Search

The use of learner modelling approaches is critical for providing adaptive support in educational computer games, with predictive learner modelling being among the key approaches. While adaptive supports have been shown to improve the effectiveness of educational games, improperly customized support can have negative effects on learning outcomes. To tackle these challenges, we present a novel approach, called DeepLM, that considers a series of time windows representing both sequences of learners' actions during gameplay and estimation of their current competencies (using stealth assessment) to model learners and accordingly predict their future performance. The approach employs a variant of deep neural networks to early predict learners' midterm and final scores simultaneously. The results show that using 20-50% of learners' action sequences can early predict their final scores, with a cross-validated convolutional neural network (CNN) achieving an area under the curve (AUC) and accuracy of 0.879 and 85.3%, respectively. The same model can also achieve high accuracy in predicting midterm and final scores at the same time, with an AUC and accuracy of 0.848 and 77.9%. Overall, the CNN model outperforms recurrent neural network, long short-term memory, and baseline multilayer perceptron (MLP) models in predicting learners' final performance and performs better than the baseline MLP model in predicting learners' midterm and final performance using both cross-validation and independent datasets. These findings show the potential of the proposed approach in accurately early predicting learners' performance, allowing educators and game designers to tailor interventions and support mechanisms that could lead to optimized learning outcomes.

Chemical recycling of polyurethane (PU) waste is essential to displace the need for virgin polyol production and enable sustainable PU production. Currently, less than 20% of PU waste is downcycled through rebinding to lower value products than the original PU. Chemical recycling of PU waste often requires significant input of materials like solvents and slow reaction rates. Here, we report the fast (

Abstract Introducing an innovative dual-layer coating technique to enhance solar panel durability against dust, this method uses a translucent aluminum zinc oxide conductive film to prevent accumulation through active dust repulsion. A secondary TiO2-infused coating, applied via a cost-effective sol-gel method, boosts anti-soiling capabilities in a passive manner. Comprehensive tests on dust accumulation, self-cleaning efficiency, mechanical robustness, UV-VIS transmission, and chemical resilience reveal promising results. These coatings improve glass clarity, reduce dust adhesion, and maintain energy production even in calm conditions. The effectiveness relies on the precise concentrations of aluminum nitrate and Titania nanoparticles, with annealing temperature affecting transmission rates. The coatings demonstrate highly desired resistance to both alkaline and acidic environments, ensuring consistent performance across various settings. This durability supports the widespread adoption of solar energy in diverse climates, advancing global sustainable energy efforts.

Housing instability is considered a significant life stressor and preemptive screening should be applied to identify those at risk for homelessness as early as possible so that they can be targeted for specialized care. We developed models to classify patient outcomes for an established VA Homelessness Screening Clinical Reminder (HSCR), which identifies housing instability, in the two months prior to its administration. Logistic Regression and Random Forest models were fit to classify responses using the last 18 months of document activity. We measure concentration of risk across stratifications of predicted probability and observe an enriched likelihood of finding confirmed false negative responses from veterans with diagnosed housing instability. Positive responses were 34 times more likely to be detected within the top 1 % of patients predicted at risk than from those randomly selected. There is a 1 in 4 chance of detecting false negatives within the top 1 % of predicted risk. Machine learning methods can classify between episodes of housing instability using a data-driven approach that does not rely on variables curated from domain experts. This method has the potential to improve clinicians ability to identify veterans who are experiencing housing instability but are not captured by HSCR.

Abstract In the present study, the regime of motion of fullerene molecules on graphene substrate in a specific temperature range is investigated. The potential energy of fullerene molecules is analyzed using classical molecular dynamics methods. Fullerene molecules C36, C50, C60, C76, C80, and C90 are selected due to spherical shapes of different sizes and good motion performance in previous studies. Analysis of the motion regime at different temperatures is one of the main objectives of this study. To achieve this aim, the translational and rotational movements of fullerene molecules are studied independently. In the first step of the investigation, Lennard-Jone's potential energy of fullerene molecules is calculated. Subsequently, the motion regime of different fullerenes is classified based on their displacement and diffusion coefficient. Findings indicate C60 is not appropriate in all conditions. However, C90 and C76 molecules are found to be appropriate candidates in most cases in different conditions. As far as a straight-line movement is considered, the deviation of fullerene molecules is compared by their angular velocities. Although C60 has a lower angular velocity due to its symmetrical shape, it may not move well due to its low diffusion coefficient. Overall, our study helps to understand the performance of different fullerene molecules on graphene substrate and find their possible applications, especially as wheels in nanomachine or nanocarrier structures.

Abstract Targeted antineoplastic immunotherapies have achieved remarkable clinical outcomes. However, resistance to these therapies due to target absence or antigen shedding limits their efficacy and excludes tumours from candidacy. To address this limitation, here we engineer an oncolytic rhabdovirus, vesicular stomatitis virus (VSVΔ51), to express a truncated targeted antigen, which allows for HER2-targeting with trastuzumab. The truncated HER2 (HER2T) lacks signaling capabilities and is efficiently expressed on infected cell surfaces. VSVΔ51-mediated HER2T expression simulates HER2-positive status in tumours, enabling effective treatment with the antibody-drug conjugate trastuzumab emtansine in vitro, ex vivo, and in vivo. Additionally, we combine VSVΔ51-HER2T with an oncolytic vaccinia virus expressing a HER2-targeted T-cell engager. This dual-virus therapeutic strategy demonstrates potent curative efficacy in vivo in female mice using CD3+ infiltrate for anti-tumour immunity. Our findings showcase the ability to tailor the tumour microenvironment using oncolytic viruses, thereby enhancing compatibility with “off-the-shelf” targeted therapies.

Neural and symbolic architectures are key techniques in AI for learner modelling, enhancing adaptive educational services. Symbolic models offer explanation and reasoning for decisions but require significant human effort. On the other hand, neural architectures demand less human input and yield better predictions, yet lack interpretability. Given the high-risk nature of education and that incorrectly tailored support can negatively affect learning outcomes, the integration of neural and symbolic architectures becomes crucial. This research proposes a novel neural-symbolic AI approach for temporal learner modelling, called TemporaLM, that leverages unsupervised deep neural networks (i.e., autoencoders enriched with symbolic educational knowledge) and dynamic Bayesian networks for learners' knowledge tracing over time. The approach employs a dynamic Bayesian network for temporal knowledge tracking in learners' computational thinking and employs a knowledge-based autoencoder to enhance predictive performance through synthetic data augmentation. Our findings from both cross-validation and practical application demonstrate that the TemporaLM approach, trained on the neural-symbolic AI augmented dataset, achieves better generalizability, yielding an accuracy of 85% and an F1 score of 87%. This surpasses the dynamic Bayesian network trained solely on original and autoencoder-augmented data. Notably, by leveraging the transformed dataset for model training, improvements of up to 8% in F1 score and 5% in accuracy were achieved compared to the original dataset, observed in both cross-validation and application stages. The augmented prediction capabilities, coupled with interpretable knowledge tracing, cultivate trust among educators and learners in data-driven decisions. These findings underline the potential of neural-symbolic family of AI to improve limitation of existing (symbolic) AI methods in education, advancing AI's potential in education and enabling trustworthy and interpretable applications.

Despite the environmental benefits of composting, recent studies worldwide have highlighted the emergence of microplastics (MPs) in compost, posing a potential threat to soil health. This systematic review summarizes existing research on MPs pollution in compost, emphasizing abundance, sources, characteristics, potential ecological risks, and future perspectives. 19 studies from different countries, mostly China, were included in the review. Compost types analyzed included animal manures, sewage sludge, municipal solid waste (MSW), and organic solid waste. Fibers, fragments, and films were the most common shapes, and most of these MPs were between 0.5 to 3 mm in size. Polyethylene (PE) and polypropylene (PP) are among the most frequently identified polymers. MPs abundance ranged from 0 to 2.88 × 105 items/kg, with the highest levels in chicken manure and animal/plant mixtures. Primary MPs sources were MSW, sewage sludge, animal manure and plant residues. Using the Hazard Index (H), the ecological risk assessment revealed a high risk (H > 100) for certain composts. Further research is needed to understand the long-term effects of MPs in compost on soil health and ecosystem functioning. Waste management and treatment processes need to be improved to reduce MPs pollution in compost raw materials. This review highlights the growing problem of MPs in compost and the need for targeted mitigation strategies.

The degradation of 2,4-Dichlorophenoxyacetic acid (2,4-D) pesticide by photo-electrocatalytic process (PEC) equipped with special NiTiO2-NT/AC-PTFE electrodes was evaluated. The NiTiO2-NT/AC-PTFE electrodes were prepared by electrodepositing method and doping Ni into TiO2 nanotubes. Fabricated electrodes were that Ni doping, increases the removal efficiency of 2,4-D in the UV and visible light range. Characterized using SEM, EDX, and XRD analyses. The results showed that the use of an ultraviolet light source indicated a higher degradation in nickel concentration of 0.5 mg/L compared to 0.25 mg/L. Best results were achieved under the condition of a 90-min timeout, 0.1 A current, electrolyte concentration of 125 mg/L, and UV light source and the pesticide removal efficiency was 90 %. Therefore, the PEC process with the NiTiO2-NT/AC-PTFE electrode is as a relatively high-performance process for degrading 2,4-D from aqueous solutions. The organic byproducts were also identified by GC–MS analysis and toxicity tests were carried out by Chlorella vulgaris. The high concentration of pesticides increases the inhibition of algae growth due to their effects on algae.

Given the increasing reliance on plastic packaging in the beverage industry, this study investigates the presence of microplastics (MPs) in the most popular beverage brands in the Iranian market. A total of 19 bottled beverage brands, including soft drinks and non-alcoholic beverages, were randomly collected and filtered. Quantitative analysis of the MPs was then performed using stereomicroscopy and fluorescence techniques, and classification was based on color, shape, and size. In addition, the polymer type was determined using Fourier transform infrared spectroscopy (FT-IR), and the surface morphology and elemental composition of the MPs were examined using Scanning Electron Microscopy (SEM) and Energy dispersive X-ray spectroscopy (EDS). The results showed that approximately 80–90 % of the samples were contaminated with different MP types, with an average of 4.5 ± 4.8 particles/L detected by stereomicroscopy and 21.90 ± 25.72 particles/L by fluorescence microscopy. FT-IR analysis identified polyethylene terephthalate (PET) and polyethylene (PE) as the predominant polymer types and may clarify the possible role of packaging materials in the contamination of MPs. Fragments accounted for the highest proportion of MPs (71 %), followed by fibers (29 %). The size distribution of MPs was dominated by particles in the range of 1–500 μm (48 %), followed by 500–1000 μm (40 %) and 1000–1500 μm (12 %). MPs were black (84 %), with smaller proportions of red (7 %) and green (1 %), which may reflect the source of the contamination. The findings emphasize the necessity of increased monitoring and the application of countermeasures to lessen MPs contamination in the beverage sector.

Abstract Mesoporous silica nanoparticles (MSNPs) coated by chitosan (CS) were shown to be a proper candidate as a carrier for drug delivery purposes. However, choosing the suitable drug-containing complexes to be applied on MSNPs-CS is of much greater importance to evaluate the possible candidate for an efficient combination of cell viability, drug release kinetics, and atherosclerosis prevention. In this regard, this study concentrates on the synthesis and assessment of coated MSNPs-CS designed for drug delivery purposes. The MSNPs are coated with polyelectrolyte complexes (PEC) composed of CS and dextran sulfate (MSNPs-CS-DX), serving as a versatile drug carrier with favorable biological characteristics. CS-DX is applied to MSNPs without requiring complex or multi-step synthesis procedures. Rosuvastatin, a cholesterol-lowering medication, is chosen for its therapeutic relevance. Additionally, CS-DX is found to relatively impede the uptake of low-density lipoproteins (LDLs) by macrophages, enhancing their potential therapeutic utility. FTIR pattern, FESEM, and TEM images prove MSNPs-CS-DX formation. DLS measurement demonstrates the average particle size of 110 nm for MSNPs, with the combined thickness of CS and DX layers ranging from 10 to 15 nm. BET test is carried out to evaluate the pore size and porosity of structure, showing outstanding results that cause an entrapment efficiency of 57% for MSNPs-CS-DX. Furthermore, the findings demonstrate the pH sensitivity of MSNPs-CS-DX on drug release kinetics. Notably, the CS-DX layer exhibits a significant enhancement in cell viability of human umbilical vein endothelial cells (HUVEC) by approximately 24% within a 24 h timeframe compared to MSNPs lacking CS-DX. Graphical Abstract

Digital game-based learning has received increased attention in education. As the key stakeholders in education, students, parents, and teachers may have different perceptions and attitudes towards game-based learning, which have a great impact on its adoption and dissemination. However, there is a lack of research examining how the perceptions of different stakeholders towards digital educational games may differ and influence each other. This study aimed to address the gap by investigating the perceptions of students, parents and teachers towards digital educational games, the differences and relationships between their perceptions, and possible sources of their perceptions. The study was conducted with 415 participants in China, a country that has tension between play and learning in its traditional values. The results reveal that most students, parents and teachers have certain experience playing mobile games, but with limited knowledge about educational digital games. Students have more positive perceptions towards digital educational games than teachers and parents, and the perceptions of teachers and parents are correlated with each other. After an introduction to an educational digital game, students' and parents' intention to recommend game-based learning increased, which, however, was not the case for teachers. Implications of the findings were discussed.

BackgroundRenal colic is characterized by severe pain that is highly disabling. Gabapentin, an antiepileptic medication, is often recommended as a first-line therapy for neuropathic pain. However, its effectiveness in managing somatic pain, which is defined as the result of activity by pain receptors in the deep tissues, such as renal colic pain, is not as well-established.MethodA phase 3 randomized clinical trial was conducted to evaluate the adjuvant analgesic effects of gabapentin on acute renal colic pain. Eligible patients participated in the study via random allocation to the control or gabapentin groups using the block randomization method. All patients received a shared regimen of ketorolac and rescue morphine as the conventional analgesic treatment for renal colic pain. Gabapentin was added as an adjuvant analgesic for the gabapentin group.ResultA total of 63 individuals with an average age of 41.35 ± 13.08, were enrolled and completed the study. At the time of admission, there were no significant differences between the baseline characteristics of two groups, with exception of weight. The gabapentin group showed a significantly higher percentage of patients with pain severity of less than 5 after 60 and 90 min, as well as a significantly lower percentage of morphine rescue requirement and total morphine intake (mg) and mg/kg.ConclusionIn cases of acute renal colic, gabapentin significantly decreases both the amount of morphine required and the degree of pain, indicating that it may be a useful adjutant to standard analgesic regimens. Treatment regimens that include gabapentin may help individuals manage their pain and become less reliant on opioids. Clinical Trial Registrationhttps://irct.behdasht.gov.ir/trial/56066, identifier: IRCT20200322046833N2.

Key Clinical Message Multiple sclerosis (MS) is one of the common central nervous system diseases, but it can cause dysfunction in other organs such as periodontal tissues. However, it has not been as noticeable. This report aimed to present a 44‐year‐old patient with severe chronic periodontitis, and sudden teeth loss since the diagnosis of MS.

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.

Microplastics (MPs) pollution represents a nascent environmental contaminant that has recently infiltrated human life and the food chain. The primary objective of this study was to investigate the presence of MPs in different brands of Iranian sausages. Qualitative and quantitative analyses of MPs particles were conducted using stereo- and fluorescent microscopy, FT-IR (Fourier-transform infrared spectroscopy), and SEM-EDS (Scanning electron microscopy-energy dispersive X-ray spectroscopy) techniques. Samples were collected from the most commonly consumed sausage brands in Iranian markets. The findings showed that the various sausage brands contained an average abundance of 25.7 ± 21.68 (range 10–70) and 55.45 ± 45.5 (range 10–175) particles/kg based on optical and fluorescent microscopy analyses, respectively. Predominantly, MPs were identified in fiber form (77–89 %), with a smaller proportion present in fragmented form (11–23 %). Polymer analysis using FT-IR identified polyethylene (PE) and polystyrene (PS) as the primary constituents. Furthermore, the estimated annual intake (EAI) of MPs was calculated at 804 and 3517 particles/kg bw/year for adults and children, respectively, based on optical microscopy observations. In comparison, fluorescent microscopy indicated an intake of 1734 and 7589 particles/kg bw/year for the respective age groups. These results emphasize the potential of MPs contamination to penetrate into different food products including sausages through processing routes, which can threaten human health.

Key Clinical Message This case report presents an uncommon variant of Ebstein anomaly, where all three tricuspid valve leaflets exhibited apical displacement—a rare finding. It illustrates the complexities in diagnosing and managing such atypical presentations, with successful surgical correction through annuloplasty. The report adds valuable insights to the limited literature on this congenital heart disease. Abstract Ebstein anomaly (EA), a rare congenital heart disorder, presents with diverse clinical spectrums. This case report explores a distinctive manifestation of EA, where all three tricuspid valve (TV) leaflets exhibited apical displacement, highlighting a novel aspect in the presentation of this condition. A 44‐year‐old woman, under long‐term medical surveillance for EA, showcased an atypical clinical trajectory marked by the apical displacement of all TV leaflets, which is uncommon in EA. Despite a predominantly asymptomatic course, recent exacerbation of symptoms prompted further evaluation. Diagnostic modalities, including echocardiography and cardiac magnetic resonance imaging, revealed severe tricuspid regurgitation concomitant with unprecedented apical displacement of the anterior, septal, and posterior tricuspid leaflets. The displacement of the anterior leaflet was contrary to typical embryonic valvular formation expectations, indicating a unique presentation within EA. The patient underwent annuloplasty surgery, which successfully rectified the anomalous TV architecture. Postoperative evaluation demonstrated mild residual tricuspid regurgitation, and the patient was discharged in stable condition. This case underscores the variability in EA presentations and accentuates the significance of tailored surgical interventions. The observation of apical displacement involving all TV leaflets adds a unique dimension to the existing EA literature, reinforcing the need for careful diagnosis and personalized treatment approaches.