RESUMO
Stress has emerged as a major concern in modern society, significantly impacting human health and well-being. Statistical evidence underscores the extensive social influence of stress, especially in terms of work-related stress and associated healthcare costs. This paper addresses the critical need for accurate stress detection, emphasising its far-reaching effects on health and social dynamics. Focusing on remote stress monitoring, it proposes an efficient deep learning approach for stress detection from facial videos. In contrast to the research on wearable devices, this paper proposes novel Hybrid Deep Learning (DL) networks for stress detection based on remote photoplethysmography (rPPG), employing (Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), 1D Convolutional Neural Network (1D-CNN)) models with hyperparameter optimisation and augmentation techniques to enhance performance. The proposed approach yields a substantial improvement in accuracy and efficiency in stress detection, achieving up to 95.83% accuracy with the UBFC-Phys dataset while maintaining excellent computational efficiency. The experimental results demonstrate the effectiveness of the proposed Hybrid DL models for rPPG-based-stress detection.
Assuntos
Aprendizado Profundo , Humanos , Fotopletismografia , Face , Custos de Cuidados de Saúde , Memória de Longo PrazoRESUMO
DNA methylation is an epigenetic mechanism that controls gene expression. In Alzheimer's disease (AD), global DNA hypomethylation of neurons has been described in the human cerebral cortex. Moreover, several variants in the methylation pattern of candidate genes have been identified in brain tissue when comparing AD patients and controls. Specifically, DNA methylation changes have been observed in PSEN1 and APOE, both genes previously being involved in the pathophysiology of AD. In other degenerative dementias, methylation variants have also been described in key genes, such as hypomethylation of the SNCA gene in Parkinson's disease and dementia with Lewy bodies or hypermethylation of the GRN gene promoter in frontotemporal dementia. The finding of aberrant DNA methylation patterns shared by brain tissue and peripheral blood opens the door to use those variants as epigenetic biomarkers in the diagnosis of neurodegenerative diseases.
Assuntos
Doença de Alzheimer/genética , Metilação de DNA , Epigênese Genética , Demência/genética , Marcadores Genéticos , HumanosRESUMO
La metilación del ADN es un mecanismo epigenético que controla la expresión génica. En la enfermedad de Alzheimer (EA) se ha encontrado hipometilación global del ADN en neuronas del córtex cerebral humano. Además, se han identificado variaciones en el patrón de metilación de genes candidatos en el tejido cerebral entre pacientes y controles, como el gen PSEN1 y APOE, relacionados con la fisiopatología de la EA. En otras demencias degenerativas también se han descrito variaciones en la metilación de genes clave, como hipometilación del gen SNCA en la enfermedad de Parkinson y la demencia con cuerpos de Lewy o hipermetilación del promotor del gen GRN en la demencia frontotemporal. Algunas de estas variaciones en el patrón de metilación del ADN son compartidas por el tejido cerebral y la sangre periférica. Este hallazgo permitirá su utilización como biomarcadores epigenéticos en el diagnóstico de las enfermedades neurodegenerativas (AU)
DNA methylation is an epigenetic mechanism that controls gene expression. In Alzheimer's disease (AD), global DNA hypomethylation of neurons has been described in the human cerebral cortex. Moreover, several variants in the methylation pattern of candidate genes have been identified in brain tissue when comparing AD patients and controls. Specifically, DNA methylation changes have been observed inPSEN1 and APOE, both genes previously being involved in the pathophysiology of AD. In other degenerative dementias, methylation variants have also been described in key genes, such as hypomethylation of the SNCA gene in Parkinson's disease and dementia with Lewy bodies or hypermethylation of the GRN gene promoter in frontotemporal dementia. The finding of aberrant DNA methylation patterns shared by brain tissue and peripheral blood opens the door to use those variants as epigenetic biomarkers in the diagnosis of neurodegenerative diseases (AU)