Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: neurodegenerative disorder

Sortuj według:

Ogranicz wyniki do:

Textural feature of EEG signals as a new biomarker of reward processing in Parkinson’s disease detection

Ezazi Yasamin, Ghaderyan Peyvand

Biocybernetics and Biomedical Engineering

2022

Vol. 42, no. 3

950--962

Background: Parkinson’s disease (PD) detection holds great potential for providing effective treatments, slowing the disease process, and improving the quality of patient’s life, but the development of a clinical accurate, generalized, robust and cost-effective method is a challenge. Method: In this paper, a novel PD detection method based on textural features of clinical electroencephalogram (EEG) signals has been proposed. In contrast to most existing methods, which do not consider reward positivity (RP)-relevant features for automatic PD detection, this method has focused on providing a novel EEG marker of RP using an enhanced time-frequency representation, texture descriptors based on Gray Level Co-occurrence Matrix, local binary pattern, and sparse coding classifier. Results: The proposed method has been evaluated using EEG signals recorded during a reinforcement-learning task from 28 patients with PD and 28 sex- and age matched healthy controls. Results have demonstrated that the proposed architecture reaches a high detection with an average accuracy rate of 100%, presenting better performance and outperforming previous techniques. Conclusions: it can provide a new solution to detect RP changes in PD and can offer obvious stability advantages on several clinical and technical variables (medication states, type of textural descriptors, reduced channels), suggesting a generalizable detection system.

Regularization based discriminative feature pattern selection for the classification of Parkinson cases using machine learning

Kaliyan Kamalakannan, Ganesan Anandharaj

Bio-Algorithms and Med-Systems

2021

Vol. 17, no. 3

181--189

Objectives: This paper focuses on developing a regularization-based feature selection approach to select the most effective attributes from the Parkinson’s speech dataset. Parkinson’s disease is a medical condition that progresses as the dopamine-producing nerve cells are affected. Early diagnosis often reduces the effect on the individuals, minimizes the advancement over time. In recent times, intelligent computational models are used in many complex cases to diagnose a clinical condition with high precision. These models are intended to find meaningful representation from the data to diagnose the disease. Machine learning acts as a tool, gears up the model learning process through a mathematical baseline. But, not in all cases, machine learning will be demanded to perform optimally. It comes with a few constraints, mainly the representation of the data. The learning models expect a clean, noise-free input, which in-turns produces better discriminative patterns over different categories of classes. Methods: The proposed model identified five candidate features as predictors. This feature subset is trained with different varieties of supervised classifiers to trace out the best-performing model. Results: The results are validated through accuracy, precision, recall, and receiver’s operational characteristic curves. The proposed regularization- based feature selection model outperformed the benchmark algorithms by attaining 100% accuracy on most of the classifiers, other than linear discriminant analysis (99.90%) and naïve Bayes (99.51%). Conclusions: This paper exhibits the need for intelligent models to analyze complex data patterns to assist medical practitioners in better disease diagnosis. The results exhibit that the regularization methods find the best features based on their importance score, which improved the model performance over other feature selection methods.