https://repositorio.ufu.br/handle/123456789/5145 2026-07-06T20:49:06Z https://repositorio.ufu.br/handle/123456789/48798 Title: Ferramenta mmbarcada para diagnóstico e simulação de comunicação Modbus Abstract: This work presents the development of a portable and multifunctional embedded tool for Modbus RTU communication analysis, logging, and simulation, aimed at the maintenance and diagnostics of industrial networks in the field. Based on an STM32F407 microcontroller with a touchscreen graphical interface, the device operates in three modes selectable at runtime: master, slave, and sniffer/datalogger, with support for RS-232 and RS-485 interfaces. The firmware was structured around a custom Hardware Abstraction Layer (HAL) based on opaque pointers and dependency injection, easing maintenance and code portability. The results confirmed correct operation in all three modes, with reliable traffic capture and continuous frame logging to an SD card with timestamps. As a contribution, this work delivers a compact tool to support maintenance, diagnostics, testing, and educational activities related to Modbus RTU networks. 2026-03-25T00:00:00Z https://repositorio.ufu.br/handle/123456789/48781 Title: Protótipo de exoesqueleto de membro superior 2026-03-10T00:00:00Z https://repositorio.ufu.br/handle/123456789/48761 Title: Uma proposta metodológica não invasiva para o compartilhamento da responsabilidade sobre desequilíbrios de tensão baseada na minimização da correlação das fontes Abstract: Electrical power systems have undergone substantial transformations due to the incorporation of new technologies, bringing significant impacts on power quality, notably the voltage imbalance arising from operational conditions imposed by modern power grids. In fact, this indicator and others associated with the loss of power quality have grown and, for many installations, reach proportions exceeding the limits established by regulatory bodies. Such violations represent sources of harmful impact for the agents involved, who may suffer various losses, such as a decrease in network operational efficiency, reduction in the useful life of installation components, and untimely supply interruptions, among others. In these circumstances, when such regulatory standard violations occur, mitigation alternatives emerge that represent high financial costs; recognizing that connection buses — the Points of Common Coupling — unite two or more agents, this can lead to conflicts between the parties. Focusing on the search for means of responsibility sharing regarding the final effects, the literature presents a vast bibliography that, however, still lacks non-invasive analysis methods with consolidated physical and application properties for practical field use. Considering this fact, this thesis proposes the development of the Correlation Minimization Method, a new non-invasive strategy for the sharing of responsibility over total voltage unbalances measured at the PCC that offers reliability, robustness, and practical applicability. The methodology is based on the statistical independence of the fast-varying components of the agents' current sources and stands out for not requiring physical interventions in the network for the analysis process. Besides establishing the theoretical foundations of this new strategy, the work evaluates its performance comparatively with the main methodologies in literature, such as Least Squares and Complex Independent Component Analysis Method, demonstrating, through computational analysis and experimental validations in a real facility, its superiority in terms of reliability, robustness, and operational practicality. 2026-05-06T00:00:00Z https://repositorio.ufu.br/handle/123456789/48733 Title: Efeitos dos Canabinoides no Tremor Parkinsoniano e interações medicamentosas: análise por inteligência artificial explicável dos dados Fox Insight Abstract: Parkinson’s disease constitutes the second most prevalent neurodegenerative condition worldwide, affecting 1-2% of the population over 65 years of age, with tremor present in 70% of cases. Conventional pharmacological treatments present limitations in 30-40% of patients, establishing the need for therapeutic alternatives. This thesis aimed to develop an explainable artificial intelligence methodology for personalizing medical cannabis use in treating parkinsonian tremor, quantifying determinants of individual heterogeneity in therapeutic response. The methodology employed analysis based on SHAP (SHapley Additive exPlanations) values applied to 2,616 records from the Fox Insight platform, structured in three progressive datasets: SINGLE (n=973, isolated cannabis), FULL_NUMERICO (n=931, pharmacological groups), and FULL_GFEM (n=931, detailed individual characteristics). Machine learning models achieved elevated performance metrics: SINGLE (LightGBM) with accuracy 96.31%, precision 96.33%, recall 96.31%, F1-score 96.31%, and specificity 96.03%; FULL_NUMERICO (LightGBM) with accuracy 97.42%, precision 97.47%, recall 97.42%, F1-score 97.42%, and specificity 97.07%; FULL_GFEM (XGBoost) with accuracy 97.42%, precision 97.54%, recall 97.42%, F1-score 97.42%, and specificity 96.91%, demonstrating that interpretability does not compromise predictive performance when architecture is adequately designed. Results quantified eight main findings: (1) pronounced sexual dimorphism, with women presenting mean SHAP values of +1.52 ± 0.48 (improvement rate 94.1%) versus men -0.93 ± 0.37 (rate 38.5%), establishing a magnitude of 2.44x in the probability of favorable response; (2) identification of six distinct profiles through clustering, with 55% of patients presenting elevated improvement rates (89% to 100%) and SHAP values between +1.94 and +2.57; (3) non-linear inverted-U age pattern, with critical group 60-70 years (n=559, 60% of sample) presenting worse response (rate 38.8%) and partial recovery in 70-80 years (rate 76.2%, n=181); (4) hierarchy of administration routes quantified by MASV (Mean Absolute SHAP Value): oil (0.705) > sublingual (0.4959) > food (0.657 Class 1), demonstrating importance superior to dose; (5) bifasic optimal therapeutic windows for THC (1.5-2.5 mg/day, MASV = 0.2888) and CBD (2-4 mg/day, MASV = 0.2654), empirically validating that supra-therapeutic doses reduce efficacy; (6) quantified synergy with MAO-B inhibitors (MASV = 0.4485), superior to interactions with levodopa (MASV = 0.2506) and other dopaminergics (MASV = 0.2454); (7) moderate optimal frequency of 3-5 times/week, superior to continuous daily use; (8) therapeutic learning curve with optimization in 2-3 years and possible tolerance after >3 years. Findings were operationalized in a clinical nomogram that stratifies patients into five predictive categories, with 87.3% concordance with phenotypic clusters. Computational analysis through clustering identified difference in improvement rates between subgroups with elevated response (89-100%, n=513) and general population (66.4%, n=931), suggesting potential for therapeutic personalization based on identifiable clinical characteristics, hypothesis requiring confirmation in future clinical studies. This investigation establishes a new methodological standard for research in precision neurological medicine, providing computational tools and quantitative knowledge for prospective identification of subgroups with high probability of benefit, individualized therapeutic regimen optimization, and establishment of expectations based on measurable patient characteristics. 2025-12-01T00:00:00Z