Abstract
Network security encloses a wide set of technologies dealing with intrusions detection. Despite the massive adoption of signature-based network intrusion detection systems (IDSs), they fail in detecting zero-day attacks and previously unseen vulnerabilities exploits. Behaviour-based network IDSs have been seen as a way to overcome signature-based IDS flaws, namely through the implementation of machine-learning-based methods, to tolerate new forms of normal network behaviour, and to identify yet unknown malicious activities. A wide set of machine learning methods has been applied to implement behaviour-based IDSs with promising results on detecting new forms of intrusions and attacks. Innovative machine learning techniques have emerged, namely deep-learning-based techniques, to process unstructured data, speed up the classification process, and improve the overall performance obtained by behaviour-based network intrusion detection systems. The use of realistic datasets of normal and malicious networking activities is crucial to benchmark machine learning models, as they should represent real-world networking scenarios and be based on realistic computers network activity. This paper aims to evaluate CSE-CIC-IDS2018 dataset and benchmark a set of deep-learning-based methods, namely convolutional neural networks (CNN) and long short-term memory (LSTM). Autoencoder and principal component analysis (PCA) methods were also applied to evaluate features reduction in the original dataset and its implications in the overall detection performance. The results revealed the appropriateness of using the CSE-CIC-IDS2018 dataset to benchmark supervised deep learning models. It was also possible to evaluate the robustness of using CNN and LSTM methods to detect unseen normal activity and variations of previously trained attacks. The results reveal that feature reduction methods decreased the processing time without loss of accuracy in the overall detection performance.

Abstract

Abstract
Breast cancer is currently one of the main causes of death and tumoral diseases in women. Even if early diagnosis processes have evolved in the last years thanks to the popularization of mammogram tests, nowadays, it is still a challenge to have available reliable diagnosis systems that are exempt of variability in their interpretation. To this end, in this work, the design and development of an intelligent clinical decision support system to be used in the preventive diagnosis of breast cancer is presented, aiming both to improve the accuracy in the evaluation and to reduce its uncertainty. Through the integration of expert systems (based on Mamdani-type fuzzy-logic inference engines) deployed in cascade, exploratory factorial analysis, data augmentation approaches, and classification algorithms such as k-neighbors and bagged trees, the system is able to learn and to interpret the patient's medical-healthcare data, generating an alert level associated to the danger she has of suffering from cancer. For the system's initial performance tests, a software implementation of it has been built that was used in the diagnosis of a series of patients contained into a 130-cases database provided by the School of Medicine and Public Health of the University of Wisconsin-Madison, which has been also used to create the knowledge base. The obtained results, characterized as areas under the ROC curves of 0.95-0.97 and high success rates, highlight the huge diagnosis and preventive potential of the developed system, and they allow forecasting, even when a detailed and contrasted validation is still pending, its relevance and applicability within the clinical field.

Abstract
One of the areas with the potential to be explored in quantum computing (QC) is machine learning (ML), giving rise to quantum machine learning (QML). In an era when there is so much data, ML may benefit from either speed, complexity or smaller amounts of storage. In this work, we explore a quantum approach to a machine learning problem. Based on the work of Mari et al., we train a set of hybrid classical-quantum neural networks using transfer learning (TL). Our task was to solve the problem of classifying full-image mammograms into malignant and benign, provided by BCDR. Throughout the course of our work, heatmaps were used to highlight the parts of the mammograms that were being targeted by the networks while evaluating different performance metrics. Our work shows that this method may hold benefits regarding the generalization of complex data; however, further tests are needed. We also show that, depending on the task, some architectures perform better than others. Nonetheless, our results were superior to those reported in the state-of-the-art (accuracy of 84% against 76.9%, respectively). In addition, experiments were conducted in a real quantum device, and results were compared with the classical and simulator.

Abstract
Convolutional Neural Networks (CNN) have been successfully applied to images, text and audio, but their performance are not so good when applied to feature-based tabular data. Exceptions are works such as TabNet and DeepInsight, which employ end-to-end approaches. In this work, we propose an alternative way of using CNNs to model tabular data where knowledge is extracted from the feature space before being introduced to the network. Our strategy, Map-Optimize-Learn (MOL), changes the shape representation of samples in order to produce suitable input data for the CNN architecture. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against baseline and state of the art Machine Learning (ML) algorithms for tabular datasets. Preliminary results suggest that the strategy has potential to improve prediction quality of tabular data over end-to-end CNN methods and classical ML methods.

Abstract
This research aims to extract knowledge of sensors behavior resorting to Bayesian networks (BNs) and dynamic Bayesian networks (DBNs), a time-based BN version. These two types of models belong to the group of probabilistic graphical models (PGMs). These graphical models can be very useful to get insights from data in order to improve sensor capabilities in the industry of fire detection systems, since it can provide the conditional dependence structure among various sensor variables. Relevant sensors with fire alerts were selected and studied at device level. We conduct a data fusion analysis since we deal with heterogeneous data sources, Remote Alert (RA) with sensor states and Condition Monitoring (CM) with numerical data. To achieve an accurate fusion of the data, a pipeline was designed to align both sources of data in a regular time interval. Furthermore, a change point detection (CPD) method was used to discretize the numerical variables. In addition, one-hot encoding was used to create binarized datasets and combine all data (RA+CM). Our modeling helps understanding the dependencies among the sensor variables, highlighting that individual devices of the same type can have a very different probabilistic behavior along the time, probably due to be installed in distinct regions. Moreover, the models helped capturing strange probabilistic sensor behavior such as a low probability of a NORMAL state happening given that states FIRE, WARNING and TROUBLE did not happen. © 2022 IEEE.