Jose Mata

With the increasing complexity of cyber-physical systems, combined with the potential risk of cyber-attacks, the possibility of having reliable anomaly detection systems plays a significant role in every process, promoting the scientific community’s efforts. Due to the remarkable importance of this kind of tool, a wide variety of approaches and techniques model the expected behavior of a system. An intuitive way to deal with this problem consists of determining the boundaries of the dataset. This document presents a novel procedure to speed up an existing anomaly detection technique based on non-convex boundaries.

Robust road surface estimation is required for autonomous ground vehicles to navigate safely. Despite it becoming one of the main targets for autonomous mobility researchers in recent years, it is still an open problem in which cameras and LiDAR sensors have demonstrated to be adequate to predict the position, size and shape of the road a vehicle is driving on in different environments. In this work, a novel Convolutional Neural Network model is proposed for the accurate estimation of the roadway surface. Furthermore, an ablation study has been conducted to investigate how different encoding strategies affect model performance, testing 6 slightly different neural network architectures. Our model is based on the use of a Twin Encoder–Decoder Neural Network (TEDNet) for independent camera and LiDAR feature extraction and has been trained and evaluated on the Kitti–Road dataset. Bird’s Eye View projections of the camera and LiDAR data are used in this model to perform semantic segmentation on whether each pixel belongs to the road surface. The proposed method performs among other state-of-the-art methods and operates at the same frame rate as the LiDAR and cameras, so it is adequate for its use in real-time applications.

The Internet of Things (IoT) presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT systems. This study addresses these challenges by exploring efficient data reduction techniques within a model-based intrusion detection system (IDS) for IoT environments. Specifically, the study explores the efficacy of an autoencoder’s latent space combined with three different classification techniques. Utilizing a validated IoT dataset, particularly focusing on the Constrained Application Protocol (CoAP), the study seeks to develop a robust model capable of identifying security breaches targeting this protocol. The research culminates in a comprehensive evaluation, presenting encouraging results that demonstrate the effectiveness of the proposed methodologies in strengthening IoT cybersecurity with more than a 99% of precision using only 2 learned features.

The large number of sensors and actuators that make up the Internet of Things obliges these systems to use diverse technologies and protocols. This means that IoT networks are more heterogeneous than traditional networks. This gives rise to new challenges in cybersecurity to protect these systems and devices which are characterized by being connected continuously to the Internet. Intrusion detection systems are used to protect IoT systems from the various anomalies and attacks at the network level. Intrusion Detection Systems can be improved through machine learning techniques. Our work focuses on creating classification models that can feed an IDS using a dataset containing frames under attacks of an IoT system that uses the MQTT protocol. We have addressed two types of method for classifying the attacks, ensemble methods and deep learning models, more specifically recurrent networks with very satisfactory results.

Batteries are a fundamental storage component due to its various applications in mobility, renewable energies and consumer electronics among others. Regardless of the battery typology, one key variable from a user’s perspective is the remaining energy in the battery. It is usually presented as the percentage of remaining energy compared to the total energy that can be stored and is labeled State Of Charge (SOC). This work addresses the development of a hybrid model based on a Lithium Iron Phosphate (LiFePO4) power cell, due to its broad implementation. The proposed model calculates the SOC, by means of voltage and electric current as inputs and the latter as the output. Therefore, four models based on k-Means, Agglomerative Clustering, Gaussian Mixture and Spectral Clustering techniques have been tested in order to obtain an optimal solution.

This paper aims to enhance security in IoT device networks through a visual tool that utilizes three projection techniques, including Beta Hebbian Learning (BHL), t-distributed Stochastic Neighbor Embedding (t-SNE) and ISOMAP, in order to facilitate the identification of network attacks by human experts. This work research begins with the creation of a testing environment with IoT devices and web clients, simulating attacks over Message Queuing Telemetry Transport (MQTT) for recording all relevant traffic information. The unsupervised algorithms chosen provide a set of projections that enable human experts to visually identify most attacks in real-time, making it a powerful tool that can be implemented in IoT environments easily.

We propose a task for eliciting attitudes toward risk that is close to real-world risky decisions which typically involve gains and losses. The task consists of accepting or rejecting gambles that provide a gain with probability p\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p$$\end{document} and a loss with probability 1-p\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1-p$$\end{document}. We employ finite mixture models to uncover heterogeneity in risk preferences and find that behavior is heterogeneous, with one half of the subjects behaving as expected utility maximizers, for the others, reference-dependent models perform better than those where subjects derive utility from final outcomes, models with sign-dependent decision weights perform better than those without, and there is no evidence for loss aversion. The procedure is sufficiently simple so that it can be easily used in field or lab experiments where risk elicitation is not the main experiment.

In a controlled laboratory experiment we use one sample of college students and one of mature executives to investigate how positive skew influences risky choices. In reduced-form regressions we find that both students and executives make riskier choices when lotteries display positive skew. We estimate decision models to explore three explanations for skew seeking choices: risk-loving, optimism and likelihood insensitivity. We find no role for love for risk as neither students nor executives have convex utility. Both optimism and likelihood insensitivity play a part in skew seeking choices. Likelihood insensitivity is larger for students than for executives. Executives have more concave utility and are more optimistic than students, but this is found to be largely due to them being older.