Info
이 질문은 마감되었습니다. 편집하거나 답변을 올리려면 질문을 다시 여십시오.
GMM for classification: how to avoid the super tiny number in results
조회 수: 1 (최근 30일)
이전 댓글 표시
Hello, I am a student of control engineering, Recently, I used GMM model to classify the signal types. Firstly, I used gmdistribution.fit function to fit the gmm model for each class. Then, I used the model to compute the probability density of each class.
The problem is that the probability density I got is very small, e.g. 4.2e-40. How to avoid this problem? Thank you very much.
댓글 수: 0
답변 (1개)
Jang Bahadur Singh
2017년 12월 7일
Actually, probability density function sum to 1, check it. try: look for major peak, check code, use more data, change y-axis.
댓글 수: 0
이 질문은 마감되었습니다.
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!