Applying machine learning: a multi-role perspective

Machine (and deep) learning technologies are more and more present in several fields. It is undeniable that many aspects of our society are empowered by such technologies: web searches, content filtering on social networks, recommendations on e-commerce websites, mobile applications, etc., in addition to academic research. Moreover, mobile devices and internet sites, e.g., social networks, support the collection and sharing of information in real time. The pervasive deployment of the aforementioned technological instruments, both hardware and software, has led to the production of huge amounts of data. Such data has become more and more unmanageable, posing challenges to conventional computing platforms, and paving the way to the development and widespread use of the machine and deep learning. Nevertheless, machine learning is not only a technology. Given a task, machine learning is a way of proceeding (a way of thinking), and as such can be approached from different perspectives (points of view). This, in particular, will be the focus of this research. The entire work concentrates on machine learning, starting from different sources of data, e.g., signals and images, applied to different domains, e.g., Sport Science and Social History, and analyzed from different perspectives: from a non-data scientist point of view through tools and platforms; setting a problem stage from scratch; implementing an effective application for classification tasks; improving user interface experience through Data Visualization and eXtended Reality. In essence, not only in a quantitative task, not only in a scientific environment, and not only from a data-scientist perspective, machine (and deep) learning can do the difference.

Contributions to the performance analysis of continuum parallel robots

Continuum parallel robots (CPRs) are manipulators employing multiple flexible beams arranged in parallel and connected to a rigid end-effector. CPRs promise higher payload and accuracy than serial CRs while keeping great flexibility. As the risk of injury during accidental contacts between a human and a CPR should be reduced, CPRs may be used in large-scale collaborative tasks or assisted robotic surgery. There exist various CPR designs, but the prototype conception is rarely based on performance considerations, and the CPRs realization in mainly based on intuitions or rigid-link parallel manipulators architectures. This thesis focuses on the performance analysis of CPRs, and the tools needed for such evaluation, such as workspace computation algorithms. In particular, workspace computation strategies for CPRs are essential for the performance assessment, since the CPRs workspace may be used as a performance index or it can serve for optimal-design tools. Two new workspace computation algorithms are proposed in this manuscript, the former focusing on the workspace volume computation and the certification of its numerical results, while the latter aims at computing the workspace boundary only. Due to the elastic nature of CPRs, a key performance indicator for these robots is the stability of their equilibrium configurations. This thesis proposes the experimental validation of the equilibrium stability assessment on a real prototype, demonstrating limitations of some commonly used assumptions. Additionally, a performance index measuring the distance to instability is originally proposed in this manuscript. Differently from the majority of the existing approaches, the clear advantage of the proposed index is a sound physical meaning; accordingly, the index can be used for a more straightforward performance quantification, and to derive robot specifications.

Machine learning "as a service" for high energy physics (MLaaS4HEP): evolution of a framework for ML-based physics analyses

The scientific success of the LHC experiments at CERN highly depends on the availability of computing resources which efficiently store, process, and analyse the amount of data collected every year. This is ensured by the Worldwide LHC Computing Grid infrastructure that connect computing centres distributed all over the world with high performance network. LHC has an ambitious experimental program for the coming years, which includes large investments and improvements both for the hardware of the detectors and for the software and computing systems, in order to deal with the huge increase in the event rate expected from the High Luminosity LHC (HL-LHC) phase and consequently with the huge amount of data that will be produced. Since few years the role of Artificial Intelligence has become relevant in the High Energy Physics (HEP) world. Machine Learning (ML) and Deep Learning algorithms have been successfully used in many areas of HEP, like online and offline reconstruction programs, detector simulation, object reconstruction, identification, Monte Carlo generation, and surely they will be crucial in the HL-LHC phase. This thesis aims at contributing to a CMS R&D project, regarding a ML "as a Service" solution for HEP needs (MLaaS4HEP). It consists in a data-service able to perform an entire ML pipeline (in terms of reading data, processing data, training ML models, serving predictions) in a completely model-agnostic fashion, directly using ROOT files of arbitrary size from local or distributed data sources. This framework has been updated adding new features in the data preprocessing phase, allowing more flexibility to the user. Since the MLaaS4HEP framework is experiment agnostic, the ATLAS Higgs Boson ML challenge has been chosen as physics use case, with the aim to test MLaaS4HEP and the contribution done with this work.

Virtual commissioning of automatic machines for mesh panels manufacturing

The purpose of this thesis is to present the concept of simulation for automatic machines and how it might be used to test and debug software implemented for an automatic machine. The simulation is used to detect errors and allow corrections of the code before the machine has been built. Simulation permits testing different solutions and improving the software to get an optimized one. Additionally, simulation can be used to keep track of a machine after the installation in order to improve the production process during the machine’s life cycle. The central argument of this project is discussing the advantage of using virtual commissioning to test the implemented software in a virtual environment. Such an environment is getting benefit in avoiding potential damages as well as reduction of time to have the machine ready to work. Also, the use of virtual commissioning allows testing different solutions without high losses of time and money. Subsequently, an optimized solution could be found after testing different proposed solutions. The software implemented is based on the Object-Oriented Programming paradigm which implies different features such as encapsulation, modularity, and reusability of the code. Therefore, this way of programming helps to get simplified code that is easier to be understood and debugged as well as its high efficiency. Finally, different communication protocols are implemented in order to allow communication between the real plant and the simulation model. By the outcome that this communication provides, we might be able to gather all the necessary data for the simulation and the analysis, in real-time, of the production process in a way to improve it during the machine life cycle.

Development of a heterogeneous clustering algorithm for particle shower reconstruction in high energy physics using the SYCL abstraction layer

Nei prossimi anni è atteso un aggiornamento sostanziale di LHC, che prevede di aumentare la luminosità integrata di un fattore 10 rispetto a quella attuale. Tale parametro è proporzionale al numero di collisioni per unità di tempo. Per questo, le risorse computazionali necessarie a tutti i livelli della ricostruzione cresceranno notevolmente. Dunque, la collaborazione CMS ha cominciato già da alcuni anni ad esplorare le possibilità offerte dal calcolo eterogeneo, ovvero la pratica di distribuire la computazione tra CPU e altri acceleratori dedicati, come ad esempio schede grafiche (GPU). Una delle difficoltà di questo approccio è la necessità di scrivere, validare e mantenere codice diverso per ogni dispositivo su cui dovrà essere eseguito. Questa tesi presenta la possibilità di usare SYCL per tradurre codice per la ricostruzione di eventi in modo che sia eseguibile ed efficiente su diversi dispositivi senza modifiche sostanziali. SYCL è un livello di astrazione per il calcolo eterogeneo, che rispetta lo standard ISO C++. Questo studio si concentra sul porting di un algoritmo di clustering dei depositi di energia calorimetrici, CLUE, usando oneAPI, l'implementazione SYCL supportata da Intel. Inizialmente, è stato tradotto l'algoritmo nella sua versione standalone, principalmente per prendere familiarità con SYCL e per la comodità di confronto delle performance con le versioni già esistenti. In questo caso, le prestazioni sono molto simili a quelle di codice CUDA nativo, a parità di hardware. Per validare la fisica, l'algoritmo è stato integrato all'interno di una versione ridotta del framework usato da CMS per la ricostruzione. I risultati fisici sono identici alle altre implementazioni mentre, dal punto di vista delle prestazioni computazionali, in alcuni casi, SYCL produce codice più veloce di altri livelli di astrazione adottati da CMS, presentandosi dunque come una possibilità interessante per il futuro del calcolo eterogeneo nella fisica delle alte energie.

ICE Emissions Estimation through Machine-learning techniques to support real-world R&D experiments

The emissions estimation, both during homologation and standard driving, is one of the new challenges that automotive industries have to face. The new European and American regulation will allow a lower and lower quantity of Carbon Monoxide emission and will require that all the vehicles have to be able to monitor their own pollutants production. Since numerical models are too computationally expensive and approximated, new solutions based on Machine Learning are replacing standard techniques. In this project we considered a real V12 Internal Combustion Engine to propose a novel approach pushing Random Forests to generate meaningful prediction also in extreme cases (extrapolation, very high frequency peaks, noisy instrumentation etc.). The present work proposes also a data preprocessing pipeline for strongly unbalanced datasets and a reinterpretation of the regression problem as a classification problem in a logarithmic quantized domain. Results have been evaluated for two different models representing a pure interpolation scenario (more standard) and an extrapolation scenario, to test the out of bounds robustness of the model. The employed metrics take into account different aspects which can affect the homologation procedure, so the final analysis will focus on combining all the specific performances together to obtain the overall conclusions.

Energy consumption of parallel algorithms for solving linear systems on HPC architecture

Modern High-Performance Computing HPC systems are gradually increasing in size and complexity due to the correspondent demand of larger simulations requiring more complicated tasks and higher accuracy. However, as side effects of the Dennard’s scaling approaching its ultimate power limit, the efficiency of software plays also an important role in increasing the overall performance of a computation. Tools to measure application performance in these increasingly complex environments provide insights into the intricate ways in which software and hardware interact. The monitoring of the power consumption in order to save energy is possible through processors interfaces like Intel Running Average Power Limit RAPL. Given the low level of these interfaces, they are often paired with an application-level tool like Performance Application Programming Interface PAPI. Since several problems in many heterogeneous fields can be represented as a complex linear system, an optimized and scalable linear system solver algorithm can decrease significantly the time spent to compute its resolution. One of the most widely used algorithms deployed for the resolution of large simulation is the Gaussian Elimination, which has its most popular implementation for HPC systems in the Scalable Linear Algebra PACKage ScaLAPACK library. However, another relevant algorithm, which is increasing in popularity in the academic field, is the Inhibition Method. This thesis compares the energy consumption of the Inhibition Method and Gaussian Elimination from ScaLAPACK to profile their execution during the resolution of linear systems above the HPC architecture offered by CINECA. Moreover, it also collates the energy and power values for different ranks, nodes, and sockets configurations. The monitoring tools employed to track the energy consumption of these algorithms are PAPI and RAPL, that will be integrated with the parallel execution of the algorithms managed with the Message Passing Interface MPI.

Exploratory Study Of The Effect Of Lifestyle Counselling On Bone Mineral Density And Body Composition In Users Of The Contraceptive Depot-medroxyprogesterone Acetate.

To compare variations in bone mineral density (BMD) and body composition (BC) in depot-medroxyprogesterone acetate (DMPA) users and nonusers after providing counselling on healthy lifestyle habits. An exploratory study in which women aged 18 to 40 years participated: 29 new DMPA users and 25 new non-hormonal contraceptive users. All participants were advised on healthy lifestyle habits: sun exposure, walking and calcium intake. BMD and BC were assessed at baseline and 12 months later. Statistical analysis included the Mann-Whitney test or Student's t-test followed by multiple linear regression analysis. Compared to the controls, DMPA users had lower BMD at vertebrae L1 and L4 after 12 months of use. They also had a mean increase of 2 kg in total fat mass and an increase of 2.2% in body fat compared to the non-hormonal contraceptive users. BMD loss at L1 was less pronounced in DMPA users with a calcium intake ≥ 1 g/day compared to DMPA users with a lower calcium intake. DMPA use was apparently associated with lower BMD and an increase in fat mass at 12 months of use. Calcium intake ≥ 1 g/day attenuates BMD loss in DMPA users. Counselling on healthy lifestyle habits failed to achieve its aims.

Growth And Body Composition In Brazilian Female Rhythmic Gymnastics Athletes.

The aim was to analyse the physical growth and body composition of rhythmic gymnastics athletes relative to their level of somatic maturation. This was a cross-sectional study of 136 athletes on 23 teams from Brazil. Mass, standing height and sitting height were measured. Fat-free and fat masses, body fat percentages and ages of the predicted peak height velocity (PHV) were calculated. The z scores for mass were negative during all ages according to both WHO and Brazilian references, and that for standing height were also negative for all ages according to WHO reference but only until 12 years old according to Brazilian reference. The mean age of the predicted PHV was 12.1 years. The mean mass, standing and sitting heights, body fat percentage, fat-free mass and fat mass increased significantly until 4 to 5 years after the age of the PHV. Menarche was reached in only 26% of these athletes and mean age was 13.2 years. The mass was below the national reference standards, and the standing height was below only for the international reference, but they also had late recovery of mass and standing height during puberty. In conclusion, these athletes had a potential to gain mass and standing height several years after PHV, indicating late maturation.

Communication: Transient Anion States Of Phenol…(h₂o)n (n = 1, 2) Complexes: Search For Microsolvation Signatures.

We report on the shape resonance spectra of phenol-water clusters, as obtained from elastic electron scattering calculations. Our results, along with virtual orbital analysis, indicate that the well-known indirect mechanism for hydrogen elimination in the gas phase is significantly impacted on by microsolvation, due to the competition between vibronic couplings on the solute and solvent molecules. This fact suggests how relevant the solvation effects could be for the electron-driven damage of biomolecules and the biomass delignification [E. M. de Oliveira et al., Phys. Rev. A 86, 020701(R) (2012)]. We also discuss microsolvation signatures in the differential cross sections that could help to identify the solvated complexes and access the composition of gaseous admixtures of these species.

Biochemical, Anthropometric And Body Composition Indicators As Predictors Of Hepatic Steatosis In Obese Adolescents.

To describe the prevalence of hepatic steatosis and to assess the performance of biochemical, anthropometric and body composition indicators for hepatic steatosis in obese teenagers. Cross-sectional study including 79 adolecents aged from ten to 18 years old. Hepatic steatosis was diagnosed by abdominal ultrasound in case of moderate or intense hepatorenal contrast and/or a difference in the histogram ≥7 on the right kidney cortex. The insulin resistance was determined by the Homeostasis Model Assessment-Insulin Resistance (HOMA-IR) index for values >3.16. Anthropometric and body composition indicators consisted of body mass index, body fat percentage, abdominal circumference and subcutaneous fat. Fasting glycemia and insulin, lipid profile and hepatic enzymes, such as aspartate aminotransferase, alanine aminotransferase, gamma-glutamyltransferase and alkaline phosphatase, were also evaluated. In order to assess the performance of these indicators in the diagnosis of hepatic steatosis in teenagers, a ROC curve analysis was applied. Hepatic steatosis was found in 20% of the patients and insulin resistance, in 29%. Gamma-glutamyltransferase and HOMA-IR were good indicators for predicting hepatic steatosis, with a cutoff of 1.06 times above the reference value for gamma-glutamyltransferase and 3.28 times for the HOMA-IR. The anthropometric indicators, the body fat percentage, the lipid profile, the glycemia and the aspartate aminotransferase did not present significant associations. Patients with high gamma-glutamyltransferase level and/or HOMA-IR should be submitted to abdominal ultrasound examination due to the increased chance of having hepatic steatosis.

Characterization Of Morphology And Composition Of Inorganic Fillers In Dental Alginates.

Energy dispersive X-ray spectroscopy microanalysis (EDX), scanning electron microscopy (SEM), and Archimedes' Principle were used to determine the characteristics of inorganic filler particles in five dental alginates, including Cavex ColorChange (C), Hydrogum 5 (H5), Hydrogum (H), Orthoprint (O), and Jeltrate Plus (JP). The different alginate powders (0.5 mg) were fixed on plastic stubs (n = 5) and sputter coated with carbon for EDX analysis, then coated with gold, and observed using SEM. Volume fractions were determined by weighing a sample of each material in water before and after calcining at 450(°)C for 3 h. The alginate materials were mainly composed of silicon (Si) by weight (C-81.59%, H-79.89%, O-78.87%, H5-77.95%, JP-66.88%, wt). The filler fractions in volume (vt) were as follows: H5-84.85%, JP-74.76%, H-70.03%, O-68.31%, and C-56.10%. The tested materials demonstrated important differences in the inorganic elemental composition, filler fraction, and particle morphology.

Chemical Composition And Free Radical-scavenging, Anticancer And Anti-inflammatory Activities Of The Essential Oil From Ocimum Kilimandscharicum.

The essential oil from the leaves of Ocimum kilimandscharicum (EOOK), collected in Dourados-MS, was investigated for anticancer, anti-inflammatory and antioxidant activity and chemical composition. The essential oil was extracted by hydrodistillation, and the chemical composition was performed by gas chromatography-mass spectrometry. The essential oil was evaluated for free radical-scavenging activity using the DPPH assay and was tested in an anticancer assay against ten human cancer cell lines. The response parameter (GI50) was calculated for the cell lines tested. The anti-inflammatory activity was evaluated using carrageenan-induced pleurisy in mice. The chemical composition showed 45 components with a predominance of monoterpenes, such as camphor (51.81%), 1,8 cineole (20.13%) and limonene (11.23%). The EOOK exhibited potent free radical-scavenging activity by the DPPH assay with a GI50 of 8.31 μg/ml. The major constituents, pure camphor (IC50=12.56 μg/ml) and mixture of the limonene: 1, 8 cineole (IC50=23.25 μg/ml) displayed a potent activity. The oral administration of EOOK (at 30 and 100 mg kg(-1)), as well as the pure camphor or a mixture of 1,8 cineole with limonene, significantly inhibited the carrageenan (Cg) induced pleurisy, reducing the migration of total leukocytes in mice by 82 ± 4% (30 mg kg(-1) of EOOK), 95 ± 4% (100 mg kg(-1) of EOOK), 83 ± 9% (camphor) and 80 ± 5% (mixture of 1,8 cineole:limonene 1:1). In vitro cytotoxicity screening against a human ovarian cancer cell line displayed high selectivity and potent anticancer activity with GI50=31.90 mg ml(-1). This work describes the anti-inflammatory, anticancer and antioxidant effects of EOOK for the first time. The essential oil exhibited marked anti-inflammatory, antioxidant and anticancer effects, an effect that can be attributed the presence of majorital compounds, and the response profiles from chemical composition differed from other oils collected in different locales.

Effects Of Programmed Physical Activity On Body Composition In Post-pubertal Schoolchildren.

To assess body composition modifications in post-pubertal schoolchildren after practice of a physical activity program during one school year. The sample consisted of 386 students aged between 15 and 17 years and divided into two groups: the study group (SG) comprised 195 students and the control group (CG), 191. The SG was submitted to a physical activity program and the CG attended conventional physical education classes. Body composition was assessed using body mass index (BMI), percentage of body fat (%BF), fat mass (FM), and lean mass (LM). A positive effect of the physical activity program on body composition in the SG (p<0.001) was observed, as well as on the interaction time x group in all the variables analyzed in both genders. A reduction in %BF (mean of differences = -5.58%) and waist circumference (-2.33cm), as well as an increase in LM (+2.05kg) were observed in the SG for both genders, whereas the opposite was observed in the CG. The practice of programmed physical activity promotes significant reduction of body fat in post-pubertal schoolchildren.

Influence Of The Stage Of Ripeness On The Composition Of Iridoids And Phenolic Compounds In Genipap (genipa Americana L.).

Genipap fruits, native to the Amazon region, were classified in relation to their stage of ripeness according to firmness and peel color. The influence of the part of the genipap fruit and ripeness stage on the iridoid and phenolic compound profiles was evaluated by HPLC-DAD-MS(n), and a total of 17 compounds were identified. Geniposide was the major compound in both parts of the unripe genipap fruits, representing >70% of the total iridoids, whereas 5-caffeoylquinic acid was the major phenolic compound. In ripe fruits, genipin gentiobioside was the major compound in the endocarp (38%) and no phenolic compounds were detected. During ripening, the total iridoid content decreased by >90%, which could explain the absence of blue pigment formation in the ripe fruits after their injury. This is the first time that the phenolic compound composition and iridoid contents of genipap fruits have been reported in the literature.