ABSTRACT
Stress has an impact, not only on a person's physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.
ABSTRACT
Bangladesh's forest-dependent people rely on medicinal plants for traditional healthcare practices, as plant-based medicines are easily available and cost-effective. This study evaluated and documented ethnomedicinal practices for, and traditional knowledge of, utilising plants to cure ailments. Ethnobotanical indices quantified the use value (UV), frequency of citation, relative frequency of citation (RFC) and the informant consensus factor. Using a semi-structured questionnaire, the study interviewed 231 respondents from 18 villages in and around Chunati Wildlife Sanctuary (CWS). The study documented 134 medicinal plant species from 60 families; tree species were dominant (37.31%). Malvaceae (seven species), Rutaceae and Lamiaceae (six species each) families covered more species. Nearly half of the species (46.02%) were collected from CWS. Both above-ground and below-ground plant parts treated 71 types of ailments under 21 categories, with leaves (66 species) being the most widely used plant part. In total 33 species were used to treat dysentery, 25 species each for fever and jaundice, and 24 species for cuts and wounds. The average UV value was 0.24 and RFC value was 0.47%. Communities were found to utilise medicinal plants more at home than to sell at markets, substantially relying on medicinal plants to meet their domestic needs. Plants used for healthcare and cultural and religious beliefs have a strong connection that plays a vital role in plant conservation. This study identified 42 medicinal plant species that could be considered to treat COVID-19 patients in Bangladesh. The findings suggest that community awareness of sustainable harvesting and commercial cultivation could lead to conservation and use of these invaluable plant species for healthcare, new drugs discovery and sustainable forest management. Supplementary Information: The online version contains supplementary material available at 10.1007/s42398-022-00230-z.