Search

Artificial neural networks (ANNs) have proven to be among the most important artificial intelligence (AI) techniques in educational applications, providing adaptive educational services. However, their educational potential is limited in practice due to challenges such as the following: (i) the difficulties in incorporating symbolic educational knowledge (e.g., causal relationships and practitioners’ knowledge) in their development, (ii) a propensity to learn and reflect biases, and (iii) a lack of interpretability. As education is classified as a ‘high-risk’ domain under recent regulatory frameworks like the EU AI Act—highlighting its influence on individual futures and discrimination risks—integrating educational insights into ANNs is essential. This ensures that AI applications adhere to essential educational restrictions and provide interpretable predictions. This research introduces NSAI, a neural-symbolic AI approach that integrates neural networks with knowledge representation and symbolic reasoning. It injects and extracts educational knowledge into and from deep neural networks to model learners’ computational thinking, aiming to enhance personalized learning and develop computational thinking skills. Our findings revealed that the NSAI approach demonstrates better generalizability compared to deep neural networks trained on both original training data and data enriched by SMOTE and autoencoder methods. More importantly, we found that, unlike traditional deep neural networks, which mainly relied on spurious correlations in their predictions, the NSAI approach prioritizes the development of robust representations that accurately capture causal relationships between inputs and outputs. This focus significantly reduces the reinforcement of biases and prevents misleading correlations in the models. Furthermore, our research showed that the NSAI approach enables the extraction of rules from the trained network, facilitating interpretation and reasoning during the path to predictions, as well as refining the initial educational knowledge. These findings imply that neural-symbolic AI not only overcomes the limitations of ANNs in education but also holds broader potential for transforming educational practices and outcomes through trustworthy and interpretable applications.

Background and Objectives: Temperature-sensitive (TS) mutants of TP53 are thermally unstable, unfolded, and inactive at body temperature but can be refolded and reactivated at sub-physiological temperatures. TS TP53 may be amenable for functional rescue by hypothermia or structure-stabilizing drugs, and may retain low-level transcriptional activity at 37 °C. TP53 mutations are observed in 47% of all esophageal cancers (ECs) and 25% to 40% of gastric cancers (GCs). We aimed to investigate the trends and outcomes of EC and GC with TS TP53 mutations using cBioportal. We hypothesize that TS TP53 mutants in EC and GC present a unique prognostic profile distinct from non-TS TP53 mutants, potentially affecting overall survival and cancer progression. Materials and Methods: We identified 1924 patients from cBioportal with GC or EC, harboring any TP53 mutation. Patients were then stratified based on the TP53 temperature sensitivity according to a recently reported functional analysis of its activity. Patients were also stratified based on a history of Barrett’s esophagus (BE), cancer stage, sex, and race. We then compared populations (TS vs. non-TS TP53) to assess differences and evaluated survival outcomes. Results: Males represented 77% of the cohort, and 51.6% of the samples were from patients with stage IV cancer. No association was found between TS vs. non-TS mutational status and BE, cancer stage, or race. Interestingly, a significantly higher proportion of females (22.9%) than males (14.5%) displayed a TS TP53 mutation (p = 0.012). No significant difference was seen in overall survival between the TS and non-TS mutations capable of ≥50% growth suppression at 32 °C (median = 33 vs. 28 months, p = 0.36). This trend was also observed when the patients were filtered based on cancer location. The median survival for EC was 32.5 months compared to 33 months (p = 0.67). In cases of GC, median survival times could not be determined due to the insufficient number of events. Conclusions: Although no statistical significance was observed, a decrease in overall survival for patients with TS TP53 mutations was noted. The result is counterintuitive given that TS mutants have less severe structural destabilization and suggests TS TP53 mutations may have a unique prognostic value that warrants further investigation.

Goji berry is acknowledged for its notable medicinal attributes and elevated free radical scavenger properties. Nevertheless, its susceptibility to mechanical injuries and biological disorders reduces the commercial diffusion of the fruit. A hyperspectral imaging system (HSI) was employed to identify common defects in the Vis-NIR range (400–1000 nm). The sensorial evaluation of visual appearance was used to obtain the reference measurement of defects. A supervised classification model employing PLS-DA was developed using raw and pre-processed spectra, followed by applying a covariance selection algorithm (CovSel). The classification model demonstrated superior performance in two classifications distinguishing between sound and defective fruit, achieving an accuracy and sensitivity of 94.9% and 96.9%, respectively. However, when extended to a more complex task of classifying fruit into four categories, the model exhibited reliable results with an accuracy and sensitivity of 74.5% and 77.9%, respectively. These results indicate that a method based on hyperspectral visible-NIR can be implemented for rapid and reliable methods of online quality inspection securing high-quality goji berries.

Maize (Zea mays L.) has been shown to be sensitive to temperature deviations, influencing its yield potential. The development of new maize hybrids resilient to unfavourable weather is a desirable aim for crop breeders. In this paper, we showcase the development of a multimodal deep learning model using RGB images, phenotypic, and weather data under temporal effects to predict the yield potential of maize before or during anthesis and silking stages. The main objective of this study was to assess if the inclusion of historical weather data, maize growth captured through imagery, and important phenotypic traits would improve the predictive power of an established multimodal deep learning model. Evaluation of the model performance when training from scratch showed its ability to accurately predict ~89% of hybrids with high-yield potential and demonstrated enhanced explanatory power compared with previously published models. Shapley Additive explanations (SHAP) analysis indicated the top influential features include plant density, hybrid placement in the field, date to anthesis, parental line, temperature, humidity, and solar radiation. Including weather historical data was important for model performance, significantly enhancing the predictive and explanatory power of the model. For future research, the use of the model can move beyond maize yield prediction by fine-tuning the model on other crop data, serving as a potential decision-making tool for crop breeders to determine high-performing individuals from diverse crop types.

This paper explores advanced machine learning approaches to enhance the prediction accuracy of compressive strength (CoS) in geopolymer composites (GePC). Geopolymers, as sustainable alternatives to Ordinary Portland Cement (OPC), offer significant environmental benefits by utilizing industrial by-products such as fly ash and ground granulated blast furnace slag (GGBS). The accurate prediction of their compressive strength is crucial for optimizing their mix design and reducing experimental efforts. We present a comparative analysis of two hybrid models, Harris Hawks Optimization with Random Forest (HHO-RF) and Sine Cosine Algorithm with Random Forest (SCA-RF), against traditional regression methods and classical models like the Extreme Learning Machine (ELM), General Regression Neural Network (GRNN), and Radial Basis Function (RBF). Using a comprehensive dataset derived from various scientific publications, we focus on key input variables including the fine aggregate, GGBS, fly ash, sodium hydroxide (NaOH) molarity, and others. Our results indicate that the SCA-RF model achieved a superior performance with a root mean square error (RMSE) of 1.562 and a coefficient of determination (R2) of 0.987, compared to the HHO-RF model, which obtained an RMSE of 1.742 and an R2 of 0.982. Both hybrid models significantly outperformed traditional methods, demonstrating their higher accuracy and reliability in predicting the compressive strength of GePC. This research underscores the potential of hybrid machine learning models in advancing sustainable construction materials through precise predictive modeling, paving the way for more environmentally friendly and efficient construction practices.

The integration of advanced control systems in prostheses necessitates the accurate identification of human locomotion activities, a task that can significantly benefit from EEG-based measurements combined with machine learning techniques. The main contribution of this study is the development of a novel framework for the recognition and classification of locomotion activities using electroencephalography (EEG) data by comparing the performance of different machine learning algorithms. Data of the lower limb movements during level ground walking as well as going up stairs, down stairs, up ramps, and down ramps were collected from 10 healthy volunteers. Time- and frequency-domain features were extracted by applying independent component analysis (ICA). Successively, they were used to train and test random forest and k-nearest neighbors (kNN) algorithms. For the classification, random forest revealed itself as the best-performing one, achieving an overall accuracy up to 92%. The findings of this study contribute to the field of assistive robotics by confirming that EEG-based measurements, when combined with appropriate machine learning models, can serve as robust inputs for prosthesis control systems.

This paper deals with spatio-temporal field estimation with efficient sensor placement based on the QR decomposition. The proposed method also identifies the optimal number of sensors needed for field estimation that captures the most relevant features of the field of interest. To address the uncertainties inherent in spatio-temporal field estimation, a robust data-driven control method is utilized, providing resilience against unpredictable environmental and model changes. In particular, the approach uses the Kriged Kalman Filter (KKF) for uncertainty-aware field reconstruction. Unlike other reconstruction methods, the positional uncertainty originating from the data acquisition platform is integrated into the KKF estimator. Numerical results are presented to show the efficacy of the proposed dynamic sensor placement strategy together with the KKF field estimator.

The cutting operation significantly affects the shelf-life of fresh-cut produce due to the mechanical damage impacting molecular, physiological, and sensory responses, depending on tissue type and tool characteristics. The degree of sharpness (DoS), defined as the force required to cut a reference body, is crucial for this process. A methodology was developed to objectively evaluate cutting damage on fresh-cut ‘Golden Delicious’ apples using three knives at four DoS levels (30, 100, 140, and 190 N) to cut 96 apples into 288 slices. The study assessed color, visual acceptance score, electrolytic leakage, and nutritional quality over 14 days at 5 °C. A two-way ANOVA showed no significant correlation between DoS and nutritional quality. However, a* values and browning index significantly increased with DoS, with values rising from 39.4 and 2.7 at 30 N to 41.4 and 3.1, respectively, at 190 N. The best visual acceptance score (4.0) and shelf-life (14 days) were at 30 N, while the worst score (2.9) and shelf-life (5 days) were at 190 N. Positive correlations were found between DoS and both browning index and a* value, with coefficients r of 0.97 and 0.93, respectively, highlighting the importance of using sharp tools for optimal post-cutting quality.

Artificial intelligence (AI) has demonstrated significant potential in addressing educational challenges in digital learning. Despite this potential, there are still concerns about the interpretability and trustworthiness of AI methods. Dynamic Bayesian networks (DBNs) not only provide interpretability and the ability to integrate data-driven insights with expert judgment for enhanced trustworthiness but also effectively process temporal dynamics and relationships in data, crucial for early predictive modeling tasks. This research introduces an approach for the temporal modeling of learners’ computational thinking abilities that incorporates higher-order influences of latent variables (hereafter referred to as memory of the model) and accordingly predicts learners’ performance early. Our findings on educational data from the AutoThinking game indicate that when using only first-order influences, our proposed model can predict learners’ performance early, with an 86% overall accuracy (i.e., time stamps 0, 5, and 9) and a 94% AUC (at the last time stamp) during cross-validation and 91% accuracy and 98% AUC (at the last time stamp) in a holdout test. The introduction of higher-order influences improves model accuracy in both cross-validation and holdout tests by roughly 4% and improves the AUC at timestamp 0 by roughly 2%. This suggests that integrating higher-order influences into a DBN not only potentially improves the model’s predictive accuracy during the cross-validation phase but also enhances its overall and time stamp-specific generalizability. DBNs with higher-order influences offer a trustworthy and interpretable tool for educators to foresee and support learning progression.

Polymer blending has attracted considerable attention because of its ability to overcome the permeability–selectivity trade-off in gas separation applications. In this study, polysulfone (PSU)-modified cellulose acetate (CA) membranes were prepared using N-methyl-2-pyrrolidone (NMP) and tetrahydrofuran (THF) using a dry–wet phase inversion technique. The membranes were characterized using scanning electron microscopy (SEM) for morphological analysis, thermogravimetric analysis (TGA) for thermal stability, and Fourier transform infrared spectroscopy (FTIR) to identify the chemical changes on the surface of the membranes. Our analyses confirmed that the mixing method (the route chosen for preparing the casting solution for the blended membranes) significantly influences the morphological and thermal properties of the resultant membranes. The blended membranes exhibited a transition from a finger-like pore structure to a dense substructure in the presence of macrovoids. Similarly, thermal analysis confirmed the improved residual weight (up to 7%) and higher onset degradation temperature (up to 10 °C) of the synthesized membranes. Finally, spectral analysis confirmed that the blending of both polymers was physical only.

The thermal conductivity of materials is a crucial property with diverse applications, particularly in engineering. Understanding soil thermal conductivity is crucial for designing efficient geothermal systems, predicting soil temperatures, and assessing soil contamination. This paper aimed to predict quartz sand thermal conductivity by using four mathematical models: multiple linear regression (MLR), artificial neural network (ANN), classification and regression random forest (CRRF), and genetic programming (GP). A grey-box AI method, GP, was used for the first time in this topic. Seven inputs affecting thermal conductivity were evaluated in the study, including sand porosity, degree of saturation, coefficient of uniformity, coefficient of curvature, mean particle size, and minimum and maximum void ratios. In predicting thermal conductivity, the MLR model performed poorly, with a coefficient of determination R2 = 0.737 and a mean absolute error MAE = 0.300. Both ANN models using the Levenberg–Marquardt algorithm and the Bayesian Regularization (BR) algorithm outperformed the MLR model with an accuracy of R2 = 0.916 and an error of MAE = 0.151. In addition, the CRRF model had the best accuracy of R2 = 0.993 and MAE = 0.045. In addition, GP showed acceptable performance in predicting sand thermal conductivity. The R2 and MAE values of GP were 0.986 and 0.063, respectively. This paper presents the best GP equation for evaluating other databases. Additionally, the porosity and saturation of the sand were found to have the greatest impact on the model results, while coefficients of curvature and uniformity had the least influence. Overall, the results of this study demonstrate that grey-box artificial intelligence models can be used to accurately predict quartz sand thermal conductivity.

Tunnel Boring Machines (TBMs) have become prevalent in tunnel construction due to their high efficiency and reliability. The proliferation of data obtained from site investigations and data acquisition systems provides an opportunity for the application of machine learning (ML) techniques. ML algorithms have been successfully applied in TBM tunnelling because they are particularly effective in capturing complex, non-linear relationships. This study focuses on commonly used ML techniques for TBM tunnelling, with a particular emphasis on data processing, algorithms, optimisation techniques, and evaluation metrics. The primary concerns in TBM applications are discussed, including predicting TBM performance, predicting surface settlement, and time series forecasting. This study reviews the current progress, identifies the challenges, and suggests future developments in the field of intelligent TBM tunnelling construction. This aims to contribute to the ongoing efforts in research and industry toward improving the safety, sustainability, and cost-effectiveness of underground excavation projects.

Noxious gases such as sulfur-containing compounds can inflict several different adverse effects on human health even when present at extremely low concentrations. The accurate detection of these gases at sub-parts per million levels is imperative, particularly in fields where maintaining optimal air quality is crucial. In this study, we harnessed the capabilities of nanostructured metal-oxide semiconducting materials to detect sulfur dioxide, since they have been extensively explored starting from the last decades for their effectiveness in monitoring toxic gases. We systematically characterized the sensing performance of seven chemoresistive devices. As a result, the SnO2:Au sensor demonstrated to be the most promising candidate for sulfur dioxide detection, owing to its highly sensitivity (0.5–10 ppm), humidity-independent behavior (30 RH% onwards), and selectivity vs. different gases at an operating temperature of 400 °C. This comprehensive investigation facilitates a detailed performance comparison to other devices explored for the SO2 sensing, supporting advancements in gas detection technology for enhanced workplace and environmental safety.

This study employs scientometric analysis to investigate the current trajectory of research on tunnel boring machine (TBM) performance and collaborative efforts. Utilizing software tools like Pajek 5.16 and VOSviewer 1.6.18, it scrutinizes literature from 2000 to 2021 sourced from the Web of Science (WOS). The findings illuminate TBM research as an interdisciplinary and intersectoral field attracting increasing national and institutional attention. Notable contributions from China, Iran, the United States, Turkey, and Australia underscore the global significance of TBM research. The recent upsurge in annual publications, primarily driven by Chinese research initiatives, reflects a renewed vigor in TBM exploration. Additionally, the paper presents a succinct evaluation of TBM advantages and drawbacks compared to conventional drill and blast methods, discussing key considerations in excavation methodology selection. Moreover, the study comprehensively reviews TBM performance prediction models, categorizing them into theoretical, empirical, and artificial intelligence-driven approaches. Finally, rooted in metaverse theory, the discourse delves into the immersive learning model and the architecture of a TBM metaverse. In the future, the immersive training and learning model diagram can be employed in scenarios such as employee training and the promotion of safety knowledge. Additionally, the TBM metaverse architecture can simulate, monitor, diagnose, predict, and control the organization, management, and service processes and behaviors of TBMs. This will enhance efficient collaboration across various aspects of the project production cycle. This forward-looking perspective anticipates future trends in TBM technology, emphasizing societal impact and enhancement of economic benefits.

Single-point mutations in the Kirsten rat sarcoma (KRAS) viral proto-oncogene are the most common cause of human cancer. In humans, oncogenic KRAS mutations are responsible for about 30% of lung, pancreatic, and colon cancers. One of the predominant mutant KRAS G12D variants is responsible for pancreatic cancer and is an attractive drug target. At the time of writing, no Food and Drug Administration (FDA) approved drugs are available for the KRAS G12D mutant. So, there is a need to develop an effective drug for KRAS G12D. The process of finding new drugs is expensive and time-consuming. On the other hand, in silico drug designing methodologies are cost-effective and less time-consuming. Herein, we employed machine learning algorithms such as K-nearest neighbor (KNN), support vector machine (SVM), and random forest (RF) for the identification of new inhibitors against the KRAS G12D mutant. A total of 82 hits were predicted as active against the KRAS G12D mutant. The active hits were docked into the active site of the KRAS G12D mutant. Furthermore, to evaluate the stability of the compounds with a good docking score, the top two complexes and the standard complex (MRTX-1133) were subjected to 200 ns MD simulation. The top two hits revealed high stability as compared to the standard compound. The binding energy of the top two hits was good as compared to the standard compound. Our identified hits have the potential to inhibit the KRAS G12D mutation and can help combat cancer. To the best of our knowledge, this is the first study in which machine-learning-based virtual screening, molecular docking, and molecular dynamics simulation were carried out for the identification of new promising inhibitors for the KRAS G12D mutant.

The use of lactic acid bacteria (LAB) for the probiotic enrichment of minimally processed fruit is a well-established practice in the literature. In addition, several LAB demonstrated a strain-specific ability to control harmful microorganisms and decay agents, improving shelf life, maintaining quality, and promoting the safety of fruits and vegetables. Edible coatings can help modulate the phenomena of gas exchange and water loss by fruits, representing protection from physical damage and spoilage phenomena linked to oxidation and the development of undesired microorganisms. At the same time, the coating can represent an innovative delivery matrix for the LAB strains of potential interest to improve safety and quality in the postharvest management of fruits. In this work, five Lactiplantibacillus plantarum strains, previously characterised for their probiotic and antifungal activity, were incorporated into a sodium alginate coating to develop edible probiotic coatings with antifungal properties for table grapes cv. Italia. The bacterial transfer and their survival were evaluated by comparing coated and uncoated table grapes during 14 days of cold storage at 4 °C. The alginate edible coating increased the number of viable cells transferred to the surface of the berries from about 5 to more than 7 Log CFU/g, with a crucial impact on the potential functional attributes of the final product. The ability of the functionalised coatings to counteract the decay development was evaluated on table grape berries artificially contaminated with Aspergillus niger CECT 2805. A significant reduction in lesion diameter was observed in the alginate coating with L. plantarum 11-A, with a reduction from 15.40 ± 1.14 mm of uncoated berries to 8.40 ± 1.14 mm of berries coated with L. plantarum 11-A. The lesion diameter reduction was also accompanied by a reduction in the symptoms of infection, such as browning around the wound. These results suggest the application of selected strains of L. plantarum as promising bio-resources to enhance the overall value of ready-to-eat fruits and vegetables, particularly in combination with edible coating as a carrier matrix. While a strain-dependent effect was not detected with respect to the improvement in the number of cells in the edible coating, a variability depending on the biotype used was detected for the properties linked to biocontrol, suggesting that the inclusion in edible packaging may represent an innovative criterion in the selection of lactobacilli to be applied postharvest.

The business sector is rife with unethical managerial practices, such as blaming subordinates for organizational failings, along with the exploitation of colleagues, favoritism, and conflicts of leadership. In light of this, numerous researchers have endeavored to explain the phenomenon of ethical perspectives and concerns. It is recommended that organizations in the SME sector adopt ethical practices in order to achieve their long-term objectives. This study stresses the influence of ethical leadership and technological innovation, particularly the mediating role of a positive attitude in encouraging good performance. This study, which was conducted in the SME sector of Malaysia in the state of Selangor, employed a convenience sampling technique for data collection and reports that ethical leadership, technological innovation, and attitude significantly influence performance. A mediating role of attitude in relation to technological innovation and innovative performance is hereby reported, and attitude towards performance was found to have an insignificant effect on ethical leadership and innovative performance. This study contributes to the existing body of knowledge by explaining the role of ethical leadership and technological innovation in expressing and assessing the revolutionary business practices required to ensure organizational success.

Polymer research is currently focused on sustainable and degradable polymers which are cheap, easy to synthesize, and environmentally friendly. Silicon-based polymers are thermally stable and can be utilized in various applications, such as columns and coatings. Poly(silyl ether)s (PSEs) are an interesting class of silicon-based polymers that are easily hydrolyzed in either acidic or basic conditions due to the presence of the silyl ether Si-O-C bond. Synthetically, these polymers can be formed in several different ways, and the most effective and environmentally friendly synthesis is dehydrogenative cross coupling, where the byproduct is H2 gas. These polymers have a lot of promise in the polymeric materials field due to their sustainability, thermal stability, hydrolytic degradability, and ease of synthesis, with nontoxic byproducts. In this review, we will summarize the synthetic approaches for the PSEs in the recent literature, followed by the properties and applications of these materials. A conclusion and perspective will be provided at the end.

Car-sharing systems require accurate demand prediction to ensure efficient resource allocation and scheduling decisions. However, developing precise predictive models for vehicle demand remains a challenging problem due to the complex spatio-temporal relationships. This paper introduces USTIN, the Unified Spatio-Temporal Inference Prediction Network, a novel neural network architecture for demand prediction. The model consists of three key components: a temporal feature unit, a spatial feature unit, and a spatio-temporal feature unit. The temporal unit utilizes historical demand data and comprises four layers, each corresponding to a different time scale (hourly, daily, weekly, and monthly). Meanwhile, the spatial unit incorporates contextual points of interest data to capture geographic demand factors around parking stations. Additionally, the spatio-temporal unit incorporates weather data to model the meteorological impacts across locations and time. We conducted extensive experiments on real-world car-sharing data. The proposed USTIN model demonstrated its ability to effectively learn intricate temporal, spatial, and spatiotemporal relationships, and outperformed existing state-of-the-art approaches. Moreover, we employed negative binomial regression with uncertainty to identify the most influential factors affecting car usage.

Recent studies have shown that a pro-inflammatory diet and dysbiosis, especially a high level of trimethylamine-N-oxide (TMAO), are associated with various adverse health conditions. Cardiovascular diseases and pancreatic diseases are two major morbidities in the modern world. Through this narrative review, we aimed to summarize the association between a pro-inflammatory diet, gut microbiota, and cardiovascular and pancreatic diseases, along with their underlying mechanisms. Our review revealed that TMAO is associated with the development of cardiovascular diseases by promoting platelet aggregation, atherosclerotic plaque formation, and vascular inflammation. TMAO is also associated with the development of acute pancreatitis. The pro-inflammatory diet is associated with an increased risk of pancreatic cancer and cardiovascular diseases through mechanisms that include increasing TMAO levels, activating the lipopolysaccharides cascade, and the direct pro-inflammatory effect of certain nutrients. Meanwhile, an anti-inflammatory diet decreases the risk of cardiovascular diseases and pancreatic cancer.

The current study presents the first results of the passive capture of carbon dioxide from the air in aqueous sodium lysinate solutions at ambient conditions. The salt has shown good passive direct air capture (DAC) properties for carbon dioxide with spent solutions exhibiting more than 5% carbon dioxide by weight. Moreover, different quantities of sodium lysinate solutions were mixed with three commercial water-based paints, and their passive DAC performance was studied for 45 days. An average improvement of 70% in passive DAC capacity compared to the control sample was observed across all the studied paint samples. The results establish that a litre of water-based paint doped with sodium lysinate can absorb up to 40 g of CO2 and fix it stably for a short period of time, i.e., 45 days. Such paints can be used to directly capture carbon dioxide from the air. However, further research is required to address various technicalities and establish long-term sequestration.

Polycystic ovary syndrome (PCOS) is a common endocrine disorder in women that is characterized by fluid-filled sacs in the ovaries and various symptoms, including high androgen levels, endometrial irregularities, and cysts. Although the main cause of PCOS remains unknown, it has been linked to genetic, endocrine, and metabolic factors, and there are several treatment options, including lifestyle modifications, medications, and surgery. Natural products such as medicinal plants and fruits are being explored as potential treatments for PCOS because of their bioactive compounds with pharmacological effects related to antioxidant, antimicrobial, anticancer, and antidiabetic properties. Some of these compounds improve insulin sensitivity, reduce inflammation, and enhance glucose metabolism, thereby benefiting patients with PCOS. This mini-review examined the effects of natural products on PCOS, including their effects on ovarian histological changes, blood glucose, sex hormones, and lipid profiles, based on animal and human studies. This study suggests that the use of natural products as complementary medicines can be a promising resource for the development of effective therapeutics for PCOS; however, further research is needed to fully understand their benefits.

In this study, the employment of the gene expression programming (GEP) technique in forecasting models on sustainable construction materials including mineral admixtures and civil engineering quantities (e.g., compressive strength), was investigated. Compared to the artificial neural networks (ANN) based formulations, which are often too complicated to be used, GEP-based derived models provide estimation equations that are reasonably simple and may be used for practical design purposes and even for hand calculations. Many popular models, such as best-fitted curves based on regression analyses, multi-linear regression (MLR), multinomial logistic regression (MNLR), and multinomial variate regression (MNVR), can also be used for construction materials properties modeling. However, due to the nonlinearity and complexity of the target properties, the models established using linear regression analyses may not reveal the precise behavior. Additionally, regression models lack generality, and this comes from the fact that some functions are defined for regression in classical regression techniques; while in the GEP approach, there is no predefined function to be considered, and it reproduces or omits various combinations of parameters to provide the formulation that fits the experimental outcomes. If the input parameters can be evaluated through simple laboratory or rapid measurements, and also a comprehensive experimental database is made available, the models can be constructed with optimal flexibility. Flexibility in choosing the complexity and fitness functions, such as RMSE, MAE, and MSE, might lead to better performance of the approach and well-capturing the governing pattern behind the material’s characteristics. There may be minor inaccuracies with this technique; however, the explicit mathematical expressions, which can be easily implemented in the design and analysis process, may cover the minor inaccuracies compared to ANN, support vector machine (SVM), and other intelligent approaches. Based on the presented study, sometimes it would be better to provide more than one GEP model and consider different combinations of input contributing variables to afford the possible initial feed for a more settled and comprehensive model. Mostly, GEP’s strengths as a superior machine learning technique in modeling the behavior of construction materials including mineral admixtures, leading to innovative solutions in civil engineering, have been presented.

We study the back-reaction of fermion fields on the kink solution in one space and one time dimension. We employ a variational procedure to determine an upper limit for the minimum of the total energy. This energy has three contributions: the classical kink energy, the energy of valence fermions and the fermion vacuum polarization energy. The latter arises from the interaction of the kink with the Dirac sea and is required for consistency of the semi-classical expansion for the fermions. Earlier studies only considered the valence part and observed a substantial back-reaction. This was reflected by a sizable distortion of the kink profile. We find that this distortion is strongly mitigated when the Dirac sea is properly accounted for. As a result, the back-reaction merely produces a slight squeeze or stretch of the kink profile.

The present quantitative, non-experimental comparative study, delves into the long-term effects of the collaborative practicum model (specifically the “academy-class” model) on novice teachers. The research aims to discern disparities in the professional self-efficacy of novice educators who underwent training within the collaborative practicum model as opposed to those who adhered to the conventional teaching model. This comparative analysis is based on three variables: perception of the teaching profession, professional self-efficacy, and socio-economic security. Furthermore, the study examines whether the collaborative model contributes to cultivating more favorable attitudes toward the teaching profession and a greater inclination to continue teaching for an extended period exceeding three years. The study encompasses a cohort of 436 Bachelor of Education (B.Ed.) graduates from 22 Israeli Higher Education Institutions who completed their degrees within the past five years. The research findings underscore a higher level of teaching efficacy, socio-economic security, and a more positive outlook among those who participated in the collaborative practicum and expressed their intent to persist in the teaching profession. These outcomes underscore the vital role of the collaborative practicum model, hinting at its potential to positively influence the retention rate within the teaching profession. Furthermore, it underscores the crucial connection between comprehensive and meaningful training within a collaborative practicum framework and the sustainable professional growth of educators. This robust training approach can potentially secure the continued presence of dedicated and enthusiastic educators in the field over the long term.

As Malaysia undergoes a demographic transformation of population aging, the prevalence of dementia is expected to rise, posing a major public health threat issue. Early screening to detect cognitive impairment is important to implement appropriate clinical interventions. The Visual Cognitive Assessment Test (VCAT) is a language-neutral cognitive assessment screening tool suitable for multilingual populations. This study was aimed to validate the VCAT screening tool for the detection of cognitive impairment amongst the population of Malaysia. A total of 184 participants were recruited, comprising 79 cognitively healthy participants (CHP), 46 mild cognitive impairment (MCI) patients, and 59 mild dementia (Alzheimer’s disease and Vascular Dementia) patients from five hospitals between May 2018 and December 2019 to determine the usefulness of VCAT. Diagnostic performance was assessed using area under the curve (AUC), and receiver operating characteristic (ROC) analysies was performed to determine the recommended cutoff scores. ROC analyses for the VCAT was comparable with that of MoCA (Montreal Cognitive Assessment) in differentiating between CHP, MCI, and mild dementia (AD and VaD) participants. The findings of this study suggest the following optimal cutoff score for VCAT: Dementia 0–19, MCI 20–23, Normal 24–30. The mean ± SD time to complete the VCAT was 10.0 ± 2.75 min in the CHP group and 15.4 ± 4.52 min in the CI group. Results showed that 76.0% of subjects thought that the instructions in VCAT were similar or easier to understand compared with MoCA. This study showed that the VCAT is a valid and useful screening tool for patients with cognitive impairment in Malaysia and is feasible to be used in the clinical settings.

Lithium-ion capacitor technology (LiC) is well known for its higher power density compared to electric double-layer capacitors (EDLCs) and higher energy density compared to lithium-ion batteries (LiBs). However, the LiC technology is affected by a high heat generation problem in high-power applications when it is continuously being charged/discharged with high current rates. Such a problem is associated with safety and reliability issues that affect the lifetime of the cell. Therefore, for high-power applications, a robust thermal management system (TMS) is essential to control the temperature evolution of LiCs to ensure safe operation. In this regard, developing accurate electrical and thermal models is vital to design a proper TMS. This work presents a detailed 1D/3D electro-thermal model at module level employing MATLAB/SIMULINK® coupled to the COMSOL Multiphysics® software package. The effect of the inlet coolant flow rate, inlet coolant temperature, inlet and outlet positions, and the number of arcs are examined under the cycling profile of a continuous 150 A current rate without a rest period for 1400 s. The results prove that the optimal scenario for the LCTMS would be the inlet coolant flow rate of 500 mL/min, the inlet temperature of 30 °C, three inlets, three outlets, and three arcs in the coolant path. This scenario decreases the module’s maximum temperature (Tmax) and temperature difference by 11.5% and 79.1%, respectively. Moreover, the electro-thermal model shows ±5% and ±4% errors for the electrical and thermal models, respectively.

The leavening of wheat-based steamed bread is carried out either with a pure yeast culture or with traditional starter cultures containing both lactic acid bacteria and yeast/mold. The use of variable starter cultures significantly affects steamed bread’s quality attributes, including nutritional profile. In this paper, differences in physicochemical properties, the type of digested starch, the production of free amino acids, and the specific volume of steamed bread under three fermentation methods (blank, yeast, and LP-GM4-yeast) were compared. The digestion characteristics (protein and starch hydrolysis) of steamed bread produced by using either yeast alone or a combination of Lactiplantibacillus plantrum and yeast (LP-GM4-yeast) were analyzed by an in vitro simulated digestion technique. It was found that the specific volume of steamed bread fermented by LP-GM4-yeast co-culture was increased by about 32%, the proportion of resistant starch was significantly increased (more than double), and soluble protein with molecular weight of 30–40 kDa was significantly increased. The results of this study showed that steamed bread produced by LP-GM4-yeast co-culture is more beneficial to human health than that by single culture.

In recent years, kenaf has gained significant global attention as a more cost-effective, adaptable, and manageable alternative to other fibre crops. India and China, with nearly 70% of the global kenaf production, have emerged as the leading producers of kenaf plants. While kenaf was traditionally valued for its paper production, it has evolved into a multipurpose crop with diverse industrial applications over the past two decades. Conventional soil-based cultivation methods for kenaf require up to six months for plant maturity. However, in vitro propagation techniques offer a promising alternative that enables faster growth and reduced labour costs. In vitro propagation can be achieved using solid and liquid media, with limited research available on the pure liquid culture method for kenaf. This review aims to introduce and compare the production of kenaf using solid and liquid media, with a specific focus on the emerging country of Malaysia, which seeks to harness the potential of kenaf cultivation for the 15th Sustainable Development Goal, “life on land”, and its contribution to the economy.

Earthquake-induced soil liquefaction (EISL) can cause significant damage to structures, facilities, and vital urban arteries. Thus, the accurate prediction of EISL is a challenge for geotechnical engineers in mitigating irreparable loss to buildings and human lives. This research aims to propose a binary classification model based on the hybrid method of a wavelet neural network (WNN) and particle swarm optimization (PSO) to predict EISL based on cone penetration test (CPT) results. To this end, a well-known dataset consisting of 109 datapoints has been used. The developed WNN-PSO model can predict liquefaction with an overall accuracy of 99.09% based on seven input variables, including total vertical stress (σv), effective vertical stress (σv′), mean grain size (D50), normalized peak horizontal acceleration at ground surface (αmax), cone resistance (qc), cyclic stress ratio (CSR), and earthquake magnitude (Mw). The results show that the proposed WNN-PSO model has superior performance against other computational intelligence models. The results of sensitivity analysis using the neighborhood component analysis (NCA) method reveal that among the seven input variables, qc has the highest degree of importance and Mw has the lowest degree of importance in predicting EISL.

Yersinia pestis, the causative agent of plague, is a Gram-negative bacterium. If the plague is not properly treated it can cause rapid death of the host. Bubonic, pneumonic, and septicemic are the three types of plague described. Bubonic plague can progress to septicemic plague, if not diagnosed and treated on time. The mortality rate of pneumonic and septicemic plague is quite high. The symptom-defining disease is the bubo, which is a painful lymph node swelling. Almost 50% of bubonic plague leads to sepsis and death if not treated immediately with antibiotics. The host immune response is slow as compared to other bacterial infections. Clinical isolates of Yersinia pestis revealed resistance to many antibiotics such as tetracycline, spectinomycin, kanamycin, streptomycin, minocycline, chloramphenicol, and sulfonamides. Drug discovery is a time-consuming process. It always takes ten to fifteen years to bring a single drug to the market. In this regard, in silico subtractive proteomics is an accurate, rapid, and cost-effective approach for the discovery of drug targets. An ideal drug target must be essential to the pathogen’s survival and must be absent in the host. Machine learning approaches are more accurate as compared to traditional virtual screening. In this study, k-nearest neighbor (kNN) and support vector machine (SVM) were used to predict the active hits against the beta-ketoacyl-ACP synthase III drug target predicted by the subtractive genomics approach. Among the 1012 compounds of the South African Natural Products database, 11 hits were predicted as active. Further, the active hits were docked against the active site of beta-ketoacyl-ACP synthase III. Out of the total 11 active hits, the 3 lowest docking score hits that showed strong interaction with the drug target were shortlisted along with the standard drug and were simulated for 100 ns. The MD simulation revealed that all the shortlisted compounds display stable behavior and the compounds formed stable complexes with the drug target. These compounds may have the potential to inhibit the beta-ketoacyl-ACP synthase III drug target and can help to combat Yersinia pestis-related infections. The dataset and the source codes are freely available on GitHub.

Adaptive optics (AO) retinal imaging enables individual photoreceptors to be visualized in the clinical setting. AO imaging can be a powerful clinical tool for detecting photoreceptor degeneration at a cellular level that might be overlooked through conventional structural assessments, such as spectral-domain optical coherence tomography (SD-OCT). Therefore, AO imaging has gained significant interest in the study of photoreceptor degeneration, one of the most common causes of inherited blindness. Growing evidence supports that AO imaging may be useful for diagnosing early-stage retinal dystrophy before it becomes apparent on fundus examination or conventional retinal imaging. In addition, serial AO imaging may detect structural disease progression in early-stage disease over a shorter period compared to SD-OCT. Although AO imaging is gaining popularity as a structural endpoint in clinical trials, the results should be interpreted with caution due to several pitfalls, including the lack of standardized imaging and image analysis protocols, frequent ocular comorbidities that affect image quality, and significant interindividual variation of normal values. Herein, we summarize the current state-of-the-art AO imaging and review its potential applications, limitations, and pitfalls in patients with inherited retinal diseases.

While storytelling and visualization have always been recognized as invaluable techniques for imparting knowledge across generations, their importance has become even more evident in the present information age as the abundance of complex data grows exponentially. These techniques can simplify convoluted concepts and communicate them in a way to be intelligible for diverse audiences, bringing together heterogeneous stakeholders and fostering collaboration. In the field of energy and climate research, there is an increasing demand to make sophisticated models and their outcomes explainable and comprehensible for an audience of laypersons. Unfortunately, traditional tools and methods may be inefficient to provide meaning for input and output values; therefore, in this study, we employ a storytelling tool, the so-called Academic Presenter, to digest various datasets and visualize the extended BioENergy OPTimization model (BENOPTex) outcomes in different online and offline formats. The developed tool facilitates communications among collaborators with a broad spectrum of backgrounds by transforming outcomes into visually appealing stories. Although this study focuses on designing an ideal user interface for BENOPTex, the developed features and the learned lessons can be replicated for other energy system models.

The use of by-products from the agri-food industry is a promising approach for production of value-added, polyphenol-rich dietary supplements or natural pharmaceutical preparations. During pistachio nut processing, a great amount of husk is removed, leaving large biomass for potential re-use. The present study compares antiglycative, antioxidant, and antifungal activities as well as nutritional values of 12 genotypes belonging to four pistachio cultivars. Antioxidant activity was measured using DPPH and ABTS assays. Antiglycative activity was evaluated as inhibition of advanced glycation end product (AGE) formation in the bovine serum albumin/methylglyoxal model. HPLC analysis was performed to determine the major phenolic compounds. Cyanidin-3-O-galactoside (120.81–181.94 mg/100 g DW), gallic acid (27.89–45.25), catechin (7.2–11.01), and eriodictyol-7-O-glucoside (7.23–16.02) were the major components. Among genotypes, the highest total flavonol content (14.8 mg quercetin equivalents/g DW) and total phenolic content (262 mg tannic acid equivalent/g DW) were in KAL1 (Kaleghouchi) and FAN2 (Fandoghi), respectively. The highest antioxidant (EC50 = 375 μg/mL) and anti-glycative activities were obtained for Fan1. Furthermore, potent inhibitory activity against Candida species was recorded with MIC values of 3.12–12.5 µg/mL. The oil content ranged from 5.4% in Fan2 to 7.6% in Akb1. The nutritional parameters of the tested cultivars were highly variable: crude protein (9.8–15.8%), ADF (acid detergent fiber 11.9–18.2%), NDF (neutral detergent fiber, 14.8–25.6%), and condensed tannins (1.74–2.86%). Finally, cyanidin-3-O-galactoside was considered an effective compound responsible for antioxidant and anti-glycative activities.

One of the most undesirable consequences induced by blasting in open-pit mines and civil activities is flyrock. Furthermore, the production of oversize boulders creates many problems for the continuation of the work and usually imposes additional costs on the project. In this way, the breakage of oversize boulders is associated with throwing small fragments particles at high speed, which can lead to serious risks to human resources and infrastructures. Hence, the accurate prediction of flyrock induced by boulder blasting is crucial to avoid possible consequences and its’ environmental side effects. This study attempts to develop an optimized artificial neural network (ANN) by particle swarm optimization (PSO) and jellyfish search algorithm (JSA) to construct the hybrid models for anticipating flyrock distance resulting in boulder blasting in a quarry mine. The PSO and JSA algorithms were used to determine the optimum values of neurons’ weight and biases connected to neurons. In this regard, a database involving 65 monitored boulders blasting for recording flyrock distance was collected that comprises six influential parameters on flyrock distance, i.e., hole depth, burden, hole angle, charge weight, stemming, and powder factor and one target parameter, i.e., flyrock distance. The ten various models of ANN, PSO–ANN, and JSA–ANN were established for estimating flyrock distance, and their results were investigated by applying three evaluation indices of coefficient of determination (R2), root mean square error (RMSE) and value accounted for (VAF). The results of the calculation of evaluation indicators revealed that R2, values of (0.957, 0.972 and 0.995) and (0.945, 0.954 and 0.989) were determined to train and test of proposed predictive models, respectively. The yielded results denoted that although ANN model is capable of anticipating flyrock distance, the hybrid PSO–ANN and JSA–ANN models can anticipate flyrock distance with more accuracy. Furthermore, the performance and accuracy level of the JSA–ANN predictive model can estimate better compared to ANN and PSO–ANN models. Therefore, the JSA–ANN model is identified as the superior predictive model in estimating flyrock distance induced from boulder blasting. In the final, a sensitivity analysis was conducted to determine the most influential parameters in flyrock distance, and the results showed that charge weight, powder factor, and hole angle have a high impact on flyrock changes.

Toxoplasma gondii is an important zoonotic foodborne parasite capable of infecting almost all warm-blooded animal species worldwide. Toxoplasmosis is usually acquired via ingestion of undercooked infected animal tissues resulting in life-threatening consequences for unborn foetus and immunocompromised individuals. A cross-sectional study was carried out to determine the prevalence of T. gondii infection, its associated risk factors in farms, and haplotypes isolated from the native village chicken and pig populations in Peninsular Malaysia. The seroprevalence of T. gondii in village chickens at the animal level was low at 7.6% (95% CI: 4.60–11.60), while at the farm level, it was 52.0% (95% CI: 31.30–72.20). For pigs, the animal-level seroprevalence of T. gondii was 3.0% (95% CI: 1.60–5.10), while the farm-level, it was 31.6% (95% CI: 12.60–56.60). The PCR-based DNA detection on meat samples from chickens (n = 250) and pork (n = 121) detected 14.0% (95% CI: 9.95–18.9) and 5.8% (95% CI: 2.4–11.6) positive, respectively. Six unique T. gondii haplotypes were isolated from the tissue samples. Multivariable logistic regression analysis showed that feeding the chickens farm-produced feeds and allowing wild animals access to pig farms were significant determinants for farm-level seropositivity. Providing hygienic and good quality feeds to chickens and increasing biosecurity in pig farms through prevention of access by wildlife may reduce the risk of transmission of T. gondii infection in the local chickens and pig farms.

Engineered human tissues created by three-dimensional cell culture of human cells in a hydrogel are becoming emerging model systems for cancer drug discovery and regenerative medicine. Complex functional engineered tissues can also assist in the regeneration, repair, or replacement of human tissues. However, one of the main hurdles for tissue engineering, three-dimensional cell culture, and regenerative medicine is the capability of delivering nutrients and oxygen to cells through the vasculatures. Several studies have investigated different strategies to create a functional vascular system in engineered tissues and organ-on-a-chips. Engineered vasculatures have been used for the studies of angiogenesis, vasculogenesis, as well as drug and cell transports across the endothelium. Moreover, vascular engineering allows the creation of large functional vascular conduits for regenerative medicine purposes. However, there are still many challenges in the creation of vascularized tissue constructs and their biological applications. This review will summarize the latest efforts to create vasculatures and vascularized tissues for cancer research and regenerative medicine.

Penetration of wind power plants (WPPs) in the electric power system will complicate the system load flow analysis. Consequently, the traditional load flow algorithm can no longer be used to find the solution to the load flow problem of such a system. This paper proposes a doubly fed induction generator (DFIG)-based WPP model for a load flow analysis of the electric power system. The proposed model is derived based on the power formulations of the WPP—namely, DFIG power, DFIG power loss, and WPP power output formulas. The model can be applied to various DFIG power factor operating modes. In the present paper, applications of the proposed methods in two representative electric power systems (i.e., IEEE 14-bus and 30-bus systems) have been investigated. The investigation results verify the proposed method’s capability to solve the load flow problem of the system embedded with DFIG-based variable-speed WPPs.

Oregano and marjoram are important aromatic spices in the food industry, as well as medicinal plants with remarkable antioxidant properties. Despite their popularity, little is known about treatments that would influence the antioxidant capacity of essential oils. In this study, different spectra of LED light, namely blue, red, white, blue-red, and natural ambient light as a control, were applied to assess the essential oil content, composition, flavonoid, phenolic, and antioxidant capacity of oregano and marjoram. GC-MS analysis revealed thymol, terpinen-4-ol, sabinene, linalool, p-cymene, and γ-terpinene as the main compounds. In oregano, the thymol content ranged from 11.91% to 48.26%, while in marjoram it varied from 17.47% to 35.06% in different samples. In oregano and marjoram, the highest phenolic contents were in blue (61.26 mg of tannic acid E/g of DW) and in white (65.18 mg of TAE/g of DW) light, respectively, while blue-red illumination caused the highest increase in total flavonoids. The antioxidant activity of oregano and marjoram extract was evaluated using two food model systems, including DPPH and β-carotene bleaching. The highest antioxidant capacity was obtained in control light in oregano and blue-red light in marjoram. The results provide information on how to improve the desired essential oil profile and antioxidant capacity of extracts for industrial producers.

Streptococcosis and motile Aeromonad septicemia (MAS) are the main bacterial diseases in tilapia culture worldwide, causing significant economic losses. Vaccination is an effective method of preventing diseases and contributes to economic sustainability. This study investigated the immuno-protective efficacy of a newly developed feed-based bivalent vaccine against streptococcosis and MAS in red hybrid tilapia. The feed-based bivalent vaccine pellet was developed by incorporating the formalin-killed S. agalactiae and A. hydrophila antigens into a commercial feed pellet with palm oil as the adjuvant. The bivalent vaccine was subjected to feed quality analyses. For immunological analyses, 900 fish (12.94 ± 0.46 g) were divided into two treatment groups in triplicate. Fish in Group 1 were unvaccinated (control), while those in Group 2 were vaccinated with the bivalent vaccine. The bivalent vaccine was delivered orally at 5% of the fish’s body weight for three consecutive days on week 0, followed by boosters on weeks 2 and 6. Lysozyme and enzyme-linked immunosorbent assays (ELISAs) on serum, gut lavage, and skin mucus were performed every week for 16 weeks. Lysozyme activity in vaccinated fish was significantly (p ≤ 0.05) higher than in unvaccinated fish following vaccination. Similarly, the IgM antibody levels of vaccinated fish were significantly (p ≤ 0.05) higher after vaccination. The bivalent vaccine provided high protective efficacy against S. agalactiae (80.00 ± 10.00%) and A. hydrophila (90.00 ± 10.00%) and partial cross-protective efficacy against S. iniae (63.33 ± 5.77%) and A. veronii (60.00 ± 10.00%). During the challenge test, fewer clinical and gross lesions were observed in vaccinated fish compared with unvaccinated fish. Histopathological assessment showed less severe pathological changes in selected organs than the unvaccinated fish. This study showed that vaccination with a feed-based bivalent vaccine improves immunological responses in red hybrid tilapia, and thus protects against streptococcosis and MAS.

Estuaries worldwide are experiencing increasing threats from climate change, particularly from the compounding effects of sea level rise (SLR) and varying magnitude of river inflows. Understanding the tidal response of estuaries to these effects can guide future management and help assess ecological concerns. However, there is limited existing understanding on how estuarine tidal dynamics may respond to the compounding effects of SLR and altered riverine inflows in different estuaries. To partially address this knowledge gap, this study used data analysis and scrutinised idealised hydrodynamic models of different estuary shapes and boundary conditions to (i) identify broad effects of SLR on estuarine tidal dynamics under various river inflow conditions, (ii) determine how longitudinal cross-sections are impacted by these effects, and (iii) highlight some implications for environmental risk management. Results indicated that short- to moderate-length, high convergent estuaries experience the greatest and short- to moderate-length prismatic and low convergent estuaries experience the least variations in their overall tidal dynamics (i.e., tidal range, current velocity, and asymmetry). These variations were most evident in estuaries with large riverine inflows and macrotidal conditions. Compounding effects of SLR and altered riverine inflows induced spatially heterogenous changes to tidal range, current velocity, and asymmetry, with transects nearest to the estuary mouth/head and at a three-quarter estuary length (measured from estuary mouth) identified as the most and the least vulnerable zones, respectively. These findings provide an initial broad assessment of some effects of climate change in estuaries and may help to prioritise future investigations.

This research offers a combination of experimental and artificial approaches to estimate the dilatancy point under different coal conditions and develop an early warning system. The effect of water content on dilatancy point was investigated under uniaxial loading in three distinct states of coal: dry, natural, and water-saturated. Results showed that the stiffness-stress curve of coal in different states was affected differently at various stages of the process. Crack closure stages and the propagation of unstable cracks were accelerated by water. However, the water slowed the elastic deformation and the propagation of stable cracks. The peak strength, dilatancy stress, elastic modulus, and peak stress of natural and water-saturated coal were less than those of dry. An index that determines the dilatancy point was derived from the absolute strain energy rate. It was discovered that the crack initiation point and dilatancy point decreased with the increase in acoustic emission (AE) count. AE counts were utilized in artificial neural networks, random forest, and k-nearest neighbor approaches for predicting the dilatancy point. A comparison of the evaluation index revealed that artificial neural networks prediction was superior to others. The findings of this study may be valuable for predicting early failures in rock engineering.