severity-prediction

Deep Learning Models for the Early Detection of Parkinson’s Disease using the motor-based symptoms.

Code of our paper "Method-Level Bug Severity Prediction using Source Code Metrics and LLMs" which is accepted to ISSRE 2023.

This is a traffic severity prediction model built using XGBoost, deployed on flask.

A django web app that predicts the disease and severity based on the symptoms collected from user

🛡️ CyberPulse – AI-Powered Vulnerability Management System A full-stack platform for automated vulnerability assessment and remediation. CyberPulse processes OpenVAS XML reports, integrates real-time threat intelligence (NVD, Vulners, Shodan), and uses AI models to recommend fixes, predict severity, and visualize risks through dashboard

Predicts network intrusion severity using the CICIDS2017 dataset. Utilizes deep learning to classify PCAP-extracted features into risk-based severity tiers rather than standard binary detection.

Automatic road accident detection, severity estimation, V2X emergency broadcast simulation, and accident-prone zone identification with KDD Algorithm

Automates insurance claim modeling in Kedro: data processing, sampling, feature engineering, feature selection, GLM/LightGBM tuning, recalibration, and validation. Configurable via YAML. Supports generating, scheduling, and tracking hundreds of experiments. Outputs: metrics and charts. Uses Kedro, MLflow, Python.

Multimodal bug report severity prediction using fine-tuned Qwen2.5-VL-7B — image-only triage significantly outperforms text-only (McNemar p<0.01)

An advanced deep learning framework designed for accurate multi-class lung disease diagnosis and severity assessment using Chest X-ray (CXR) images.