<p dir="ltr">As the demand for IoT devices continues to grow, our reliance on networks in daily life increases. Whether we are considering individual users or large multinational companies, networks have become an essential asset for people across various industries. However, this dependence on networks also exposes us to security vulnerabilities when traffic is not adequately filtered. A successful attack on the network could have severe consequences for its users. Therefore, the implementation of a network intrusion detection system (IDS) is crucial to safeguard the well-being of our modern society.</p><p dir="ltr">While AI-based IDS is a new force in the field of intrusion detection, it outperforms some traditional approaches. However, it is not without its flaws. The performance of ML-based IDS decreases when applied to a different dataset than the one it was trained on. This decrease in performance hinders the ML-based IDS's ability to be used in a production environment, as the data generated in a production environment also differs from the data that is used to train the IDS. This paper aims to devise an ML-based IDS that is generalizable to a different environment.</p>

Áreas cultivadas com cana-de-açúcar podem sofrer o ataque do fungo Puccinia melanocephala e variedades suscetíveis desenvolvem uma doença conhecida por ferrugem da cana-de-açúcar. Por afetar, geralmente, áreas imensas, os prejuízos são grandes. Atualmente, a avaliação da doença é feita por especialistas que percorrem as áreas plantadas analisando visualmente as folhas e atribuindo à região um determinado grau de infecção. Esse modelo pode ser considerado subjetivo pois, dependendo da experiência e acuidade visual do especialista, a avaliação de uma mesma área pode apresentar resultados divergentes. Diante desta situação, este trabalho apresenta uma abordagem para automatizar o processo de identificação e avaliação, criando alternativas para minimizar os prejuízos. Este trabalho apresenta um método para classificação dos níveis de infecção da ferrugem por meio da análise de imagens aéreas de canaviais, adquiridas por um aeromodelo. Dessas fotos são extraídas características baseadas nas cores, as quais são classificadas por meio de uma rede neural backpropagation. Além disso, foi implementado um método para segmentação de imagens digitais de folhas de cana-de-açúcar infectadas com o intuito de corroborar a avaliação manual feita por especialistas. Os resultados mostram que o método é eficaz na discriminação dos três níveis de infecção disponíveis, além disso, indicam que este pode ser igualmente eficiente na discriminação dos nove níveis de infecção da escala adotada. / Cultivated areas of sugar cane may be targeted by the fungus Puccinia melanocephala and susceptible varieties may develop a disease known as sugar cane rust. Because the disease affects, in general, very large areas, the losses are very considerable. Currently, the evaluation of the disease is carried out by experts who must walk through the plantations analysing the leaves visually and assigning a certain degree of infection to the area. This model is somehow subjective because, due to experts’ experience and visual acuity, the evaluation for a specific area may present divergent results. In face of this problem, this work presents an approach to automate the process of identification and evaluation of the disease, as a new means to minimise the losses. This work shows a method to classify the infection levels of sugar cane rust through the analysis of aerial images of sugar cane plantations, acquired by an aeromodel. From these pictures, some characteristics are based on colours are extracted and further classified by a Backpropagation Neural Network. Furthermore, it has been implemented a method for the segmentation of digital images of sugar cane leaves infected by rust. This is done to corroborate the manual evaluation done by experts. The results have shown that the method is capable of discriminating the three levels of infection available and they also indicate that it can also be equally efficient in the discrimination of the nine distinct infection levels of the adopted scale.

Quick mass production of homogeneous thin film material is required in paper, plastic, fabric, and thin film industries. Due to the high feed rates and small thicknesses, machine vision and other nondestructive evaluation techniques are used to ensure consistent, defect-free material by continuously assessing post-production quality. One of the fastest growing inspection areas is for 0.5-500 micrometer thick thin films, which are used for semiconductor wafers, amorphous photovoltaics, optical films, plastics, and organic and inorganic membranes. As a demonstration application, a prototype roll-feed imaging system has been designed to inspect high-temperature polymer electrolyte membrane (PEM), used for fuel cells, after being die cast onto a moving transparent substrate. The inspection system continuously detects thin film defects and classifies them with a neural network into categories of holes, bubbles, thinning, and gels, with a 1.2% false alarm rate, 7.1% escape rate, and classification accuracy of 96.1%. In slot die casting processes, defect types are indicative of a misbalance in the mass flow rate and web speed; so, based on the classified defects, the inspection system informs the operator of corrective adjustments to these manufacturing parameters. Thickness uniformity is also critical to membrane functionality, so a real-time, full-field transmission densitometer has been created to measure the bi-directional thickness profile of the semi-transparent PEM between 25-400 micrometers. The local thickness of the 75 mm x 100 mm imaged area is determined by converting the optical density of the sample to thickness with the Beer-Lambert law. The PEM extinction coefficient is determined to be 1.4 D/mm and the average thickness error is found to be 4.7%. Finally, the defect inspection and thickness profilometry systems are compiled into a specially-designed graphical user interface for intuitive real-time operation and visualization.

Áreas cultivadas com cana-de-açúcar podem sofrer o ataque do fungo Puccinia melanocephala e variedades suscetíveis desenvolvem uma doença conhecida por ferrugem da cana-de-açúcar. Por afetar, geralmente, áreas imensas, os prejuízos são grandes. Atualmente, a avaliação da doença é feita por especialistas que percorrem as áreas plantadas analisando visualmente as folhas e atribuindo à região um determinado grau de infecção. Esse modelo pode ser considerado subjetivo pois, dependendo da experiência e acuidade visual do especialista, a avaliação de uma mesma área pode apresentar resultados divergentes. Diante desta situação, este trabalho apresenta uma abordagem para automatizar o processo de identificação e avaliação, criando alternativas para minimizar os prejuízos. Este trabalho apresenta um método para classificação dos níveis de infecção da ferrugem por meio da análise de imagens aéreas de canaviais, adquiridas por um aeromodelo. Dessas fotos são extraídas características baseadas nas cores, as quais são classificadas por meio de uma rede neural backpropagation. Além disso, foi implementado um método para segmentação de imagens digitais de folhas de cana-de-açúcar infectadas com o intuito de corroborar a avaliação manual feita por especialistas. Os resultados mostram que o método é eficaz na discriminação dos três níveis de infecção disponíveis, além disso, indicam que este pode ser igualmente eficiente na discriminação dos nove níveis de infecção da escala adotada. / Cultivated areas of sugar cane may be targeted by the fungus Puccinia melanocephala and susceptible varieties may develop a disease known as sugar cane rust. Because the disease affects, in general, very large areas, the losses are very considerable. Currently, the evaluation of the disease is carried out by experts who must walk through the plantations analysing the leaves visually and assigning a certain degree of infection to the area. This model is somehow subjective because, due to experts’ experience and visual acuity, the evaluation for a specific area may present divergent results. In face of this problem, this work presents an approach to automate the process of identification and evaluation of the disease, as a new means to minimise the losses. This work shows a method to classify the infection levels of sugar cane rust through the analysis of aerial images of sugar cane plantations, acquired by an aeromodel. From these pictures, some characteristics are based on colours are extracted and further classified by a Backpropagation Neural Network. Furthermore, it has been implemented a method for the segmentation of digital images of sugar cane leaves infected by rust. This is done to corroborate the manual evaluation done by experts. The results have shown that the method is capable of discriminating the three levels of infection available and they also indicate that it can also be equally efficient in the discrimination of the nine distinct infection levels of the adopted scale.

Atualmente os ÃrgÃos de trÃnsito utilizam os sistemas de monitoramento de trÃfego para reduÃÃo de acidentes de trÃnsito e como ferramenta fundamental para a coleta de dados estatÃsticos para auxiliar no planejamento e gerenciamento dos sistemas viÃrios. Nestes dados sÃo observadas informaÃÃes como a quantidade de veÃculos que trafegam em determinado ponto, a velocidade mÃdia e a identificaÃÃo da categoria dos veÃculos. A identificaÃÃo da categoria dos veÃculos que trafegam em uma via permite o controle de acesso a faixas de rolagem destinadas a uma classe de veÃculos especÃfica. O objetivo desse trabalho à propor uma soluÃÃo para classificaÃÃo de veÃculos atravÃs da anÃlise de sinais coletados de sensores indutivos no momento em que o veÃculo passa sobre os mesmos. O conjunto destes sinais para cada veÃculo à denominado perfil magnÃtico. Foi utilizado um classificador baseado em Rede Neural Artificial (RNA) para identificar o tipo de veÃculo de acordo com o padrÃo do perfil magnÃtico coletado. Na implementaÃÃo do sistema foi utilizado um framework Java que possibilitou a integraÃÃo da RNA ao aplicativo que opera no equipamento de monitoramento de trÃfego. TambÃm foi desenvolvido um aplicativo em Java que permite realizar o treinamento da rede utilizando dados coletados no equipamento e tambÃm permite avaliar posteriormente os resultados obtidos pela RNA. Os veÃculos foram classificados nas seguintes categorias: motos, veÃculos pequenos, veÃculos mÃdios, Ãnibus e caminhÃes. O sistema desenvolvido foi integrado a um equipamento de fiscalizaÃÃo de trÃfego fabricado pela empresa Fotosensores e apresentou resultados satisfatÃrios, pois o Ãndice de acerto geral do classificador foi de 97%, alÃm de representar uma melhoria no equipamento que anteriormente realizava a classificaÃÃo em somente quatro classes de veÃculos. / Currently, transit agencies use traffic monitoring systems to reduce traffic accidents and as a fundamental tool for collecting statistical data for planning and management of road systems. These data are observed as the amount of information vehicles that travel at a certain point, the average speed and the identification of the category of vehicles. The identification of the category of vehicles that travels on a path allows you to control access lanes connecting to a specific class of vehicles. The objective of this work is to propose a solution for vehicle classification by analyzing signals collected from inductive sensors at the time the vehicle passes over the sensors. This set of signs for each vehicle is called the magnetic profile. This work used a classifier based on Artificial Neural Network (ANN) to identify the type of vehicle according to the pattern of magnetic profile collected. The implemented system used a Java framework that enabled the integration of ANN to the application that operates in the traffic monitoring equipment. It was developed a Java application that trains the ANN using data collected in the equipment and also allows evaluating further classification results obtained by the ANN. The vehicles were classified into the following categories: motorcycles, small vehicles, medium vehicles, buses and trucks. The developed system has been integrated into a traffic monitoring equipment manufactured by Fotosensores and gave satisfactory results with an overall success rate above 97%. It represents an improvement in the equipment that carried out the classification.

This master’s thesis deals with designs and implementation of systems for music cover recognition. The introduction part is devoted to the calculation parameters from audio signal using Music Information Retrieval techniques. Subsequently, various forms of cover versions and musical aspects that cover versions share are defined. The thesis also deals in detail with the creation and distribution of a database of cover versions. Furthermore, the work presents methods and techniques for comparing and processing the calculated parameters. Attention is then paid to the OTI method, CSM calculation and methods dealing with parameter selection. The next part of the thesis is devoted to the design of systems for recognizing cover versions. Then there are compared systems already designed for recognizing cover versions. Furthermore, the thesis describes machine learning techniques and evaluation methods for evaluating the classification with a special emphasis on artificial neural networks. The last part of the thesis deals with the implementation of two systems in MATLAB and Python. These systems are then tested on the created database of cover versions.

Les traces réelles de réseaux cellulaires représentent une mine d’information utile pour améliorer les performances des réseaux. Des traces comme les CDRs (Call detail records) contiennent des informations horodatées sur toutes les interactions des utilisateurs avec le réseau sont exploitées dans cette thèse. Nous avons proposé des nouvelles approches dans l’étude et l’analyse des problématiques des réseaux de télécommunications, qui sont basé sur les traces réelles et des algorithmes d’apprentissage automatique. En effet, un outil global d’analyse de données, pour la classification automatique des stations de base, la prédiction de la charge de réseau et la gestion de la bande passante est proposé ainsi qu’un outil pour la détection automatique des anomalies de réseau. Ces outils ont été validés par des applications directes, et en utilisant différentes topologies de réseaux comme les réseaux WMN et les réseaux basés sur les drone-cells. Nous avons montré ainsi, qu’en utilisant des outils d’analyse de données avancés, il est possible d’optimiser dynamiquement les réseaux mobiles et améliorer la gestion de la bande passante. / Real datasets of mobile network traces contain valuable information about the network resources usage. These traces may be used to enhance and optimize the network performances. A real dataset of CDR (Call Detail Records) traces, that include spatio-temporal information about mobile users’ activities, are analyzed and exploited in this thesis. Given their large size and the fact that these are real-world datasets, information extracted from these datasets have intensively been used in our work to develop new algorithms that aim to revolutionize the infrastructure management mechanisms and optimize the usage of resource. We propose, in this thesis, a framework for network profiles classification, load prediction and dynamic network planning based on machine learning tools. We also propose a framework for network anomaly detection. These frameworks are validated using different network topologies such as wireless mesh networks (WMN) and drone-cell based networks. We show that using advanced data mining techniques, our frameworks are able to help network operators to manage and optimize dynamically their networks

The goal of this work is to create data mining module for information system Belinda. Data from database of clients will be analyzed using SAS Enterprise Miner. Results acquired using several data mining methods will be compared. During the second phase selected data mining method will be implemented such as module of information system Belinda. The final part of this work is evaluation of acquired results and possibility of using this module.