This research presents a brain–computer interface (BCI) framework for brain signal classificationusing deep learning (DL) and machine learning (ML) approaches on functional near-infrared spectroscopy (fNIRS) signals. fNIRS signals of motor execution for walking and rest tasks are acquired from the primary motor cortex in the brain’s left hemisphere for nine subjects. DL algorithms, including convolutional neural networks (CNNs), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM) are used to achieve average classification accuracies of 88.50%, 84.24%, and 85.13%, respectively. For comparison purposes, three conventional ML algorithms, support vector machine (SVM), k-nearest neighbor (k-NN), and linear discriminant analysis (LDA) are also used for classification, resulting in average classification accuracies of 73.91%, 74.24%, and 65.85%, respectively. This study successfully demonstrates that the enhanced performance of fNIRS-BCI can be achieved in terms of classification accuracy using DL approaches compared to conventional ML approaches. Furthermore, the control commands generated by these classifiers can be used to initiate and stop the gait cycle of the lower limb exoskeleton for gait rehabilitation.
IntroductionThe emergence of MDR-TB is a global threat and an obstacle to the effective control of TB in Pakistan. A lack of proper TB knowledge among the staff in private pharmacies and the sale of compromised quality anti-TB drugs are the main instigators of multidrug-resistant tuberculosis (MDR-TB). Thus, this study was aimed at investigating the quality and storage conditions of fixed-dose combination (FDC) anti-TB drugs along with the awareness of staff working in private pharmacies regarding the identification of potential patients with TB and dispensing the inappropriate treatment regimens contributing to MDR-TB.MethodsThe study is completed in two phases. In phase I a cross-sectional study is performed using two quantitative research designs, i.e., exploratory and descriptive, to evaluate the knowledge of private pharmacy staff. The sample of 218 pharmacies was selected. While in phase II cross sectional survey is conducted in 10 facilities from where FDC anti TB drugs were sampled for analyzing their quality.ResultResults revealed the presence of pharmacists only at 11.5% of pharmacies. Approximately 81% of staff at pharmacies had no awareness of MDR-TB, while 89% of pharmacies had no TB-related informative materials. The staff identified that most of the patients with TB (70%) were of poor socio-economic class, which restricted their purchase of four FDCs only up to 2–3 months. Only 23% were acquainted with the Pakistan National TB Program (NTP). Except for MDR-TB, the results showed a significant correlation between the experiences of staff with TB awareness. Findings from the quality evaluation of four FDC-TB drugs indicated that the dissolution and content assay of rifampicin were not according to the specifications, and overall, 30% of samples failed to comply with specifications. However, the other quality attributes were within the limits.ConclusionIn light of the data, it can be concluded that private pharmacies could be crucial to the effective management of NTP through the timely identification of patients with TB, appropriate disease and therapy-related education and counseling, and proper storage and stock maintenance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.