A list of awesome research on log analysis, anomaly detection, fault localization, and AIOps

A research project of anomaly detection on dataset IoT-23

The official implementation for ICLR23 paper "GNNSafe: Energy-based Out-of-Distribution Detection for Graph Neural Networks"

Detecting Frauds in Online Transactions using Anamoly Detection Techniques Such as Over Sampling and Under-Sampling as the ratio of Frauds is less than 0.00005 thus, simply applying Classification Algorithm may result in Overfitting

CICIDS2017 dataset

Anamoly Detection for Detecting Defected Manufactured Semi-Conductors, as in this case of Classification, the Defected Chips would be very less in comparison to perfect Chips so we have apply either Over-Sampling or Under-Sampling.

It is Based on Anamoly Detection and by Using Deep Learning Model SOM which is an Unsupervised Learning Method to find patterns followed by the fraudsters.

The official repository of TeamGabru.

This Project is detect outliers in sensor networks. We are using ISSNIP Single hop dataset for this.

Multimodal Subspace Support Vector Data Description

Subspace Support Vector Data Description

Knowledge base of python projects, modules, AI concepts and more

Media streaming for live and video-on-demand playback requires near real-time identification of and response to application problems. This architecture provides real-time monitoring and observability of systems of end-user device telemetry data with anomaly detection.

The objective of the project is to detect anomalies in credit card transactions. More precisely, given the data on time, amount and 28 transformed features, our goal is to fit a probability distribution based on authentic transactions, and then use it to correctly identify a new transaction as authentic or fraudulent.

This project focuses on the detection of credit card fraud using various data science and machine learning techniques. The dataset includes a record of credit card transactions over a specific period, with the goal of accurately identifying fraudulent activities. 🚀✨

A Python Module for Outliers Detection, Visualization and Treatment in Oil Well Datasets

Application to recover a realtime AWS Dynamodb table data without losing newly added data to resolve damages from spam attacks and accidental data deletions

Use z-score analysis to find out anomalous behavior in the room by analyzing the condition of the light in your room.

Machine Learning from Stanford University (Andrew Ng) - Assignments and Lectures