Contrast and Homogeneity Feature Analysis for Classifying Tremor Levels in Parkinson’s Disease Patients

Abstract

Early detection of different levels of tremors helps to obtain a more accurate diagnosis of Parkinson’s disease and to increase the therapy options for a better quality of life for patients. This work proposes a non-invasive strategy to measure the severity of tremors with the aim of diagnosing one of the first three levels of Parkinson’s disease by the Unified Parkinson’s Disease Rating Scale (UPDRS). A tremor being an involuntary motion that mainly appears in the hands; the dataset is acquired using a leap motion controller that measures 3D coordinates of each finger and the palmar region. Texture features are computed using sum and difference of histograms (SDH) to characterize the dataset, varying the window size; however, only the most fundamental elements are used in the classification stage. A machine learning classifier provides the final classification results of the tremor level. The effectiveness of our approach is obtained by a set of performance metrics, which are also used to show a comparison between different proposed designs.

Diferenciação de pacientes cirróticos com e sem encefalopatia hepática a partir da análise de padrões motores finos: Um estudo piloto com o Leap Motion Controller

“…Neste presente estudo, o LMC foi aplicado na obtenção de 16 pontos das mãos de cirróticos de forma minimamente invasiva e com finalidade de diferenciação motora entre diferentes níveis de complicação da doença por EH. Outros estudos também já aplicaram o dispositivo na quantificação da motricidade, em especial para a análise do tremor na doença de Parkinson (Butt et al, 2018;Vivar et al, 2019). Estes estudos utilizaram os dados com inteligência artificial e chegaram a resultados e conclusões diferentes.…”

“…Estes estudos utilizaram os dados com inteligência artificial e chegaram a resultados e conclusões diferentes. Butt et al (2018) obteve resultados variando entre 70-80% de acurácia, enquanto Vivar et al (2019) chegou a resultados com 100% de acertos na diferenciação, considerando, inclusive, que suas técnicas de processamento de dados não foram iguais.…”

Computer-vision classification of corn seed varieties using deep convolutional neural network

“…This model combines several decision tree classifiers to improve prediction compared to a single decision tree classifier. Generally, it trains a set of simple classifications by replicating the training data and, following the combination of their outputs, defines the final class by voting (Vivar et al, 2019). The bagged tree was using the learner type of decision tree and bag ensemble technique.…”

Stretchable triboelectric sensor for measurement of the forearm muscles movements and fingers motion for Parkinson's disease assessment and assisting technologies

“…On the other hand, high-frequency rest tremor in limbs also indicates rigidity and is clinically associated with PD as a classical symptom (Obeso et al, 2017). The work in Vivar et al (2019) classifies the arm tremor in one of the first three levels of the UPDRS scale using IR sensors and cameras but may not be suitable for continuous data acquisition at home. In other traditional systems, tremors can be evaluated as in Kim et al (2018), which uses wearable gyroscopes to monitor the vibration of the wrist and index finger, employing a convolutional neural network to process the signal.…”