OASW-Concept-Drift-Detection-and-Adaptation and MSANA-Online-Data-Stream-Analytics-And-Concept-Drift-Adaptation
These are ecosystem siblings—both are reference implementations of online learning frameworks from the same research lab (Western-OC2-Lab) that address concept drift in data streams, with OASW focusing on lightweight IoT scenarios while MSANA extends the approach to multi-stage network analytics.
About OASW-Concept-Drift-Detection-and-Adaptation
Western-OC2-Lab/OASW-Concept-Drift-Detection-and-Adaptation
An online learning method used to address concept drift and model drift. Code for the paper entitled "A Lightweight Concept Drift Detection and Adaptation Framework for IoT Data Streams" published in IEEE Internet of Things Magazine.
This project helps operations engineers and security analysts maintain accurate anomaly detection in IoT systems. It takes in live streams of IoT sensor data, such as network traffic, and automatically adjusts its predictive models. The output is a continuously updated anomaly detection system that remains effective even as data patterns change over time.
About MSANA-Online-Data-Stream-Analytics-And-Concept-Drift-Adaptation
Western-OC2-Lab/MSANA-Online-Data-Stream-Analytics-And-Concept-Drift-Adaptation
Data stream analytics: Implement online learning methods to address concept drift and model drift in dynamic data streams. Code for the paper entitled "A Multi-Stage Automated Online Network Data Stream Analytics Framework for IIoT Systems" published in IEEE Transactions on Industrial Informatics.
This project helps operations engineers and IT security professionals automatically analyze real-time network traffic and IoT device data. It takes continuous streams of sensor data or network logs as input and outputs optimized insights to detect anomalies or predict events, even when the data patterns change over time. This is for professionals managing Industrial Internet of Things (IIoT) systems or network security.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work