Summary of Exploring Hierarchical Classification Performance For Time Series Data: Dissimilarity Measures and Classifier Comparisons, by Celal Alagoz
Exploring Hierarchical Classification Performance for Time Series Data: Dissimilarity Measures and Classifier Comparisons
by Celal Alagoz
First submitted to arxiv on: 7 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Hierarchical classification (HC) and flat classification (FC) methodologies are compared in the context of time series data analysis. Various classifiers like MINIROCKET, STSF, and SVM are paired with dissimilarity measures such as Jensen-Shannon Distance (JSD), Task Similarity Distance (TSD), and Classifier Based Distance (CBD). A subset of multi-class datasets from the UCR archive is used for analysis. The study finds that HC performs better than FC when combined with MINIROCKET and TSD, but FC dominates in other configurations. TSD consistently outperforms CBD and JSD, except for instances involving STSF where CBD performs better. These findings highlight the importance of selecting suitable dissimilarity measures based on the dataset and classifier. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper compares two ways to classify time series data: hierarchical classification (HC) and flat classification (FC). It uses different types of classifiers like MINIROCKET, STSF, and SVM, along with special tools called dissimilarity measures. The study looks at a specific set of datasets that have more than two classes. The results show that HC is better when combined with certain things, but FC is usually better in other cases. It also shows that one type of tool (TSD) works well most of the time. |
Keywords
* Artificial intelligence * Classification * Time series
