1 / 22

Kaggle: Whale Challenge

Kaggle: Whale Challenge. 張智星 jang@cs.nthu.edu.tw http://www.cs.nthu.edu.tw/~jang 多媒體資訊檢索實驗室 台灣大學 資訊工程系. Whale Challenge. Problem definition Identify the existence of whales from sensor recordings Characteristics: Imbalance data Some recordings are hardly recognizable by non-experts.

keefer
Download Presentation

Kaggle: Whale Challenge

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Kaggle: Whale Challenge 張智星 jang@cs.nthu.edu.tw http://www.cs.nthu.edu.tw/~jang 多媒體資訊檢索實驗室 台灣大學 資訊工程系

  2. Whale Challenge • Problem definition • Identify the existence of whales from sensor recordings • Characteristics: • Imbalance data • Some recordings are hardly recognizable by non-experts

  3. Dataset • Training set • 47,844 recordings of 2 seconds • 88.97% (42,565 recordings): w/o whales • 11.03% (5,276 recordings): with whales • Test set • 25,468 recordings of 2 seconds • Recording format • 2000-Hz sample rate, 16-bit resolution

  4. Preprocessing • Potential preprocessing • Trend removal • Trend estimation via polynomial fitting • Noise removal • Band-pass filter • Removal of “non-whale” part • Linear prediction?

  5. Spectrogram kwcPreprocess.m • W/o band-pass filter • W/ band-pass filter

  6. Potential Features • Acoustic features • Volume • Pitch • Spectrum • MFCC • … • Visual features (obtained from spectrogram) • Radon transform • Hough transform • Gabor filters • …

  7. Pitch Tracking • kwcPitchTracking.m

  8. Volume • kwcVolume.m

  9. Spectrogram • kwcSpectrogram.m

  10. Visual Features viaRadon Transform • Radon transform • Projection onto lines at various angles • For grayscale images only • Detection objects at a specific angle

  11. Example of Radon Transform • Source • http://www.mathworks.com/help/images/ref/radon.html • Output Code: goRadon.m

  12. Example of Radon Transform (2) • Source image • Output Code: goRadon2.m

  13. Visual Features viaHough Transform • Hough transform • Commonly used for detection lines and circles • For BW images only (after edge detection)

  14. Visual Features viaHough Transform (2) • Hough transform • Point to curve mapping • Two points  Two sine curves • The intersection is the right θ and ρ for the line connecting these two points

  15. Example of Hough Transform • Source • http://www.ebsd-image.org/documentation/reference/ops/hough/op/houghtransform.html Image Hough space and its maxima Detected lines

  16. Example of Hough Transform (2) • Source • http://www.mathworks.com/help/images/analyzing-images.html (MATLAB code available) Image Edge image Hough space and its maxima Detected lines

  17. Methods • Thresholding • Volume variance • Pitch variance • Static classifiers • Naïve Bayes classifiers • GMM • SVM • … • Sequence classifiers • HMM • CRF • …

  18. HMM Training • kwcHmmTrain.m

  19. HMM Evaluation • kwcHmmEval.m

  20. HMM • Basic models • Class 1: sil • Class 2: sil-whale-sil • Advanced models • sil • sil-whale-sil-whale-sil • … 1.0 sil 0.9 0.4 1.0 sil w sil 0.1 0.6

  21. HMM(2) • Other approach • Train HMM models • Align each recording with the HMM • Extract features from the whale part for other static classifiers • Duration (no. of frames) • Average log likelihood per frame 0.9 0.4 1.0 sil w sil 0.1 0.6

  22. Performance Evaluation • Performance evaluation of methods based on thresholding (http://en.wikipedia.org/wiki/Receiver_operating_characteristic): • ROC, DET • AUC

More Related