YUV RAJ PANT

Mr. YUV RAJ PANT

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2025 in Algorithms
Verified
Journal Article
Open access
PDF file
YPYUV RAJ PANT
YUV RAJ PANT
LLLarry Leigh
Larry Leigh
JRJuliana Maria Fajardo Rueda
Juliana Maria Fajardo Rueda
Efficient clustering of high-spatial-dimensional satellite image datasets remains a critical challenge, particularly due to the computational demands of spectral distance calculations, random centroid initialization, and sensitivity to outliers in conventional K-Means algorithms. This study presents a comprehensive comparative analysis of eight parallelized variants of the K-Means algorithm, designed to enhance clustering efficiency and reduce computational burden for large-scale satellite image analysis. The proposed parallelized implementations incorporate optimized centroid initialization for better starting point selection using a dynamic K-Means sharp method to detect the outlier to improve cluster robustness, and a Nearest-Neighbor Iteration Calculation Reduction method to minimize redundant computations. These enhancements were applied to a test set of 114 global land cover data cubes, each comprising high-dimensional satellite images of size 3712 × 3712 × 16 and executed on multi-core CPU architecture to leverage extensive parallel processing capabilities. Performance was evaluated across three criteria: convergence speed (iterations), computational efficiency (execution time), and clustering accuracy (RMSE). The Parallelized Enhanced K-Means (PEKM) method achieved the fastest convergence at 234 iterations and the lowest execution time of 4230 h, while maintaining consistent RMSE values (0.0136) across all algorithm variants. These results demonstrate that targeted algorithmic optimizations, combined with effective parallelization strategies, can improve the practicality of K-Means clustering for high-dimensional-satellites image analysis. This work underscores the potential of improving K-Means clustering frameworks beyond hardware acceleration alone, offering scalable solutions good for large-scale unsupervised image classification tasks.

12 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
YPYUV RAJ PANT
YUV RAJ PANT
LLLarry Leigh
Larry Leigh
JRJuliana Maria Fajardo Rueda
Juliana Maria Fajardo Rueda
Efficient clustering of high-dimensional satellite image datasets remains a critical challenge, particularly due to the computational demands of spectral distance calculations, random centroid initialization, and sensitivity to outliers in conventional K-Means algorithms. This study presents a comprehensive comparative analysis of eight parallelized variants of the K-Means algorithm, designed to enhance clustering efficiency and reduce computational burden for large-scale satellite image analysis. The proposed parallelized implementations incorporate optimized centroid initialization for better starting point selection using a dynamic K-Means sharp method to detect the outlier to improve cluster robustness, and a Nearest-Neighbor Iteration Calculation Reduction method to minimize redundant computations. These enhancements were applied to a test set of 114 global land cover data cubes, each comprising high-dimensional satellite images of size 3712*3712*16, and executed on multi-core CPU architecture to leverage extensive parallel processing capabilities. Performance was evaluated across three criteria: convergence speed (iterations), computational efficiency (execution time), and clustering accuracy (RMSE). The Parallelized Enhanced K-Means (PEKM) method achieved the fastest convergence at 234 iterations and the lowest execution time of 4230 hours, while maintaining consistent RMSE values (0.0136) across all algorithm variants. These results demonstrate that targeted algorithmic optimizations, combined with effective parallelization strategies, can improve the practicality of K-Means clustering for high dimensional satellites image analysis. This work underscores the potential of improving K-Means clustering frameworks beyond hardware acceleration alone, offering scalable solutions good for large-scale unsupervised image classification tasks.

24 July 2026 in AI
Verified
Journal Article
Open access
PDF file
YPYUV RAJ PANT
YUV RAJ PANT
HAHaitham Y. Adarbah
Haitham Y. Adarbah
ANAfzel Noore
Afzel Noore
DCDunren Che
Dunren Che
AAAden Ahmed
Aden Ahmed
RARobert Ayala
Robert Ayala
Large Language Models (LLMs) show promise for supporting formative assessment by generating feedback on students’ written mathematical reasoning. However, practical use in educational settings remains constrained by the need to manually curate representative few-shot exemplars for prompt construction. This study examines whether unsupervised semantic clustering can automate few-shot exemplar selection for LLM-generated formative feedback in middle-school mathematics. As a controlled methodological feasibility study, we generated and refined 100 exam-realistic constructed responses for a Grade 7 inequality task aligned with middle-school mathematics standards. Student responses were embedded using Sentence-BERT, projected into a lower-dimensional space using Uniform Manifold Approximation and Projection (UMAP), and clustered with Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to identify dominant reasoning patterns and ambiguous responses. Representative centroid and boundary exemplars from the resulting clusters were then used to construct few-shot prompts for the Llama 3.3 70B model, which generated feedback for the remaining 93 responses. Six independent mathematics instructors evaluated the AI-generated feedback using a structured 0–5 usability rubric. Across all instructor evaluations, 538 of the 558 instructor ratings (96.42%) were 3–5, representing feedback ranging from fair, requiring moderate edits, to excellent, ready to send. More specifically, 482 of the 558 instructor ratings (86.38%) were scores of 4–5, indicating feedback requiring no edits or only minor revisions. The remaining 20 ratings (3.58%) were scores of 0–2, while 13 unique feedback messages received at least one low rating. Across all instructor evaluations, 20 of 558 ratings (3.58%) were assigned scores of 0–2, while 13 unique feedback messages received at least one low rating. Qualitative analysis of low-scoring cases revealed recurring failure modes, including hallucinated completeness in concise solutions, failed arithmetic verification, and false logic flagging for atypical reasoning patterns. These findings suggest that clustering-based exemplar selection may reduce manual prompt-engineering effort while supporting usable LLM-generated formative feedback in a controlled mathematics setting. However, the present study does not compare clustering against alternative exemplar-selection strategies, and therefore conclusions should be interpreted as evidence of feasibility rather than comparative superiority.