Cognitive Assessment System (CAS): Psychometric studies with Portuguese children from 7 to 15 years.

The Cognitive Assessment System (CAS) is a new measure of cognitive abilities based on the Planning, Attention, Simultaneous and Successive (PASS) Theory. This theory is derived from research in neuropsychological and cognitive Psychology with particular emphasis on the work of Luria (1973). According to Naglieri (1999) and Naglieri and Das (1997), the PASS cognitive processes are the basic building blocks of human intellectual functioning. Planning processes provide cognitive control, utilization of processes and knowledge, intentionality, and self-regulation to achieve a desired goal; Attention processes provide focused, selective cognitive activity and resistance to distraction; and, Simultaneous and Successive processes are the two forms of operating on information. The PASS theory has had a strong empirical base prior to the publication of the CAS (see Das, Naglieri & Kirby, 1994), and its research foundation remains strong (see Naglieri, 1999; Naglieri & Das, 1997). The four basic psychological processes can be used to (1) gain an understanding of how well a child thinks; (2) discover the child’s strengths and needs, which can then be used for effective differential diagnosis; (3) conduct fair assessment; and (4) select or design appropriate interventions. Compared to the traditional intelligence tests, including IQ tests, the Cognitive Assessment System (CAS) has the great advantage of relying on a modern theory of cognitive functioning, linking theory with practice.

Machine Learning Unsupervised Methods in the Design of an On-board Health Monitoring System for Satellite Applications

The dissertation starts by providing a description of the phenomena related to the increasing importance recently acquired by satellite applications. The spread of such technology comes with implications, such as an increase in maintenance cost, from which derives the interest in developing advanced techniques that favor an augmented autonomy of spacecrafts in health monitoring. Machine learning techniques are widely employed to lay a foundation for effective systems specialized in fault detection by examining telemetry data. Telemetry consists of a considerable amount of information; therefore, the adopted algorithms must be able to handle multivariate data while facing the limitations imposed by on-board hardware features. In the framework of outlier detection, the dissertation addresses the topic of unsupervised machine learning methods. In the unsupervised scenario, lack of prior knowledge of the data behavior is assumed. In the specific, two models are brought to attention, namely Local Outlier Factor and One-Class Support Vector Machines. Their performances are compared in terms of both the achieved prediction accuracy and the equivalent computational cost. Both models are trained and tested upon the same sets of time series data in a variety of settings, finalized at gaining insights on the effect of the increase in dimensionality. The obtained results allow to claim that both models, combined with a proper tuning of their characteristic parameters, successfully comply with the role of outlier detectors in multivariate time series data. Nevertheless, under this specific context, Local Outlier Factor results to be outperforming One-Class SVM, in that it proves to be more stable over a wider range of input parameter values. This property is especially valuable in unsupervised learning since it suggests that the model is keen to adapting to unforeseen patterns.

On the role of Computational Logic in Data Science: representing, learning, reasoning, and explaining knowledge

In this thesis we discuss in what ways computational logic (CL) and data science (DS) can jointly contribute to the management of knowledge within the scope of modern and future artificial intelligence (AI), and how technically-sound software technologies can be realised along the path. An agent-oriented mindset permeates the whole discussion, by stressing pivotal role of autonomous agents in exploiting both means to reach higher degrees of intelligence. Accordingly, the goals of this thesis are manifold. First, we elicit the analogies and differences among CL and DS, hence looking for possible synergies and complementarities along 4 major knowledge-related dimensions, namely representation, acquisition (a.k.a. learning), inference (a.k.a. reasoning), and explanation. In this regard, we propose a conceptual framework through which bridges these disciplines can be described and designed. We then survey the current state of the art of AI technologies, w.r.t. their capability to support bridging CL and DS in practice. After detecting lacks and opportunities, we propose the notion of logic ecosystem as the new conceptual, architectural, and technological solution supporting the incremental integration of symbolic and sub-symbolic AI. Finally, we discuss how our notion of logic ecosys- tem can be reified into actual software technology and extended towards many DS-related directions.

Data-stream driven Fuzzy-granular approaches for system maintenance

Intelligent systems are currently inherent to the society, supporting a synergistic human-machine collaboration. Beyond economical and climate factors, energy consumption is strongly affected by the performance of computing systems. The quality of software functioning may invalidate any improvement attempt. In addition, data-driven machine learning algorithms are the basis for human-centered applications, being their interpretability one of the most important features of computational systems. Software maintenance is a critical discipline to support automatic and life-long system operation. As most software registers its inner events by means of logs, log analysis is an approach to keep system operation. Logs are characterized as Big data assembled in large-flow streams, being unstructured, heterogeneous, imprecise, and uncertain. This thesis addresses fuzzy and neuro-granular methods to provide maintenance solutions applied to anomaly detection (AD) and log parsing (LP), dealing with data uncertainty, identifying ideal time periods for detailed software analyses. LP provides deeper semantics interpretation of the anomalous occurrences. The solutions evolve over time and are general-purpose, being highly applicable, scalable, and maintainable. Granular classification models, namely, Fuzzy set-Based evolving Model (FBeM), evolving Granular Neural Network (eGNN), and evolving Gaussian Fuzzy Classifier (eGFC), are compared considering the AD problem. The evolving Log Parsing (eLP) method is proposed to approach the automatic parsing applied to system logs. All the methods perform recursive mechanisms to create, update, merge, and delete information granules according with the data behavior. For the first time in the evolving intelligent systems literature, the proposed method, eLP, is able to process streams of words and sentences. Essentially, regarding to AD accuracy, FBeM achieved (85.64+-3.69)%; eGNN reached (96.17+-0.78)%; eGFC obtained (92.48+-1.21)%; and eLP reached (96.05+-1.04)%. Besides being competitive, eLP particularly generates a log grammar, and presents a higher level of model interpretability.

Design and testing of innovative, artificial intelligence-based techniques to model and control the combustion process and to reduce the Co2 emissions in modern, high-performance, gasoline direct injection engines

This work deals with the development of calibration procedures and control systems to improve the performance and efficiency of modern spark ignition turbocharged engines. The algorithms developed are used to optimize and manage the spark advance and the air-to-fuel ratio to control the knock and the exhaust gas temperature at the turbine inlet. The described work falls within the activity that the research group started in the previous years with the industrial partner Ferrari S.p.a. . The first chapter deals with the development of a control-oriented engine simulator based on a neural network approach, with which the main combustion indexes can be simulated. The second chapter deals with the development of a procedure to calibrate offline the spark advance and the air-to-fuel ratio to run the engine under knock-limited conditions and with the maximum admissible exhaust gas temperature at the turbine inlet. This procedure is then converted into a model-based control system and validated with a Software in the Loop approach using the engine simulator developed in the first chapter. Finally, it is implemented in a rapid control prototyping hardware to manage the combustion in steady-state and transient operating conditions at the test bench. The third chapter deals with the study of an innovative and cheap sensor for the in-cylinder pressure measurement, which is a piezoelectric washer that can be installed between the spark plug and the engine head. The signal generated by this kind of sensor is studied, developing a specific algorithm to adjust the value of the knock index in real-time. Finally, with the engine simulator developed in the first chapter, it is demonstrated that the innovative sensor can be coupled with the control system described in the second chapter and that the performance obtained could be the same reachable with the standard in-cylinder pressure sensors.

Efficient and low-computational predictive models for spectral sensors

Spectral sensors are a wide class of devices that are extremely useful for detecting essential information of the environment and materials with high degree of selectivity. Recently, they have achieved high degrees of integration and low implementation cost to be suited for fast, small, and non-invasive monitoring systems. However, the useful information is hidden in spectra and it is difficult to decode. So, mathematical algorithms are needed to infer the value of the variables of interest from the acquired data. Between the different families of predictive modeling, Principal Component Analysis and the techniques stemmed from it can provide very good performances, as well as small computational and memory requirements. For these reasons, they allow the implementation of the prediction even in embedded and autonomous devices. In this thesis, I will present 4 practical applications of these algorithms to the prediction of different variables: moisture of soil, moisture of concrete, freshness of anchovies/sardines, and concentration of gasses. In all of these cases, the workflow will be the same. Initially, an acquisition campaign was performed to acquire both spectra and the variables of interest from samples. Then these data are used as input for the creation of the prediction models, to solve both classification and regression problems. From these models, an array of calibration coefficients is derived and used for the implementation of the prediction in an embedded system. The presented results will show that this workflow was successfully applied to very different scientific fields, obtaining autonomous and non-invasive devices able to predict the value of physical parameters of choice from new spectral acquisitions.

Computational methods applied to undeciphered scripts from the Aegean and Cyprus: Linear A and Cypro-Minoan

The study of ancient, undeciphered scripts presents unique challenges, that depend both on the nature of the problem and on the peculiarities of each writing system. In this thesis, I present two computational approaches that are tailored to two different tasks and writing systems. The first of these methods is aimed at the decipherment of the Linear A afraction signs, in order to discover their numerical values. This is achieved with a combination of constraint programming, ad-hoc metrics and paleographic considerations. The second main contribution of this thesis regards the creation of an unsupervised deep learning model which uses drawings of signs from ancient writing system to learn to distinguish different graphemes in the vector space. This system, which is based on techniques used in the field of computer vision, is adapted to the study of ancient writing systems by incorporating information about sequences in the model, mirroring what is often done in natural language processing. In order to develop this model, the Cypriot Greek Syllabary is used as a target, since this is a deciphered writing system. Finally, this unsupervised model is adapted to the undeciphered Cypro-Minoan and it is used to answer open questions about this script. In particular, by reconstructing multiple allographs that are not agreed upon by paleographers, it supports the idea that Cypro-Minoan is a single script and not a collection of three script like it was proposed in the literature. These results on two different tasks shows that computational methods can be applied to undeciphered scripts, despite the relatively low amount of available data, paving the way for further advancement in paleography using these methods.

Anticancer drug discovery using artificial intelligence: an application in pharmacological activity prediction

Hematological cancers are a heterogeneous family of diseases that can be divided into leukemias, lymphomas, and myelomas, often called “liquid tumors”. Since they cannot be surgically removable, chemotherapy represents the mainstay of their treatment. However, it still faces several challenges like drug resistance and low response rate, and the need for new anticancer agents is compelling. The drug discovery process is long-term, costly, and prone to high failure rates. With the rapid expansion of biological and chemical "big data", some computational techniques such as machine learning tools have been increasingly employed to speed up and economize the whole process. Machine learning algorithms can create complex models with the aim to determine the biological activity of compounds against several targets, based on their chemical properties. These models are defined as multi-target Quantitative Structure-Activity Relationship (mt-QSAR) and can be used to virtually screen small and large chemical libraries for the identification of new molecules with anticancer activity. The aim of my Ph.D. project was to employ machine learning techniques to build an mt-QSAR classification model for the prediction of cytotoxic drugs simultaneously active against 43 hematological cancer cell lines. For this purpose, first, I constructed a large and diversified dataset of molecules extracted from the ChEMBL database. Then, I compared the performance of different ML classification algorithms, until Random Forest was identified as the one returning the best predictions. Finally, I used different approaches to maximize the performance of the model, which achieved an accuracy of 88% by correctly classifying 93% of inactive molecules and 72% of active molecules in a validation set. This model was further applied to the virtual screening of a small dataset of molecules tested in our laboratory, where it showed 100% accuracy in correctly classifying all molecules. This result is confirmed by our previous in vitro experiments.

Computational modeling of human atrial cardiomyocytes: integration of electro-mechanical & mechano-electric feedback pathways

The cardiomyocytes are very complex consisting of many interlinked non-linear regulatory mechanisms between electrical excitation and mechanical contraction. Thus given a integrated electromechanically coupled system it becomes hard to understand the individual contributor of cardiac electrics and mechanics under both physiological and pathological conditions. Hence, to identify the causal relationship or to predict the responses in a integrated system the use of computational modeling can be beneficial. Computational modeling is a powerful tool that provides complete control of parameters along with the visibility of all the individual components of the integrated system. The advancement of computational power has made it possible to simulate the models in a short timeframe, providing the possibility of increased predictive power of the integrated system. My doctoral thesis is focused on the development of electromechanically integrated human atrial cardiomyocyte model with proper consideration of feedforward and feedback pathways.

6G enabled IoV scenarios with distributed intelligence mechanisms

The Internet of Vehicles (IoV) paradigm has emerged in recent times, where with the support of technologies like the Internet of Things and V2X , Vehicular Users (VUs) can access different services through internet connectivity. With the support of 6G technology, the IoV paradigm will evolve further and converge into a fully connected and intelligent vehicular system. However, this brings new challenges over dynamic and resource-constrained vehicular systems, and advanced solutions are demanded. This dissertation analyzes the future 6G enabled IoV systems demands, corresponding challenges, and provides various solutions to address them. The vehicular services and application requests demands proper data processing solutions with the support of distributed computing environments such as Vehicular Edge Computing (VEC). While analyzing the performance of VEC systems it is important to take into account the limited resources, coverage, and vehicular mobility into account. Recently, Non terrestrial Networks (NTN) have gained huge popularity for boosting the coverage and capacity of terrestrial wireless networks. Integrating such NTN facilities into the terrestrial VEC system can address the above mentioned challenges. Additionally, such integrated Terrestrial and Non-terrestrial networks (T-NTN) can also be considered to provide advanced intelligent solutions with the support of the edge intelligence paradigm. In this dissertation, we proposed an edge computing-enabled joint T-NTN-based vehicular system architecture to serve VUs. Next, we analyze the terrestrial VEC systems performance for VUs data processing problems and propose solutions to improve the performance in terms of latency and energy costs. Next, we extend the scenario toward the joint T-NTN system and address the problem of distributed data processing through ML-based solutions. We also proposed advanced distributed learning frameworks with the support of a joint T-NTN framework with edge computing facilities. In the end, proper conclusive remarks and several future directions are provided for the proposed solutions.

Computational investigation of a stereoselective synthesis of atropisomeric hydrazides possessing an N–N stereogenic axis

Axially chiral substrates are an interesting and widely studied class of compounds as they can be found in bioactive natural products and are employed as functional materials or as ligands in asymmetric catalytic processes. One branch of this family is the well-known world of the atropisomers. Among them, atropisomeric compounds possessing an N–N stereogenic axis are one truthfully fascinating system but not completely understood yet. In this thesis, we computationally investigated the mechanism of the diastereoselective formation of the N – N chiral axis of a hydrazide under asymmetric phase transfer catalytic conditions. Moreover, during this study, torsional barriers have been calculated for both the reagent and the product at the density functional theory (DFT). These values turned out to suitably match the experimental values and observations. Finally, Electronic Circular Dichroism (ECD) spectra have been simulated in order to assign the chiral absolute configuration to the products.

Robotics and neurodevelopmental disorder: design and implementation of a system of engagement metrics in human-robot interactions.

In the recent decades, robotics has become firmly embedded in areas such as education, teaching, medicine, psychology and many others. We focus here on social robotics; social robots are designed to interact with people in a natural and interpersonal way, often to achieve positive results in different applications. To interact and cooperate with humans in their daily-life activities, robots should exhibit human-like intelligence. The rapid expansion of social robotics and the existence of various kinds of robots on the market have allowed research groups to carry out multiple experiments. The experiments carried out have led to the collections of various kinds of data, which can be used or processed for psychological studies, and studies in other fields. However, there are no tools available in which data can be stored, processed and shared with other research groups. This thesis proposes the design and implementation of visual tool for organizing dataflows in Human Robot Interaction (HRI).

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.

Integrating an Emotion Recognition Model for the Flobi System

This thesis investigates if emotional states of users interacting with a virtual robot can be recognized reliably and if specific interaction strategy can change the users’ emotional state and affect users’ risk decision. For this investigation, the OpenFace [1] emotion recognition model was intended to be integrated into the Flobi [2] system, to allow the agent to be aware of the current emotional state of the user and to react appropriately. There was an open source ROS [3] bridge available online to integrate OpenFace to the Flobi simulation but it was not consistent with some other projects in Flobi distribution. Then due to technical reasons DeepFace was selected. In a human-agent interaction, the system is compared to a system without using emotion recognition. Evaluation could happen at different levels: evaluation of emotion recognition model, evaluation of the interaction strategy, and evaluation of effect of interaction on user decision. The results showed that the happy emotion induction was 58% and fear emotion induction 77% successful. Risk decision results show that: in happy induction after interaction 16.6% of participants switched to a lower risk decision and 75% of them did not change their decision and the remaining switched to a higher risk decision. In fear inducted participants 33.3% decreased risk 66.6 % did not change their decision The emotion recognition accuracy was and had bias to. The sensitivity and specificity is calculated for each emotion class. The emotion recognition model classifies happy emotions as neutral in most of the time.

Cyber threat intelligence: identifying hardcoded secrets in GitHub

The usage of version control systems and the capabilities of storing the source code in public platforms such as GitHub increased the number of passwords, API Keys and tokens that can be found and used causing a massive security issue for people and companies. In this project, SAP's secret scanner Credential Digger is presented. How it can scan repositories to detect hardcoded secrets and how it manages to filter out the false positives between them. Moreover, how I have implemented the Credential Digger's pre-commit hook. A performance comparison between three different implementations of the hook based on how it interacts with the Machine Learning model is presented. This project also includes how it is possible to use already detected credentials to decrease the number false positive by leveraging the similarity between leaks by using the Bucket System.