Traditional Assessment Methods Research Articles

G2LCPS: End-to-end semi-supervised landmark prediction with global-to-local cross pseudo supervision for airway difficulty assessment

Difficult tracheal intubation is a major cause of anesthesia-related injuries, including brain damage and death. While deep neural networks have improved difficult airways (DA) predictions over traditional assessment methods, existing models are often black boxes, making them difficult to trust in critical medical settings. Traditional DA assessment relies on facial and neck features, but detecting neck landmarks is particularly challenging. This paper introduces a novel semi-supervised method for landmark prediction, namely G2LCPS, which leverages hierarchical filters and cross-supervised signals. The novelty lies in ensuring that the networks select good unlabeled samples at the image level and generate high-quality pseudo heatmaps at the pixel level for cross-pseudo supervision. The extended versions of the public AFLW, CFP, CPLFW and CASIA-3D FaceV1 face datasets and show that G2LCPS achieves superior performance compared to other state-of-the-art semi-supervised methods, achieving the lowest normalized mean error (NME) of 3.588 when only 1/8 of data is labelled. Notably, the inclusion of the local filter improved the prediction by at least 0.199 NME, whereas the global filter contributed an additional improvement of at least 0.216 NME. These findings underscore the effectiveness of our approach, particularly in scenarios with limited labeled data, and suggest that G2LCPS can significantly enhance the reliability and accuracy of DA predictions in clinical practice. The results highlight the potential of our method to improve patient safety by providing more trustworthy and precise predictions for difficult airway management.

Post-earthquake functionality and resilience prediction of bridge networks based on data-driven machine learning method

Earthquake-induced bridge damage can disrupt transportation networks, potentially hindering emergency response and post-disaster recovery efforts, and posing public safety risks in affected areas. Rapid and accurate assessment of post-earthquake resilience of bridge networks is crucial for evaluating urban seismic performance. Traditional resilience assessment methods, constrained by complex traffic distribution processes, struggle to quickly evaluate the traffic performance of bridge networks during the post-earthquake recovery period. This paper presents a two-layer stacking ensemble model for predicting the functionality and resilience of bridge networks. The first layer integrates advantages of four base learners, including random forest (RF), artificial neural network (ANN), convolutional neural network (CNN), and extreme gradient boosting (XGBoost). The second layer completes regression of functionality based on a support vector machine (SVM). Bayesian optimization and 5-fold cross-validation are employed for hyperparameter tuning of the ensemble model. Finally, the proposed model is validated using the Sioux-Falls bridge network. Results demonstrate that the developed model provides rapid predictions of post-earthquake network functionality and resilience. Additionally, this model can guide post-earthquake repair decisions and assist in optimizing the allocation of regional repair resources.

Strategic approaches to enhancing credit risk management in microfinance institutions

Microfinance institutions (MFIs) play a critical role in providing financial services to underserved, low-income populations, yet face significant challenges in managing credit risk due to the nature of their clientele and loan structures. Enhancing credit risk management in MFIs is essential for ensuring financial stability, reducing default rates, and fostering sustainable growth. This review examines strategic approaches to credit risk management tailored to the microfinance context, where traditional credit assessment methods may be less effective. It explores innovative client profiling techniques, such as segmented risk analysis and customized credit scoring models, which leverage demographic and behavioral data to more accurately assess borrower reliability. The use of data-driven decision-making, particularly through predictive analytics and machine learning, is highlighted as a means to anticipate client repayment behaviors and improve risk forecasting. Further, real-time loan monitoring systems with early warning indicators offer MFIs proactive risk mitigation strategies, enabling prompt interventions to prevent defaults. Institutional improvements, including standardized risk frameworks, enhanced training for loan officers, and regular compliance checks, strengthen organizational resilience against credit risks. Portfolio diversification strategies, such as sectoral and geographic diversification, and the integration of group lending models, are also discussed as effective means of reducing risk concentration. By implementing these multifaceted, strategic approaches, MFIs can improve their credit risk management frameworks, better serve their clients, and achieve greater financial sustainability. The review emphasizes the importance of adapting to rapidly evolving risk factors and adopting innovative tools and practices to meet the unique challenges of microfinance. The findings advocate for continuous research and investment in advanced credit risk methodologies, ultimately contributing to the broader goal of financial inclusion.

Perception of undergraduate medical students and examiners towards grand objective structured clinical examination

BackgroundThe assessment of undergraduate medical students consists of a written component and an advanced clinical competency test that evaluates the students’ skills. The Objective Structured Clinical Examinations (OSCE) were only implemented in most medical schools in the last ten years, similar in many developing countries. It was first used with other clinical assessment methods. This study was designed to investigate how medical students in the fourth and sixth grades and examiners perceived the unique format, features, and quality of the Grand Objective Structured Clinical Examinations (GOSCE), a novel method for assessing students. The aim was to understand how this innovative method, distinct from traditional assessment methods, prepares students for real-world scenarios where they encounter different specialty cases. Additionally, the study aimed to understand the significant role and challenges faced by the Faculty of General Medicine at Koya University in implementing this type of OSCE and to identify potential improvements to enhance the quality of the assessment process.MethodsFollowing the administration of two distinct GOSCE examinations for the fourth and sixth stages, feedback forms were created using Google Forms and distributed to students and examiners. The feedback forms covered all aspects of the examination process. The responses were then rigorously analyzed using the scientific tool SPSS, allowing for a comparison between students from both stages and the faculty and external examiners.ResultsIn the survey of 104 undergraduate students (78% of attendants), the majority (84n,80%) rated the fairness of the assessment as good, which is the primary goal of GOSCE. A large percentage (89n,85.6%) agreed that the examination covered a wide range of clinical skills. Eighty students (76.85%) believed the patients cooperated and found the findings precise; on the other hand, The obtained responses from 24 out of 33 faculty staff members (75%) and 29 out of 35 external examiners (82%) strongly agreed that the examination adequately covered a wide variety of clinical abilities. Only two of 68 examiners (2.9%) believed the examination needed more to provide a learning opportunity.ConclusionWith the insightful suggestions for improvement provided by the participants, GOSCE has a promising potential to evolve into a fair, objective clinical tool for assessing medical students, instilling a sense of optimism for its future development.

Discriminant analysis of occupational performance characteristics in patients with major depressive disorders and healthy individuals.

Assessing symptoms and daily functioning in patients with major depressive disorder (MDD) can be challenging, as their limited self-monitoring abilities may result in behavior observed during structured interviews not accurately reflecting their daily lives. This study aimed to determine if specific occupational behaviors could distinguish individuals with MDD from healthy individuals. Baseline data were collected from medical records and activity programs. Three occupational therapists conducted content analysis to assess occupational performance characteristics. Chi-squared tests compared the prevalence of these characteristics between patients with MDD and healthy controls. Multivariable logistic regression controlled for potential confounders, with independent variables selected based on clinical relevance and sample size (p < 0.01). Discriminant analysis was used to enhance group differentiation, assessing prediction rates using area under the curve (AUC) values. A total of 69 occupational performance characteristics were identified, with 12 showing significant differences between 27 patients with MDD and 43 healthy controls. Key discriminators included "Ask questions and consult" (p < 0.001, odds ratio [OR] = 0.051, 95% confidence interval [CI] = 0.009-0.283), "Concentrate on work" (p = 0.003, OR = 0.078, 95% CI = 0.015-0.416), "Choose simple work" (p = 0.004, OR = 17.803, 95% CI = 2.446-129.597), and "Punctual" (p = 0.017, OR = 0.030, 95% CI = 0.002-0.530). Discriminant analysis using these variables yielded a Wilks' λ of 0.493 (p < 0.001), achieving an 88.6% accuracy rate. The receiver operating characteristic curve's AUC value was 0.911 (sensitivity = 95.3%, specificity = 77.8%). This study highlights the importance of occupational performance characteristics in tailoring treatment strategies for MDD, providing insights beyond traditional assessment methods.

Harnessing Machine Intelligence to Bridge the Learning Divide for Students with Disabilities

Learning disabilities affect a significant number of students, often going undiagnosed until academic struggles become evident. Early identification and personalized interventions are crucial for improving educational outcomes, yet traditional assessment methods can be time-consuming and inconsistent. This research explores the potential of machine learning (ML) to detect learning disabilities such as dyslexia, ADHD, and dysgraphia by analysing student performance, cognitive abilities, and behavioural data. We implemented various ML models to predict the likelihood of these disabilities, comparing their performance based on accuracy, precision, and recall. Our findings highlight the effectiveness of ML in early detection and demonstrate how identified disabilities can inform tailored educational support, ultimately creating a more inclusive learning environment. This research emphasizes the transformative potential of ML in enhancing diagnostic accuracy and facilitating personalized interventions, leading to better outcomes for students with disabilities.

Leveraging ChatGPT for Enhanced Aesthetic Evaluations in Minimally Invasive Facial Procedures.

In recent years, the application of AI technologies like ChatGPT has gained traction in the field of plastic surgery. AI models can analyze pre- and post-treatment images to offer insights into the effectiveness of cosmetic procedures. This technological advancement enables rapid, objective evaluations that can complement traditional assessment methods, providing a more comprehensive understanding of treatment outcomes. The study aimed to comprehensively assess the effectiveness of custom ChatGPT model, "Face Rating and Review AI," in facial feature evaluation in minimally invasive aesthetic procedures, particularly before and after Botox treatments. An analysis was conducted on the Web of Science (WoS) database, identifying 79 articles published between 2023 and 2024 on ChatGPT in the field of plastic surgery from various countries. A dataset of 23 patients from Kaggle, including pre- and post-Botox images, was used. The custom ChatGPT model, "Face Rating & Review AI," was used to assess facial features based on objective parameters such as the golden ratio, symmetry, proportion, side angles, skin condition, and overall harmony, as well as subjective parameters like personality, temperament, and social attraction. The WoS search found 79 articles on ChatGPT in plastic surgery from 27 countries, with most publications originating from the USA, Australia, and Italy. The objective and subjective parameters were analyzed using a paired t-test, and all facial features showed low p-values (<0.05). Higher mean scores on features such as the golden ratio (mean = 5.86, SD = 0.69), skin condition (mean = 3.78, SD = 0.73), and personality (mean = 5.0, SD = 0.79) indicate positive shifts after the treatment. The custom ChatGPT model "Face Rating and Review AI" is a valuable tool for assessing facial features in Botox treatments. It effectively evaluates objective and subjective attributes, aiding clinical decision-making. However, ethical considerations highlight the need for diverse datasets in future research to improve accuracy and inclusivity. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Flood Mapping Through Satellite Images Using Deep Learning

Flooding is a pervasive natural disaster that significantly impacts agriculture, infrastructure, and communities, particularly in rural and agricultural regions. Traditional methods of flood assessment and compensation are often manual, time-intensive, and prone to inaccuracies, resulting in delayed aid and inequitable resource distribution. With advancements in technology, satellite imagery and artificial intelligence (AI) provide new opportunities for real-time flood mapping and automated disaster response. This project proposes a Real-Time Flood Mapping and Compensation System using the Attention U-Net deep learning model. Satellite imagery is analysed to detect and segment flood-affected regions with high precision. The Attention U-Net architecture enhances segmentation accuracy by focusing on the most relevant regions in the images while ignoring irrelevant or noisy areas, such as clouds or non-flooded landscapes. The system integrates geospatial data on land boundaries to assess flood severity for individual properties, enabling fair and data-driven compensation for affected landowners. This project holds significant potential for transforming flood disaster management by reducing response times, fostering transparency, and empowering affected communities to recover more effectively. The integration of advanced AI and geospatial technologies marks a critical step toward mitigating the impacts of natural disasters in a rapidly changing climate

Design and Visual Implementation of a Regional Energy Risk Superposition Model for Oil Tank Farms

Ensuring the safety of oil tank farms is essential to maintaining energy security and minimizing the impact of potential accidents. This paper develops a quantitative regional risk model designed to assess both individual and societal risks in oil tank farms, with particular attention to energy-related risks such as leaks, fires, and explosions. The model integrates factors like day–night operational variations, weather conditions, and risk superposition to provide a comprehensive and accurate evaluation of regional risks. By considering the cumulative effects of multiple hazards, including those tied to energy dynamics, and the stability and validity of the model are researched through Monte Carlo simulations and case application. The results show that the model enhances the reliability of traditional risk assessment methods, making it more applicable to oil tank farm safety concerns. Furthermore, this study introduces a practical tool that simplifies the risk assessment process, allowing operators and decision-makers to evaluate risks without requiring in-depth technical expertise. The methodology improves the ability to safeguard oil tank farms, ensuring the stability of energy supply chains and contributing to broader energy security efforts. This study provides a valuable method for researchers and engineers seeking to enhance regional risk calculation efficiency, with a specific focus on energy risks.

Harnessing Risks with Data: A Leakage Assessment Framework for WDN Using Multi-Attention Mechanisms and Conditional GAN-Based Data Balancing

Assessing leakage risks in water distribution networks (WDNs) and implementing preventive monitoring for high-risk pipelines has become a widely accepted approach for leakage control. However, existing methods face significant data barriers between Geographic Information System (GIS) and leakage prediction systems. These barriers hinder traditional pipeline risk assessment methods, particularly when addressing challenges such as data imbalance, poor model interpretability, and lack of intuitive prediction results. To overcome these limitations, this study proposes a leakage assessment framework for water distribution networks based on multiple attention mechanisms and a generative model-based data balancing method. Extensive comparative experiments were conducted using water distribution network data from B2 and B3 District Metered Areas in Zhengzhou. The results show that the proposed model, optimized with a balanced data method, achieved a 40.76% improvement in the recall rate for leakage segment assessments, outperforming the second-best model using the same strategy by 1.7%. Furthermore, the strategy effectively enhanced the performance of all models, further proving that incorporating more valid data contributes to improved assessment results. This study comprehensively demonstrates the application of data-driven models in the field of “smart water management”, providing practical guidance and reference cases for advancing the development of intelligent water infrastructure.

Prediction of mechanical properties of basalt fiber concrete using hybrid recurrent neural networks based on freeze-thaw damage quantification

In the domain of contemporary building materials, the freeze durability of concrete is paramount for ensuring structural safety and longevity. However, traditional assessment methods have hindered research advancement due to their time-intensive and intricate nature. This study presents a novel model that integrates physical damage mechanisms with machine learning to analyze freeze-thaw damage in basalt fiber concrete (BFC). Experimental data on the performance of BFC with various admixtures subjected to freeze-thaw cycles (FTC) were collected. Due to the limited data availability, a hybrid recurrent neural network (HRNN) model was developed by combining recurrent neural network (RNN) and long-short-term memory network (LSTM) techniques to address the challenge of training an effective neural network. Furthermore, irreversible thermodynamics and continuous damage mechanics were incorporated into the loss function of the original model, resulting in a novel hybrid damage function that served to train and constrain the model. The data flow and structural parameters were meticulously adjusted to enhance prediction accuracy and model stability. The results indicate that basalt fibers significantly enhance the frost resistance of concrete, particularly at a dosage of 0.1 %, where the model achieves its lowest prediction error of less than 10 %. Stability and robustness were evidenced under the influence of data with identical parameters. Sensitivity analysis underscored the model's precision in capturing the effects of various parameters. By synergizing thermodynamic principles with data-driven methodologies, the model exhibited remarkable adaptability across FTC damage scenarios. This study offers a novel solution for enhancing the durability of concrete in cold regions and opens up new avenues for the engineering applications of multi-material systems.

Evaluating culinary skill transfer: A deep learning approach to comparing student and chef dishes using image analysis

Evaluating the transfer of culinary skills from educators to students is essential but challenging due to the subjective nature of traditional assessment methods like direct observation. This study proposes using deep learning and image analysis, particularly convolutional neural networks (CNNs) such as VGG-16, to objectively and automatically evaluate the skill transfer by identifying and quantifying visual differences between student and instructor-prepared dishes. The results show that CNNs can effectively capture critical visual features, offering a more consistent and scalable assessment approach. However, challenges remain, including sensitivity to image quality and discrepancies between automated evaluations and human judgments. These findings highlight the need for further refinement of models and expanding datasets to better capture the diversity of real-world culinary outputs. This research lays the foundation for integrating advanced analytical techniques into culinary education, with future work focusing on developing specialized datasets, fine-tuning models, and standardizing protocols to enhance the accuracy and reliability of automated culinary assessments.

Through the Lens of Age: Using Dog Photographs to Uncover Welfare and Stress

This study evaluated the potential of using dogs’ apparent age, judged from photographs, as a non-invasive tool for assessing their welfare. Traditional welfare assessment methods often rely on behavioral and physiological indicators, which can be resource-intensive and invasive. This research explored whether apparent age, a measure used in humans to predict health and longevity, can also serve as an indicator of welfare in dogs by investigating its association with relative telomere length (RTL), a biomarker of biological aging. Photographs of 60 domestic dogs were evaluated by canine specialists and general volunteers via the citizen science platform Zooniverse. Participants estimated the age of 20 dogs from three different age categories: young (0–2 years), adult (2–5 years), and senior (6+ years). The accuracy of these predictions was compared to the dogs’ chronological ages and RTLs. Generalized linear models were used to assess factors influencing prediction accuracy, including the dogs’ age, sex, and origin. Results indicated that both specialists and volunteers reliably estimated the age of senior dogs, with no significant differences in accuracy between groups. Dogs with accurate apparent age estimates had RTLs matching their chronological age, while those with premature aging signs had shorter RTLs. This suggests apparent age could be a practical, non-invasive welfare assessment tool, offering a potentially accessible method for new welfare assessment protocols.

Quantifying the relation between aging-related trabecular bone microstructure and mechanical properties with digital volume correlation approach

Trabecular bone, a highly porous 3D network of interconnected rods and plates known as trabeculae, plays a critical role in bone strength and integrity. Osteoporosis, a condition commonly associated with aging, leads to deteriorations in bone mass and microarchitecture, manifesting as reduced bone mineral density, thinner trabecular struts, increased trabecular spacing, and a shift from trabecular plates to rods. These microstructural alterations contribute to age-related fragility fractures. To quantitatively explore the link between microstructural changes and the mechanical properties of trabecular bone, we combined mechanical testing with micro-computed tomography (micro-CT) and digital volume correlation (DVC) to measure 3D full-field deformation in trabecular bone samples from healthy and osteoporotic human cadaver vertebrae. Our multi-step mechanical testing characterized strain concentration propagation under axial compressive loading, providing new insights into how microstructural parameters influence trabecular bone’s mechanical strength. This study demonstrates that imaging-based approaches for evaluating bone mechanical strength could serve as an alternative to traditional fracture risk assessment methods, which primarily rely on bone mineral density.

A Hybrid Deep Learning Model for Enhanced Structural Damage Detection: Integrating ResNet50, GoogLeNet, and Attention Mechanisms.

Quick and accurate structural damage detection is essential for maintaining the safety and integrity of infrastructure, especially following natural disasters. Traditional methods of damage assessment, which rely on manual inspections, can be labor-intensive and subject to human error. This paper introduces a hybrid deep learning model that combines the capabilities of ResNet50 and GoogLeNet, further enhanced by a convolutional block attention module (CBAM), proposed to improve both the accuracy and performance in detecting structural damage. For training purposes, a diverse dataset of images depicting both structural damage cases and undamaged cases was used. To further enhance the robustness, data augmentation techniques were also employed. In this research, precision, recall, F1-score, and accuracy were employed to evaluate the effectiveness of the introduced hybrid deep learning model. Our findings indicate that the hybrid deep neural network introduced in this study significantly outperformed standalone architectures such as ResNet50 and GoogLeNet, making it a highly effective solution for applications in disaster response and infrastructure maintenance.

Using a Device-Free Wi-Fi Sensing System to Assess Daily Activities and Mobility in Low-Income Older Adults: Protocol for a Feasibility Study.

Older adults belonging to racial or ethnic minorities with low socioeconomic status are at an elevated risk of developing dementia, but resources for assessing functional decline and detecting cognitive impairment are limited. Cognitive impairment affects the ability to perform daily activities and mobility behaviors. Traditional assessment methods have drawbacks, so smart home technologies (SmHT) have emerged to offer objective, high-frequency, and remote monitoring. However, these technologies usually rely on motion sensors that cannot identify specific activity types. This group often lacks access to these technologies due to limited resources and technology experience. There is a need to develop new sensing technology that is discreet, affordable, and requires minimal user engagement to characterize and quantify various in-home activities. Furthermore, it is essential to explore the feasibility of developing machine learning (ML) algorithms for SmHT through collaborations between clinical researchers and engineers and involving minority, low-income older adults for novel sensor development. This study aims to examine the feasibility of developing a novel channel state information-based device-free, low-cost Wi-Fi sensing system, and associated ML algorithms for localizing and recognizing different patterns of in-home activities and mobility in residents of low-income senior housing with and without mild cognitive impairment. This feasibility study was conducted in collaboration with a wellness care group, which serves the healthy aging needs of low-income housing residents. Prior to this feasibility study, we conducted a pilot study to collect channel state information data from several activity scenarios (eg, sitting, walking, and preparing meals) using the proposed Wi-Fi sensing system continuously over a week in apartments of low-income housing residents. These activities were videotaped to generate ground truth annotations to test the accuracy of the ML algorithms derived from the proposed system. Using qualitative individual interviews, we explored the acceptability of the Wi-Fi sensing system and implementation barriers in the low-income housing setting. We use the same study protocol for the proposed feasibility study. The Wi-Fi sensing system deployment began in November 2022, with participant recruitment starting in July 2023. Preliminary results will be available in the summer of 2025. Preliminary results are focused on the feasibility of developing ML models for Wi-Fi sensing-based activity and mobility assessment, community-based recruitment and data collection, ground truth, and older adults' Wi-Fi sensing technology acceptance. This feasibility study can make a contribution to SmHT science and ML capabilities for early detection of cognitive decline among socially vulnerable older adults. Currently, sensing devices are not readily available to this population due to cost and information barriers. Our sensing device has the potential to identify individuals at risk for cognitive decline by assessing their level of physical function by tracking their in-home activities and mobility behaviors, at a low cost. DERR1-10.2196/53447.

Machine-learning-based prediction of cardiovascular events for hyperlipidemia population with lipid variability and remnant cholesterol as biomarkers.

Dyslipidemia poses a significant risk for the progression to cardiovascular diseases. Despite the identification of numerous risk factors and the proposal of various risk scales, there is still an urgent need for effective predictive models for the onset of cardiovascular diseases in the hyperlipidemic population, which are essential for the prevention of CVD. We carried out a retrospective cohort study with 23,548 hyperlipidemia patients in Shenzhen Health Information Big Data Platform, including 11,723 CVD onset cases in a 3-year follow-up. The population was randomly divided into 70% as an independent training dataset and remaining 30% as test set. Four distinct machine-learning algorithms were implemented on the training dataset with the aim of developing highly accurate predictive models, and their performance was subsequently benchmarked against conventional risk assessment scales. An ablation study was also carried out to analyze the impact of individual risk factors to model performance. The non-linear algorithm, LightGBM, excelled in forecasting the incidence of cardiovascular disease within 3years, achieving an area under the 'receiver operating characteristic curve' (AUROC) of 0.883. This performance surpassed that of the conventional logistic regression model, which had an AUROC of 0.725, on identical datasets. Concurrently, in direct comparative analyses, machine-learning approaches have notably outperformed the three traditional risk assessment methods within their respective applicable populations. These include the Framingham cardiovascular disease risk score, 2019 ESC/EAS guidelines for the management of dyslipidemia and the 2016 Chinese recommendations for the management of dyslipidemia in adults. Further analysis of risk factors showed that the variability of blood lipid levels and remnant cholesterol played an important role in indicating an increased risk of CVD. We have shown that the application of machine-learning techniques significantly enhances the precision of cardiovascular risk forecasting among hyperlipidemic patients, addressing the critical issue of disease prediction's heterogeneity and non-linearity. Furthermore, some recently-suggested biomarkers, including blood lipid variability and remnant cholesterol are also important predictors of cardiovascular events, suggesting the importance of continuous lipid monitoring and healthcare profiling through big data platforms.

Designing a machine learning-based lending model to enhance access to capital for small and medium enterprises

This paper presents the design of a machine learning-based lending model aimed at enhancing access to capital for Small and Medium Enterprises (SMEs). SMEs play a crucial role in driving economic growth, yet they often face significant barriers in securing funding due to traditional credit assessment methods that rely heavily on financial history and collateral. By leveraging machine learning (ML) algorithms, this proposed model incorporates diverse data sources, including financial statements, market trends, customer behavior, and non-traditional data such as social media activity and payment histories, to better assess creditworthiness. The model utilizes supervised learning techniques, such as decision trees, random forests, and neural networks, to analyze this diverse data and identify patterns that traditional models may overlook. Additionally, it integrates real-time data processing to continuously update credit profiles, allowing for more dynamic and responsive lending decisions. The primary aim is to improve the accuracy of risk assessment, reduce default rates, and ultimately facilitate more inclusive lending practices for SMEs. One of the core advantages of the ML-based model is its ability to offer personalized lending terms and products by identifying the unique characteristics and risk factors of each SME. This approach not only improves access to capital for underbanked businesses but also ensures that lenders can manage risk more effectively. The paper also discusses the potential ethical considerations, such as ensuring data privacy and avoiding biases in algorithmic decision-making, which are critical for the responsible implementation of such a system. In conclusion, this machine learning-based lending model presents an innovative solution to the long-standing challenges SMEs face in accessing capital. By harnessing the power of data analytics and advanced algorithms, it paves the way for more equitable and efficient lending processes, supporting the growth and sustainability of SMEs. Keywords: Machine Learning, Lending Model, Access To Capital, Small And Medium Enterprises, Risk Assessment, Creditworthiness, Financial Inclusion, Data Privacy, Algorithmic Decision-Making, Supervised Learning.

An IoT-Based Framework for Automated Assessing and Reporting of Light Sensitivities in Children with Autism Spectrum Disorder.

Identification of light sensitivities, manifesting either as hyper-sensitive (over-stimulating) or hypo-sensitive (under-stimulating) in children with autism spectrum disorder (ASD), is crucial for the development of personalized sensory environments and therapeutic strategies. Traditional methods for identifying light sensitivities often depend on subjective assessments and manual video coding methods, which are time-consuming, and very keen observations are required to capture the diverse sensory responses of children with ASD. This can lead to challenges for clinical practitioners in addressing individual sensory needs effectively. The primary objective of this work is to develop an automated system using Internet of Things (IoT), computer vision, and data mining techniques for assessing visual sensitivities specifically associated with light (color and illumination). For this purpose, an Internet of Things (IoT)-based light sensitivities assessing system (IoT-LSAS) was designed and developed using a visual stimulating device, a bubble tube (BT). The IoT-LSAS integrates various electronic modules for (i) generating colored visual stimuli with different illumination levels and (ii) capturing images to identify children's emotional responses during sensory stimulation sessions. The system is designed to operate in two different modes: a child control mode (CCM) and a system control mode (SCM). Each mode uses a distinct approach for assessing light sensitivities, where CCM uses a preference-based approach, and SCM uses an emotional response tracking approach. The system was tested on a sample of 20 children with ASD, and the results showed that the IoT-LSAS effectively identified light sensitivities, with a 95% agreement rate in the CCM and a 90% agreement rate in the SCM when compared to the practitioner's assessment report. These findings suggest that the IoT-LSAS can be used as an alternative to traditional assessment methods for diagnosing light sensitivities in children with ASD, significantly reducing the practitioner's time required for diagnosis.

Assessment of groundwater quality for agricultural purposes in Qazvin Province, northwestern Iran: A fuzzy inference and indicator Kriging approach

This study addresses the challenge of assessing groundwater quality for agriculture in Qazvin Province, northwestern Iran. In this region, over-extraction has led to significant degradation of groundwater resources. Traditional assessment methods often overlook uncertainties and spatial variability in groundwater quality. To address this, our study aimed to integrate fuzzy inference and geostatistical methods to assess groundwater quality under uncertain conditions. The research was conducted in two stages. First, a fuzzy inference system classified six key water quality parameters: Electrical Conductivity (EC), Sodium Adsorption Ratio (SAR), Residual Sodium Carbonate (RSC), Total Hardness (TH), sodium ion concentration (Na⁺), and chloride concentration (Cl⁻), into three categories: “desirable,” “acceptable,” and “unacceptable,” using 54 fuzzy rules. In the second stage, we applied ordinary Kriging and indicator Kriging to spatially interpolate these classifications and produce probabilistic maps of groundwater quality risk across the study area. In ordinary Kriging, the average Root Mean Square Error (RMSE) values for EC, SAR, RSC, TH, Na⁺, and Cl⁻ were 0.94 dS/m, 1.54, 1.42 meq/L, 3.13 mg/L, 3.03 mg/L, and 2.62 mg/L, respectively, indicating reliable assessments of groundwater quality parameters. Results also suggest that by 2023, areas classified as “unacceptable” increased by 142.0% since 2009, with an additional 25.2% of the region facing a 40–80% probability of further degradation. These findings highlight important trends in groundwater quality, assisting local authorities in prioritizing areas for preventive interventions. This supports sustainable agricultural practices and aligns with the United Nations Sustainable Development Goal 6 for water resource management.