RESUMEN
Attention Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder mainly affecting children. ADHD children brain activity is reported to present alterations from neurotypically developed children, yet establishment of an EEG biomarker, which is of high importance in clinical practice and research, has not been achieved. In this work, task-related EEG recordings from 61 ADHD and 60 age-matched non-ADHD children are analyzed to examine the underlying Cross-Frequency Coupling phenomena. The proposed framework introduces personalized brain rhythm extraction in the form of oscillatory modes via Swarm Decomposition, allowing for the transition from sensor-level connectivity to source-level connectivity. Oscillatory modes are then subjected to a phase locking value-based feature extraction and the efficiency of the extracted features in separating ADHD from non-ADHD individuals is evaluated by means of a nested 5-fold cross validation scheme. The experimental results of the proposed framework (Area Under the Receiver Operating Characteristics Curve-AUROC: 0.9166) when benchmarked against the commonly used filter-based brain rhythm extraction (AUROC: 0.8361) underscore its efficiency and demonstrate its overall superiority over other state-of-the-art functional connectivity approaches in this classification task for this dataset.Clinical relevance-This framework provides novel insights about brain regions of interest that are involved in ADHD task-related function and holds promise in providing objective ADHD biomarkers by extending classic sensor-level connectivity to source-level.
Asunto(s)
Trastorno por Déficit de Atención con Hiperactividad , Niño , Humanos , Trastorno por Déficit de Atención con Hiperactividad/diagnóstico , Encéfalo , Electroencefalografía/métodosRESUMEN
Emotion recognition in conversations using artificial intelligence (AI) has recently gained a lot of attention, as it can provide additional emotion cues that can be correlated with human social behavior. An extension towards an AI-based emotional climate (EC) recognition, i.e., the recognition of the joint emotional atmosphere dynamically created and perceived by the peers throughout a conversation, is proposed here. In our approach, namely MLBispeC (Machine Learning Based Bispectral Classification), the peers' speech signals during their conversation are subjected to time-windowed bispectral analysis, allowing for feature extraction related to dynamic harmonics nonlinear interactions. In addition, peers' affect dynamics, derived from their same time-windowed emotion labeling, are combined to form an extended feature vector, inputted into two well-known machine learning classifiers (Support Vector Machine, K-Nearest Neighbor). MLBispeC was evaluated on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) open access dataset, which contains 2D emotions, i.e., Arousal (A) and valence (V) that are divided into (low/high) classes. The experimental results have shown that MLBispeC outperforms previous state-of-the-art techniques, achieving an accuracy of 0.826A/0.754V, sensitivity of 0.864A/0.774V, and area under the curve (AUC) of 0.821A/0.799V. This demonstrates the effectiveness of MLBispeC to objectively recognize peers' EC during their conversation, allowing for insights into their emotional and social interactions.Clinical relevance-Unobtrusive, objective and dynamic recognition of the EC built during peers' conversation can scaffold effective assessment of patients with physiological, psychological, and mental diseases, at various age ranges (children, adults, and older adults).
Asunto(s)
Inteligencia Artificial , Habla , Niño , Humanos , Anciano , Emociones/fisiología , Reconocimiento en Psicología , Nivel de AlertaRESUMEN
After the breakthroughs of Transformer networks in Natural Language Processing (NLP) tasks, they have led to exciting progress in visual tasks as well. Nonetheless, there has been a parallel growth in the number of parameters and the amount of training data, which led to the conclusion that Transformers are not suited for small datasets. This paper is the first to convey the feasibility of Compact Convolutional Transformers (CCT) for the prediction of Parkinsonian postural tremor based on the Bispectrum (BS) representation of IMU accelerometer time series. The dataset includes tri-axial accelerometer signals collected unobtrusively in-the-wild while subjects are on a phone call, and labelled by neurologists and signal processing experts. The BS is a noise-immune, higher-order representation that reflects a signal's deviation from Gaussianity and measures quadratic phase coupling. We performed comparative classification experiments using the CCT, pre-trained CNNs such as VGG-16 and ResNet-50, and the conventional Vision Transformer (ViT). Our model achieves competitive prediction accuracy and F1 score of 96% with only 1.016 M trainable parameters, compared to the ViT with 21.659 M trainable parameters, in a five-fold cross-validation scheme. Our model also outperforms pre-trained CNNs such as VGG-16 and ResNet-50. Furthermore, we show that the performance gains are maintained when training on a larger dataset of BS images. Our effort here is motivated by the hypothesis that data-efficient transformers outperform transfer learning using pre-trained CNNs, paving the way for promising deep learning architecture for small-scale, novel and noisy medical imaging datasets.Clinical relevance- Novel deep learning model for unobtrusive prediction of Parkinsonian Postural Tremor from Bispectrum image representation of tri-axial accelerometer signals collected in-the-wild.