disaster-classification

Exploration of BERT-BiLSTM models with Layer Aggregation (attention-based and capsule-routing-based) and Hidden-State Aggregation (attention-based and capsule-routing-based).

We design a multi-task model for joint disaster classification and victim detection. We train the model using both the Centralized Learning (CL) and Federated Learning (FL) methods. We also tried Active Learning (AL) to see how it could help in reducing the labeling workload for disaster dataset. Lastly, we optimized the model using OpenVINO.

An image processing model to classify the type of disaster based on the image dataset.

Train a lightweight MobileNetV2 model for disaster classification using the Crisis Image Benchmark Datasets (CrisisIBD).

Presentation slides, materials, and certificate from 3MT Bangladesh 2025 — based on our published IEEE SPICSCON 2025 paper on multimodal disaster classification.

Deep learning-based disaster image classification using CNN and Inception ResNet V2.

Official repo for "BanglaMM-Disaster" (IEEE SPICSCON 2025). Multimodal deep learning framework fusing Transformers (mBERT, BanglaBERT, XLM-R) and CNNs (ResNet50) for 9-class disaster classification in Bangla social media. Achieves 83.76% accuracy (+16.91% over vision, +3.84% over text).