Deep neural networks have made tremendous strides in the categorization of facial photos in the last several years. Due to the complexity of features, the enormous size of the picture/frame, and the severe inhomogeneity of image data, efficient face image classification using deep convolutional neural networks remains a challenge. Therefore, as data volumes continue to grow, the effective categorization of face photos in a mobile context utilizing advanced deep learning techniques is becoming increasingly important. In the recent past, some Deep Learning (DL) approaches for learning to identify face images have been designed; many of them use convolutional neural networks (CNNs). To address the problem of face mask recognition in facial images, we propose to use a Depthwise Separable Convolution Neural Network based on MobileNet (DWS-based MobileNet). The proposed network utilizes depth-wise separable convolution layers instead of 2D convolution layers. With limited datasets, the DWS-based MobileNet performs exceptionally well. DWS-based MobileNet decreases the number of trainable parameters while enhancing learning performance by adopting a lightweight network. Our technique outperformed the existing state of the art when tested on benchmark datasets. When compared to Full Convolution MobileNet and baseline methods, the results of this study reveal that adopting Depthwise Separable Convolution-based MobileNet significantly improves performance (Acc. = 93.14, Pre. = 92, recall = 92, F-score = 92).
In this study, a first attempt has been made to deliver levosulpiride transdermally through a thiolated chitosan microneedle patch (TC-MNP). Levosulpiride is slowly and weakly absorbed from the gastrointestinal tract with an oral bioavailability of less than 25% and short half-life of about 6 h. In order to enhance its bioavailability, levosulpiride-loaded thiolated chitosan microneedle patches (LS-TC-MNPs) were fabricated. Firstly, thiolated chitosan was synthesized and characterized by nuclear magnetic resonance (1HNMR) spectroscopy, attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopy, differential scanning calorimetry (DSC), and X-ray diffraction (XRD). Thiolated chitosan has been used in different drug delivery systems; herein, thiolated chitosan has been used for the transdermal delivery of LS. LS-TC-MNPs were fabricated from different concentrations of thiolated chitosan solution. Furthermore, the levosulpiride-loaded thiolated chitosan microneedle patch (LS-TC-MNP) was characterized by FTIR spectroscopic analysis, scanning electron microscopy (SEM) study, penetration ability, tensile strength, moisture content, patch thickness, and elongation test. LS-TC-MNP fabricated with 3% thiolated chitosan solution was found to have the best tensile strength, moisture content, patch thickness, elongation, drug-loading efficiency, and drug content. Thiolated chitosan is biodegradable, nontoxic and has good absorption and swelling in the skin. LS-TC-MNP-3 consists of 100 needles in 10 rows each with 10 needles. The length of each microneedle was 575 μm; they were pyramidal in shape, with sharp pointed ends and a base diameter of 200 µm. The microneedle patch (LS-TC-MNP-3) resulted in-vitro drug release of 65% up to 48 h, ex vivo permeation of 63.6%, with good skin biocompatibility and enhanced in-vivo pharmacokinetics (AUC = 986 µg/mL·h, Cmax = 24.5 µg/mL) as compared to oral LS dispersion (AUC = 3.2 µg/mL·h, Cmax = 0.5 µg/mL). Based on the above results, LS-TC-MNP-3 seems to be a promising strategy for enhancing the bioavailability of levosulpiride.