Bharathi Women's College

Well defined and transparent credit risk evaluation continues to be a fundamental issue in financial decision-making, particularly when dealing with intricate borrower profiles in the forms of organized tabular data. While traditional machine learning models often lack interpretability for predictive accuracy, recent deep learning approaches struggle to generalize across such data formats. We propose an innovative hybrid Tabular Deep Learning system that combines feature tokenizer transformer (FT-transformer) and TabNet architectures with an adaptive feature routing (AFR) method. The AFR module dynamically identifies significant aspects for each data instance, facilitating context-aware representation learning and enhancing generalization across other borrower groups. To guarantee explainability and compliance with regulations, our approach integrates a multimodal interpretability package that includes Shapley additive explanations (SHAP)-based attributions, attention mapping, and counterfactual reasoning for actionable what-if analysis. Comprehensive experiments on the benchmark dataset reveal the model's exceptional performance, attaining an AUC of 0.985, an F1-score of 0.972, and a premier ranking according to the Gini coefficient. Visual metrics of AUC vs. Gini coefficient, cost-benefit curves, and the counterfactual dashboards showcase the model's transparency and practical applicability. This study observes the application of explainable AI in credit risk modeling by successfully reconciling the balance between higher predictive accuracy and interpretability, hence facilitating explainable financial decision-making scenarios.

Abstract This study investigates workplace stress and emotional burnout among employees in the manufacturing sector in Chennai city. In the modern industrial environment, employees face high workloads, tight deadlines, repetitive tasks, and physical demands, which often lead to stress and burnout, negatively impacting health, job satisfaction, and productivity. A descriptive research design was adopted, and primary data was collected from 160 employees using a structured questionnaire. A proportionate random sampling technique ensured representation across age, gender, job roles, and work experience. Descriptive statistics, T-tests, ANOVA, and correlation analysis were employed to examine the relationships between demographics, stressors, burnout levels, coping strategies, and organizational interventions. The analysis revealed that key stressors include workload, time pressure, and physical demands, with production staff and mid-career employees being most affected. Stress and burnout were found to significantly impact physical and mental health, work performance, absenteeism, and job satisfaction. Coping strategies such as exercise, relaxation, and time management, along with organizational support, wellness programs, and flexible work policies, significantly reduce stress and improve employee well-being. The study concludes that combining individual coping mechanisms with organizational preventive measures is essential to reduce burnout and promote a healthy, motivated, and productive workforce. These findings provide actionable insights for HR managers and policymakers in the manufacturing sector to implement effective stress management programs. Keywords: Workplace Stress, Emotional Burnout, Manufacturing Sector, Employee Well-Being, Coping Strategies, Organizational Support, Chennai, Job Performance, Stress Management

Polyendocrine metabolic ovarian syndrome (PMOS) is a prevalent hormonal disorder that affects approximately one in eight women of reproductive age. In Indian systems of traditional medicine, kanyasara (solidified exudate of Aloe vera Burm.f.) has been used for treating PMOS. This study evaluated the anti-PMOS effect of kanyasara using a preclinical model. Kanyasara was standardised by quantifying the aloin content using HPLC. PMOS was established by feeding Sprague Dawley rats with a high fat diet for eight weeks and orally administering letrozole (1 mg/kg) for three weeks. Kanyasara (25 to 50 mg/kg) treatment was given consecutively for 28 days; metformin (120 mg/kg) was used as a positive control. Kanyasara used in this study contained 37.58% of aloin. Compared to the HFD-letrozole animals, kanyasara-treated animals (50 mg/kg) showed 54.94% reduction in blood glucose. The treatment significantly lowered total cholesterol (28.28%) and triglyceride (25.72%) levels at 50 mg/kg concentration. The treatment also lowered the levels of plasma FSH (50.06%) and LH (59.16%). Histological examination showed normal follicles, corpus luteum, and ovarian stroma by kanyasara treatment. This study supported the use of kanyasara for the treatment of PMOS; detailed investigations are needed to establish its efficacy and safety.

The increasing demand for sustainable food production has intensified the search for biodegradable and cost effective alternatives to conventional hydroponic growing substrates. The present study investigated the potential of Eichhornia crassipes (water hyacinth) biomass incorporated with carboxymethyl cellulose (CMC) as a biodegradable hydrogel substrate for the cultivation of Vigna radiata L. An aqueous extraction method was employed to recover polymer from E. crassipes, yielding approximately 10% polymer with a pH of 6.0. The extracted polymer was incorporated with CMC to develop an Eichhornia-CMC hydrogel, and its performance was compared with CMC hydrogel and conventional soil. Seed germination, seedling vigour, shoot and root growth, leaf development, chlorophyll content, water retention, biochemical composition, mineral accumulation, and endogenous auxin content were evaluated. The Eichhornia-CMC hydrogel promoted rapid seed germination and superior seedling development, with a Seed Vigour Index of 382 compared with 287 and 370 in CMC hydrogel and soil, respectively.

Introduction: Tropical dry forest ecotones rely on soil fungal communities for nutrient cycling and ecosystem stability. The Sathyamangalam Tiger Reserve (STR) in Tamil Nadu, India, acts as a crucial biogeographical bridge between the Eastern and Western Ghats. This study evaluated structural and functional shifts in soil mycobiomes exposed to physical human encroachment within this protected ecotone. Materials and methods: Environmental DNA (eDNA) metabarcoding of the fungal internal transcribed spacer (ITS) region was performed using Illumina NextSeq 550 sequencing. Two composite soil libraries ( n = 1 per zone, each pooled from nine sub-cores) were analyzed from the Hasanur division: a conserved forest zone (CFZ) and an anthropogenically impacted zone (AIZ). QIIME 2 and DADA2 processed sequences against the UNITE database, with functional roles inferred via FUNGuild. Results: High-throughput processing generated 149,703 high-quality reads, resolving into 247 species-level amplicon sequence variants (ASVs). Observed species richness dropped sharply in the AIZ (60 species, 55 families) compared to the CFZ (223 species, 116 families). While Ascomycota and Basidiomycota dominated both regimes (>79% relative sequence abundance), lower-abundance phyla showed marked compositional shifts. The AIZ exhibited increased relative sequence representation of Mortierellales and arbuscular mycorrhizal fungi (Glomerales), alongside reduced Chytridiomycota (4.13% in the CFZ compared to 0.28% in the AIZ). Functional profiling indicated decreased relative sequence abundance of specialized lignicolous saprotrophs ( Ganoderma eickeri , Polyporus sp.) and microclimate-associated yeasts ( Hannaella sp., Vishniacozyma sp.) in the AIZ. Additionally, 18 species-level candidate taxa unlisted in regional checklists were detected, providing targets for future multi-locus validation. Conclusions: Soil fungal communities exhibited marked structural and compositional differences between management regimes, with the impacted perimeter displaying a restricted species pool dominated by generalist and ruderal lineages compared to the intact forest core. These descriptive snapshots highlight the importance of conserving undisturbed dry forest tracts to maintain specialized soil fungal diversity across tropical ecotones.