User Tools

Site Tools


projects

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
projects [2014/07/15 19:44]
admin
projects [2017/09/15 17:58] (current)
Line 8: Line 8:
 Do Machine Learning on slightly changing datasets. I.e. try out text classification with adding noise, changing the font, rotating and scaling, etc.  Do Machine Learning on slightly changing datasets. I.e. try out text classification with adding noise, changing the font, rotating and scaling, etc. 
 See [[programming:​pattrec_ml|Pattern Recognition and Machine Learning]] See [[programming:​pattrec_ml|Pattern Recognition and Machine Learning]]
-  * [[http://​stackoverflow.com/​questions/​11786918/​ocr-solution-that-detects-numeric-handwriting|OpenCV does this with kNN and SVM]] for handwriting recognition ([[http://​opencv-python-tutroals.readthedocs.org/​en/​latest/​py_tutorials/​py_ml/​py_knn/​py_knn_opencv/​py_knn_opencv.html|docs]] if they help). Somehow it does multi-class SVM??? 
-    * Tesseract ([[http://​stackoverflow.com/​questions/​19533273/​best-ocr-optical-character-recognition-example-in-android|2]]?​) is another option, but seems heavier. 
-    * In general for machine learning, one should say the uncertainty of the guess for the user to use. 
-  * This should be very similar to Can Ye's work on arrhythmia detection at CMU.  
-    * {{::​ecg_classification_ye.pdf|Arrhythmia detection and classification using morphological and dynamic features of ECG signals (ICA, SVM)}} 
-    * {{::​ecg_individual_customization_ye.pdf|Customizing the Training Dataset to an Individual for Improved ​ Heartbeat Recognition Performance in Long-Term ECG Signals}} 
-  * Can Neural Networks / Deep Learning **figure out good features autonomously**? ​ 
  
-Frequency response estimation in real-time. I think we did LD recursion or something in Advanced DSP.+ 
 +==== Frequency response estimation ​==== 
 +in real-time. I think we did LD recursion or something in Advanced DSP.
     * Add a distracting signal like Sullivan talking too.     * Add a distracting signal like Sullivan talking too.
     * [[g>​System Identification]]     * [[g>​System Identification]]
projects.txt · Last modified: 2017/09/15 17:58 (external edit)