Intelligent irrigation systems play a crucial role in addressing the global issues of water scarcity, climate variability, and sustainable agricultural production. These systems can help identify the efficient time and the exact quantity of irrigation through the use of data-driven ideas, which ensures maximum crop yield with minimal use of water. This paper provides a thorough comparative analysis of the four most commonly used Machine Learning (ML) models: Support Vector Machines (SVM), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and Logistic Regression (LR), to predict the need of irrigation based on critical environmental and agronomic variables. The dataset features include soil moisture, air temperature, relative humidity, solar radiation, and crop types, among other features, obtained using sensor networks installed on farmland. We trained and tested each model before comparing its performance using standard evaluation metrics, which include accuracy, precision, recall, F1 Score, and the Area Under the Curve. These findings indicate that GB and KNN models performed better than SVM and LR. For instance, GB and KNN achieved precisions of 95.6% and 92.4%, respectively, compared to SVM and LR, which achieved precisions of 86.2% and 72.8%, respectively. In both accuracy and generalization, the GB model performs overall best. This study contributes a fair investigation of the suitability of well-known ML models in irrigation forecasting for smart farming in the south-western region of Nigeria. This study makes use of a region-specific dataset that is gathered by sensor networks, involving 100,000 records in two farming seasons.

Distichochlamys citrea, an endemic plant native to central Vietnam, holds significant ethnomedicinal value in Vietnamese herbal medicine. Although the essential oil derived from the rhizome of D. citrea is known for its bioactivities, including antibacterial and antioxidant properties, its anti-inflammatory potential has not been extensively explored yet. In this study, the anti-inflammatory effect of the essential oil has been comprehensively evaluated from in silico to in vivo studies. A molecular docking study revealed that cineole, neral, and geranial, three main components of the essential oil, were capable of forming promising interactions with 5-lipoxygenase and inducible nitric oxide synthase (ranging from -4.7 to -6.3 kcal/mol). Furthermore, the essential oil exhibited a strong inhibitory effect against protein denaturation (86.67%, 100 µg/mL). In the carrageenan-induced paw edema model, the essential oil (4%) could inhibit 32.83% of paw edema as compared to the NaCl-treated group. Collectively, these findings position the essential oil extracted from rhizomes of D. citrea as a novel candidate for the development of anti-inflammatory medicine.

Automated customer consulting is a form of automated customer care and consulting that utilizes texting and chat functions to replace human interaction. This research improves the Bi-LSTM language model. We aim to enhance the accuracy and applicability of an automated customer consultation system, which may impact enterprises and traders. Our question-answer system uses querying the entity and model textual similarity to match models. Automated customer care systems utilize computers or other technologies to assist customers. It empowers clients to address problems without human assistance in customer care. Human resources can address complex requests or high-value consumers, as automation handles many repetitive and straightforward activities. Many firms utilize it, especially fast-growing ones that need to arrange support.

This paper addresses the challenge of face recognition in Low-Resolution (LR) images, mainly when the resolution is below 48x48 pixels, which is common in surveillance systems. Current face recognition algorithms struggle to deliver satisfactory results with such low-resolution images. This study utilizes over 16,000 face images with an average resolution of 20x20 pixels to improve recognition, applying deep learning and bicubic interpolation to enhance image resolution. Unlike traditional Super-Resolution (SR) methods that operate in the LR space, our approach introduces a novel data constraint that evaluates errors in the High-Resolution (HR) image domain. By leveraging the finer details in HR images, the reconstructed HR images significantly improve visual quality and recognition accuracy. This unique data constraint seamlessly incorporates discriminative features into the optimization process. Experimental results demonstrate that our method outperforms existing visual quality and recognition performance approaches.

The elements sodium, calcium, potassium, iodine, and magnesium are essential in our diets for nutritional guidance and avoiding excessive intake and effects. Among other factors, healthcare and the high cost of conventional medicines compelled many people to use herbal snuffs for medicinal or psychoactive means. Likewise, sodium, potassium, calcium, and magnesium pollution levels could be exaggerated and harm humans. The objective of this work was to detect the levels of sodium, potassium, calcium, magnesium, and iodine present in four different types of herbal snuffs consumed in Sokoto and nearby in Nigeria by using atomic bsorption spectroscopy and prospect the effect of calcium and agnesium on iodine. Four brands of herbal snuffs bought in Sokoto were used for this work. The highest sodium was detected in herbal two and the lowest in herbal 1. The potassium was highest in herb 2 (39.41 ± 1.4ppm) and lowest in herbal snuffs 3 (6.61 + 1.4ppm). The lowest levels of Ca and Mg were determined in herbal snuff brands sold in Sokoto, Nigeria. The highest calcium was detected in herbal snuff 4 (35.51 ± 6.10ppm), and the lowest was in snuff 1 (31.00 ± 9.10ppm). The magnesium concentration was highest in herbal stock 4 (9.31 ± 1.11ppm) and lowest in herbal stuff 3 (3.05 ± 0.60ppm). Generally, the levels of the analyzed elements are in the order of sodium > calcium > potassium > magnesium. Thus, there are significant (p < 0.05) sodium, potassium, calcium, and magnesium levels in herbal snuffs in Sokoto, Nigeria, and may contribute to the daily elemental requirements of consumers in the state and nearby.

Diospyros kaki is a famous commercial plant with its edible fruit (persimmon) and is widely used as a traditional remedy in Vietnam. However, the anti-oxidant and anti-bacterial effects against gastrointestinal microbes of the D. kaki leaf extract have not been elucidated yet. In this study, the methanol extract from D. kaki leaves contained some chemical groups, such as tannins, flavonoids, phenolic compounds, alkaloids, and saponins, mainly it was rich in polyphenols and flavonoids (528.11 ± 12.96 mg GAE/g and 44.49 ± 6.77 mg QE/g, respectively). The extract exhibited a strong anti-oxidant ability (DPPH scavenging activity of about 91.83 ± 1.02% and total anti-oxidant capacity of approximately 110.58 ± 2.65 mg AAE/g). Furthermore, the anti-bacterial activity of the extract against some gastrointestinal bacteria, including Staphylococcus aureus, Enterococcus durans, Enterococcus faecium, and Yersinia enterocolitica, has been reported for the first time (the zone of inhibition ranging from 14.17 - 24.67mm). MIC of the extract was 0.6125 - 1.25 mg/mL, and MBC was 2.5 - 5 mg/mL, which implied the extract exerted a bactericidal effect. These findings suggest D. kaki leaf extract is a promising source of extracting bioactive compounds, such as anti-oxidant and anti-microbial agents, and a potential medicine for the treatment of gastrointestinal infections.

The rapidly increasing volume of textual data has made manual labeling extremely costly and time-consuming. To address this limitation, researchers have gradually focused on unsupervised learning techniques that enable models to classify text without relying on labeled data. Among these, deep clustering has garnered significant interest. However, most existing deep clustering methods are primarily designed for computer vision tasks. In this paper, we propose modifications to two of the most powerful deep clustering methods, including DEKM and DeepCluster, by integrating transformer algorithms in the Natural Language Processing (NLP) domain, enabling these methods to handle textual data. With the proposed methods, we achieved the best results on the test set of the Financial Phrase Bank (FPB) dataset with an accuracy of 57.71% and on the test set of the Twitter Financial News (TFN) dataset with an accuracy of 65.58%. Although these results are still lower than those of traditional supervised deep learning methods, we have demonstrated that the performance of our proposed methods can be further improved when trained with more data. This highlights the promising potential of deep clustering methods for natural language processing tasks. Especially when addressing tasks where the data is either unlabeled or lacks sufficient labeling.

Kinship verification is crucial in daily life, especially in the legal field. Nowadays, most kinship verification methods utilize the advantages of human DNA and facial features. However, these methods require a lot of complex procedures, so they are unsuitable for real-time application. Therefore, researchers started to propose other promising biometrics, and the human ear is one of the most potential. The human ear has long been recognized as a robust biometric trait, comparable to others, such as face, iris, and fingerprint. This paper proposes using ear images to identify human kinship based on several well-known deep-learning networks. Moreover, an ear image set is presented to tackle the lack of a kinship-annotated dataset.

Overexpression of cyclooxygenase-2 (COX-2) plays a crucial role in cancer therapy. In this study, we investigated the role of two coumarin derivatives with the chlorobenzylamide group in inhibiting COX-2 activity and growth inhibition of cancer cells. The effect of synthesized 2a and 2b coumarin derivatives on COX-2 enzyme was investigated in vitro. Besides that, A549, HT-29, MDA-MMB-231, and HeLa tumor cell lines were used to evaluate potential inhibition growth using the MTT assay. According to the results, two synthesized compounds showed an inhibitory effect on COX-2 enzymes. In particular, 2a exhibited the best activity with an IC50 value of 49.54μM on COX-2. The 2a and 2b exhibited a noteworthy dose-dependent inhibitory growth activity against all the tested cancer cell lines, indicating their broad-spectrum anti-cancer properties. Based on the in vitro data, we strongly recommend this new coumarin-o-chlorobenzylamide as a preclinical development candidate for novel anti-cancer agents targeting COX-2 inhibition.

Cashew nut testa (Anacardium occidentale L.) is a valuable source of polyphenols known for their strong bioactivities. This study optimized the extraction conditions to obtain polyphenol-rich extracts from cashew nut testa. The effects of three key factors, extraction time, material-to-solvent ratio, and temperature, on Total Polyphenol Content (TPC, mg GAE/g extract) were investigated. Response surface methodology, using a Box-Behnken design, was applied to design the experiments and optimize the extraction process. The results showed that the relationship between TPC and extraction conditions followed a second-order model with an R² value of 0.9999. All three factors significantly influenced TPC (p < 0.05), and their interactions were also significant. The model predicted optimal conditions for maximum TPC at an extraction time of 19.85h, a temperature of 58.80°C, and a material-to-solvent ratio of 1:16.39 (w/v). Validation experiments under the optimized conditions of 20h, 59°C, and a 1:16 ratio confirmed the model's accuracy, yielding a TPC of 534.67mg GAE/g extract, statistically equivalent to the predicted value. These findings demonstrate the efficacy of the optimized conditions in maximizing polyphenol extraction from cashew nut testa.