Investigation on the Impact of Preprocessing Methods and Parameter Selection in Acoustic Scene Classification Based on K-means Clustering Algorithm
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This research investigates the effectiveness of various preprocessing methods and parameters on Acoustic Scene Classification (ASC) using the Kmeans clustering algorithm.Utilizing the ESC-50 dataset, a combination of Principal Component Analysis (PCA) and StandardScaler was employed for preprocessing.The study's key findings include the identification of an optimal number of PCA components, around 30, which maximized the accuracy of the K-means algorithm.Additionally, the results revealed an unexpected phenomenon where increasing the number of clusters beyond the actual class count improved the model's accuracy, indicating potential nuanced subgroupings within classes.These insights highlight the significance of preprocessing methods and the choice of parameters on the performance of ASC models.However, the findings may not be universally applicable across other datasets or feature sets.The study offers potential directions for future research, suggesting the exploration of other machine learning algorithms and further investigation into the potential sub-groupings within classes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it