Search

To decipher human activities and facilitate organic computer-human interactions, facial expression recognition is crucial using four datasets JAFFE, CKPlus, KDEF and AffectNet, we achieve excellent accuracy in human face emotion classification with the VGG 16 pre-trained model with transfer learning. To obtain a comprehensive insight of the model’s decision-making process, we employ Layerwise Relevance Propagation (LRP), a method from explainable Artificial Intelligence (XAI). Only positive relevance scores are taken into account for successfully predicted test images from the datasets. Contributory pixels towards predicting the intensity of emotion are pixels with good relevance ratings. By combining emotion recognition with LRP, we can forecast emotion labels and ranks. Using a confusion matrix, we checked if our predictions were in line with reality. Our model achieved intensity prediction accuracy of 96.33% on JAFFE, 95.78% on CKPlus, 95.78% on KDEF, and 93.89% on AffectNet. A group of ten annotators work together to generate ground truth by assigning ratings of “MINIMAL, “AVERAGE, and “STRONG to each image. This study demonstrates how well our method predicts the ranks of emotion intensity and provides information on how trustworthy and interpretable the model is. Facial emotion recognition’s intensity ranking is made more robust with the addition of XAI techniques like LRP.

Post-harvest loss significantly impacts food security, economy, and the overall health of the entire population. About 30% of fresh produce is lost after harvest every year. Physical, macro-biological, microbiological, and enzymatic factors play key roles in losing quality and quantity of harvested crops. Management practices are strategized and executed to address these factors, bringing about new and improved technologies, along with conventional techniques that are easily available for farmers and handlers and effectively minimize loss. In this review, we have consolidated the various existing processing and value-added methods to reduce the loss of crops after harvest including physical and chemical methods and advanced packaging solutions employed in the food and agricultural sectors. The different physical techniques help to prevent or minimize microbial contamination, moderate enzymatic reactions, and maintain the intended organoleptic properties of the crops. These physical interventions are noteworthy for their environment-friendliness, which aligns with the global trend of agriculture adopting more sustainable and ecologically sensitive methods. Chemical techniques involving the use of preservatives and antimicrobial agents are essential to extend the shelf-life of the produce. Nonetheless, a cautious approach is necessary, considering the possible adverse effects of chemical residues on human health and the environment. Striking an appropriate balance between preservation techniques and sustainable agriculture is crucial for the long-term sustainability of post-harvest management measures. Packaging is another key component in the post-harvest management process. Coatings, intelligent and active packaging, and modified (MAP) monitor and control the interior atmospheric conditions of packed products while serving as strong barriers against external contaminants. These packaging innovations, driven by advancements in materials science and nanotechnology, serve as formidable barriers against spoilage, contributing significantly to reducing food waste and ensuring the availability of fresh produce for extended periods. An integrated and holistic approach to these strategies is essential to ensure food security, decrease losses, extend shelf-life and thus, increase the market availability period and quality of the produce to meet the import and export standards. This will in turn alleviate the burden on the farmers and agricultural sector, thereby improving their economic condition. [ABSTRACT FROM AUTHOR]

With the ever-increasing request for speed and the increasing number of Cyber Attacks are having fast and accurate skill to provide verification that is convenient, rapid and exact. Even though possible that it is very difficult to fool Image Recognition Skill in this makes it helpful in serving preclude fraud. In this paper, we propose a model for pixel wise operations, which is needed for identification of a location point. The computer vision is not limited to pixel wise operations. It can be complex and far more complex than image processing. Initially, we take the unstructured Image Segmentation with the help of K-Means Clustering Algorithm is used. Once complete the preprocessing step then extracts the segmented image from the surveillance cameras to identify the expressions and vehicle images. In the raw image from the surveillance camera is the image of a person and vehicle is to classify with the help DWT. Further, the images of the appearances stood also taken with phenomenon called Smart Selfie Click (SSC). These two features are extracted in-order to identify whether the vehicle should be permitted into the campus or not. Thus, verification is possible. These two images are nothing but reliable object extracted for location identification.

Researchers are interested in Facial Emotion Recognition (FER) because it could be useful in many ways and has promising applications. The main task of FER is to identify and recognize the original facial expressions of users from digital inputs. Feature extraction and emotion recognition make up the majority of the traditional FER. Deep Neural Networks, specifically Convolutional Neural Network (CNN), are popular and highly used in FER due to their inherent image feature extraction process. This work presents a novel method dubbed as EfficientNet-XGBoost that is based on Transfer Learning (TL) technique. EfficientNet-XGBoost is basically a cascading of the EfficientNet and the XGBoost techniques along with certain enhancements by experimentation that reflects the novelty of the work. To ensure faster learning of the network and to overcome the vanishing gradient problem, our model incorporates fully connected layers of global average pooling, dropout and dense. EfficientNet is fine-tuned by replacing the upper dense layer(s) and cascading the XGBoost classifier making it suitable for FER. Feature map visualization is carried out that reveals the reduction in the size of feature vectors. The proposed method is well-validated on benchmark datasets such as CK+, KDEF, JAFFE, and FER2013. To overcome the issue of data imbalance, in some of the datasets namely CK+ and FER2013, we augmented data artificially through geometric transformation techniques. The proposed method is implemented individually on these datasets and corresponding results are recorded for performance analysis. The performance is computed with the help of several metrics like precision, recall and F1 measure. Comparative analysis with competent schemes are carried out on the same sample data sets separately. Irrespective of the nature of the datasets, the proposed scheme outperforms the rest with overall rates of accuracy being 100%, 98% and 98% for the first three datasets respectively. However, for the FER2013 datasets, efficiency is less promisingly observed in support of the proposed work.

INTRODUCTION Tobacco use during pregnancy has harmful consequences both to the women and their fetuses. There is a lack of national-level information on the prevalence and predictors of tobacco use among pregnant women in India. This study fills this gap by investigating the prevalence and predictors of tobacco use among currently married pregnant women in India. METHODS Unit level data from the fourth National Family Health Survey, conducted in India during 2015-2016, were used in this study. Logistic regression analyses were performed to identify independent factors associated with tobacco use. RESULTS Our results suggest the prevalence of tobacco use among currently married pregnant women in India is 4.6% (95% CI: 4.3-5.1), and more than 80% of pregnant tobacco users use tobacco in the smokeless form only. Age of woman, region of residence, education level, religion, caste, wealth quintile, frequency of watching television were the independent predictors of tobacco use among currently married pregnant women in India. In general, lower socioeconomic status is positively associated with tobacco use among them. CONCLUSIONS Around 4.6% of pregnant women in India use tobacco, and the smokeless form of tobacco use is predominant among pregnant tobacco users. Socioeconomic disadvantage is positively associated with tobacco use among pregnant women in India. The findings of the present study need to be used to reduce tobacco use among pregnant women in the country by identifying subpopulations at risk, and sensitizing them to the harmful consequences of tobacco use, by offering tobacco cessation services during prenatal checkups. [ABSTRACT FROM AUTHOR]

This paper reports on the eco-friendly synthesis of gold nanoparticles (AuNPs) using Solanum indicum fruit extract (SFE). We have evaluated various parameters for synthesis of AuNPs such as SFE (0.03%), HAuCl4 (0.5 mM) and reaction time (20 seconds). The synthesized AuNPs were characterized with different physical techniques such as transmission electron microscopy (TEM), Fourier transform infrared (FT-IR) spectroscopy, X-ray diffraction (XRD) and energy dispersive X-ray spectroscopy (EDX). TEM experiments showed that AuNPs presented an anisotropic shape and size ranging from 5-50nm. FT-IR spectroscopy revealed that biomolecules containing an amine group (-NH2), a carbonyl group, -OH groups and other stabilizing functional groups were adsorbed on the surface of the synthesized AuNPs. EDX showed the presence of the elements on the surface of the AuNPs. The cytotoxicity of the synthesized AuNPs were tested on two different human cancer cell lines, HeLa and MCF-7 and were found to be nontoxic, thus providing an opportunity to be used in biomedical applications. [ABSTRACT FROM AUTHOR]

We report the synthesis of gold nanoparticles using coconut water through microwave irradiation. Synthesis was found to be very rapid with an optimum time of 17 s. The particles obtained were characterized by UV-visible spectroscopy, transmission electron microscopy (TEM), high-resolution TEM (HRTEM), and atomic force microscopy (AFM). The synthesized gold nanoparticles were found to be mostly spherical with an average diameter of 10.5 ± 5 nm. The crystalline nature of gold nanoparticles was confirmed by X-ray diffraction (XRD) patterns. Fourier transform infrared (FTIR) analysis suggested the presence of organic biomolecules on the surface of the gold nanoprticles, which may be responsible for the stability of the particles. Cytotoxicity of the gold nanoparticles was tested on two human cancer cell lines, HeLa (human cervical cancer) and MCF-7 (human breast cancer), and found to be nontoxic, which thus proved their biocompatibility. The method exploits a cheap and easily available biomaterial that can be directly used for the synthesis of gold nanoparticles and has the potential for the synthesis of metallic nanoparticles other than gold. [ABSTRACT FROM AUTHOR]

Here we report the synthesis of gold nanoparticles using ethanolic extract of Mentha arvensis leaves, an edible plant used as a condiment and traditional medicine in India. UV-Vis spectroscopy analysis confirmed the formation of gold nanoparticle. Transmission electron microscope (TEM) images showed that the gold nanoparticles (GNPs) formed were hexagonal and nearly spherical in shape with an average size of 39 ± 15 nm and were stable even after 6 weeks of storage at room temperature. The crystalline nature of gold nanoparticles was confirmed from X-ray diffraction (XRD) analysis. In addition to gold, energy-dispersive X-ray analysis (EDX) showed the presence of carbon and oxygen elements. The evidence from Fourier transform infrared (FTIR) spectroscopy and EDX suggested that flavonoids and phenol compounds were involved in reduction and stability of GNPs synthesized using Mentha arvensis. [ABSTRACT FROM AUTHOR]