Abstract

Abstract
The Electroencephalogram (EEG) is a medical tool that captures, in a non-invasive way, electrical signals from the brain activities performed by neurons. EEG signals have been the target of study as a biomarker of Parkinsons disease (PD), where several methods of analysis are applied. The present work aims to evaluate features extracted from EEG signals, through methodologies such as HOS, Haralick descriptors, and Fractal Features, as new biomarkers for PD identification. Data from 50 individuals, available at the Open Neuro repository, who underwent an attentional cognitive task were analyzed. RF and SVM algorithms were employed for the classification of the extracted features. The best accuracy achieved was 79.49% in differentiating between Parkinsons subjects and control subjects using Haralick descriptors and RF classifier, suggesting that these features can identify activations in brain areas caused by dopaminergic medication.

Abstract

Abstract
The constant stream of news nowadays highlights the necessity for meticulous assessment to ensure that the information accurately reaches its intended audience with the least amount of delay least delay. Despite the flexibility and efficiency of Deep Learning (DL) models, their intricate training and substantial resource demands pose significant challenges for their deployment in real-time applications. In this regard, this study evaluates the performance of resource-efficient Machine Learning (ML) techniques – Multinomial Naive Bayes (MNB), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR) – in categorizing news. Based on the results, all the evaluated models attain a commendable level of accuracy in news categorization. Notably, the SVM excels, achieving an accuracy rate of 98% and a mean squared error of 0.28. This performance exemplifies the robust effectiveness of classical ML models in the categorization of news, particularly when enhanced by a suitably tailored preprocessing pipeline. © 2024, Universidade do Porto - Faculdade de Engenharia. All rights reserved.

Abstract
The development of Artificial Intelligence (AI) models with an accurate prediction of human facial expression has become a significant challenge for the cases in which masks and sunglasses cover critical facial areas. Given that a substantial portion of human interactions involves non-verbal communication, accurately detecting human emotions such as anger, fear, disgust, happiness, sadness, and surprise would benefit a wide range of applications, from security assessments to psychological treatments. As a workaround, the current study explores the performance of a novel multi-channel arrangement comprised of a Haar-wavelet, Histogram of Oriented Gradients (HOG), and grayscale filters to improve the predictions of deep Convolutional Neural Network (CNN) on occluded results. This study uses the FER-2013 dataset and produces occluded samples by applying a virtual mask that covers almost 55% of facial areas comprising the mouth, lips, and jaw locations. Further investigations, including the impact of each filter, utilizing pre-trained models on occluded samples (transfer learning), and comparison to prior models are also carried out. The proposed approach yields an accuracy rate of 71% for non-occluded and 66% for the occluded samples, which are 6% to 11% higher than the base model. Further transfer learning technique increases the accuracy metrics by 18%, indicating that non-occluded pre-trained models can reveal a broader range of features and their relation, which to some extent compensates for the removed features due to the occlusion. These results suggest the potential capabilities of the proposed technique for similar imaging applications.

Abstract