Disaster Rescue AI: Advanced AI for Finding Alive People in Disasters and Alert System

Simple item page
dc.contributor.advisorDr. Sifat Momen
dc.contributor.authorMd. Adham Wahid
dc.contributor.authorFatema Afsan Ema
dc.contributor.authorIstiak Ahasan
dc.contributor.id2111177042
dc.contributor.id2022281642
dc.contributor.id2012082642
dc.coverage.departmentElectrical and Computer Engineering
dc.date.accessioned2026-08-19
dc.date.accessioned2026-08-19T10:00:52Z
dc.date.available2026-08-19T10:00:52Z
dc.date.issued2025-04-30
dc.description.abstractA developmental illness that may manifest in early childhood is Attention Deficit Hyperactivity Disorder (ADHD). It may lead to poor self-esteem and social function in children if it’s not considered at an early age. Early detection and diagnosis of ADHD results in early interventions that improve social development, academic performance, and treatment outcomes among children. This is the first integrated framework that not only predicts ADHD in early childhood using Machine learning and Natural language processing techniques but also offers a Dialogflow-based therapeutic chatbot as a primary intervention an approach not addressed in existing literature. A total of fourteen Machine Learning and five BERT-based transformer algorithms with optimized hyperparameters have been applied to classify ADHD-positive and ADHD-free children identifying the key factors. The Stacking ensemble model came out with the best-performing metrics with 94.27% accuracy, 87.00% precision, 82.07% recall and 84.30% f1 score, and AUC of 0.97 that achieves state-of-the-art performance on CAHMI survey and dataset. While DistilBERT outshined among other BERT-based transformer models with 93.45% accuracy, 19.25s runtime, and AUC of 0.968 highlighting the natural language processing. LIME and SHAP have added enhanced transparency and dynamic decision-making interpretability. Unlike prior studies that focus solely on prediction, our model emphasizes both early diagnosis and immediate therapeutic support, bridging a critical gap between detection and intervention. Moreover, domain experts raw feedback and generalization through unseen datasetscontribute significantly to the novelty and practical relevance of the proposed system. This study presents a comprehensive statistical analysis through a well-structured machine learning and transformer pipeline, incorporating detailed visualizations alongside textual explanations.
dc.description.degreeUndergraduate
dc.identifier.cd600000706
dc.identifier.urihttps://repository.northsouth.edu/handle/123456789/1736
dc.language.isoen_US
dc.publisherNorth South University
dc.rights@ NSU Library
dc.titleDisaster Rescue AI: Advanced AI for Finding Alive People in Disasters and Alert System
dc.typeProject
oaire.citation.endPage74
oaire.citation.startPage1
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
600000706 - abstract.pdf
Size:
135.85 KB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
600000706.pdf
Size:
1.79 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Theses - Undergraduate