LLM-powered security log analyzer: detect threats & anomalies with zero regex — just declare a Pydantic schema. Real-time Telegram alerts, SIEM-ready with Elasticsearch/Kibana. Supports OpenAI, Ollama, vLLM.

Official development code of the Automatic Scoring of Atopic Dermatitis (ASCORAD) by Legit.Health 🩺🤖

LogAnalysisTool: provide a new approach for pattern attack search and for calculation of severity of logins in Linux's Wtmp, Btmp and Secure log. Searched patterns: Brute Force, Password Spraying. Also check of IPWhois and Reputation. Plus utility functions.

This project uses the National Transportation Safety Board's aircraft incident dataset to identify factors that contribute to small airplane accidents, identify hotspots where accidents occur and calculate an accident severity index rating for each U.S. airport. The findings are displayed in an interactive shiny web application.

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

Paez, A., Hassan, H., Ferguson, M., Razavi, S. (2020) A systematic assessment of the use of opponent variables, data subsetting and hierarchical specification in two-party crash severity analysis, Accident Analysis and Prevention, 144:105666

Group 2 - Final Project for the UTK Machine Learning Course (COSC-522)

SegAgent-AI: A Dockerized AI Platform for Industrial Defect Segmentation, Severity Analysis, and Cloud Deployment

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

Machine learning project done during Monsoon Semester 2023 in IIITD.

Intelligent Weakness Reasoning Model — Multi-Signal Bayesian Engine + Interactive Next.js Dashboard with D3 Knowledge Graph, Severity Matrix, and Study Simulator

This analysis examines the Claim Settlement Ratio from two distinct perspectives that are seldom analyzed together: settlement performance by claim count and by claim amount.

A Flask web app that transcribes speech from audio/video using Whisper, detects emotions and stammering severity, and converts stammered speech into fluent speech using Text-to-Speech technology.

This actuarial project models accident severity using Maximum Likelihood Estimation with Gamma and Burr distributions on truncated claims data. It also performs solvency analysis via ruin theory, determining the adjustment coefficient in the Cramér-Lundberg model.