Made available in DSpace on 2016-08-17T14:53:05Z (GMT). No. of bitstreams: 1 Aurea Celeste da Costa Ribeiro.pdf: 590401 bytes, checksum: 1ec80bb8ac1a3e674ff49966fa9b383c (MD5) Previous issue date: 2009-06-30 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Diabetes is a disease caused by the pancreas failing to produce insulin. It is incurable and its treatment is based on a diet, exercise and drugs. The costs for diagnosis and human resources for it have become high and ine±cient. Computer- aided design (CAD) systems are essential to solve this problem. Our study proposes a CAD system based on the one-class support vector machine (SVM) method and the eficient coding with independent component analysis (ICA) to classify a patient's data set in diabetics or non-diabetics. First, the classification tests were done using both non-invasive and invasive characteristics of the disease. Then, we made one test without the invasive characteristics: plasma glucose concentration and 2-Hour serum insulin (mu U/ml), which use blood samples. We have obtained an accuracy of 99.84% and 99.28%, respectively. Other tests were made without the invasive characteristics, also excluding one non-invasive characteristic at a time, to observe the influence of each one in the final results. / Diabetes é uma doença causada pela falência do pâncreas em produzir insulina, é incurável e seu tratamento é baseado em dietas, exercícios e remédios. Os custos com o tratamento, diagnóstico na população e combate da doença tornam-se cada vez mais altos. Sistemas de auxíio ao diagnóstico da doença são uma das soluções para ajudar na diminuição dos custos com a doença. Nosso método propõe um sistema de auxílio de diagnóstico baseado nas máquinas de vetor de suporte para uma classe e na codificação eficiente através da análise de componentes independentes para classificar uma base de dados de pacientes em diabéticos e não-diabéticos. Primeiramente, foram feitos testes de classificação com as características não- invasivas e invasivas da base de dados juntas. Em seguida, fizemos um teste sem as características invasivas da base de dados, que são glicose e insulina em jejum, que são feitas com a coleta sanguínea. Obteve-se uma taxa de acurácia de 99,84% e 99,28%, respectivamente. Outros testes foram feitos sem as características invasivas, tirando uma característica não-invasiva por vez, com o fim de observar a influência de cada uma no resultado final.

While many of the currently used network intrusion detection systems (NIDS) employ signature-based approaches, there is an increasing research interest in the examination of anomaly-based detection methods, which seem to be more suited for recognizing zero-day attacks. Nevertheless, requirements for their practical deployment, as well as objective and reproducible evaluation methods, are hereby often neglected. The following thesis defines aspects that are crucial for a practical evaluation of anomaly-based NIDS, such as the focus on modern attack types, the restriction to one-class classification methods, the exclusion of known attacks from the training phase, a low false detection rate, and consideration of the runtime efficiency. Based on those principles, a framework dedicated to developing, testing and evaluating models for the detection of network anomalies is proposed. It is applied to two datasets featuring modern traffic, namely the UNSW-NB15 and the CIC-IDS-2017 datasets, in order to compare and evaluate commonly-used network intrusion detection methods. The implemented approaches include, among others, a highly configurable network flow generator, a payload analyser, a one-hot encoder, a one-class support vector machine, and an autoencoder. The results show a significant difference between the two chosen datasets: While for the UNSW-NB15 dataset several reasonably well performing model combinations for both the autoencoder and the one-class SVM can be found, most of them yield unsatisfying results when the CIC-IDS-2017 dataset is used. / Obwohl viele der derzeit genutzten Systeme zur Erkennung von Netzwerkangriffen (engl. NIDS) signaturbasierte Ansätze verwenden, gibt es ein wachsendes Forschungsinteresse an der Untersuchung von anomaliebasierten Erkennungsmethoden, welche zur Identifikation von Zero-Day-Angriffen geeigneter erscheinen. Gleichwohl werden hierbei Bedingungen für deren praktischen Einsatz oft vernachlässigt, ebenso wie objektive und reproduzierbare Evaluationsmethoden. Die folgende Arbeit definiert Aspekte, die für eine praxisorientierte Evaluation unabdingbar sind. Dazu zählen ein Schwerpunkt auf modernen Angriffstypen, die Beschränkung auf One-Class Classification Methoden, der Ausschluss von bereits bekannten Angriffen aus dem Trainingsdatensatz, niedrige Falscherkennungsraten sowie die Berücksichtigung der Laufzeiteffizienz. Basierend auf diesen Prinzipien wird ein Rahmenkonzept vorgeschlagen, das für das Entwickeln, Testen und Evaluieren von Modellen zur Erkennung von Netzwerkanomalien bestimmt ist. Dieses wird auf zwei Datensätze mit modernem Netzwerkverkehr, namentlich auf den UNSW-NB15 und den CIC-IDS- 2017 Datensatz, angewendet, um häufig genutzte NIDS-Methoden zu vergleichen und zu evaluieren. Die für diese Arbeit implementierten Ansätze beinhalten, neben anderen, einen weit konfigurierbaren Netzwerkflussgenerator, einen Nutzdatenanalysierer, einen One-Hot-Encoder, eine One-Class Support Vector Machine sowie einen Autoencoder. Die Resultate zeigen einen großen Unterschied zwischen den beiden ausgewählten Datensätzen: Während für den UNSW-NB15 Datensatz verschiedene angemessen gut funktionierende Modellkombinationen, sowohl für den Autoencoder als auch für die One-Class SVM, gefunden werden können, bringen diese für den CIC-IDS-2017 Datensatz meist unbefriedigende Ergebnisse.

As more IoT devices enter the market it becomes increasingly important to develop reliable and adaptive ways of dealing with the data they generate. These must address data quality and reliability. Such solutions could benefit both the device producers and their customers who, as a result, could receive faster and better customer support services. Thus, this project's goal is twofold. First, it is to identify faulty data points generated by such devices. Second, it is to evaluate whether the knowledge gained from available/known sensors and appliances is transferable to other sensors on similar devices. This would make it possible to evaluate the behaviour of new appliances as soon as they are first switched on, rather than after sufficient data from them has been collected. This project uses time series data from three appliances: washing machine, washer&dryer and refrigerator. For these, two solutions are developed and tested: one for categorical and another for numerical variables. Categorical variables are analysed using the Average Value Frequency and the pure frequency of state-transition methods. Due to the limited number of possible states, the pure frequency proves to be the better solution, and the knowledge gained is transferred from the source device to the target one, with moderate success. Numerical variables are analysed using a One-class Support Vector Machine pipeline, with very promising results. Further, learning and forgetting mechanisms are developed to allow for the pipelines to adapt to changes in appliance patterns of behaviour. This includes a decay function for the numerical variables solution. Interestingly, the different weights for the source and target have little to no impact on the quality of the classification. / Nya IoT-enheter träder in på marknaden så det blir allt viktigare att utveckla tillförlitliga och anpassningsbara sätt att hantera de data de genererar. Dessa bör hantera datakvalitet och tillförlitlig- het. Sådana lösningar kan gynna båda tillverkarna av apparater och deras kunder som som ett resultat kan dra nytta av snabbare och bättre kundsupport / tjänster. Således har detta projekt två mål. Det första är att identifiera felaktiga datapunkter som genereras av sådana enheter. För det andra är det att utvärdera om kunskapen från tillgängliga / kända sensorer och apparater kan överföras till andra sensorer på liknande enheter. Detta skulle göra det möjligt att utvärdera beteendet hos nya apparater så snart de slås på första gången, snarare än efter att tillräcklig information från dem har samlats in. Detta projekt använder tidsseriedata från tre apparater: tvättmaskin, tvättmaskin och torktumlare och kylskåp. För dessa utvecklas och testas två lösningar: en för kategoriska variabler och en annan för numeriska variabler. De kategoriska variablerna analyseras med två metoder: Average Value Frequency och den rena frekvensen för tillståndsövergång. På grund av det begränsade antalet möjliga tillstånd visar sig den rena frekvensen vara den bättre lösningen, och kunskapen som erhålls överförs från källanordningen till målet, med måttlig framgång. De numeriska variablerna analyseras med hjälp av en One-class Support Vector Machine-pipeline, med mycket lovande resultat. Vidare utvecklas inlärnings- och glömningsmekanismer för att möjliggöra för rörledningarna att anpassa sig till förändringar i apparatens beteendemönster. Detta inkluderar en sönderfallningsfunktion för den numeriska variabellösningen. Intressant är att de olika vikterna för källan och målet har liten eller ingen inverkan på kvaliteten på klassificeringen.

This work proposes a new approach to fast detection of abnormal behaviour of cooling, IT, and power distribution systems in micro data centers based on machine learning techniques. Conventional protection of micro data centers focuses on monitoring individual parameters such as temperature at different locations and when these parameters reach certain high values, then an alarm will be triggered. This research employs machine learning techniques to extract normal and abnormal behaviour of the cooling and IT systems. Developed data acquisition system together with unsupervised learning methods quickly learns the physical dynamics of normal operation and can detect deviations from such behaviours. This provides an efficient way for not only producing health index for the micro data center, but also a rich label logging system that will be used for the supervised learning methods. The effectiveness of the proposed detection technique is evaluated on an micro data center placed at Computing Infrastructure Research Center (CIRC) in McMaster Innovation Park (MIP), McMaster University. / Thesis / Master of Science (MSc)

Master of Science / There has been an astronomical increase in data at the network edge due to the rapid development of 5G infrastructure and the proliferation of the Internet of Things (IoT). In order to improve the network controller's decision-making capabilities and improve the user experience, it is of paramount importance to properly analyze this data. However, transporting such a large amount of data from edge devices to the network controller requires large bandwidth and increased latency, presenting a significant challenge to resource-constrained wireless networks. By using information processing techniques, one could effectively address this problem by sending only pertinent and critical information to the network controller. Nevertheless, finding critical information from high-dimensional observation is not an easy task, especially when large amounts of background information are present. Our thesis proposes to extract critical but low-dimensional information from high-dimensional observations using an information-theoretic deep learning framework. We focus on two distinct problems where critical information extraction is imperative. In the first problem, we study the problem of feature extraction from video frames collected in a dynamic environment and showcase its effectiveness using a video game simulation experiment. In the second problem, we investigate the detection of anomaly signals in the spectrum by extracting and analyzing useful features from spectrograms. Using extensive simulation experiments based on a practical data set, we conclude that our proposed approach is highly effective in detecting anomaly signals in a wide range of signal-to-noise ratios.

In the hope to increase the detection rate of faults in combined heat and power plant boilers thus lowering unplanned maintenance three machine learning models are constructed and evaluated. The algorithms; k-Nearest Neighbor, One-Class Support Vector Machine, and Auto-encoder have a proven track record in research for anomaly detection, but are relatively unexplored for industrial applications such as this one due to the difficulty in collecting non-artificial labeled data in the field.The baseline versions of the k-Nearest Neighbor and Auto-encoder performed very similarly. Nevertheless, the Auto-encoder was slightly better and reached an area under the precision-recall curve (AUPRC) of 0.966 and 0.615 on the trainingand test period, respectively. However, no sufficiently good results were reached with the One-Class Support Vector Machine. The Auto-encoder was made more sophisticated to see how much performance could be increased. It was found that the AUPRC could be increased to 0.987 and 0.801 on the trainingand test period, respectively. Additionally, the model was able to detect and generate one alarm for each incident period that occurred under the test period.The conclusion is that ML can successfully be utilized to detect faults at an earlier stage and potentially circumvent otherwise costly unplanned maintenance. Nevertheless, there is still a lot of room for improvements in the model and the collection of the data. / I hopp om att öka identifieringsgraden av störningar i kraftvärmepannor och därigenom minska oplanerat underhåll konstrueras och evalueras tre maskininlärningsmodeller.Algoritmerna; k-Nearest Neighbor, One-Class Support Vector Machine, och Autoencoder har bevisad framgång inom forskning av anomalidetektion, men är relativt outforskade för industriella applikationer som denna på grund av svårigheten att samla in icke-artificiell uppmärkt data inom området.Grundversionerna av k-Nearest Neighbor och Auto-encoder presterade nästan likvärdigt. Dock var Auto-encoder-modellen lite bättre och nådde ett AUPRC-värde av 0.966 respektive 0.615 på träningsoch testperioden. Inget tillräckligt bra resultat nåddes med One-Class Support Vector Machine. Auto-encoder-modellen gjordes mer sofistikerad för att se hur mycket prestandan kunde ökas. Det visade sig att AUPRC-värdet kunde ökas till 0.987 respektive 0.801 under träningsoch testperioden. Dessutom lyckades modellen identifiera och generera ett larm vardera för alla incidenter under testperioden. Slutsatsen är att ML framgångsrikt kan användas för att identifiera störningar iett tidigare skede och därigenom potentiellt kringgå i annat fall dyra oplanerade underhåll. Emellertid finns det fortfarande mycket utrymme för förbättringar av modellen samt inom insamlingen av data.

In the manufacturing industry, predictive maintenance (PdM) stands out by leveraging data analytics and IoT technologies to predict machine failures, offering a significant advancement over traditional reactive and scheduled maintenance practices. The aim of this thesis was to examine how anomaly detection algorithms could be utilized to anticipate potential breakdowns in manufacturing operations, while also investigating the feasibility and potential benefits of integrating PdM strategies into a production line. The methodology of this projectconsisted of a literature review, application of machine learning (ML) algorithms, and conducting interviews. Firstly, the literature review provided a foundational basis to explore the benefits of PdM and its impact on production line productivity, thereby shaping the development of interview questions. Secondly, ML algorithms were employed to analyze data and predict equipment failures. The algorithms used in this project were: Isolation Forest (IF), Local Outlier Factor (LOF), Logistic Regression (LR), One-Class Support Vector Machine(OC-SVM) and Random Forest (RF). Lastly, interviews with production line personnel provided qualitative insights into the current maintenance practices and perceptions of PdM. The findings from this project underscore the efficacy of the IF model in identifying potential equipment failures, emphasizing its key role in improving future PdM strategies to enhance maintenance schedules and boost operational efficiency. Insights gained from both literature and interviews underscore the transformative potential of PdM in refining maintenance strategies, enhancing operational efficiency, and minimizing unplanned downtime. More broadly, the successful implementation of these technologies is expected to revolutionize manufacturing processes, driving towards more sustainable and efficient industrial operations. / I tillverkningsindustrin utmärker sig prediktivt underhåll (PdM) genom att använda dataanalys och IoT-teknologier för att förutse maskinfel, vilket erbjuder ett betydande framsteg jämfört med traditionella reaktiva och schemalagda underhållsstrategier. Syftet med denna avhandling var att undersöka hur algoritmer för avvikelsedetektering kunde användas för att förutse potentiella haverier i tillverkningsoperationer, samtidigt som genomförbarheten och de potentiella fördelarna med att integrera PdM-strategier i en produktionslinje undersöktes. Metodologin för detta projekt bestod av en litteraturöversikt, tillämpning av maskininlärningsalgoritmer (ML) och genomförande av intervjuer. Först och främst gav litteraturöversikten en grundläggande bas för att utforska fördelarna med PdM och dess inverkan på produktionslinjens produktivitet, vilket därmed påverkade utformningen av intervjufrågorna. För det andra användes ML-algoritmer för att analysera data och förutsäga utrustningsfel. Algoritmerna som användes i detta projekt var: Isolation Forest (IF), Local Outlier Factor (LOF), Logistic Regression (LR), One-Class Support Vector Machine (OCSVM) och Random Forest (RF). Slutligen gav intervjuer med produktionslinjepersonal kvalitativa insikter i de nuvarande underhållsstrategierna och uppfattningarna om PdM.Resultaten från detta projekt understryker effektiviteten hos IF-modellen för att identifiera potentiella utrustningsfel, vilket betonar dess centrala roll i att förbättra framtida PdM-strategier för att förbättra underhållsscheman och öka den operativa effektiviteten. Insikter vunna från både litteratur och intervjuer understryker PdM:s transformativa potential att finslipa underhållsstrategier, öka operativ effektivitet och minimera oplanerade driftstopp. Mer generellt förväntas den framgångsrika implementeringen av dessa teknologier revolutionera tillverkningsprocesser och driva mot mer hållbara och effektiva industriella operationer.

Rolling element bearings are a vital part in many rotating machinery, including vehicles. A defective bearing can be a symptom of other problems in the machinery and is due to a high failure rate. Early detection of bearing defects can therefore help to prevent malfunction which ultimately could lead to a total collapse. The thesis is done in collaboration with Scania that wants a better understanding of how external sensors such as accelerometers, can be used for condition monitoring in their gearboxes. Defective bearings creates vibrations with specific frequencies, known as Bearing Characteristic Frequencies, BCF [23]. A key component in the proposed method is based on identification and extraction of these frequencies from vibration signals from accelerometers mounted near the monitored bearing. Three solutions are proposed for automatic bearing fault detection. Two are based on data-driven classification using a set of machine learning methods called Support Vector Machines and one method using only the computed characteristic frequencies from the considered bearing faults. Two types of features are developed as inputs to the data-driven classifiers. One is based on the extracted amplitudes of the BCF and the other on statistical properties from Intrinsic Mode Functions generated by an improved Empirical Mode Decomposition algorithm. In order to enhance the diagnostic information in the vibration signals two pre-processing steps are proposed. Separation of the bearing signal from masking noise are done with the Cepstral Editing Procedure, which removes discrete frequencies from the raw vibration signal. Enhancement of the bearing signal is achieved by band pass filtering and amplitude demodulation. The frequency band is produced by the band selection algorithms Kurtogram and Autogram. The proposed methods are evaluated on two large public data sets considering bearing fault classification using accelerometer data, and a smaller data set collected from a Scania gearbox. The produced features achieved significant separation on the public and collected data. Manual detection of the induced defect on the outer race on the bearing from the gearbox was achieved. Due to the small amount of training data the automatic solutions were only tested on the public data sets. Isolation performance of correct bearing and fault mode among multiplebearings were investigated. One of the best trade offs achieved was 76.39 % fault detection rate with 8.33 % false alarm rate. Another was 54.86 % fault detection rate with 0 % false alarm rate.

Στο πρόβλημα της ταξινόμησης μιας κλάσης μία από τις κλάσεις, που ονομάζεται target κλάση, πρέπει να διαχωριστεί από όλα τα άλλα πιθανά αντικείμενα. Αυτά θεωρούνται σαν outliers (ή non-targets). Η ανάγκη για τη λύση ενός τέτοιου προβλήματος προκύπτει σε πολλές πρακτικές εφαρμογές, π.χ. στη μηχανική ανίχνευση λάθους, στην αναγνώριση προσώπου, στην επαλήθευση συγγραφικών δικαιωμάτων, στην αναγνώριση απάτης ή στη ταυτοποίηση ατόμου με βάση βιομετρικά δεδομένα. Στη συγκεκριμένη διπλωματική γίνεται ταξινόμηση μιας κλάσης ηλεκτροεγκεφαλικών σημάτων. Με αυτό τον τρόπο επιτυγχάνεται η ανίχνευση ενός πυραύλου μέσα σε δορυφορικές εικόνες, χρησιμοποιώντας τα ηλεκτροεγκεφαλικά σήματα ενός υποκειμένου το οποίο βλέπει δορυφορικές εικόνες σε μια LCD οθόνη. Για να γίνει η ταξινόμηση δημιουργήθηκε ένα σετ target και ένα σετ outlier αντικειμένων(δεδομένα).Τα target αντικείμενα είναι τα τμήματα από τα αρχικά ηλεκτροεγκεφαλικά σήματα τα οποία συνδέονται με την παρατήρηση πυραύλου μέσα σε μία δορυφορική εικόνα από το υποκείμενο, ενώ τα outlier αντικείμενα είναι άλλα τμήματα(ίδιου μεγέθους με τα target) των αρχικών ηλεκτροεγκεφαλικών σημάτων. Tα αντικείμενα μεταφέρονται σε ένα χώρο χαρακτηριστικών λιγότερων διαστάσεων από τον αρχικό τους χώρο, χρησιμοποιώντας τη γραμμική μέθοδο MCA (Minor Component Analysis). Για τη ταξινόμηση μιας κλάσης των αντικειμένων μελετώνται και χρησιμοποιούνται οι ταξινομητές MST_CD (Minimum Spanning Tree Class Descriptor), k-NNDD (k Nearest Neighbors Data Description) και SVDD (Support Vector Domain Description). Η εκπαίδευση των ταξινομητών αυτών γίνεται με ένα μικρό ποσοστό των target αντικειμένων (αντικείμενα εκπαίδευσης). Υπολογίζεται η απόδοση ταξινόμησης για κάθε έναν από αυτούς χρησιμοποιώντας τα υπόλοιπα target αντικείμενα μαζί με τα outlier αντικείμενα. Τέλος συγκρίνονται οι αποδόσεις και εξάγονται τα συμπεράσματα για τις υψηλές τιμές τους. Στο παράρτημα Α φαίνεται ο εκτελέσιμος στο matlab κώδικας με τον οποίο έγιναν όλα τα παραπάνω. Ο κώδικας γράφτηκε αποκλειστικά για τη συγκεκριμένη διπλωματική εργασία. / In the problem of one-class classification one of the classes, called the target class, has to be distinguished from all other possible objects. These are considered as outliers (or non-targets). The need for solving such a task arises in many practical applications, e.g. in fault detection, face recognition, authorship verification, fraud recognition or person identification based on biometric data. In this thesis a one-class classification of EEG (Electroencephalographic) data is being done. By this way, the detection of an air missile is achieved by using the EEG data of a subject, which is watching satellite images in a LCD monitor. For the classification a set of target and a set of outlier objects (data) were created. The target objects are parts of the original EEG data that are event-related with the detection of an air missile in a satellite image by the subject and the outlier objects are other parts (of the same size with target) of the original EEG data. The objects are mapped in a feature space of fewer dimensions than their original space, by using the linear method MCA (Minor Component Analysis). For the one-class classification of the objects, the classifiers that are studied and used are MST_CD (Minimum Spanning Tree Class Descriptor), k-NNDD (k Nearest Neighbors Data Description) and SVDD (Support Vector Domain Description). For the training of these classifiers a small percentage of target objects (training objects) are used. The performance of the classification is calculated for every classifier by using the rest target objects and the outlier objects. Finally the performances are compared and conclusions for their high values are made. In the appendix A there is the executable code in matlab which does all the above. The code created just for the purposes of this thesis.

Throughout the world, there is a great demand to map out the increasing environmental changes and life habitats on Earth. The vast majority of Earth Observations today, are collected using satellites. The Global Watch Center (GWC) initiative was started with the purpose of producing a global situational awareness of the premises for all life on Earth. By collecting, studying and analyzing vast amounts of data in an automatic, scalable and transparent way, the GWC aims are to work towards reaching the United Nations (UN) Sustainable Development Goals (SDG). The GWC vision is to make use of qualified accessible data together with leading organizations in order to lay the foundation of the important decisions that have the biggest potential to make an actual difference for the common awaited future. As a show-case for the initiative, the UN strategic department has recommended a specific use-case, involving mapping large accumulation of waste in areas greatly affected, which they believe will profit the initiative very much. This Master Thesis aim is, in an automatic and scalable way, to detect and classify dumpsites in Kampala, the capital of Uganda, by using available satellite imagery. The hopes are that showing technical feasibility and presenting interesting remarks will aid in spurring further interest in coming closer to a realization of the initiative. The technical approach is to use a lightweight version of Automatic Target Recognition. This is conventionally used in military applications but is here used, to detect and classify features of large accumulations of solid-waste by using techniques from the field of Image Analysis and Data Mining. Choice of data source, this study's area of interest as well as choice of methodology for Feature Extraction and choice of the Machine Learning algorithm Support Vector Machine will all be described and implemented. With a classification precision of 95 percent will technical results be presented, with the ambition to promote further work and contribute to the GWC initiative with valuable information for later realization.