exogenous and endogenous pressures and socio-technical transitions. Bengaluru's management of C&D waste encompasses a diverse array of stakeholders, including real estate organizations, urban development agencies, construction firms, both formal and informal markets, a solitary C&D processing plant situated at the periphery of the city, unapproved landfills located in abandoned stone quarries, local transportation providers, governance bodies, and low-carbon building methodologies. Furthermore, it is imperative to note that there exist significant deficiencies in the execution of C&D waste management by established protocols, as well as their enforcement. This is compounded by an acute shortage of facilities for the collection and disposal of such waste, insufficient vehicular resources at the disposal of the Bruhat Bengaluru Mahanagara Palike (BBMP), limited participation from stakeholders, negative attitudes towards the effective use of recycled materials and the repurposing of building components, a lack of incentivisation and punitive measures, inadequate awareness among proprietors and constructors of private edifices, and the indiscriminate dumping of C&D waste, which has led to the obstruction of commuting and communal well being. The effects of landfills on wildlife, such as avian migration and urban inundation, have prompted a transition towards more ecologically sound management of C&D waste in Bengaluru. Formulating sustainable strategies for managing C&D waste in Bengaluru is encouraged to incorporate socio-economic and environmental factors, business models, and governmental cooperation. The importance of sharing information, the power of nudging people to alter their habits, and the value of considering new approaches to building are also highlighted.

Classification tasks are an integral part of science, industry, medicine, and business; being such a pervasive technique, its smallest improvement is valuable. Artificial Neural Network (ANN) is one of the strongest techniques used in many disciplines for classification. The ANN technique suffers from drawbacks such as intransparency in spite of its high prediction power. In this dissertation, motivated by learning styles in human brains, ANN’s shortcomings are assuaged and its learning power is improved. Self-Organizing Map (SOM), an ANN variation which has strong unsupervised power, and Feedforward ANN, traditionally used for classification tasks, are hybridized to solidify their benefits and help remove their limitations. These benefits are in two directions: enhancing ANN’s learning power, and improving decision-making. First, the proposed method, named Self-Organizing Error-Driven (SOED) Artificial Neural Network (ANN), shows significant improvements in comparison with usual ANNs. We show SOED is a more accurate, more reliable, and more transparent technique through experimentation with five famous benchmark datasets. Second, the hybridization creates space for inclusion of decision-making goals at the level of ANN’s learning. This gives the classifier the opportunity to handle the inconclusiveness of the data smarter and in the direction of decision-making goals. Through three case studies, naming 1) churn decision analytics, 2) breast cancer diagnosis, and 3) quality control decision making through thermal monitoring of additive manufacturing processes, this novel and cost-sensitive aspect of SOED has been explored and lead to much quantified improvement in decision-making.

The topic of Impact Investing has been creating waves and generating a lot of interest in the funding ecosystem with the growth of impact startups & because of pressure from the populace in the face of global challenges. At the same time the field has been under-explored by scholars. The exploration of the investment industry is performed by collecting investors' perspective on the self defined concept of Impact investing. The research attempts to portray the perspective of the established Venture Capital regime on Impact Investment and understand whether it is still perceived as philanthropic endeavors investing in an alternative asset class, suggested by previous academic research or an industry wide transition and change of investment practices as portrayed by the industry research. This study is focused on the Swedish & U.S. Venture Capital regimes. Sweden, a country that has been described as the “Impact Capital”, and the U.S. that represents worlds largest VC capital sector. Semi-structured qualitative interviews were used in this study to explore the industry dynamics using a MLP(Multi Level Perspective) framework. The interviews with VCs help understand the current sentiment on the growth in impact investing and why the Swedish market is seeing an industry-wide transition while the U.S. VC’s treat it as a separate asset class.  The authors identified that the U.S. regime is currently in the emergence phase of transition while the Swedish regime has reached the transformation phase. Additionally four key themes that differentiate the perspective of the Swedish and US regimes were identified; Risk, Profitability, Use-Case & Branding. / Impact Investing är ett ämne som har skapat vågor och genererat ett stort intresse för finansieringsekosystemet i samband med tillväxten av nystartade företag och påtryckningar från befolkningen inför de globala utmaningarna. Trots det har ämnet sett begränsad akademisk forskning. Explorationen av investeringsbranschen utförs genom att samla investerarnas perspektiv på det självdefinierade konceptet Impact Investing. Forskningen försöker skildra hur den etablerade riskkapitalregimen ser på Impact Investment och förstå om det fortfarande uppfattas som filantropiska initiativ av att investera i en alternativ tillgångskategori, som föreslås av tidigare akademisk forskning eller en branschomfattande övergång och förändring av investeringspraxis som framställts av industriforskningen.  Denna studie fokuserar på riskkapitalsregiment i Sverige och Amerika. Sverige, ett land som har beskrivits som "Impact Capital", och USA som representerar världens största VC-kapitalsektor. Semistrukturerade kvalitativa intervjuer används i denna studie för att utforska industridynamiken med hjälp av MLP(Multi Level Perspective)-ramverket. Intervjuerna med riskkapitalister hjälper till att förstå den nuvarande uppfattningen om tillväxten av impact investment och varför den svenska marknaden ser en branschomfattande förändringsprocess medan amerikanska VC:s behandlar det som en separat tillgångskategori. Författarna identifierade att den amerikanska regimen för närvarande befinner sig i begynnelsefasen medan den svenska regimen har nått transformationsfasen. Dessutom identifierades fyra nyckelteman som skiljer de svenska och amerikanska regimernas perspektiv; Risk, Lönsamhet, användningsfall & varumärke.

Network intrusion detection is a task aimed to identify malicious network traffic. Malicious networktraffic is generated when a perpetrator attacks a network or internet-connected device with the intent todisrupt, steal or destroy a service or information. Two approaches for this particular task is the rule-basedmethod and the use of machine learning. The purpose of this paper was to contribute with knowledgeon how to evaluate and build better network intrusion detection systems (NIDS). That was fulfilled bycomparing the detection ability of two machine learning models, a neural network and a random forestmodel, with a rule-based NIDS called Snort. The paper describes how the two models and Snort wereconstructed and how performance metrics were generated on a dataset called CIC-IDS2017. It also describes how we capture our own malicious network traffic and the models ability to classify that data. Thecomparisons shows that the neural network outperforms Snort and the Random forest. We also presentfour factors that may influence which method that should be used for intrusion detection. In addition weconclude that we see potential in using CIC-IDS2017 to build NIDS based on machine learning.

The goal of this thesis is to be able to predict customer traffic at postal service points. The expectation is that when customers are made aware of queue times at the service points, they will redistribute themselves to avoid standing in line. This boils down to a form of time series prediction problem. When working with time series prediction, there are potentially other factors that may help the models make a more accurate prediction. Factors that may affect people’s behavior are unlimited, but this thesis examines the effect of the external calendar variables (weekday, date and public holiday) and weather variables (temperature, precipitation and sun, among others) when making the predictions. Non-linear models are examined, with the focus on Multilayer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) models that have shown promising results in time series prediction, and these models are referred to as Artificial Neural Networks (ANNs). Support Vector Regression (SVR), Autoregressive Moving Average (ARIMA) and statistical average models are used for comparison. The results show that using external variables as additional input to LSTM, MLP and SVR models increases the test prediction performance. Further, the MLP model generally performs better than the LSTM models. The results are acquired using six postal service points, and the final results are based on a six-fold cross validation across all six service points. The LSTM and MLP are able to better use the external variables and show greater adaptability during e.g. public holidays, compared with the SVR model. The ARIMA and historical average model show less accurate predictions compared with the aforementioned models. / Målet med detta examensarbete är att förutspå kundtrafik hos postserviceställen. Förhoppningen är att kunderna omfördelar sig själva om de får tillgång till kundtrafikprognoser för att undvika stå i kö. Detta resulterar i ett tidsserie-förutsägelseproblem. Vid sådana problem finns det potentiellt andra faktorer som kan påverka modellernas prediktioner positivt. Antalet faktorer som påverkar människors beteende är obegränsat, men detta examensarbete undersöker effekterna av att använda externa kalendervariabler (veckodag, datum och röd dag) och vädervariabler (temperatur, nederbörd och sol, bland annat). För att göra prediktionerna används främst de icke-linjära modellerna Multilayer Perceptron (MLP) och Long Short-Term Memory (LSTM), som båda refereras till som Artificial Neural Network (ANN). Båda modellerna har visat lovande resultat i liknande problem. Utöver dem används även modellerna Support Vector Regression (SVR) och Autoregressive Moving Average (ARIMA) samt det historiska genomsnittet som jämförelse. Resultaten visar på att om LSTM-, MLPoch SVR-modellerna får externa variabler som tilläggsinput så förbättras modellernas förutsägelser. Vidare presterar MLP-modellen generellt bättre än LSTMmodellen. Resultaten är skapade genom att använda sex stycken postserviceställen och de slutgiltiga resultaten är baserade på en 6-vägs korsvalidering för samtliga serviceställen. LSTMoch MLP-modellerna är bättre på att använda informationen från de externa variablerna och visar på större anpassningsförmåga, under till exempel röda dagar, jämfört med SVR-modellen. ARIMA-modellen och den historiska genomsnittsmodellen skapar sämre prediktioner än de förutnämndamodellerna.