The main contributions of this work are summarized as
follows:
1) We create a kind of framework that combines three
things: EfficientNetB1, ResNet50 and MobileNetV2.
This combination helps the framework to work when
it comes to classifying diseases in rice leaves that look
very similar.
2) We try out six pre-trained networks. VGG19, ResNet50,
DenseNet121, MobileNetV2, EfficientNetB0 and EfficientNetB1. To see which one works best. We keep
everything the same like how we prepare the data and
how we train the networks.
3) We also test the trained models using pictures of rice
leaves that were taken in the field. These pictures were
taken in light with different backgrounds and, with
different cameras. This helps us see how well the models
can work in life when the conditions are not perfect.
4) To make the models more understandable we use something called Grad-CAM visualization. This helps us see
which parts of the leaf the model is looking at when it
makes a prediction.

Dental caries is a widespread oral disease whose
early detection remains difficult because conventional visual
assessment is subjective, time-consuming, and prone to examiner variability. This study proposes an automated detection
framework that combines deep residual feature extraction with
bidirectional multi-scale feature aggregation to improve localization of small and low-contrast carious lesions in intraoral
photographs. Transfer learning, image normalization, and geometric and photometric augmentation are employed to enhance
robustness. The framework is evaluated on the publicly available
Annotated Intraoral Image Dataset for Dental Caries Detection
and compared with several alternative backbone architectures.
Experimental results show a precision of 0.8173, recall of 0.7601,
F1-score of 0.7877, mAP@0.5 of 0.7998, and mAP@0.5:0.95
of 0.6361. Image-level evaluation further yields a sensitivity
of 0.8894, specificity of 0.9502, and accuracy of 0.9283. These
findings demonstrate effective lesion localization and clinically
relevant screening performance while providing a reproducible
benchmark for future research on reliable computer-aided dental
caries detection.

This paper proposes CIDR, a three-stage framework integrating entropy-based drift detection, influence-guided targeted unlearning, and conformal recalibration to restore model reliability under distribution shift. CIDR restores coverage to 0.903 ± 0.034 against a target of 0.90 with no statistically significant accuracy degradation, outperforms full retraining in accuracy (0.770 vs. 0.669) and efficiency (30% smaller prediction sets, 1/10 the cost), and provides a practical solution for maintaining trustworthy AI under drift.

Software testing remains one of the most labor-intensive stages of the software development lifecycle, and conventional automation frameworks rely on brittle, manually written scripts that require constant upkeep as applications evolve. The recent emergence of large language models (LLMs) capable of understanding natural-language requirements and producing syntactically correct code has opened a new path toward intelligent test automation. This paper synthesizes current research and proposes a layered architecture, referred to as the LLM-Driven Test Automation Framework (LTAF), that integrates retrieval-augmented context ingestion, LLM-based test-case generation, automated script synthesis for common automation stacks, a self-healing locator component, and a closed feedback loop between test execution and the generative model. We describe the architecture and design rationale of each component, discuss how the framework could be evaluated against established baselines such as search-based test generation, and summarize the reported strengths and limitations of LLM-based testing approaches drawn from the current body of work. We further identify open challenges, including the test-oracle problem, hallucinated assertions, flaky-test diagnosis, and data-privacy concerns when proprietary code is shared with external model providers, and we outline directions for future research toward reliable, self-repairing test automation pipelines.

Cardiac arrhythmia is a major cause of cardiovascular mortality, therefore accurate and timely analysis of ECG is essential for early diagnosis. In this study, a lightweight One-dimensional Convolutional Neural Network (1D CNN) with Convolutional Block Attention Module (CBAM) is proposed for explainable ECG classification according to the AAMI standard. The CBAM-ECGnet model performs convolutional feature extraction with channel and spatial attention with only 4,088 total parameters (≈16 KB). The proposed model is evaluated on the MIT-BIH Arrhythmia Database and achieves an overall accuracy of 98.53%, and a ROC-AUC of 99% . In this study we use Grad-CAM to visualize the regions of the ECG that contribute to each prediction, improving the explainability of the model. This model achieves high accuracy classification with low computational complexity and thus is suitable for real-time and low-resource ECG monitoring application.

This paper introduces CalForget, a four-stage pipeline that detects conformal prediction calibration drift under distribution shift, attributes miscalibration to specific training points using influence functions, selectively removes their influence via a soft-miscoverage objective, and restores finite-sample coverage guarantees through reconformalization. Unlike full retraining, CalForget recovers most of the calibration benefit while modifying only a small fraction (≈2.5%) of the training data, demonstrated across four UCI regression benchmarks and three shift severities.

Glaucoma is a major cause of irreversible blindness,
and early screening from fundus photographs is essential because
structural damage may progress before noticeable visual symp-
toms occur. This paper proposes HMSGA-Net, a Hybrid Multi-
Scale Gated Attention Network for automated glaucoma classi-
fication. The framework combines a ConvNeXt-Small primary
branch and a ConvNeXt-Tiny auxiliary branch, each equipped
with an HMSGA module comprising parallel 1 × 1, 3 × 3, and
5 × 5 depth-wise convolutions, Efficient Channel Attention, dual
sigmoid gating, and residual feature refinement. The two branch
probabilities are fused using a validation-selected ensemble
weight and decision threshold. Integrated Gradients and Occlu-
sion Sensitivity are employed to assess whether predictions focus
on clinically relevant optic-disc and neuroretinal-rim regions. On
the ACRIMA dataset, the best seed-42 configuration achieved
98.84% accuracy, 98.97% F1-score, 99.72% AUC-ROC, and
100% glaucoma recall. Across three independent splits, HMSGA-
Net obtained mean accuracy and AUC-ROC values of 94.14%
and 97.28%, respectively, demonstrating strong discrimination
while also revealing sensitivity to data partitioning.

Accurate brain tumor identification from magnetic
resonance imaging (MRI) is essential for early clinical decision
support, yet reliable multi-class classification remains challenging
because tumor appearance varies across shape, texture, and
intensity patterns. This study proposes an explainable deep
ensemble framework for four-class brain tumor MRI classification, covering glioma, meningioma, pituitary tumor, and
no-tumor cases. The pipeline applies image preprocessing and
augmentation, evaluates multiple pretrained convolutional base-
lines, and combines complementary transfer-learning models
through weighted decision fusion to improve generalization.
Model performance is assessed using accuracy, precision, recall,
F1-score, bootstrap confidence estimation, and train-validation
stability analysis. Experimental results on the Kaggle brain tumor
MRI dataset show that the proposed framework achieves a
verified accuracy of 99.44%, with precision, recall, and F1-score
above 0.994. Explainability analysis further supports the clinical
relevance of the learned decision regions. The results indicate
that ensemble-based transfer learning can provide robust and
interpretable MRI-based brain tumor screening support

Colorectal cancer remains one of the leading causes
of cancer-related mortality, making accurate polyp segmentation
important for early diagnosis and treatment. This study proposes
a PVT-v2-B2 + FPN framework for automatic colorectal polyp
segmentation. The model combines a hierarchical transformer
encoder with feature pyramid decoding to integrate global
context and multi-scale spatial features for accurate boundary
localization. Geometric and photometric augmentations were applied to improve robustness under diverse colonoscopy conditions.
Experiments were conducted on Kvasir-SEG using a 700/150/150
train-validation-test split with multi-seed and multi-resolution
evaluation. The selected proposed configuration achieved a test
Dice score of 91.05% and IoU of 83.71%, while the best
individual run reached 91.08% Dice. Compared with CNN-,
transformer-, and hybrid-based baselines, the proposed model
showed competitive segmentation performance with 29.8M parameters. These results indicate that hierarchical transformer
features with FPN-based fusion can provide an effective balance
between segmentation accuracy and computational practicality
for colonoscopy-assisted polyp analysis.