Los ciberdelincuentes están en constante desarrollo de nuevas técnicas para evadir las medidas de seguridad implementadas por expertos e investigadores, lo que permite que el malware evolucione rápidamente. Además, detectar malware en varios sistemas es un desafío debido a que cada entorno informático tiene sus propias características únicas. Las técnicas tradicionales, como la detección de malware basada en firmas, han perdido efectividad y han sido en gran medida reemplazadas por enfoques más modernos, que incluyen el ML y la detección de amenazas basada en el comportamiento robusto en múltiples plataformas. Los investigadores aplican estas técnicas a diversas fuentes de datos, como el tráfico de red, binarios y datos de comportamiento, para extraer características relevantes y alimentar modelos que permiten hacer predicciones precisas. El objetivo de esta investigación es proporcionar un nuevo conjunto de datos compuesto por una cantidad sustancial de muestras de alta calidad basadas en el comportamiento del software. Debido a la falta de un formato de representación estándar para el comportamiento del malware en la investigación actual, también presentamos un método innovador para representar el comportamiento del malware, convirtiendo las llamadas a API en imágenes 2D. Además, proponemos y describimos la implementación de un nuevo modelo de ML basado en la clasificación binaria (malware o software benigno) utilizando el conjunto de datos novedoso mencionado anteriormente, lo que establece una base para su evaluación. Hemos realizado experimentos exhaustivos, validando el modelo propuesto tanto con el conjunto de datos propuesto como con datos del mundo real. En términos de métricas, este supera a un modelo conocido que también se basa en el análisis del comportamiento y tiene una arquitectura similar.

The proposed study develops a framework that can accurately capture and model input and output variables for multidisciplinary systems to mitigate the computational cost when uncertainties are involved. The dimension of the random input variables is reduced depending on the degree of correlation calculated by relative entropy. Feature extraction methods; namely Principal Component Analysis (PCA), the Auto-Encoder (AE) algorithm are developed when the input variables are highly correlated. The Independent Features Test (IndFeaT) is implemented as the feature selection method if the correlation is low to select a critical subset of model features. Moreover, Artificial Neural Network (ANN) including Probabilistic Neural Network (PNN) is integrated into the framework to correctly capture the complex response behavior of the multidisciplinary system with low computational cost. The efficacy of the proposed method is demonstrated with electro-mechanical engineering examples including a solder joint and stretchable patch antenna examples.

Fantastic progress has been made within the field of machine learning and deep neural networks in the last decade. Deep convolutional neural networks (CNN) have been hugely successful in imageclassification and object detection. These networks can automate many processes in the industries and increase efficiency. One of these processes is image classification implementing various CNN-models. This thesis addressed two different approaches for solving the same problem. The first approach implemented two CNN-models to classify images. The large pre-trained VGG-model was retrained using so-called transfer learning and trained only the top layers of the network. The other model was a smaller one with customized layers. The trained models are an end-to-end solution. The input is an image, and the output is a class score. The second strategy implemented several classical image processing algorithms to detect the individual defects existed in the pictures. This method worked as a ruled based object detection algorithm. Canny edge detection algorithm, combined with two mathematical morphology concepts, made the backbone of this strategy. Sandvik Coromant operators gathered approximately 1000 microscopical images used in this thesis. Sandvik Coromant is a leading producer of high-quality metal cutting tools. During the manufacturing process occurs some unwanted defects in the products. These defects are analyzed by taking images with a conventional microscopic of 100 and 1000 zooming capability. The three essential defects investigated in this thesis defined as Por, Macro and Slits. Experiments conducted during this thesis show that CNN-models is a good approach to classify impurities and defects in the metal industry, the potential is high. The validation accuracy reached circa 90 percentage, and the final evaluation accuracy was around 95 percentage , which is an acceptable result. The pretrained VGG-model reached a much higher accuracy than the customized model. The Canny edge detection algorithm combined dilation and erosion and contour detection produced a good result. It detected the majority of the defects existed in the images.

Major advances in machine learning have made image recognition applications, with Artificial Neural Network, blossom over the recent years. The aim of this thesis was to find a solution to recognize digits from a number sequence on an ID tag, used to identify farm animals, with the help of image recognition. A Recurrent Convolutional Neural Network solution called PPNet was proposed and tested on a data set called Animal Identification Tags. A transfer learning method was also used to test if it could help PPNet generalize and better recognize digits. PPNet was then compared against Microsoft Azures own image recognition API, to determine how PPNet compares to a general solution. PPNet, while not performing as good, still managed to achieve competitive results to the Azure API.

Dialectal Arabic speech research suffers from the lack of labelled resources and standardised orthography. There are three main challenges in dialectal Arabic speech recognition: (i) finding labelled dialectal Arabic speech data, (ii) training robust dialectal speech recognition models from limited labelled data and (iii) evaluating speech recognition for dialects with no orthographic rules. This thesis is concerned with the following three contributions: Arabic Dialect Identification: We are mainly dealing with Arabic speech without prior knowledge of the spoken dialect. Arabic dialects could be sufficiently diverse to the extent that one can argue that they are different languages rather than dialects of the same language. We have two contributions: First, we use crowdsourcing to annotate a multi-dialectal speech corpus collected from Al Jazeera TV channel. We obtained utterance level dialect labels for 57 hours of high-quality consisting of four major varieties of dialectal Arabic (DA), comprised of Egyptian, Levantine, Gulf or Arabic peninsula, North African or Moroccan from almost 1,000 hours. Second, we build an Arabic dialect identification (ADI) system. We explored two main groups of features, namely acoustic features and linguistic features. For the linguistic features, we look at a wide range of features, addressing words, characters and phonemes. With respect to acoustic features, we look at raw features such as mel-frequency cepstral coefficients combined with shifted delta cepstra (MFCC-SDC), bottleneck features and the i-vector as a latent variable. We studied both generative and discriminative classifiers, in addition to deep learning approaches, namely deep neural network (DNN) and convolutional neural network (CNN). In our work, we propose Arabic as a five class dialect challenge comprising of the previously mentioned four dialects as well as modern standard Arabic. Arabic Speech Recognition: We introduce our effort in building Arabic automatic speech recognition (ASR) and we create an open research community to advance it. This section has two main goals: First, creating a framework for Arabic ASR that is publicly available for research. We address our effort in building two multi-genre broadcast (MGB) challenges. MGB-2 focuses on broadcast news using more than 1,200 hours of speech and 130M words of text collected from the broadcast domain. MGB-3, however, focuses on dialectal multi-genre data with limited non-orthographic speech collected from YouTube, with special attention paid to transfer learning. Second, building a robust Arabic ASR system and reporting a competitive word error rate (WER) to use it as a potential benchmark to advance the state of the art in Arabic ASR. Our overall system is a combination of five acoustic models (AM): unidirectional long short term memory (LSTM), bidirectional LSTM (BLSTM), time delay neural network (TDNN), TDNN layers along with LSTM layers (TDNN-LSTM) and finally TDNN layers followed by BLSTM layers (TDNN-BLSTM). The AM is trained using purely sequence trained neural networks lattice-free maximum mutual information (LFMMI). The generated lattices are rescored using a four-gram language model (LM) and a recurrent neural network with maximum entropy (RNNME) LM. Our official WER is 13%, which has the lowest WER reported on this task. Evaluation: The third part of the thesis addresses our effort in evaluating dialectal speech with no orthographic rules. Our methods learn from multiple transcribers and align the speech hypothesis to overcome the non-orthographic aspects. Our multi-reference WER (MR-WER) approach is similar to the BLEU score used in machine translation (MT). We have also automated this process by learning different spelling variants from Twitter data. We mine automatically from a huge collection of tweets in an unsupervised fashion to build more than 11M n-to-m lexical pairs, and we propose a new evaluation metric: dialectal WER (WERd). Finally, we tried to estimate the word error rate (e-WER) with no reference transcription using decoding and language features. We show that our word error rate estimation is robust for many scenarios with and without the decoding features.

Knowledge Graph is a rising topic in the field of Artificial Intelligence. As the current trend of knowledge representation, Knowledge graph research is utilizing the large knowledge base freely available on the internet. Knowledge graph also allows inspection, analysis, the reasoning of all knowledge in reality. To enable the ambitious idea of modeling the knowledge of the world, different theory and implementation emerges. Nowadays, we have the opportunity to use freely available information from Wikipedia and Wikidata. The thesis investigates and formulates a theory about learning from Knowledge Graph. The thesis researches probabilistic knowledge graph. It only focuses on a branch called latent feature models in learning probabilistic knowledge graph. These models aim to predict possible relationships of connected entities and relations. There are many models for such a task. The metrics and training process is detailed described and improved in the thesis work. The efficiency and correctness enable us to build a more complex model with confidence. The thesis also covers possible problems in finding and proposes future work.

Before a radiation treatment on a cancer patient can get accomplished the treatment planning system (TPS) needs to undergo a quality assurance (QA). The QA consists of a pre-treatment (PT-QA) on a synthetic phantom body. During the PT-QA, data is collected from the phantom detectors, a set of monitors (transmission detectors) and the angular state of the machine. The outcome of this thesis project is to investigate if it is possible to predict the radiation dose distribution on the phantom body based on the data from the transmission detectors and the angular state of the machine. The motive for this is that an accurate prediction model could remove the PT-QA from most of the patient treatments. Prediction difficulties lie in reducing the contaminated noise from the transmission detectors and correctly mapping the transmission data to the phantom. The task is solved by modeling an artificial neuron network (ANN), that uses a u-net architecture to reduce the noise and a novel model that maps the transmission values to the phantom based on the angular state. The results show a median relative dose deviation ~ 1%.

The new approach for sensor diagnostics is presented. The approach, Enhanced Autoassociative Neural Networks (E-AANN), adds enhancement to Autoassociative Neural Networks (AANN) developed by Kramer in 1992. This enhancement allows AANN to identify faulty sensors. E-AANN uses a secondary optimization process to identify and reconstruct sensor faults. Two common types of sensor faults are investigated, drift error and shift or offset error. In the case of drift error, the sensor error occurs gradually while in the case of shift error, the sensor error occurs abruptly. EAANN catches these error types. A chiller model provided synthetic data to test the diagnostic approach under various noise level conditions. The results show that sensor faults can be detected and corrected in noisy situations with the E-AANN method described. In high noisy situations (10% to 20% noise level), E-AANN performance degrades. E-AANN performance in simple dynamic systems was also investigated. The results show that in simple dynamic situations, E-AANN identifies faulty sensors.

Power quality has attracted considerable attentions from utilities and customers due to the popular uses of the sensitive electronic equipment. Harmonics, voltage swell, voltage sag, and power interruption could downgrade the service quality. Harmonic currents injected by non-linear loads throughout the network could degrade the quality of services to sensitive high-tech customers such as the science park of Xin-Zhu and Tai-Nan in Taiwan. In recent years, massive rapid transit system (MRT) and high speed railway (HSR) have been rapidly developed, with the applications of wide-spread semi-conductor technologies in the auto-traction system. Swell and sag could occur from thundering, capacitor switching, motor starting, nearby circuit faults, or artificial calamity, and could also attribute to the power interruption. To ensure the power quality, harmonic and voltage disturbances detection becomes important. Fourier transformation is used to analyze distorted waves in the frequency domain, with low-pass filter used to eliminate the fundamental component, and then characteristic harmonics can be detected. The complicated process is difficult to operate in real-time. The method-based processing model with physical harmonic data is needed to simplify the processing architecture. The thesis proposes to use wavelet transformation (WT) and probabilistic neural network (PNN) for power quality and characteristic harmonics detection. Wavelet-probabilistic network (WPN) is first used to extract distorted waves. PNN based processing model will then analyze the harmonic components. Computer simulation shows a simplified model to shorten the processing time in this study.

The paper proposes a model of detection for voltages and harmonics using wavelet-probabilistic network (WPN). WPN is a two-layer structure, containing the wavelet layer and probabilistic network. It uses the wavelet transformation (WT) and probabilistic neural network (PNN) to analyze distorted waves and classify tasks. In this thesis, the field programmable gate array (FPGA) is employed for the hardware realization of WPN. In the implementation process, by the use of the hardware description language, the WPN algorithm has been embedded into the FPGA chip. Firstly, we divide the mathematical formula of basic WPN algorithm into several parts in order to set up each module individually, then we integrate all modules to complete the design of basic WPN algorithm with digital circuits by the bottom-up process.