A Soft Computing Approach to Acute Coronary Syndrome

Acute Coronary Syndrome (ACS) is transversal to a broad and heterogeneous set of human beings, and assumed as a serious diagnosis and risk stratification problem. Although one may be faced with or had at his disposition different tools as biomarkers for the diagnosis and prognosis of ACS, they have to be previously evaluated and validated in different scenarios and patient cohorts. Besides ensuring that a diagnosis is correct, attention should also be directed to ensure that therapies are either correctly or safely applied. Indeed, this work will focus on the development of a diagnosis decision support system in terms of its knowledge representation and reasoning mechanisms, given here in terms of a formal framework based on Logic Programming, complemented with a problem solving methodology to computing anchored on Artificial Neural Networks. On the one hand it caters for the evaluation of ACS predisposing risk and the respective Degree-of-Confidence that one has on such a happening. On the other hand it may be seen as a major development on the Multi-Value Logics to understand things and ones behavior. Undeniably, the proposed model allows for an improvement of the diagnosis process, classifying properly the patients that presented the pathology (sensitivity ranging from 89.7% to 90.9%) as well as classifying the absence of ACS (specificity ranging from 88.4% to 90.2%).

An Assessment of Pharmacological Properties of Schinus Essential Oils: A Soft Computing Approach

Plants of genus Schinus are native South America and introduced in Mediterranean countries, a long time ago. Some Schinus species have been used in folk medicine, and Essential Oils of Schinus spp. (EOs) have been reported as having antimicrobial, anti-tumoural and anti-inflammatory properties. Such assets are related with the EOs chemical composition that depends largely on the species, the geographic and climatic region, and on the part of the plants used. Considering the difficulty to infer the pharmacological properties of EOs of Schinus species without a hard experimental setting, this work will focus on the development of an Artificial Intelligence grounded Decision Support System to predict pharmacological properties of Schinus EOs. The computational framework was built on top of a Logic Programming Case Base approach to knowledge representation and reasoning, which caters to the handling of incomplete, unknown, or even self-contradictory information. New clustering methods centered on an analysis of attribute’s similarities were used to distinguish and aggregate historical data according to the context under which it was added to the Case Base, therefore enhancing the prediction process.

An Integrated Soft Computing Approach to Hughes Syndrome Risk Assessment

The AntiPhospholipid Syndrome (APS) is an acquired autoimmune disorder induced by high levels of antiphospholipid antibodies that cause arterial and veins thrombosis, as well as pregnancy-related complications and morbidity, as clinical manifestations. This autoimmune hypercoagulable state, usually known as Hughes syndrome, has severe consequences for the patients, being one of the main causes of thrombotic disorders and death. Therefore, it is required to be preventive; being aware of how probable is to have that kind of syndrome. Despite the updated of antiphospholipid syndrome classification, the diagnosis remains difficult to establish. Additional research on clinically relevant antibodies and standardization of their quantification are required in order to improve the antiphospholipid syndrome risk assessment. Thus, this work will focus on the development of a diagnosis decision support system in terms of a formal agenda built on a Logic Programming approach to knowledge representation and reasoning, complemented with a computational framework based on Artificial Neural Networks. The proposed model allows for improving the diagnosis, classifying properly the patients that really presented this pathology (sensitivity higher than 85%), as well as classifying the absence of APS (specificity close to 95%).

The Determinants of Individual Performance: Empirical Essays on the Importance of Soft Skills and Monetary Incentives

This dissertation consists of three papers. The first paper "Managing the Workload: an Experiment on Individual Decision Making and Performance" experimentally investigates how decision-making in workload management affects individual performance. I designed a laboratory experiment in order to exogenously manipulate the schedule of work faced by each subject and to identify its impact on final performance. Through the mouse click-tracking technique, I also collected interesting behavioral measures on organizational skills. I found that a non-negligible share of individuals performs better under externally imposed schedules than in the unconstrained case. However, such constraints are detrimental for those good in self-organizing. The second chapter, "On the allocation of effort with multiple tasks and piecewise monotonic hazard function", tests the optimality of a scheduling model, proposed in a different literature, for the decisional problem faced in the experiment. Under specific assumptions, I find that such model identifies what would be the optimal scheduling of the tasks in the Admission Test. The third paper "The Effects of Scholarships and Tuition Fees Discounts on Students' Performances: Which Monetary Incentives work Better?" explores how different levels of monetary incentives affect the achievement of students in tertiary education. I used a Regression Discontinuity Design to exploit the assignment of different monetary incentives, to study the effects of such liquidity provision on performance outcomes, ceteris paribus. The results show that a monetary increase in the scholarships generates no effect on performance since the achievements of the recipients are all centered near the requirements for non-returning the benefit. Secondly, students, who are actually paying some share of the total cost of college attendance, surprisingly, perform better than those whose cost is completely subsidized. A lower benefit, relatively to a higher aid, it motivates students to finish early and not to suffer the extra cost of a delayed graduation.

Metal additive manufacturing of soft magnetic material for electric machines

This research work concerns the application of additive manufacturing (AM) technologies in new electric mobility sectors. The unmatched freedom that AM offers can potentially change the way electric motors are designed and manufactured. The thesis investigates the possibility of creating optimized electric machines that exploit AM technologies, with potential in various industrial sectors, including automotive and aerospace. In particular, we will evaluate how the design of electric motors can be improved by producing the rotor core using Laser Powder Bed Fusion (LPBF) and how the resulting design choices affect component performance. First, the metallurgical and soft magnetic properties of the pure iron and silicon iron alloy parts (Fe-3% wt.Si) produced by LPBF will be defined and discussed, considering the process parameters and the type of heat treatment. This research shows that using LPBF, both pure iron and iron silicon, the parts have mechanical and magnetic properties different from the laminated ones. Hence, FEM-based modeling will be employed to design the rotor core of an SYN RM machine to minimize torque ripple while maintaining structural integrity. Finally, we suggest that further research should extend the field of applicability to other electrical devices.

Electrospun hierarchical artificial muscle for soft robotics applications

Nowadays, one of the most ambitious challenges in soft robotics is the development of actuators capable to achieve performance comparable to skeletal muscles. Scientists have been working for decades, inspired by Nature, to mimic both their complex structure and their perfectly balanced features in terms of linear contraction, force-to-weight ratio, scalability and flexibility. The present Thesis, contextualized within the FET open Horizon 2020 project MAGNIFY, aims to develop a new family of innovative flexible actuators in the field of soft-robotics. For the realization of this actuator, a biomimetic approach has been chosen, drawing inspiration from skeletal muscle. Their hierarchical fibrous structure was mimicked employing the electrospinning technique, while the contraction of sarcomeres was designed employing chains of molecular machines, supramolecular systems capable of performing movements useful to execute specific tasks. The first part deals with the design and production of the basic unit of the artificial muscle, the artificial myofibril, consisting in a novel electrospun core-shell nanofiber, with elastomeric shell and electrically conductive core, coupled with a conductive coating, for the realization of which numerous strategies have been investigated. The second part deals instead with the integration of molecular machines (provided by the project partners) inside these artificial myofibrils, preceded by the study of several model molecules, aimed at simulating the presence of these molecular machines during the initial phases of the project. The last part concerns the realization of an electrospun multiscale hierarchical structure, aimed at reproducing the entire muscle morphology and fibrous organization. These research will be joined together in the near future like the pieces of a puzzle, recreating the artificial actuator most similar to biological muscle ever made, composed of millions of artificial myofibrils, electrically activated in which the nano-scale movement of molecular machines will be incrementally amplified to the macro-scale contraction of the artificial muscle.

Nanomechanical characterization of soft bioelectronic interfaces via modeling-informed atomic force microscopy

The field of bioelectronics involves the use of electrodes to exchange electrical signals with biological systems for diagnostic and therapeutic purposes in biomedical devices and healthcare applications. However, the mechanical compatibility of implantable devices with the human body has been a challenge, particularly with long-term implantation into target organs. Current rigid bioelectronics can trigger inflammatory responses and cause unstable device functions due to the mechanical mismatch with the surrounding soft tissue. Recent advances in flexible and stretchable electronics have shown promise in making bioelectronic interfaces more biocompatible. To fully achieve this goal, material science and engineering of soft electronic devices must be combined with quantitative characterization and modeling tools to understand the mechanical issues at the interface between electronic technology and biological tissue. Local mechanical characterization is crucial to understand the activation of failure mechanisms and optimizing the devices. Experimental techniques for testing mechanical properties at the nanoscale are emerging, and the Atomic Force Microscope (AFM) is a good candidate for in situ local mechanical characterization of soft bioelectronic interfaces. In this work, in situ experimental techniques with solely AFM supported by interpretive models for the characterization of planar and three-dimensional devices suitable for in vivo and in vitro biomedical experimentations are reported. The combination of the proposed models and experimental techniques provides access to the local mechanical properties of soft bioelectronic interfaces. The study investigates the nanomechanics of hard thin gold films on soft polymeric substrates (Poly(dimethylsiloxane) PDMS) and 3D inkjet-printed micropillars under different deformation states. The proposed characterization methods provide a rapid and precise determination of mechanical properties, thus giving the possibility to parametrize the microfabrication steps and investigate their impact on the final device.

Low-molecular-weight gels: from the rational design to the application of versatile soft materials

Low-molecular-weight (LMW) gels are a versatile class of soft materials that gained increasing interest over the last few decades. They are made of a small percentage, often lower than 1.0 %, of organic molecules called gelators, dispersed in a liquid medium. Such molecules have a molecular weight usually lower than 1 kDa. The gelator molecules start to interact after the addition of a trigger, and form fibres, whose entanglement traps the solvent through capillary forces. A plethora of LMW gelators have been designed, including short peptides. Such gelators present several advantages: the synthesis is easy and can be easily scaled up; they are usually biocompatible and biodegradable; the gelation phenomenon can be rationalised by making small variation on the peptide scaffold; they find application in several fields. In this thesis, an overview of several peptide based LMW gels is presented. In each study, the gelation conditions were carefully studied, and the final materials were thoroughly investigated. First, the gelation ability of a fluorinated phenylalanine was assessed, to understand how the presence of a rigid moiety and the presence of fluorine may influence the gelation. In this context, a method for the dissolution of sensitive gelators was studied. Then, the control over the gel formation was studied both over time and space, taking advantage of either the pH-annealing of the gel or the reaction-diffusion of a hydrolysing reagent. Some gels were probed for various applications. Due to their ability of trapping water and organic solvents, we used gels for trapping pollutants dissolved in water, as well as a medium for the controlled release of either fragrances or bioactive compounds. Finally, the interaction of the gel matrix with a light-responsive molecule was assessed to understand wether the gel properties or the interaction of the additive with light were affected.

ADDITIVE MANUFACTURING: tecnologia innovativa per l'ottimizzazione di macchine elettriche

Lo scopo di questa tesi è quello di mostrare le potenzialità e le possibili soluzioni dell’Additive Manufacturing per l’ottimizzazione di macchine elettriche in risposta al problema delle terre rare. Nel primo capitolo viene presentato lo stato dell’arte dell’Additive Manufacturing mostrando una rapida panoramica delle sue caratteristiche principali, le potenzialità future e i settori di utilizzo. Il secondo capitolo propone le principali tecniche di Stampa 3D per la realizzazione di oggetti evidenziando di ognuna i pregi e i difetti. All’interno del terzo capitolo, viene illustrata la struttura di una macchina elettrica mostrando le varie componenti e presentando delle possibili ottimizzazioni realizzate tramite Additive Manufacturing. Nel quarto capitolo vengono presentati esempi di macchine elettriche complete realizzate attraverso le tecniche dell’Additive Manufacturing. Nel quinto capitolo vengono confrontati un Interior Permanent Magnets motor e un Synchronous Relectance Machine.

Sviluppo di Metodi di Soft Labeling per la Multi-Document Summarization in Ambito Legale

In questo elaborato viene trattata l’analisi del problema di soft labeling applicato alla multi-document summarization, in particolare vengono testate varie tecniche per estrarre frasi rilevanti dai documenti presi in dettaglio, al fine di fornire al modello di summarization quelle di maggior rilievo e più informative per il riassunto da generare. Questo problema nasce per far fronte ai limiti che presentano i modelli di summarization attualmente a disposizione, che possono processare un numero limitato di frasi; sorge quindi la necessità di filtrare le informazioni più rilevanti quando il lavoro si applica a documenti lunghi. Al fine di scandire la metrica di importanza, vengono presi come riferimento metodi sintattici, semantici e basati su rappresentazione a grafi AMR. Il dataset preso come riferimento è Multi-LexSum, che include tre granularità di summarization di testi legali. L’analisi in questione si compone quindi della fase di estrazione delle frasi dai documenti, della misurazione delle metriche stabilite e del passaggio al modello stato dell’arte PRIMERA per l’elaborazione del riassunto. Il testo ottenuto viene poi confrontato con il riassunto target già fornito, considerato come ottimale; lavorando in queste condizioni l’obiettivo è di definire soglie ottimali di upper-bound per l’accuratezza delle metriche, che potrebbero ampliare il lavoro ad analisi più dettagliate qualora queste superino lo stato dell’arte attuale.

Analisi numerica e sperimentale di un soft-gripper Fin Ray integrato con un dispositivo elettroadesivo

Una delle applicazioni maggiormente richieste in ambito industriale è quella della presa e movimentazioni di oggetti. Questa tipologia di operazione trova diverse soluzioni nel mondo della robotica e automazione. Nella loro forma più comune un dispositivo di presa si presenta come una pinza motorizzata attraverso la quale è possibile eseguire l’afferraggio di oggetti. Tra essi si possono distinguere i Soft Gripper, ovvero quella classe di pinze che ricorrono a componenti flessibili e parti in materiali soffici che nell’azione di presa si conformano all’oggetto per deformazione dei componenti. Un esempio di questa tipologia di strumenti di presa è il Fin Ray. Tuttavia, questa tipologia di soft-gripper possiede delle limitazioni, come il carico massimo movimentabile determinato sostanzialmente dalla rigidezza della struttura. In questo contesto, al fine di superare tale limite, viene proposto di implementare sulla superficie di contatto un dispositivo a film-sottile elettroadesivo, per generare forze di taglio superficiali per principio elettrostatico, che aumentino la capacità di sollevamento del soft-gripper senza intaccare la sua caratteristica principale di conformità. Lo scopo della tesi è proprio un’analisi numerica e sperimentale di un Fin Ray integrato con un dispositivo elettroadesivo, con lo scopo di analizzare la forza scambiata con un oggetto. Il gripper progettato in questo lavoro, è così prima simulato, e poi realizzato in laboratorio per eseguire la caratterizzazione sperimentale. Gli esperimenti sono stati condotti su un banco prova per la misurazione della forza di contatto scambiata durante l’afferraggio. Per ottenere una validazione del modello sviluppato, sono stati realizzati dei gripper con due differenti materiali altamente deformabili, e con una combinazione di parametri fondamentali diversi, come la posizione e la dimensione dell’oggetto in presa, ottenendo infine una caratterizzazione completa del gripper sviluppato.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

[diet Quality And Associated Factors Among The Elderly: A Population-based Study In Campinas, São Paulo State, Brazil].

The aim of this study was to assess the quality of diet among the elderly and associations with socio-demographic variables, health-related behaviors, and diseases. A population-based cross-sectional study was conducted in a representative sample of 1,509 elderly participants in a health survey in Campinas, São Paulo State, Brazil. Food quality was assessed using the Revised Diet Quality Index (DQI-R). Mean index scores were estimated and a multiple regression model was employed for the adjusted analyses. The highest diet quality scores were associated with age 80 years or older, Evangelical religion, diabetes mellitus, and physical activity, while the lowest scores were associated with home environments shared with three or more people, smoking, and consumption of soft drinks and alcoholic beverages. The findings emphasize a general need for diet quality improvements in the elderly, specifically in subgroups with unhealthy behaviors, who should be targeted with comprehensive strategies.

Hearing Preservation And Cochlear Implants According To Inner Ear Approach: Multicentric Evaluation.

Electroacoustic stimulation is an excellent option for people with residual hearing in the low frequencies, who obtain insufficient benefit with hearing aids. To be effective, the subject's residual hearing should be preserved during cochlear implant surgery. To evaluate the hearing preservation in patients that underwent implant placement and to compare the results in accordance with the approach to the inner ear. 19 subjects underwent a soft surgical technique, and the electrode MED-EL FLEX™ EAS, designed to be atraumatic, was used. We evaluated pre- and postoperative tonal audiometric tests with an average of 18.4 months after implantation, to measure the rate of hearing preservation. 17 patients had total or partial preservation of residual hearing; 5 had total hearing preservation and two individuals had no preservation of hearing. The insertion of the electrode occurred through a cochleostomy in 3 patients, and in 2 of these there was no hearing preservation; the other 16 patients experienced electrode insertion through a round window approach. All patients benefited from the cochlear implant, even those who are only using electrical stimulation. The hearing preservation occurred in 89.4% of cases. There was no significant difference between the forms of inner ear approach.