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.

Design and implementation of a Reinforcement Learning framework for iOS devices

Reinforcement Learning is an increasingly popular area of Artificial Intelligence. The applications of this learning paradigm are many, but its application in mobile computing is in its infancy. This study aims to provide an overview of current Reinforcement Learning applications on mobile devices, as well as to introduce a new framework for iOS devices: Swift-RL Lib. This new Swift package allows developers to easily support and integrate two of the most common RL algorithms, Q-Learning and Deep Q-Network, in a fully customizable environment. All processes are performed on the device, without any need for remote computation. The framework was tested in different settings and evaluated through several use cases. Through an in-depth performance analysis, we show that the platform provides effective and efficient support for Reinforcement Learning for mobile applications.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Fighting child marriage in developing countries: design and development of a mobile application

Child marriage is still a great issue in developing countries and even if the interventions to prevent it are having results, they are not enough to eliminate the problem. Among the strategies that seem to work most to fight child marriage, there is the empowerment of girls with information combined with education of parents and community. As smartphones are more accessible year after year in developing countries, this thesis wants to investigate if a mobile app could be effective in fighting child marriage and which characteristics such an app should have. The research was organized in four phases and used design and creation and case study methodologies. Firstly, the literature was analyzed and an initial design was proposed. Secondly, expert interviews were performed to gain feedback on the proposed design, and afterwards prototype was built. Thirdly, a case study in the Democratic Republic of Congo (DRC) was performed to test the prototype, gaining insights and improvements through group interviews with 26 girls aged 15-19. Finally, a first version of the app was developed and a second phase of the case study was run in the DRC to understand if the girls were able to use the app. This phase included 14 girls of which 6 had participated in the prototype testing and used questionnaires as a data generation method. The app was built following the Principles for Digital Development. Even if this app is built based on the case study in DRC is modular and easily adaptable to other contexts as it is not content-specific. It was shown that is worth continuing to study this topic and it was defined a conceptual framework for designing learning apps for developing countries, in particular, to fight child, early, and forced marriage.

Design of a wearable platform for PPG analysis with multicore low-power processor

Photoplethysmography (PPG) sensors allow for noninvasive and comfortable heart-rate (HR) monitoring, suitable for compact wearable devices. However, PPG signals collected from such devices often suffer from corruption caused by motion artifacts. This is typically addressed by combining the PPG signal with acceleration measurements from an inertial sensor. Recently, different energy-efficient deep learning approaches for heart rate estimation have been proposed. To test these new solutions, in this work, we developed a highly wearable platform (42mm x 48 mm x 1.2mm) for PPG signal acquisition and processing, based on GAP9, a parallel ultra low power system-on-chip featuring nine cores RISC-V compute cluster with neural network accelerator and 1 core RISC-V controller. The hardware platform also integrates a commercial complete Optical Biosensing Module and an ARM-Cortex M4 microcontroller unit (MCU) with Bluetooth low-energy connectivity. To demonstrate the capabilities of the system, a deep learning-based approach for PPG-based HR estimation has been deployed. Thanks to the reduced power consumption of the digital computational platform, the total power budget is just 2.67 mW providing up to 5 days of operation (105 mAh battery).

Synthetic data generation for the assessment of antimicrobial resistance through machine learning

As a consequence of the diffusion of next generation sequencing techniques, metagenomics databases have become one of the most promising repositories of information about features and behavior of microorganisms. One of the subjects that can be studied from those data are bacteria populations. Next generation sequencing techniques allow to study the bacteria population within an environment by sampling genetic material directly from it, without the needing of culturing a similar population in vitro and observing its behavior. As a drawback, it is quite complex to extract information from those data and usually there is more than one way to do that; AMR is no exception. In this study we will discuss how the quantified AMR, which regards the genotype of the bacteria, can be related to the bacteria phenotype and its actual level of resistance against the specific substance. In order to have a quantitative information about bacteria genotype, we will evaluate the resistome from the read libraries, aligning them against CARD database. With those data, we will test various machine learning algorithms for predicting the bacteria phenotype. The samples that we exploit should resemble those that could be obtained from a natural context, but are actually produced by a read libraries simulation tool. In this way we are able to design the populations with bacteria of known genotype, so that we can relay on a secure ground truth for training and testing our algorithms.

Trajectory Planning in UAV-Aided Wireless Networks Via Reinforcement Learning

This thesis is focused on the design of a flexible, dynamic and innovative telecommunication's system for future 6G applications on vehicular communications. The system is based on the development of drones acting as mobile base stations in an urban scenario to cope with the increasing traffic demand and avoid network's congestion conditions. In particular, the exploitation of Reinforcement Learning algorithms is used to let the drone learn autonomously how to behave in a scenario full of obstacles with the goal of tracking and serve the maximum number of moving vehicles, by at the same time, minimizing the energy consumed to perform its tasks. This project is an extraordinary opportunity to open the doors to a new way of applying and develop telecommunications in an urban scenario by mixing it to the rising world of the Artificial Intelligence.

Machine Learning in Automatic Tabulation for Constraint Model Reformulation

Combinatorial decision and optimization problems belong to numerous applications, such as logistics and scheduling, and can be solved with various approaches. Boolean Satisfiability and Constraint Programming solvers are some of the most used ones and their performance is significantly influenced by the model chosen to represent a given problem. This has led to the study of model reformulation methods, one of which is tabulation, that consists in rewriting the expression of a constraint in terms of a table constraint. To apply it, one should identify which constraints can help and which can hinder the solving process. So far this has been performed by hand, for example in MiniZinc, or automatically with manually designed heuristics, in Savile Row. Though, it has been shown that the performances of these heuristics differ across problems and solvers, in some cases helping and in others hindering the solving procedure. However, recent works in the field of combinatorial optimization have shown that Machine Learning (ML) can be increasingly useful in the model reformulation steps. This thesis aims to design a ML approach to identify the instances for which Savile Row’s heuristics should be activated. Additionally, it is possible that the heuristics miss some good tabulation opportunities, so we perform an exploratory analysis for the creation of a ML classifier able to predict whether or not a constraint should be tabulated. The results reached towards the first goal show that a random forest classifier leads to an increase in the performances of 4 different solvers. The experimental results in the second task show that a ML approach could improve the performance of a solver for some problem classes.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.