TCC Sistemas de Informação

URI Permanente para esta coleção

https://repositorio.ifal.edu.br/handle/123456789/46

Navegar

Agora exibindo 1 - 5 de 5

Análise de movimentos motores finos dos dedos utilizando visão computacional: um estudo de caso do Finger Tapping Test (FTT) na doença de Parkinson
(2025-11-26) Campos, Herbert Douglas Silva da Silva; Nascimento, Arlyson Alves do; http://lattes.cnpq.br/9395417554768580; Medeiros, Leonardo Melo de; http://lattes.cnpq.br/1080593968001453; Passos, Frederico Salgueiro; Calado, Ivo Augusto; http://lattes.cnpq.br/5748220882915553
Parkinson’s disease (PD) is characterized as a neurodegenerative and progressive disorder that affects a significant portion of the elderly population worldwide. The most common symptoms in PD include cognitive problems, which predominantly begin to appear in more advanced stages, unlike the motor symptoms that manifest at the onset of the disease. The Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) is one of the assessments that aid in diagnosing and monitoring the levels of Parkinson’s disease in patients. Within the MDS-UPDRS III, which assesses the motor aspects of patients, there is the Finger Tapping Test (FTT), used to assess bradykinesia and rigidity of movement. FTT is typically administered by a healthcare professional who observes the patient performing the test. However, the use of computer vision can provide a more effective alternative by accurately capturing the movement’s characteristics. The aim of this study was to develop a computer vision system capable of acquiring data from fine finger movements during the FTT and subsequently classify Parkinson’s disease levels according to the MDS-UPDRS. For this study, a computer vision algorithm was created to record data resulting from the abduction and adduction of hand movements during the FTT, calculating the amplitude generated by these movements. A dataset comprising 532 videos of both Parkinson’s and non-Parkinson’s patients, classified into four levels according to the MDS-UPDRS, was used. Subsequently, biomechanical signal processing procedures were conducted. The results obtained indicate that the use of computer vision in assisting healthcare professionals is promising. Data collection from movements allows for the creation of a database that can be used in machine learning models to predict the patient’s disease level based on the MDS-UPDRS. Additionally, a binary classifier was developed to determine the level at which each patient falls, using a Support Vector Machine (SVM) along with the leave-one-out cross-validation technique. This resulted in an accuracy of 73.3% when using the entire available dataset and 76.6% when using only the right-hand FTT.
Análise do monitoramento dos sinais motores da doença de Parkinson: uma revisão sistemática
(Instituto Federal de Educação Ciência e Tecnologia de Alagoas, 2023-05-31) Lima, Mayara Rysia de Assis; Medeiros, Leonardo Melo de; http://lattes.cnpq.br/1080593968001453; Costa, Breno Jacinto Duarte da; http://lattes.cnpq.br/7418697922506495; Passos, Frederico Salgueiro; http://lattes.cnpq.br/6590059682506348
Parkinson’s Disease (PD) is a chronic degenerative disease that causes a motor disorder affecting the individual’s routine tasks and destabilizing their quality of life. The most notable motor signs make up a tetrad: rigidity, bradykinesia, postural and gait changes, and resting tremor. Thus, the medical examination requires an assessment of motor movements, emphasizing the speed, amplitude and rhythm of each movement, in order to monitor the symptoms and improve the clinical diagnosis. In order to distinguish improvements or evolutions of PD, motor assessment methods become increasingly indispensable, and in the literature, systems or mechanisms for quantifying these symptoms are found, the most recurrent being for the signs of bradykinesia, aided by the most well-known skill test, the Finger-Tapping Test (FTT). However, none of them is yet able to prove a definitive diagnosis, therefore relying on the interpretation of a neurologist. This research presents a Systematic Literature Review (SLR) with academic artifacts produced, which demonstrate relevant data on motor movements and their quantification, using mostly the MDS UPDRS part III scale as a guide, in order to extract a set of requirements to be developed in a system for monitoring the progress of Parkinson’s motor signs, using the finger tapping test (FTT) as a technique. As a result, the RSL aimed to identify the most current techniques and approaches that quantify motor assessments, in addition to clarifying whether these methods demonstrate positive interference in the assessment process with the FTT technique.
Fundamentação do Programa Triple-N com o método do estudo e da escrita imanente à vida
(2026-06-10) Silva Neto, Natalício Nunes da; Bezerra, Ciro de Oliveira; http://lattes.cnpq.br/8755460275894251; Medeiros, Leonardo Melo de; http://lattes.cnpq.br/1080593968001453; Pinto, Charridy Max Fontes; http://lattes.cnpq.br/4139562888411167; Cruz , Jailton Cardoso da; http://lattes.cnpq.br/9366016044068759
Our research focuses on the study of Parkinson’s Disease (PD). But what is Parkinson’s Disease? It is a progressive neurological disorder that develops gradually and compromises the sensorimotor system. For example, it causes symptoms such as tremors, slowness of movement (bradykinesia), and postural imbalance. PD affects millions of people worldwide, across all age groups; however, the elderly population is the most affected. Data from the World Health Organization (WHO) show that approximately 1% of the global population over the age of 65 has the disease. The main reason is the progressive loss of dopamine, which, in confirmed cases of PD, is found to be far below normal levels. Interestingly, studies have shown that reading and writing stimulate the production of neurotransmitters that increase dopamine. Thus, among the various possibilities for preventing the disease, we highlight that studying and writing, when practiced regularly as a personal and social habit, may mitigate the effects of Parkinson’s Disease. Diagnosing PD with precision is challenging, especially in its early stages. Among the existing techniques, micrography is commonly employed. This method essentially consists of handwriting examinations. It is precisely in the refinement of such techniques that Machine Learning (ML) emerges as a powerful category within computer science, improving data classification methods that identify patterns and assist in PD detection. Our research employs three ML models: HOG (Histogram of Oriented Gradients) + Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Transfer Learning (MobileNetV2), with the aim of classifying handwriting samples and contributing to greater accuracy and efficiency in medical diagnosis of PD. The results of our study highlight the use of a supervised ML program (developed by us and named Triple-N, after the author), which achieved promising performance. Specifically, it reached accuracy rates of 80% for HOG + SVM, 96% for CNN, and 98% for Transfer Learning, when combined with Data Augmentation techniques. These findings suggest that the application of Machine Learning, particularly with Data Augmentation, in the classification of handwriting examinations, can be a valuable tool in PD diagnosis. Two key advantages stand out: [1] low cost and [2] rapid delivery of results, enabling the majority of patients to access diagnosis from the early stages of the disease.
Predição de crimes violentos contra o patrimônio em Maceió e Arapiraca usando o ConvLSTM
(2026-05-02) Ferreira, Leonardo Victor Fernandes; Medeiros, Leonardo Melo de; http://lattes.cnpq.br/1080593968001453; Cruz, Jailton Cardoso da; http://lattes.cnpq.br/9366016044068759; Costa, Breno Jacinto Duarte da; http://lattes.cnpq.br/7418697922506495
Spatiotemporal forecasting of violent property crimes is a relevant problem for the planning of preventive actions and for the allocation of public security resources. This work presents a methodological replication, in the context of the cities of Maceió and Arapiraca, of the fine-grained crime forecasting pipeline proposed by Albors Zumel, Tizzoni, and Campedelli (2025), based on a ConvLSTM architecture. From georeferenced records of violent property crimes provided by the Military Police of Alagoas, covering the period from 2012 to 2022, the work organizes the data into regular grids with cells of approximately 0.2 km2, aggregates occurrences in 12-hour windows, binarizes the cell-level signal, and trains a ConvLSTM with explicit imbalance treatment via weighted BCEWithLogitsLoss. Evaluation is performed by sweeping the classification threshold, reporting precision, recall, and F1 both in the traditional variant (cell-by-cell) and with spatial tolerance (Chebyshev neighborhood ≤ 1). The results show that, in both cities, the model achieves performance in the spatial variant significantly higher than in the traditional variant (spatial F1 of approximately 0.24 in Maceió and 0.21 in Arapiraca, against values below 0.05 in the traditional variant), evidencing that the network learns to correctly locate risk neighborhoods even when missing the exact cell. The work also discusses the main limitations of the approach, particularly the extreme sparsity of the data, and proposes directions for future developments, including the incorporation of sociodemographic and human mobility channels and comparison against baseline models.
Quantificação do sinal do tremor parkinsoniano em exames manuscritos em espiral utilizando Machine Learning
(Instituto Federal de Educação Ciência e Tecnologia de Alagoas, 2023-10-27) Correia, Igor Matheus Barros; Medeiros, Leonardo Melo de; http://lattes.cnpq.br/1080593968001453; Costa, Breno Jacinto Duarte da; http://lattes.cnpq.br/7418697922506495; Costa, Alex Emanuel Barros; http://lattes.cnpq.br/2231272728491909
Parkinson’s disease (PD) is a progressive neurological disease that develops gradually and causes motor symptoms, such as tremors, slow movement (bradykinesia) and postural imbalance. PD affects millions of people worldwide, especially the elderly population. Data from the World Health Organization (WHO) shows that approximately 1% of the world’s population over the age of 65 has the disease. Diagnosing PD is difficult and misdiagnosis is common, especially in the early stages. Micrography is a technique commonly used in the diagnosis of Parkinson’s disease and essentially consists of performing handwritten examinations. In this context, Machine Learning (ML) emerges as a powerful tool to apply data classification techniques that can identify patterns and assist in the detection of PD. This study uses two Machine Learning models, namely Support Vector Machine (SVM) and Random Forest Classifier (RFC), with the aim of classifying handwritten exams and contributing to improving the accuracy and effectiveness in diagnosing PD. The results show that both models achieved promising performance, with high accuracy rates, reaching 86% for the RFC and 82% for the SVM. These results suggest that the application of Machine Learning to classify handwritten exams can be a valuable tool in diagnosing PD.

Navegar

Navegando TCC Sistemas de Informação por Orientador "Medeiros, Leonardo Melo de"

Resultados por página

Opções de Ordenação