Fun-TSG: Function-Driven Multivariate Time Series Generator with Anomaly Labeling
The Fun-TSG dataset is designed to provide a more realistic and challenging environment for evaluating anomaly detection methods. The dataset includes fine-grained anomaly annotations, allowing for a more detailed analysis of these methods. The generator is function-driven, meaning it can produce time series data that mimics real-world scenarios. This is particularly useful for evaluating the performance of anomaly detection algorithms in various contexts.
The Fun-TSG dataset is expected to be a valuable resource for researchers and developers working on anomaly detection and time series analysis. It can help improve the evaluation of existing methods and pave the way for the development of new, more effective anomaly detection techniques. The dataset is available for download on the arXiv repository.
Key Takeaways
- → Fun-TSG is a function-driven multivariate time series generator with variable-level anomaly labeling
- → The dataset includes fine-grained anomaly annotations for more detailed analysis
- → The generator produces time series data that mimics real-world scenarios
Original Sources
Tags
More in Models & Research
Researchers Introduce Artifact-based Agent Framework for Reproducible Medical Image Processing
Researchers have developed an artifact-based agent framework for adaptive and reproducible medical image processing.
Anthropic Says Stronger AI Models Cut Better Deals, Losers Unaware
Anthropic conducted an experiment with 69 AI agents trading on behalf of employees, finding that stronger models secured better deals, with weaker models' users unaware of the difference.
AI-Based Automated Course of Action Generation System for Military Operations
Researchers have developed an AI-based system for generating automated courses of action for military operations.