Search

Malware detection is a problem that has become particularly challenging over the last decade. A common strategy for detecting malware is to scan network traffic for malicious connections between infected devices and their command and control (C&C) servers. However, malware developers are aware of this detection method and begin to incorporate new strategies to go unnoticed. In particular, they generate domain names instead of using static Internet Protocol addresses or regular domain names pointing to their C&C servers. By using a domain generation algorithm, the effectiveness of the blacklisting of domains is reduced, as the large number of domain names that must be blocked greatly increases the size of the blacklist. In this paper, we study different Long Short-Term Memory neural network hyperparameters to find the best network configuration for algorithmically generated domain name detection. In particular, we focus on determining whether the (complex) feature engineering efforts required when using other deep learning techniques, such as Random Forest, can be avoided. In this regard, we have conducted a comparative analysis to study the effect of using different network sizes and configurations on network performance metrics. Our results show an accuracy of 97.62% and an area under the receiver operating characteristic curve of 0.9956 in the test dataset, indicating that it is possible to obtain good classification results despite avoiding the feature engineering process and additional readjustments required in other machine learning techniques.

The objective of this work is to develop a prediction system for mortality risk based on ESCARVAL-RISK study, a large cardiovascular cohort (54,678 patients) with a follow-up starting in January 2008 through December 2012. The main challenge to face in this problem is the highly unbalanced classes that may lead to a poor performance in the classification, this work proposes a way to balance classes in order to circumvent that problem. Achieved results show that several factors emerged as the main factors of mortality in this population with a high cardiovascular (CV) risk, besides age and gender, treatments for hypertension, diabetes and dyslipidemia are the most relevant factors present in the cohort although the weight of each of them varies with the model. Despite the variation among the models, treatment for hypertension seems to be the most relevant factor. The presence of chronic kidney disease (CKD) defined by an estimated glomerular filtration rate

Adaptive filters are used in a wide range of applications such as noise cancellation, system identification, and prediction. One of the main problems for theses filters is the impulsive noise as it generates algorithm unstability. This work shows the development, simulation and hardware implementation of a new algorithm robust to impulsive noise. Hardware implementation becomes essential in many cases where a real time execution, reduced size, or low power system is needed. An efficient hardware architecture is proposed and different optimizations for size and speed are developed: no need for control state machine, reduced computation requirements due to simplifications, etc. Furthermore, two different implementations were done to test two simplified cost functions. Finally, comparison results are provided to test accuracy, performance and logic occupation, showing an efficient architecture for impulsive noise robustness.

Feature selection methods in machine learning models are a powerful tool to knowledge extraction. In this work they are used to analyse the intrinsic modifications of cardiac response during ventricular fibrillation due to physical exercise. The data used are two sets of registers from isolated rabbit hearts: control (G1: without physical training), and trained (G2). Four parameters were extracted (dominant frequency, normalized energy, regularity index and number of occurrences). From them, 18 features were extracted. This work analyses the relevance of each feature to classify the records in G1 and G2 using Logistic Regression, Multilayer Perceptron and Extreme Learning Machine. Three feature selection methods are presented: one based on the output variation, other on the classification results and, finally, another method based in the variation in ROC curve. Although we obtained different sorting of features for each used classifier, the features related to the mean value and standard deviation of dominant frequency and regularity index were the most relevant, stating that the modifications in VF response produced by physical exercise are related to the cardiac activation rate, as to the regularity of that activation.

The aim of this work is to study the applicability of reinforcement learning methods to design adaptive treatment strategies that optimize, in the long-term, the dosage of erythropoiesis-stimulating agents (ESAs) in the management of anemia in patients undergoing hemodialysis. Adaptive treatment strategies are recently emerging as a new paradigm for the treatment and long-term management of the chronic disease. Reinforcement Learning (RL) can be useful to extract such strategies from clinical data, taking into account delayed effects and without requiring any mathematical model. In this work, we focus on the so-called Fitted Q Iteration algorithm, a RL approach that deals with the data very efficiently. Achieved results show the suitability of the proposed RL policies that can improve the performance of the treatment followed in the clinics. The methodology can be easily extended to other problems of drug dosage optimization.

Clustering techniques have been widely applied to extract information from high-dimensional data structures in the last few years. Graphs are especially relevant for clustering, but many graphs associated with hierarchical clustering do not give any information about the values of the centroids' attributes and the relationships among them. In this paper, we propose a new visualization approach for hierarchical cluster analysis in which the above-mentioned information is available. The method is based on pie charts. The pie charts are divided into several pie segments or sectors corresponding to each cluster. The radius of each pie segment is proportional to the number of patterns included in each cluster. By means of new divisions in each pie sector and a color bar with as many labels as attributes, we can extract all the existing relationships among centroids' attributes at any hierarchy level. The methodology is tested in one synthetic data set and one real data set. Achieved results show the suitability and usefulness of the proposed approach.

We present a combination of two state-of-the-art machine learning methods for predicting mortality in patients with unstable angina (UA). Support vector machines (SVM) are used as non-linear discrimination tools. However, before building the models, selection of the best subset of variables is carried out with genetic algorithms (GA). The best subset of descriptors selected by the GA was constituted by five variables from the originally 75 collected The data was split into a training set (483 patients; 22 cases with UA) and a validation set (243 patients; 12 of cases with UA). The criterion used to select the best model was based on the sensitivity (SE), specificity (SP) and negative predictive values (NPV) in the validation data set. The final SVM model (RBF kernel) yielded good results (SE = 66.67%, SP = 79.77% in the validation set). The recognition rate was 79.12% and a high rate of NPV (97.87%) was obtained. Methods proposed have proven to be well-suited for this problem, simplifying the solution and providing excellent discrimination scores.

The objective of the present work has been to develop a collision detection algorithm suitable for real-time applications. It is applicable to box-shaped objects and it is based on the relation between the colliding object positions and the impact point. The most known neural network (multilayer perceptron) trained with the familiar backpropagation learning algorithm has been used for this problem; such algorithm models the collision, then decides the impact point and the direction of the forces. The algorithm results are very good for the case of box-shaped objects. Furthermore, the computational cost is independent from the object positions and the way the surfaces are modeled, so it is also suitable for real-time applications. The model is being used and validated in a real harbor crane simulator developed by the Robotics Institute for Valencia Harbor in Spain.