[ 04 ] · 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

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

Thesis that fuses a gradient-boosting classifier with a three-layer neural network by averaging their probability outputs. Trained on 2,237 survey responses from Bangladeshi university students, the ensemble beats every standalone model across all metrics and pinpoints the lifestyle factors that most strongly predict cognitive decline.

95.20%

accuracy

94.40%

precision

96.10%

recall

95.24%

0.982

ROC-AUC

2,237

survey responses

Natural Language ProcessingMachine Learning

Twitter Sentiment Analysis with TF-IDF and Multinomial Naïve Bayes

Natural Language Processing

Course research on the Sentiment140 corpus. 1.6M tweets are balanced down to 200k (100k positive + 100k negative), run through a deep preprocessing chain: lowercasing, URL/@/# removal, punctuation stripping, stopword removal, WordNet synonym substitution, Porter stemming, and lemmatization, then vectorized with TF-IDF and classified by Multinomial Naïve Bayes on a stratified 80/20 split.

Machine LearningPredictive AnalyticsBusiness Intelligence

Early Warning Model for High-Value Customer Drop-Off

Data Science · Customer Analytics

Course research in Data Science. Cleans 541,909 transactions into a 4,338-customer RFM matrix, segments customers with unsupervised clustering compared across three algorithms, then builds a supervised early-warning classifier on month-over-month RFM decay to flag high-value customers at risk of churn.

early-warning signals

0.788

ROC-AUC

Computer VisionDeep LearningTransfer Learning

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

Computer Vision & Pattern Recognition

Course paper that tackles image-based turbidity classification with a small custom dataset of 300+ photos taken on three different smartphones in natural, uncontrolled lighting. An ImageNet-pretrained EfficientNet-B0 with partial fine-tuning learns to separate Low / Medium / High turbidity, and the paper candidly reports the limits of doing so from photos alone.

Natural Language ProcessingBERTTransformersExplainable AI

Explainable Bangla Toxic Comment Detection using BanglaBERT with SHAP and LIME

Data Warehouse & Data Mining

Data-mining research (IEEE-format paper) that fine-tunes BanglaBERT on Bengali toxicity data using 5-fold stratified cross-validation and adds an explainability layer: SHAP and LIME reveal which words drove each toxic / non-toxic decision, tackling the black-box problem in low-resource Bangla NLP.