Increase of nutritional security in Sub-Saharan Africa through the production of dried products from underutilized crops

Currently, an estimated 20% of the population in Sub-Saharan Africa is food insecure with the incidence of hunger and malnutrition still rising. This trend is amplified by the socio-economic consequences of the COVID-19 pandemic. In contrast, more than a third of the harvestable perishable produce is lost due to a lack of preservation or failure to utilize preservation as is the case for underutilized crops (UCs). Moreover, some of the preservation techniques utilized are poor, leading to the deterioration of food quality, especially the micronutrients. In this study, we thus exemplarily investigated the impact of different drying settings on the quality of two highly nutritious UCs, namely cocoyam and orange-flesh sweet potato (OFSP) (40, 60, and 80 °C for cocoyam and 40, 50, 60, and 70 °C for OFSP) to deduce the optimum quality retention and further develop a theoretical design of processing units and processing guidelines for decentralized food processing. Drying cocoyam at 80 °C and OFSP at 60 °C, respectively resulted in a relatively shorter drying time (135 and 210 min), a lower total color difference (2.29 and 11.49-13.92), greater retentions for total phenolics (0.43 mg GAE/100 gDM and 155.0-186.5 mg GAE/100 gDM), total flavonoid (128 mg catechin/100 gDM and 79.5-81.7 mg catechin/100 gDM) and total antioxidant activity (80.85% RSA and 322.58-334.67 mg AAE/100 gDM), respectively for cocoyam and OFSP. The β-carotene, ascorbic acid and vitamin A activity per 100 gDM of the OFSP flours ranged between 6.91- 9.53 mg, 25.90 − 35.72 mg, and 0.53 − 0.73 mg RAE, respectively. © 2022 The Author(s). Published with license by Taylor and Francis Group, LLC.

AI-app development for Yolov5-based face mask wearing detection

Corona is one of the most destructive viruses that has ever produced a pandemic in human life, not only in terms of direct victims but also in terms of the socio-economic consequences of the virus' transmission. The 2nd anniversary of the global coronavirus pandemic passed away in 2021. However, it's still impossible to say how long the epidemic will last. After reviewing a study by the World Health Organization on COVID-19, the country's national government urged residents to use facemask in order to reduce the incidence of COVID-19 transmission. As a result of COVID-19, there are presently no facemask detection app that are in great demand for ensuring safety in public area. In the context of the outbreak of COVID-19, A facemask detection model based on deep learning approach of state-of-the-art YOLOv5 may be useful in real-time applications. In this paper, we propose a web app for detecting if the people wears facemask or not in real-time via webcam or public camera. In the app, we deployed and persisted many different YOLOv5-based models that the users can switch between them to guarantee the performance and timing trade-off. Furthermore, our system is able to detect if an individual person captured by surveillance cameras is wearing facemask in acceptable counting time at staging level. In our opinion, this kind of system is extremely efficient for use in airports, train stations, offices, and other public areas, as well as in military. © 2022 IEEE.

A Multi-Objective Optimization-based Clustering Approach for CORD-19 Scholarly Articles

The pandemic disease COVID-19, originated from the SARS-CoV-2 virus has spread globally. Researchers are working tirelessly on areas including studying the transmission of COVID-19, promoting its identification, designing new vaccines and therapies, and recognizing its socio-economic consequences. This extensive research leads to the exploration of thousands of scientific papers related to biology, chemistry, genetics, health, and economy. Therefore, it is essential to develop an intelligent text mining technique for segregating this rich source of data to perform easy access, information retrieval, and interpretation within minimum time and resources. We propose a multi-objective optimization-based document clustering approach for the CORD-19 (COVID-19 Open Research Dataset) dataset in this paper. Here, a new technique utilizing BioBERT has been proposed, which benefits from the and the document text, rather than only the brief , to perceive a concise understanding of the text to generate clusters with better definitions. The main contributions of the proposed work are two-fold: in the first step, we have used BioBERT to generate the sentence embedding which is further used for the document representation. In the next step, we have developed a multi-objective optimization (MOO) based clustering algorithm for grouping the generated document vector representations. In this MOO-based clustering, we have used Non-dominated Sorting Genetic Algorithm-II and Fuzzy c-means algorithm as the underlying MOO and clustering technique, respectively. This model is evaluated using the Silhouette Score (Silhouette score) and Calinski-Harabasz index (CH index), and the clustering solutions are visualized using word clouds. The clustering results exhibit significant improvements over various other existing clustering models. © 2021 IEEE.