Skip to main content

Questions tagged [knn]

K Nearest Neighbor is a classification algorithm used to classify data based on set of already classified examples.

Filter by
Sorted by
Tagged with
4 votes
1 answer

If a K-NN ($ k $ Nearest Neighbors) Algorithm Performs Very Well for Low $ k $, Can Something Be Inferred About the Data Set?

I am running kNN on a very small data set for binary classification. Each class has 100 samples. I am getting the best performances for $k=1$ and $k=3$. Can I deduce information about my data set ...
prax1telis's user avatar
0 votes
0 answers

Using MFCCs in kNN classification

I'm working on adding MFCCs to my kNN classifier. Originally my kNN classifier was using the zero-crossing-rate, centroid, bandwidth, skew, kurtosis. This was about 80% accurate for drum tracks using ...
scarlso9's user avatar
  • 111
2 votes
3 answers

Using neural networks for rotation invariant OCR

I have video with text which can be rotated in any direction. If I trained a neural network on images of each letter at all possible degrees of rotation, would it be possible to classify the ...
Jack Simpson's user avatar
0 votes
1 answer

k-NN match for object recognition

The $\frac{d_1}{d_2}<0.6$ gives a large number of false matches and it assumes the nearest neighbour is a correct match. Anybody knows any good method to reduce number of false matches or filter ...
Ankit Nayan's user avatar
0 votes
0 answers

can we use machine learning concepts to extract blood vessel from retinal image?

I am working on blood vessel extraction, i want to know whether we can extract blood vessel using machine learning algorithm? which algorithm i can use to yield good results?
vidya's user avatar
  • 1
2 votes
1 answer

Training k-NN classifier with MFCC data

I am doing a personal project which aims to detect infant cry. I have an infant cry audio database and extracted the MFCC from these files using MATLAB. I've come up with 12 coefficients for each ...
gustavsl's user avatar
6 votes
2 answers

Mahalanobis vs Normalization+Euclidean

I'm using a set of features extracted from a signal for classifying the data window with KNN algorithm. Since the features have different value ranges, their influence on distance calculation is ...
mostar's user avatar
  • 259