stream-learning

CapyMOA does efficient machine learning for data streams in Python. CapyMOA is a toolbox of methods and evaluators for: classification, regression, clustering, anomaly detection, semi-supervised learning, online continual learning, and drift detection for data streams.

Data stream mining extracts information from large quantities of data flowing fast and continuously (data streams). They are usually affected by changes in the data distribution, giving rise to a phenomenon referred to as concept drift. Thus, learning models must detect and adapt to such changes, so as to exhibit a good predictive performance af…

'Asips' is a Research conducted for automating the pulsar star candidate selection process. This is the API of Asips which can be used by anyone. This implementation uses the HTRU2 dataset.

ActiSiamese (Neurocomputing 2022)

🚀 GPU-accelerated prototype learning framework. Condenses infinite data streams into differentiable topological grids, reducing metric inference complexity from O(N×D) to strictly O(K×D) .

SiameseDuo++ (Neurcomputing 2025)

Augmented Queues (IEEE SSCI 2022)

Detection and classification of anomalous events in oil extraction. Incremental learning methods applied to the Petrobras 3W dataset.

Client-server backend for real-time Activity of Daily Living (ADL) classification. Handles window ingestion, prediction, label requests, and incremental model updates.

Complete system for the classification of Activities of Daily Living (ADL) by collecting inertial data from smartphones and evaluating supervised models (RF, SVM) under a Stream Learning approach, including online architecture for real-time classification.

Reference implementation for AdaptiveStreamFL: Bayesian-enhanced multi-scale federated learning for dynamic data streams.