Speech signal is being used in the meaning of nonlinear dynamic system. As such, it is transform to multidimensional phase space, where filtration method based on time series neighbors of analysed signal is used. For embedding phase space methods time delay and false nearest neighbors are applied.

The thesis investigates APT attacks, which are professional targeted attacks that are characterised by long-term duration and use of advanced techniques. The thesis summarises current knowledge about APT attacks and suggests seven symptoms that can be used to check, whether an organization is under an APT attack. Thesis suggests a system for detection of APT attacks based on interaction of those symptoms. This system is elaborated further for detection of attacks in computer networks, where it uses user behaviour modelling for anomaly detection. The detector uses k-nearest neighbors (k-NN) method. The APT attack recognition ability in network environment is verified by implementing and testing this detector.

This project is dedicated to the problem of vehicle classification using inductive loop sensors. We created the dataset that contains more than 11000 labeled inductive loop signatures collected at different times and from different parts of the world. Multiple classification methods and their optimizations were employed to the vehicle classification. Final model that combines K-nearest neighbors and logistic regression achieves 94\% accuracy on classification scheme with 9 classes. The vehicle classifier was implemented in C++.

Cette thèse étudie deux tâches fondamentales d'apprentissage non supervisé: la recherche des plus proches voisins et le clustering de données massives en grande dimension pour respecter d'importantes contraintes de temps et d'espace.Tout d'abord, un nouveau cadre théorique permet de réduire le coût spatial et d'augmenter le débit de traitement du Cross-polytope LSH pour la recherche du plus proche voisin presque sans aucune perte de précision.Ensuite, une méthode est conçue pour apprendre en une seule passe sur des données en grande dimension des codes compacts binaires. En plus de garanties théoriques, la qualité des sketches obtenus est mesurée dans le cadre de la recherche approximative des plus proches voisins. Puis, un algorithme de clustering sans paramètre et efficace en terme de coût de stockage est développé en s'appuyant sur l'extraction d'un arbre couvrant minimum approché du graphe de dissimilarité compressé auquel des coupes bien choisies sont effectuées. / This thesis focuses on how to perform efficiently unsupervised machine learning such as the fundamentally linked nearest neighbor search and clustering task, under time and space constraints for high-dimensional datasets. First, a new theoretical framework reduces the space cost and increases the rate of flow of data-independent Cross-polytope LSH for the approximative nearest neighbor search with almost no loss of accuracy.Second, a novel streaming data-dependent method is designed to learn compact binary codes from high-dimensional data points in only one pass. Besides some theoretical guarantees, the quality of the obtained embeddings are accessed on the approximate nearest neighbors search task.Finally, a space-efficient parameter-free clustering algorithm is conceived, based on the recovery of an approximate Minimum Spanning Tree of the sketched data dissimilarity graph on which suitable cuts are performed.

With advancements in technology, the dimensions of transistors are scaling down. It leads to shrinkage in the size of memory bitcells, increasing its sensitivity to process variations introduced during manufacturing. Failure of a single bitcell can cause the failure of an entire memory; hence careful statistical analysis is essential in estimating the highest reliable performance of the bitcell before using them in memory design. With high repetitiveness of bitcell, the traditional method of Monte Carlo simulation would require along time for accurate estimation of rare failure events. A more practical approach is importance sampling where more samples are collected from the failure region. Even though importance sampling is much faster than Monte Carlo simulations, it is still fairly time-consuming as it demands an iterative search making it impractical for large simulation sets. This thesis proposes two machine learning models that can be used in estimating the performance of a bitcell. The first model predicts the time taken by the bitcell for read or write operation. The second model predicts the minimum voltage required in maintaining the bitcell stability. The models were trained using the K-nearest neighbors algorithm and Gaussian process regression. Three sparse approximations were implemented in the time prediction model as a bigger dataset was available. The obtained results show that the models trained using Gaussian process regression were able to provide promising results.

Tracking a moving object and reconstructing its trajectory can be done with a stereo camera system, since the two cameras enable depth vision. However, such a system would not work if one of the cameras fails to detect the object. If that happens, it would be beneficial if the system could still use the functioning camera to make an approximate trajectory reconstruction. In this study, I have investigated how past observations from a stereo system can be used to recreate trajectories when video from only one of the cameras is available. Several approaches have been implemented and tested, with varying results. The best method was found to be a nearest neighbors-search optimized by a Kalman filter. On a test set with 10000 golf shots, the algorithm was able to create estimations which on average differed around 3.5 meters from the correct trajectory, with better results for trajec-tories originating close to the camera. / Att spåra ett objekt i rörelse och rekonstruera dess bana kan göras med ett stereokamerasystem, eftersom de två kamerorna möjliggör djupseende. Ett sådant system skulle dock inte fungera om en av kamerorna misslyckas med att detektera objektet. Om det händer skulle det vara fördelaktigt om systemet ändå kunde använda den fungerande kameran för att göra en approximativ rekonstruktion av banan. I den här studien har jag undersökt hur tidigare observationer från ett stereosystem kan användas för att rekonstruera banor när video från enbart en av kamerorna är tillgänglig. Ett flertal metoder har implementerats och testats, med varierande resultat. Den bästa metoden visade sig vara en närmaste-grannar-sökning optimerad med ett Kalman-filter. På en testmängd bestående av 10000 golfslag kunde algoritmen skapa uppskattningar som i genomsnitt skiljde sig 3.5 meter från den korrekta banan, med bättre resultat för banor som startat nära kameran.

Machine learning is an area of computer science that only grows as time goes on, and there are applications in areas such as finance, biology, and computer vision. Some common applications are stock price prediction, data analysis of DNA expressions, and optical character recognition. This thesis uses machine learning techniques to predict prices for different stocks and indices on the Swedish stock market. These techniques are then compared to see which performs best and why. To accomplish this, we used some of the most popular models with sets of historical stock and index data. Our best-performing models are linear regression and neural networks, this is because they are the best at handling the big spikes in price action that occur in certain cases. However, all models are affected by overfitting, indicating that feature selection and hyperparameter optimization could be improved.

Public transport is essential for both residents and city planners because of its environmentally and economically beneficial characteristics. During the past decade climatechange, coupled with fuel and energy crises have attracted significant attention toward public transportation. Increasing the demand for public transport on the one hand and its complexity on the other hand have made the optimum network design quite challenging for city planners. The ridership is affected by numerous variables and features like space and time. These fluctuations, coupled with inherent uncertaintiesdue to different travel behaviors, make this procedure challenging. Any demand and supply mismatching can result in great user dissatisfaction and waste of energy on the horizon. During the past years, due to recent technologies in recording and storing data and advances in data analysis techniques, finding patterns, and predicting ridership based on historical data have improved significantly. This study aims to develop forecasting models by regressing boardings toward population, time of day, month, and station. Using the available boarding dataset for blue bus line number 4 in Stockholm, Sweden, seven different machine learning algorithms were assessed for prediction: Multiple Linear Regression, Decision Tree, Random Forest, Bayesian Ridge Regression, Neural Networks, Support Vector Machines, K-Nearest Neighbors. The models were trained and tested on the dataset from 2012 to 2019, before the start of the pandemic. The best model, KNN, with an average R-squared of 0.65 in 10-fold cross-validation was accepted as the best model. This model is then used to predict reduced ridership during the pandemic in 2020 and 2021. The results showed a reduction of 48.93% in 2020 and 82.24% in 2021 for the studied bus line.

Background: Cloud computing’s rapid growth has highlighted the need for efficientresource allocation. While cloud platforms offer scalability and cost-effectiveness for a variety of applications, managing resources to match dynamic workloads remains a challenge. Auto-scaling, the dynamic allocation of resources in response to real-time demand and performance metrics, has emerged as a solution. Traditional rule-based methods struggle with the increasing complexity of cloud applications. Machine Learning models offer promising accuracy by learning from performance metrics and adapting resource allocations accordingly.  Objectives: This thesis addresses the topic of cloud environments auto-scaling recommendations emphasizing the integration of Machine Learning models and significant application metrics. Its primary objectives are determining the critical metrics for accurate recommendations and evaluating the best recommendation techniques for auto-scaling. Methods: The study initially identifies the crucial metrics—like CPU usage and memory consumption that have a substantial impact on auto-scaling selections through thorough experimentation and analysis. Machine Learning(ML) techniques are selected based on literature review, and then further evaluated through thorough experimentation and analysis. These findings establish a foundation for the subsequent evaluation of ML techniques for auto-scaling recommendations. Results: The performance of Random Forests (RF), K-Nearest Neighbors (KNN), and Support Vector Machines (SVM) are investigated in this research. The results show that RF have higher accuracy, precision, and recall which is consistent with the significance of the metrics which are identified earlier. Conclusions: This thesis enhances the understanding of auto-scaling recommendations by combining the findings from metric importance and recommendation technique performance. The findings show the complex interactions between metrics and recommendation methods, establishing the way for the development of adaptive auto-scaling systems that improve resource efficiency and application functionality.

No description available.