Exploring domain-informed and physics-guided learning in image-to-image translation

Image-to-image (i2i) translation networks can generate fake images beneficial for many applications in augmented reality, computer graphics, and robotics. However, they require large scale datasets and high contextual understanding to be trained correctly. In this thesis, we propose strategies for solving these problems, improving performances of i2i translation networks by using domain- or physics-related priors. The thesis is divided into two parts. In Part I, we exploit human abstraction capabilities to identify existing relationships in images, thus defining domains that can be leveraged to improve data usage efficiency. We use additional domain-related information to train networks on web-crawled data, hallucinate scenarios unseen during training, and perform few-shot learning. In Part II, we instead rely on physics priors. First, we combine realistic physics-based rendering with generative networks to boost outputs realism and controllability. Then, we exploit naive physical guidance to drive a manifold reorganization, which allowed generating continuous conditions such as timelapses.

Thermal and air quality modeling of an electric vehicle cabin with low-cost sensors and reinforcement learning

The design process of any electric vehicle system has to be oriented towards the best energy efficiency, together with the constraint of maintaining comfort in the vehicle cabin. Main aim of this study is to research the best thermal management solution in terms of HVAC efficiency without compromising occupant’s comfort and internal air quality. An Arduino controlled Low Cost System of Sensors was developed and compared against reference instrumentation (average R-squared of 0.92) and then used to characterise the vehicle cabin in real parking and driving conditions trials. Data on the energy use of the HVAC was retrieved from the car On-Board Diagnostic port. Energy savings using recirculation can reach 30 %, but pollutants concentration in the cabin builds up in this operating mode. Moreover, the temperature profile appeared strongly nonuniform with air temperature differences up to 10° C. Optimisation methods often require a high number of runs to find the optimal configuration of the system. Fast models proved to be beneficial for these task, while CFD-1D model are usually slower despite the higher level of detail provided. In this work, the collected dataset was used to train a fast ML model of both cabin and HVAC using linear regression. Average scaled RMSE over all trials is 0.4 %, while computation time is 0.0077 ms for each second of simulated time on a laptop computer. Finally, a reinforcement learning environment was built in OpenAI and Stable-Baselines3 using the built-in Proximal Policy Optimisation algorithm to update the policy and seek for the best compromise between comfort, air quality and energy reward terms. The learning curves show an oscillating behaviour overall, with only 2 experiments behaving as expected even if too slow. This result leaves large room for improvement, ranging from the reward function engineering to the expansion of the ML model.

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.

A deep learning model for controlling the galvanizing process in a production line

In the industry of steelmaking, the process of galvanizing is a treatment which is applied to protect the steel from corrosion. The air knife effect (AKE) occurs when nozzles emit a steam of air on the surfaces of a steel strip to remove excess zinc from it. In our work we formalized the problem to control the AKE and we implemented, with the R&D dept.of MarcegagliaSPA, a DL model able to drive the AKE. We call it controller. It takes as input the tuple : a tuple of the physical conditions of the process line (t,h,s) with the target value of the zinc coating (c); and generates the expected tuple of (pres and dist) to drive the mechanical nozzles towards the (c). According to the requirements we designed the structure of the network. We collected and explored the data set of the historical data of the smart factory. Finally, we designed the loss function as sum of three components: the minimization between the coating addressed by the network and the target value we want to reach; and two weighted minimization components for both pressure and distance. In our solution we construct a second module, named coating net, to predict the coating of zinc resulting from the AKE when the conditions are applied to the prod. line. Its structure is made by a linear and a deep nonlinear “residual” component learned by empirical observations. The predictions made by the coating nets are used as ground truth in the loss function of the controller. By tuning the weights of the different components of the loss function, it is possible to train models with slightly different optimization purposes. In the tests we compared the regularization of different strategies with the standard one in condition of optimal estimation for both; the overall accuracy is ± 3 g/m^2 dal target for all of them. Lastly, we analyze how the controller modeled the current solutions with the new logic: the sub-optimal values of pres and dist can be optimize of 50% and 20%.

Utilization Of (15)no3 (-) By Nodulated Soybean Plants Under Conditions Of Root Hypoxia.

Waterlogging of soils is common in nature. The low availability of oxygen under these conditions leads to hypoxia of the root system impairing the development and productivity of the plant. The presence of nitrate under flooding conditions is regarded as being beneficial towards tolerance to this stress. However, it is not known how nodulated soybean plants, cultivated in the absence of nitrate and therefore not metabolically adapted to this compound, would respond to nitrate under root hypoxia in comparison with non-nodulated plants grown on nitrate. A study was conducted with (15)N labelled nitrate supplied on waterlogging for a period of 48 h using both nodulated and non-nodulated plants of different physiological ages. Enrichment of N was found in roots and leaves with incorporation of the isotope in amino acids, although to a much smaller degree under hypoxia than normoxia. This demonstrates that nitrate is taken up under hypoxic conditions and assimilated into amino acids, although to a much lesser extent than for normoxia. The similar response obtained with nodulated and non-nodulated plants indicates the rapid metabolic adaptation of nodulated plants to the presence of nitrate under hypoxia. Enrichment of N in nodules was very much weaker with a distinct enrichment pattern of amino acids (especially asparagine) suggesting that labelling arose from a tissue source external to the nodule rather than through assimilation in the nodule itself.

Endocytosis Of Tight Junctions Caveolin Nitrosylation Dependent Is Improved By Cocoa Via Opioid Receptor On Rpe Cells In Diabetic Conditions.

Retinal pigment epithelium cells, along with tight junction (TJ) proteins, constitute the outer blood retinal barrier (BRB). Contradictory findings suggest a role for the outer BRB in the pathogenesis of diabetic retinopathy (DR). The aim of this study was to investigate whether the mechanisms involved in these alterations are sensitive to nitrosative stress, and if cocoa or epicatechin (EC) protects from this damage under diabetic (DM) milieu conditions. Cells of a human RPE line (ARPE-19) were exposed to high-glucose (HG) conditions for 24 hours in the presence or absence of cocoa powder containing 0.5% or 60.5% polyphenol (low-polyphenol cocoa [LPC] and high-polyphenol cocoa [HPC], respectively). Exposure to HG decreased claudin-1 and occludin TJ expressions and increased extracellular matrix accumulation (ECM), whereas levels of TNF-α and inducible nitric oxide synthase (iNOS) were upregulated, accompanied by increased nitric oxide levels. This nitrosative stress resulted in S-nitrosylation of caveolin-1 (CAV-1), which in turn increased CAV-1 traffic and its interactions with claudin-1 and occludin. This cascade was inhibited by treatment with HPC or EC through δ-opioid receptor (DOR) binding and stimulation, thereby decreasing TNF-α-induced iNOS upregulation and CAV-1 endocytosis. The TJ functions were restored, leading to prevention of paracellular permeability, restoration of resistance of the ARPE-19 monolayer, and decreased ECM accumulation. The detrimental effects on TJs in ARPE-19 cells exposed to DM milieu occur through a CAV-1 S-nitrosylation-dependent endocytosis mechanism. High-polyphenol cocoa or EC exerts protective effects through DOR stimulation.

Surgical Site Infections In Women And Their Association With Clinical Conditions.

Surgical site infections (SSIs) can affect body tissues, cavities, or organs manipulated in surgery and constitute 14% to 16% of all infections. This study aimed to determine the incidence of SSIs in women following their discharge from a gynecology outpatient clinic, to survey different types of SSIs among women, and to verify the association of SSIs with comorbidities and clinical conditions. Data were collected via analytical observation with a cross-sectional design, and the study was conducted in 1,026 women who underwent gynecological surgery in a teaching hospital in the municipality of Teresina, in the northeast Brazilian State of Piauí, from June 2011 to March 2013. The incidence of SSIs after discharge was 5.8% among the women in the outpatient clinic. The most prevalent surgery among the patients was hysterectomy, while the most prevalent type of SSI was superficial incisional. Comorbidities in women with SSIs included cancer, diabetes mellitus, and hypertension. Surveillance of SSIs during the post-discharge period is critical for infection prevention and control. It is worth reflecting on the planning of surgical procedures for patients who have risk factors for the development of SSIs.

Leaf-, Panel- And Latex-expressed Sequenced Tags From The Rubber Tree (hevea Brasiliensis) Under Cold-stressed And Suboptimal Growing Conditions: The Development Of Gene-targeted Functional Markers For Stress Response.

Hevea brasiliensis is a native species of the Amazon Basin of South America and the primary source of natural rubber worldwide. Due to the occurrence of South American Leaf Blight disease in this area, rubber plantations have been extended to suboptimal regions. Rubber tree breeding is time-consuming and expensive, but molecular markers can serve as a tool for early evaluation, thus reducing time and costs. In this work, we constructed six different cDNA libraries with the aim of developing gene-targeted molecular markers for the rubber tree. A total of 8,263 reads were assembled, generating 5,025 unigenes that were analyzed; 912 expressed sequence tags (ESTs) represented new transcripts, and two sequences were highly up-regulated by cold stress. These unigenes were scanned for microsatellite (SSR) regions and single nucleotide polymorphisms (SNPs). In total, 169 novel EST-SSR markers were developed; 138 loci were polymorphic in the rubber tree, and 98 % presented transferability to six other Hevea species. Locus duplication was observed in H. brasiliensis and other species. Additionally, 43 SNP markers in 13 sequences that showed similarity to proteins involved in stress response, latex biosynthesis and developmental processes were characterized. cDNA libraries are a rich source of SSR and SNP markers and enable the identification of new transcripts. The new markers developed here will be a valuable resource for linkage mapping, QTL identification and other studies in the rubber tree and can also be used to evaluate the genetic variability of other Hevea species, which are valuable assets in rubber tree breeding.

Long-term Follow-up Of Patients With 46,xy Partial Gonadal Dysgenesis Reared As Males.

Background/Aims. Studies on 46,XY partial gonadal dysgenesis (PGD) have focused on molecular, gonadal, genital, and hormone features; little is known about follow-up. Our aim was to analyze long-term outcomes of PGD. Methods. Retrospective longitudinal study conducted at a reference service in Brazil. Ten patients were first evaluated in the 1990s and followed up until the 2010s; follow-up ranged from 13.5 to 19.7 years. All were reared as males and had at least one scrotal testis; two bore NR5A1 mutations. Main outcomes were: associated conditions, pubertal development, and growth. Results. All patients had normal motor development but three presented cognitive impairment; five had various associated conditions. At the end of the prepubertal period, FSH was high or high-normal in 3/6 patients; LH was normal in all. At the last evaluation, FSH was high or high-normal in 8/10; LH was high or high-normal in 5/10; testosterone was decreased in one. Final height in nine cases ranged from -1.57 to 0.80 SDS. All had spontaneous puberty; only one needed androgen therapy. Conclusions. There is good prognosis for growth and spontaneous pubertal development but not for fertility. Though additional studies are required, screening for learning disabilities is advisable.

Ecological Literacy And Beyond: Problem-based Learning For Future Professionals.

Ecological science contributes to solving a broad range of environmental problems. However, lack of ecological literacy in practice often limits application of this knowledge. In this paper, we highlight a critical but often overlooked demand on ecological literacy: to enable professionals of various careers to apply scientific knowledge when faced with environmental problems. Current university courses on ecology often fail to persuade students that ecological science provides important tools for environmental problem solving. We propose problem-based learning to improve the understanding of ecological science and its usefulness for real-world environmental issues that professionals in careers as diverse as engineering, public health, architecture, social sciences, or management will address. Courses should set clear learning objectives for cognitive skills they expect students to acquire. Thus, professionals in different fields will be enabled to improve environmental decision-making processes and to participate effectively in multidisciplinary work groups charged with tackling environmental issues.

Theobromine Increases Nad⁺/sirt-1 Activity And Protects The Kidney Under Diabetic Conditions.

Reduction in sirtuin 1 (Sirt-1) is associated with extracellular matrix (ECM) accumulation in the diabetic kidney. Theobromine may reduce kidney ECM accumulation in diabetic rats. In the current study, we aimed to unravel, under diabetic conditions, the mechanism of kidney ECM accumulation induced by a reduction in Sirt-1 and the effect of theobromine in these events. In vitro, we used immortalized human mesangial cells (iHMCs) exposed to high glucose (HG; 30 mM), with or without small interfering RNA for NOX4 and Sirt-1. In vivo, spontaneously hypertensive rats (SHR) were rendered diabetic by means of streptozotocin and studied after 12 wk. The effects of treatment with theobromine were investigated under both conditions. HG leads to a decrease in Sirt-1 activity and NAD(+) levels in iHMCs. Sirt-1 activity could be reestablished by treatment with NAD(+), silencing NOX4, and poly (ADP-ribose) polymerase-1 (PARP-1) blockade, or with theobromine. HG also leads to a low AMP/ATP ratio, acetylation of SMAD3, and increased collagen IV, which is prevented by theobromine. Sirt-1 or AMPK blockade abolished these effects of theobromine. In diabetic SHR, theobromine prevented increases in albuminuria and kidney collagen IV, reduced AMPK, elevated NADPH oxidase activity and PARP-1, and reduced NAD(+) levels and Sirt-1 activity. These results suggest that in diabetes mellitus, Sirt-1 activity is reduced by PARP-1 activation and NAD(+) depletion due to low AMPK, which increases NOX4 expression, leading to ECM accumulation mediated by transforming growth factor (TGF)-β1 signaling. It is suggested that Sirt-1 activation by theobromine may have therapeutic potential for diabetic nephropathy.

Flicker perimetry in healthy subjects: influence of age and gender, learning effect and short-term fluctuation

PURPOSE: To determine the mean critical fusion frequency and the short-term fluctuation, to analyze the influence of age, gender, and the learning effect in healthy subjects undergoing flicker perimetry. METHODS: Study 1 - 95 healthy subjects underwent flicker perimetry once in one eye. Mean critical fusion frequency values were compared between genders, and the influence of age was evaluated using linear regression analysis. Study 2 - 20 healthy subjects underwent flicker perimetry 5 times in one eye. The first 3 sessions were separated by an interval of 1 to 30 days, whereas the last 3 sessions were performed within the same day. The first 3 sessions were used to investigate the presence of a learning effect, whereas the last 3 tests were used to calculate short-term fluctuation. RESULTS: Study 1 - Linear regression analysis demonstrated that mean global, foveal, central, and critical fusion frequency per quadrant significantly decreased with age (p<0.05).There were no statistically significant differences in mean critical fusion frequency values between males and females (p>0.05), with the exception of the central area and inferonasal quadrant (p=0.049 and p=0.011, respectively), where the values were lower in females. Study 2 - Mean global (p=0.014), central (p=0.008), and peripheral (p=0.03) critical fusion frequency were significantly lower in the first session compared to the second and third sessions. The mean global short-term fluctuation was 5.06±1.13 Hz, the mean interindividual and intraindividual variabilities were 11.2±2.8% and 6.4±1.5%, respectively. CONCLUSION: This study suggests that, in healthy subjects, critical fusion frequency decreases with age, that flicker perimetry is associated with a learning effect, and that a moderately high short-term fluctuation is expected.

Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs) for glaucoma diagnosis using Spectral Domain OCT (SD-OCT) and standard automated perimetry (SAP). METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP) and retinal nerve fiber layer (RNFL) imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG), Naive-Bayes (NB), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Random Forest (RAN), Ensemble Selection (ENS), Classification Tree (CTREE), Ada Boost M1(ADA),Support Vector Machine Linear (SVML) and Support Vector Machine Gaussian (SVMG). Areas under the receiver operating characteristic curves (aROC) obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE) to 0.946 (RAN).The best OCT+SAP aROC obtained with RAN (0.946) was significantly larger the best single OCT parameter (p<0.05), but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19). CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

Adaptação do handebol para a prática em cadeira de rodas

Universidade Estadual de Campinas . Faculdade de Educação Física

Imigrantes bolivianos em São Paulo : a Praça Kantuta e o futebol

Universidade Estadual de Campinas . Faculdade de Educação Física