SSajidur Rahman Sajid

[ 02 ] — Research

Work that pushes a claim until it holds.

Every study uses a real dataset, a rigorous method, and honest numbers. The flagship is the thesis below.

Featured thesis

Read it

Neuro-Screen: A Hybrid ML and DL Ensemble Framework for Detection of Cognitive Impairment in Insomniac University Students

CatBoost + ANN ensemble blending on a 2,237-student survey dataset. 95.20% accuracy, 0.982 ROC-AUC.

95.20%
accuracy
0.982
ROC-AUC
Computer VisionTransfer Learning

Improving Generalization of Image-Based Water Turbidity Classification Using Fine-Tuning with Small Real-World Datasets

Computer Vision & Pattern Recognition · 2025

EfficientNet-B0 + transfer learning on ~300 self-collected phone photos, with auxiliary cat/dog/panda data to fight overfitting.

NLPExplainable AI

Explainable Bangla Toxic Comment Detection using BanglaBERT with SHAP and LIME

Data Mining (IEEE format) · 2025

BanglaBERT with SHAP + LIME explanations, k-fold (5) and 70/15/15 splits across multiple Bangla toxicity datasets.

NLPTransformers

Financial Sentiment Analysis with Fine-Tuned Transformers

NLP course research · 2025

Fine-tuned FinBERT vs vanilla BERT on financial text — why domain-specific transformers win on jargon-heavy corpora.

HCI

Adaptive InteractOut: A Context-Aware, Personalized Intervention for Smartphone Overuse

Human–Computer Interaction · 2025

Context-aware intervention design for smartphone overuse — group paper and poster.

RM

Entrepreneurship Over Employment: Guiding Bangladeshi Youth Towards Innovation and Self-Reliance

Research Methodology · 2025

A study on the drivers of entrepreneurship among Bangladeshi youth.