Evolution of classifiers for pitch estimation of piano music using cartesian genetic programming

Pitch Estimation, also known as Fundamental Frequency (F0) estimation, has been a popular research topic for many years, and is still investigated nowadays. The goal of Pitch Estimation is to find the pitch or fundamental frequency of a digital recording of a speech or musical notes. It plays an important role, because it is the key to identify which notes are being played and at what time. Pitch Estimation of real instruments is a very hard task to address. Each instrument has its own physical characteristics, which reflects in different spectral characteristics. Furthermore, the recording conditions can vary from studio to studio and background noises must be considered. This dissertation presents a novel approach to the problem of Pitch Estimation, using Cartesian Genetic Programming (CGP).We take advantage of evolutionary algorithms, in particular CGP, to explore and evolve complex mathematical functions that act as classifiers. These classifiers are used to identify piano notes pitches in an audio signal. To help us with the codification of the problem, we built a highly flexible CGP Toolbox, generic enough to encode different kind of programs. The encoded evolutionary algorithm is the one known as 1 + , and we can choose the value for . The toolbox is very simple to use. Settings such as the mutation probability, number of runs and generations are configurable. The cartesian representation of CGP can take multiple forms and it is able to encode function parameters. It is prepared to handle with different type of fitness functions: minimization of f(x) and maximization of f(x) and has a useful system of callbacks. We trained 61 classifiers corresponding to 61 piano notes. A training set of audio signals was used for each of the classifiers: half were signals with the same pitch as the classifier (true positive signals) and the other half were signals with different pitches (true negative signals). F-measure was used for the fitness function. Signals with the same pitch of the classifier that were correctly identified by the classifier, count as a true positives. Signals with the same pitch of the classifier that were not correctly identified by the classifier, count as a false negatives. Signals with different pitch of the classifier that were not identified by the classifier, count as a true negatives. Signals with different pitch of the classifier that were identified by the classifier, count as a false positives. Our first approach was to evolve classifiers for identifying artifical signals, created by mathematical functions: sine, sawtooth and square waves. Our function set is basically composed by filtering operations on vectors and by arithmetic operations with constants and vectors. All the classifiers correctly identified true positive signals and did not identify true negative signals. We then moved to real audio recordings. For testing the classifiers, we picked different audio signals from the ones used during the training phase. For a first approach, the obtained results were very promising, but could be improved. We have made slight changes to our approach and the number of false positives reduced 33%, compared to the first approach. We then applied the evolved classifiers to polyphonic audio signals, and the results indicate that our approach is a good starting point for addressing the problem of Pitch Estimation.

Predicting the concentration of residual methanol in industrial formalin using machine learning

In this thesis, a machine learning approach was used to develop a predictive model for residual methanol concentration in industrial formalin produced at the Akzo Nobel factory in Kristinehamn, Sweden. The MATLABTM computational environment supplemented with the Statistics and Machine LearningTM toolbox from the MathWorks were used to test various machine learning algorithms on the formalin production data from Akzo Nobel. As a result, the Gaussian Process Regression algorithm was found to provide the best results and was used to create the predictive model. The model was compiled to a stand-alone application with a graphical user interface using the MATLAB CompilerTM.

Knockin' on Digital Doors. Dealing with online [dis]credit in an era of digital scientific inquiry

This chapter aims at presenting and discussing credible online recruitment eliciting techniques targeting scientific purposes adjusted to the digital age. Based on several illustrations conducted by the author within the framework of both quantitative and qualitative inquiries, this chapter critically explores the digital ethos in three main challenges faced when dealing with online recruitment for scientific purposes: entering the normality of the everyday life, entering the idiosyncrasy of multicultural lives, and entering the chaos of busy lives. By the end, a toolbox for establishing and evaluating (dis)credibility within online recruitment strategies is presented. Moreover, it is argued that success of data collection at the present time in online environments seems to rely as ever on internal factors of the communication process vis-à-vis e-mail content, design and related strategies.

On The Use of Genetic Algorithms for Parameter Identification in Anaerobic Digestion Modelling

Anaerobic digestion (AD) of wastewater is a very interesting option for waste valorization, energy production and environment protection. It is a complex, naturally occurring process that can take place inside bioreactors. The capability of predicting the operation of such bioreactors is important to optimize the design and the operation conditions of the reactors, which, in part, justifies the numerous AD models presently available. The existing AD models are not universal, have to be inferred from prior knowledge and rely on existing experimental data. Among the tasks involved in the process of developing a dynamical model for AD, the estimation of parameters is one of the most challenging. This paper presents the identifiability analysis of a nonlinear dynamical model for a batch reactor. Particular attention is given to the structural identifiability of the model, which considers the uniqueness of the estimated parameters. To perform this analysis, the GenSSI toolbox was used. The estimation of the model parameters is achieved with genetic algorithms (GA) which have already been used in the context of AD modelling, although not commonly. The paper discusses its advantages and disadvantages.

Visualising In/Equalities through Contemporary Documentary Cinema. A Diffractive Reading of Feminist Practices in Spanish and Italian Non-Fiction Films

This thesis brings together feminist documentary film theory and feminist new materialism(s) to describe how feminist material-discursive practices in a sample of Spanish and Italian documentary cinema made between 2013-2018 (can) visualise gender in/equalities. The accomplished objectives have been: 1. Building a bridge between feminist documentary film theory and Karen Barad’s diffractive methodology by approaching non-fiction cinema that deals with social inequalities as a diffraction apparatus. 2. Developing a feminist toolbox for a response-able gaze by gathering different insights from feminist film theory. 3. Identifying feminist material-discursive practices in a sample of documentary films produced in Spain and Italy over the last six years (2013-2018). 4. Analysing the effects that these feminist material-discursive practices in documentary cinema have, particularly in terms of visualising gender in/equalities on both sides of the camera and on both sides of the screen. 5. Revealing patterns between the ten case studies by reading through one another (i.e. diffractively) insights raised in each one of them. In ten documentary films/case studies, I identify patterns of continuities and differences concerning feminist material-discursive practices at four levels: content, form, production and reception. In terms of contents, I detect two patterns in which feminist material-discursive practices may operate: enacting the right to appear or enacting the right to look back and/or against the grain. As for the forms, I exemplify how feminism politicises Bill Nichols’s six modes of representation. My analysis of production practices is elaborated along the filmmakers’ self-positions/situatedness, tensions/obstructions, and effects/affects/emotions regarding four key concepts: documentary cinema, equality, gender and feminism(s). And in the case of reception practices, I identify patterns of affective identification and/or intellectual reflections.

Distributed Large-scale Mixed-Integer Optimization with Application to Energy and Multi-robot Networks

Several decision and control tasks in cyber-physical networks can be formulated as large- scale optimization problems with coupling constraints. In these "constraint-coupled" problems, each agent is associated to a local decision variable, subject to individual constraints. This thesis explores the use of primal decomposition techniques to develop tailored distributed algorithms for this challenging set-up over graphs. We first develop a distributed scheme for convex problems over random time-varying graphs with non-uniform edge probabilities. The approach is then extended to unknown cost functions estimated online. Subsequently, we consider Mixed-Integer Linear Programs (MILPs), which are of great interest in smart grid control and cooperative robotics. We propose a distributed methodological framework to compute a feasible solution to the original MILP, with guaranteed suboptimality bounds, and extend it to general nonconvex problems. Monte Carlo simulations highlight that the approach represents a substantial breakthrough with respect to the state of the art, thus representing a valuable solution for new toolboxes addressing large-scale MILPs. We then propose a distributed Benders decomposition algorithm for asynchronous unreliable networks. The framework has been then used as starting point to develop distributed methodologies for a microgrid optimal control scenario. We develop an ad-hoc distributed strategy for a stochastic set-up with renewable energy sources, and show a case study with samples generated using Generative Adversarial Networks (GANs). We then introduce a software toolbox named ChoiRbot, based on the novel Robot Operating System 2, and show how it facilitates simulations and experiments in distributed multi-robot scenarios. Finally, we consider a Pickup-and-Delivery Vehicle Routing Problem for which we design a distributed method inspired to the approach of general MILPs, and show the efficacy through simulations and experiments in ChoiRbot with ground and aerial robots.

New chemical modalities for leishmaniasis drug discovery

Leishmaniasis is one of the major parasitic diseases among neglected tropical diseases with a high rate of morbidity and mortality. Human migration and climate change have spread the disease from limited endemic areas all over the world, also reaching regions in Southern Europe, and causing significant health and economic burden. The currently available treatments are far from ideal due to host toxicity, elevated cost, and increasing rates of drug resistance. Safer and more effective drugs are thus urgently required. Nevertheless, the identification of new chemical entities for leishmaniasis has proven to be incredibly hard and exacerbated by the scarcity of well-validated targets. Trypanothione reductase (TR) represents one robustly validated target in Leishmania that fulfils most of the requirements for a good drug target. However, due to the large and featureless active site, TR is considered extremely challenging and almost undruggable by small molecules. This scenario advocates the development of new chemical entities by unlocking new modalities for leishmaniasis drug discovery. The classical toolbox for drug discovery has enormously expanded in the last decade, and medicinal chemists can now strategize across a variety of new chemical modalities and a vast chemical space, to efficiently modulate challenging targets and provide effective treatments. Beyond others, Targeted p Protein Degradation (TPD) is an emerging strategy that uses small molecules to hijack endogenous proteolysis systems to degrade disease-relevant proteins and thus reduce their abundance in the cell. Based on these considerations, this thesis aimed to develop new strategies for leishmaniasis drug discovery while embracing novel chemical modalities and navigating the chemical space by chasing unprecedented chemotypes. This has been achieved by four complementary projects. We believe that these next-generation chemical modalities for leishmaniasis will play an important role in what was previously thought to be a drug discovery landscape dominated by small molecules.

Investigation on the role of polymeric ligands in heterogeneous nanocatalysis towards the development of hybrid metal-polymer catalysts

The relationship between catalytic properties and the nature of the active phase is well-established, with increased presence typically leading to enhanced catalysis. However, the costs associated with acquiring and processing these metals can become economically and environmentally unsustainable for global industries. Thus, there is potential for a paradigm shift towards utilizing polymeric ligands or other polymeric systems to modulate and enhance catalytic performance. This alternative approach has the potential to reduce the requisite amount of active phase while preserving effective catalytic activity. Such a strategy could yield substantial benefits from both economic and environmental perspectives. The primary objective of this research is to examine the influence of polymeric hydro-soluble ligands on the final properties, such as size and dispersion of the active phase, as well as the catalytic activity, encompassing conversion, selectivity towards desired products, and stability, of colloidal gold nanoparticles supported on active carbon. The goal is to elucidate the impact of polymers systematically, offering a toolbox for fine-tuning catalytic performances from the initial stages of catalyst design. Moreover, investigating the potential to augment conversion and selectivity in specific reactions through tailored polymeric ligands holds promise for reshaping catalyst preparation methodologies, thereby fostering the development of more economically sustainable materials.

Operazioni di assemblaggio automatizzato tramite robot antropomorfo e visione artificiale

Obiettivo dello studio condotto è l’implementazione di cicli di operazioni per l’assemblaggio automatizzato di componenti che costituiscono un sistema di trasporto a catena presente in alcune macchine automatiche. L’automazione del processo, fino ad oggi svolto manualmente, prevede l’utilizzo di un robot e, per il controllo di quest’ultimo, di un sistema di visione artificiale. L’attività di tirocinio associata alla tesi di laurea, che ha incluso una parte sperimentale oltre alla scrittura degli algoritmi di controllo del robot, è stata svolta all’interno del laboratorio TAILOR (Technology and Automation for Industry LabORatory) presso Siropack Italia S.r.l dove è presente una cella dotata di robot antropomorfo (Mitsubishi Electric) e di sistema di visione artificiale con camere 2D (Omron). La presenza di quest’ultimo è risultata strategica in termini di possibilità di adattare il montaggio anche a diversi posizionamenti degli oggetti all’interno dello spazio di lavoro, fermo restando che gli stessi risultassero appoggiati su una superficie piana. In primo luogo, affinché fosse garantita la ripetibilità del processo, sono state testate le prestazioni del sistema di visione tramite opportuna calibrazione della camera e del sistema di illuminazione ad esso collegata, al fine di ottenere un’acquisizione delle immagini che fosse sufficientemente robusta e risoluta mediante lo sfruttamento del software di elaborazione Omron FH Vision System. Un’opportuna programmazione della traiettoria del robot in ambiente di simulazione RT Toolbox 3, software integrato nel sistema di controllo del robot Mitsubishi Electric, ha infine consentito le regolari operazioni di assemblaggio, garantendo un processo affidabile ed, allo stesso tempo, adattabile ad ambienti eventualmente non strutturati in cui esso si trova ad operare.