Interfaccia grafica per l'elaborazione di immagini microscopiche di colture batteriche geneticamente modificate

Le moderne tecniche di imaging e i recenti sviluppi nel campo della visione computazionale consentono sempre più diffusamente l'utilizzo di metodi di image analysis, specialmente in ambito medico e biologico, permettendo un maggiore supporto sia alla diagnosi, sia alla ricerca. Il lavoro svolto in questa tesi si pone in un contesto di ricerca di carattere interdisciplinare, e riguarda il progetto e la realizzazione di un‘interfaccia grafica per l'analisi di colture batteriche geneticamente modificate, marcate con proteine fluorescenti (GFP), acquisite tramite un microscopio ad epifluorescenza. Nota la funzione di risposta del sistema di acquisizione delle immagini, l'analisi quantitativa delle colture batteriche è effettuata mediante la misurazione di proprietà legate all'intensità della risposta al marcatore fluorescente. L'interfaccia consente un'analisi sia globale dei batteri individuati nell'immagine, sia di singoli gruppi di batteri selezionati dall'utente, fornendo utili informazioni statistiche, sia in forma grafica che numerica. Per la realizzazione dell'interfaccia sono state adottate tecniche di ingegneria del software, con particolare enfasi alla interazione uomo-macchina e seguendo criteri di usability, al fine di consentire un corretto utilizzo dello strumento anche da parte di personale senza conoscenza in campo informatico.

Progettazione ed Implementazione Front-End di un Sistema Integrato di Customer Assistance in ambito Industry 4.0

Al giorno d'oggi, l'industry 4.0 è un movimento sempre più prominente che induce ad equipaggiare gli impianti industriali con avanzate infrastrutture tecnologiche digitali, le quali operano sinergicamente con l'impianto, al fine di controllare ed aumentare la produttività, monitorare e prevenire i futuri guasti, ed altro ancora. In questo ambito, gli utenti sono parte integrante della struttura produttiva, in cui ricoprono ruoli strategici e flessibili, collaborano fra loro e con le macchine, con l’obiettivo di affrontare e risolvere proattivamente una vasta gamma di problemi complessi. In particolare, la customer assistance nel settore industriale può certamente variare in relazione a molteplici elementi: il tipo di produzione e le caratteristiche del prodotto; l'organizzazione ed infrastruttura aziendale interna; la quantità di risorse disponibili che possono essere impiegate; il grado di importanza ricoperto dalla customer assistance nel settore industriale di riferimento; altri eventuali fattori appartenenti ad un dominio specifico. Per queste ragioni, si è cercato di individuare e categorizzare nel modo più accurato possibile, il lavoro svolto in questo elaborato ed il contesto nel quale è stato sviluppato. In questa tesi, viene descritta un'applicazione web per erogare assistenza al cliente in ambito di industria 4.0, attraverso il paradigma di ticketing o ticket di supporto/assistenza. Questa applicazione è integrata nel sistema Mentor, il quale è attivo già da anni nel settore industriale 4.0. Il progetto Mentor è una suite di applicazioni cloud-based creata dal gruppo Bucci Industries, una multinazionale attiva nell'industria e nell'automazione con sede a Faenza. In questo caso di studio, si presenta la progettazione ed implementazione della parte front-end del suddetto sistema di assistenza, il quale è integrato ed interconnesso con un paio di applicazioni tipiche di industria 4.0, presenti nella stessa suite di applicazioni.

Task analysis for HMI design. Level of automation study of aircraft navigation functions

Advancements in technology have enabled increasingly sophisticated automation to be introduced into the flight decks of modern aircraft. Generally, this automation was added to accomplish worthy objectives such as reducing flight crew workload, adding additional capability, or increasing fuel economy. Automation is necessary due to the fact that not all of the functions required for mission accomplishment in today’s complex aircraft are within the capabilities of the unaided human operator, who lacks the sensory capacity to detect much of the information required for flight. To a large extent, these objectives have been achieved. Nevertheless, despite all the benefits from the increasing amounts of highly reliable automation, vulnerabilities do exist in flight crew management of automation and Situation Awareness (SA). Issues associated with flight crew management of automation include: • Pilot understanding of automation’s capabilities, limitations, modes, and operating principles and techniques. • Differing pilot decisions about the appropriate automation level to use or whether to turn automation on or off when they get into unusual or emergency situations. • Human-Machine Interfaces (HMIs) are not always easy to use, and this aspect could be problematic when pilots experience high workload situations. • Complex automation interfaces, large differences in automation philosophy and implementation among different aircraft types, and inadequate training also contribute to deficiencies in flight crew understanding of automation.

Motor Unit Spike Trains Recontruction from sEMG Signals for Gesture Classification on a Low-Power Processing Platform

Hand gesture recognition based on surface electromyography (sEMG) signals is a promising approach for the development of intuitive human-machine interfaces (HMIs) in domains such as robotics and prosthetics. The sEMG signal arises from the muscles' electrical activity, and can thus be used to recognize hand gestures. The decoding from sEMG signals to actual control signals is non-trivial; typically, control systems map sEMG patterns into a set of gestures using machine learning, failing to incorporate any physiological insight. This master thesis aims at developing a bio-inspired hand gesture recognition system based on neuromuscular spike extraction rather than on simple pattern recognition. The system relies on a decomposition algorithm based on independent component analysis (ICA) that decomposes the sEMG signal into its constituent motor unit spike trains, which are then forwarded to a machine learning classifier. Since ICA does not guarantee a consistent motor unit ordering across different sessions, 3 approaches are proposed: 2 ordering criteria based on firing rate and negative entropy, and a re-calibration approach that allows the decomposition model to retain information about previous sessions. Using a multilayer perceptron (MLP), the latter approach results in an accuracy up to 99.4% in a 1-subject, 1-degree of freedom scenario. Afterwards, the decomposition and classification pipeline for inference is parallelized and profiled on the PULP platform, achieving a latency < 50 ms and an energy consumption < 1 mJ. Both the classification models tested (a support vector machine and a lightweight MLP) yielded an accuracy > 92% in a 1-subject, 5-classes (4 gestures and rest) scenario. These results prove that the proposed system is suitable for real-time execution on embedded platforms and also capable of matching the accuracy of state-of-the-art approaches, while also giving some physiological insight on the neuromuscular spikes underlying the sEMG.

Analysis and development of interface components and procedures for the design and commissioning toolchains in automation systems

The objective of the thesis project, developed within the Line Control & Software Engineering team of G.D company, is to analyze and identify the appropriate tool to automate the HW configuration process using Beckhoff technologies by importing data from an ECAD tool. This would save a great deal of time, since the I/O topology created as part of the electrical planning is presently imported manually in the related SW project of the machine. Moreover, a manual import is more error-prone because of human mistake than an automatic configuration tool. First, an introduction about TwinCAT 3, EtherCAT and Automation Interface is provided; then, it is analyzed the official Beckhoff tool, XCAD Interface, and the requirements on the electrical planning to use it: the interface is realized by means of the AutomationML format. Finally, due to some limitations observed, the design and implementation of a company internal tool is performed. Tests and validation of the tool are performed on a sample production line of the company.

Neural Machine Translation in the Field of Law. Analysis and Evaluation against Human Reference of NMT Raw Outputs of an Atto Costitutivo of S.r.l. from Italian into German.

Artificial Intelligence (AI) is gaining ever more ground in every sphere of human life, to the point that it is now even used to pass sentences in courts. The use of AI in the field of Law is however deemed quite controversial, as it could provide more objectivity yet entail an abuse of power as well, given that bias in algorithms behind AI may cause lack of accuracy. As a product of AI, machine translation is being increasingly used in the field of Law too in order to translate laws, judgements, contracts, etc. between different languages and different legal systems. In the legal setting of Company Law, accuracy of the content and suitability of terminology play a crucial role within a translation task, as any addition or omission of content or mistranslation of terms could entail legal consequences for companies. The purpose of the present study is to first assess which neural machine translation system between DeepL and ModernMT produces a more suitable translation from Italian into German of the atto costitutivo of an Italian s.r.l. in terms of accuracy of the content and correctness of terminology, and then to assess which translation proves to be closer to a human reference translation. In order to achieve the above-mentioned aims, two human and automatic evaluations are carried out based on the MQM taxonomy and the BLEU metric. Results of both evaluations show an overall better performance delivered by ModernMT in terms of content accuracy, suitability of terminology, and closeness to a human translation. As emerged from the MQM-based evaluation, its accuracy and terminology errors account for just 8.43% (as opposed to DeepL’s 9.22%), while it obtains an overall BLEU score of 29.14 (against DeepL’s 27.02). The overall performances however show that machines still face barriers in overcoming semantic complexity, tackling polysemy, and choosing domain-specific terminology, which suggests that the discrepancy with human translation may still be remarkable.

MR spectroscopy in human prostate: in vitro and in vivo measurements to optimize new quantification algorithms

Il cancro della prostata (PCa) è il tumore maligno non-cutaneo più diffuso tra gli uomini ed è il secondo tumore che miete più vittime nei paesi occidentali. La necessità di nuove tecniche non invasive per la diagnosi precoce del PCa è aumentata negli anni. 1H-MRS (proton magnetic resonance spectroscopy) e 1H-MRSI (proton magnetic resonance spectroscopy imaging) sono tecniche avanzate di spettroscopia in risonanza magnetica che permettono di individuare presenza di metaboliti come citrato, colina, creatina e in alcuni casi poliammine in uno o più voxel nel tessuto prostatico. L’abbondanza o l’assenza di uno di questi metaboliti rende possibile discriminare un tessuto sano da uno patologico. Le tecniche di spettroscopia RM sono correntemente utilizzate nella pratica clinica per cervello e fegato, con l’utilizzo di software dedicati per l’analisi degli spettri. La quantificazione di metaboliti nella prostata invece può risultare difficile a causa del basso rapporto segnale/rumore (SNR) degli spettri e del forte accoppiamento-j del citrato. Lo scopo principale di questo lavoro è di proporre un software prototipo per la quantificazione automatica di citrato, colina e creatina nella prostata. Lo sviluppo del programma e dei suoi algoritmi è stato portato avanti all’interno dell’IRST (Istituto Romagnolo per lo Studio e la cura dei Tumori) con l’aiuto dell’unità di fisica sanitaria. Il cuore del programma è un algoritmo iterativo per il fit degli spettri che fa uso di simulazioni MRS sviluppate con il pacchetto di librerie GAMMA in C++. L’accuratezza delle quantificazioni è stata testata con dei fantocci realizzati all’interno dei laboratori dell’istituto. Tutte le misure spettroscopiche sono state eseguite con il nuovo scanner Philips Ingenia 3T, una delle machine di risonanza magnetica più avanzate per applicazioni cliniche. Infine, dopo aver eseguito i test in vitro sui fantocci, sono stati acquisiti gli spettri delle prostate di alcuni volontari sani, per testare se il programma fosse in grado di lavorare in condizioni di basso SNR.

Evoluzione delle user interface: dalla metafora del desktop al Wearable Computing

Negli ultimi decenni abbiamo assistito ad una graduale evoluzione delle interfacce utente e della tecnologia. Sono stati introdotti nuovi dispositivi mobile e wearable che negli ultimi anni hanno subito un incremento tecnologico esponenziale arrivando a fondersi con la vita di tutti i giorni. Le classiche interfacce grafiche WIMP, la metafora del desktop e le linee guida di progettazione fino ad ora sviluppate non risultano ideali per la nuova tecnologia di wearable computing. Il proposito che la tesi vuole andare ad affrontare è proprio quello di indagare lo sviluppo di nuove user inteface basate sulla tecnologia wearable ed in particolare per smart glasses.

Machine Learning methods for hepatocellular malignancies segmentation and MVI prediction

The aim of this thesis project is to automatically localize HCC tumors in the human liver and subsequently predict if the tumor will undergo microvascular infiltration (MVI), the initial stage of metastasis development. The input data for the work have been partially supplied by Sant'Orsola Hospital and partially downloaded from online medical databases. Two Unet models have been implemented for the automatic segmentation of the livers and the HCC malignancies within it. The segmentation models have been evaluated with the Intersection-over-Union and the Dice Coefficient metrics. The outcomes obtained for the liver automatic segmentation are quite good (IOU = 0.82; DC = 0.35); the outcomes obtained for the tumor automatic segmentation (IOU = 0.35; DC = 0.46) are, instead, affected by some limitations: it can be state that the algorithm is almost always able to detect the location of the tumor, but it tends to underestimate its dimensions. The purpose is to achieve the CT images of the HCC tumors, necessary for features extraction. The 14 Haralick features calculated from the 3D-GLCM, the 120 Radiomic features and the patients' clinical information are collected to build a dataset of 153 features. Now, the goal is to build a model able to discriminate, based on the features given, the tumors that will undergo MVI and those that will not. This task can be seen as a classification problem: each tumor needs to be classified either as “MVI positive” or “MVI negative”. Techniques for features selection are implemented to identify the most descriptive features for the problem at hand and then, a set of classification models are trained and compared. Among all, the models with the best performances (around 80-84% ± 8-15%) result to be the XGBoost Classifier, the SDG Classifier and the Logist Regression models (without penalization and with Lasso, Ridge or Elastic Net penalization).

Analysis and Evaluation of Tiny Machine Learning applications

The aim of TinyML is to bring the capability of Machine Learning to ultra-low-power devices, typically under a milliwatt, and with this it breaks the traditional power barrier that prevents the widely distributed machine intelligence. TinyML allows greater reactivity and privacy by conducting inference on the computer and near-sensor while avoiding the energy cost associated with wireless communication, which is far higher at this scale than that of computing. In addition, TinyML’s efficiency makes a class of smart, battery-powered, always-on applications that can revolutionize the collection and processing of data in real time. This emerging field, which is the end of a lot of innovation, is ready to speed up its growth in the coming years. In this thesis, we deploy three model on a microcontroller. For the model, datasets are retrieved from an online repository and are preprocessed as per our requirement. The model is then trained on the split of preprocessed data at its best to get the most accuracy out of it. Later the trained model is converted to C language to make it possible to deploy on the microcontroller. Finally, we take step towards incorporating the model into the microcontroller by implementing and evaluating an interface for the user to utilize the microcontroller’s sensors. In our thesis, we will have 4 chapters. The first will give us an introduction of TinyML. The second chapter will help setup the TinyML Environment. The third chapter will be about a major use of TinyML in Wake Word Detection. The final chapter will deal with Gesture Recognition in TinyML.

Rilevamento della qualità del manto stradale: un approccio sperimentale tramite Machine Learning

Il riconoscimento delle condizioni del manto stradale partendo esclusivamente dai dati raccolti dallo smartphone di un ciclista a bordo del suo mezzo è un ambito di ricerca finora poco esplorato. Per lo sviluppo di questa tesi è stata sviluppata un'apposita applicazione, che combinata a script Python permette di riconoscere differenti tipologie di asfalto. L’applicazione raccoglie i dati rilevati dai sensori di movimento integrati nello smartphone, che registra i movimenti mentre il ciclista è alla guida del suo mezzo. Lo smartphone è fissato in un apposito holder fissato sul manubrio della bicicletta e registra i dati provenienti da giroscopio, accelerometro e magnetometro. I dati sono memorizzati su file CSV, che sono elaborati fino ad ottenere un unico DataSet contenente tutti i dati raccolti con le features estratte mediante appositi script Python. A ogni record sarà assegnato un cluster deciso in base ai risultati prodotti da K-means, risultati utilizzati in seguito per allenare algoritmi Supervised. Lo scopo degli algoritmi è riconoscere la tipologia di manto stradale partendo da questi dati. Per l’allenamento, il DataSet è stato diviso in due parti: il training set dal quale gli algoritmi imparano a classificare i dati e il test set sul quale gli algoritmi applicano ciò che hanno imparato per dare in output la classificazione che ritengono idonea. Confrontando le previsioni degli algoritmi con quello che i dati effettivamente rappresentano si ottiene la misura dell’accuratezza dell’algoritmo.

Dynamic Human Robot Interaction Framework Using Deep Learning and Robot Operating System (ROS): a practical approach

Trying to explain to a robot what to do is a difficult undertaking, and only specific types of people have been able to do so far, such as programmers or operators who have learned how to use controllers to communicate with a robot. My internship's goal was to create and develop a framework that would make that easier. The system uses deep learning techniques to recognize a set of hand gestures, both static and dynamic. Then, based on the gesture, it sends a command to a robot. To be as generic as feasible, the communication is implemented using Robot Operating System (ROS). Furthermore, users can add new recognizable gestures and link them to new robot actions; a finite state automaton enforces the users' input verification and correct action sequence. Finally, the users can create and utilize a macro to describe a sequence of actions performable by a robot.

Meta-learning for informed model searches in Automated Machine Learning

Day by day, machine learning is changing our lives in ways we could not have imagined just 5 years ago. ML expertise is more and more requested and needed, though just a limited number of ML engineers are available on the job market, and their knowledge is always limited by an inherent characteristic of theirs: they are humans. This thesis explores the possibilities offered by meta-learning, a new field in ML that takes learning a level higher: models are trained on other models' training data, starting from features of the dataset they were trained on, inference times, obtained performances, to try to understand the relationship between a good model and the way it was obtained. The so-called metamodel was trained on data collected by OpenML, the largest ML metadata platform that's publicly available today. Datasets were analyzed to obtain meta-features that describe them, which were then tied to model performances in a regression task. The obtained metamodel predicts the expected performances of a given model type (e.g., a random forest) on a given ML task (e.g., classification on the UCI census dataset). This research was then integrated into a custom-made AutoML framework, to show how meta-learning is not an end in itself, but it can be used to further progress our ML research. Encoding ML engineering expertise in a model allows better, faster, and more impactful ML applications across the whole world, while reducing the cost that is inevitably tied to human engineers.

Machine Learning algorithm on seat comfort level measurement, mapping pressure values with body regions

The comfort level of the seat has a major effect on the usage of a vehicle; thus, car manufacturers have been working on elevating car seat comfort as much as possible. However, still, the testing and evaluation of comfort are done using exhaustive trial and error testing and evaluation of data. In this thesis, we resort to machine learning and Artificial Neural Networks (ANN) to develop a fully automated approach. Even though this approach has its advantages in minimizing time and using a large set of data, it takes away the degree of freedom of the engineer on making decisions. The focus of this study is on filling the gap in a two-step comfort level evaluation which used pressure mapping with body regions to evaluate the average pressure supported by specific body parts and the Self-Assessment Exam (SAE) questions on evaluation of the person’s interest. This study has created a machine learning algorithm that works on giving a degree of freedom to the engineer in making a decision when mapping pressure values with body regions using ANN. The mapping is done with 92% accuracy and with the help of a Graphical User Interface (GUI) that facilitates the process during the testing time of comfort level evaluation of the car seat, which decreases the duration of the test analysis from days to hours.

Antibody-Antigen Interface Characterization with Contextualized Pre-trained Embeddings

Artificial Intelligence (AI) has substantially influenced numerous disciplines in recent years. Biology, chemistry, and bioinformatics are among them, with significant advances in protein structure prediction, paratope prediction, protein-protein interactions (PPIs), and antibody-antigen interactions. Understanding PPIs is critical since they are responsible for practically everything living and have several uses in vaccines, cancer, immunology, and inflammatory illnesses. Machine Learning (ML) offers enormous potential for effectively simulating antibody-antigen interactions and improving in-silico optimization of therapeutic antibodies for desired features, including binding activity, stability, and low immunogenicity. This research looks at the use of AI algorithms to better understand antibody-antigen interactions, and it further expands and explains several difficulties encountered in the field. Furthermore, we contribute by presenting a method that outperforms existing state-of-the-art strategies in paratope prediction from sequence data.