Spermiogram Görüntülerinden Hareket Belirleme Yöntemleri ile Aktif Sperm Sayısının Tahmini

Abstract

Highlights:Graphical/Tabular Abstract  Only active sperms are examined using motion detection methods.  Test that made by experts in laboratories have been evaluated with a more objective approach.  Sperms and other organisms were differentiated by circularity criterion. Figure A. The diagram of applied methodPurpose: Nowadays, infertility is a serious health problem. The most important parameters that cause infertility in males are sperm morphology, sperm motility and sperm density. For this reason, sperm motility, density and morphology are analyzed in semen analysis and these analyzes are done by experts in the laboratory. Analysis based on observation in the laboratory is easy to mistake, subjective application. Our study aims to eliminate the experts errors caused by manual segmentation. Theory and Methods:The Gaussian Mixture Model statistically compared the consecutive frames in the video sequence and determined the moving regions. The fast moving sperm is outside the area determined by the single frame difference and the noise occurs due to the movement of the fluid. Morphological processes are used to solve these problems. Then shape analysis is done on organelles in the foreground areas, which are improved by morphological processes. The video images used in the proposed study were monitored by experts and approved by them and their real values were determined in the determined areas. Then, the success rate of the classification was calculated by comparing the actual values with the results of our proposed method. Results:In this study, semen analysis was done by using image processing algorithms and it was aimed to detect active sperm on Isfahan semen video set. It is observed that the 81.81% accuracy rate is calculated on the Isfahan semen video set. Conclusion:When the obtained results are examined, it is seen that the proposed method performs very successful classification according to other studies in the literature.

Uydu verilerinden karar ağaçları kullanarak orman yangını tahmini

“…Özellikle veri madenciliği ve yapay zekâ algoritmaları son yıllarda verileri işlemede oldukça yoğun kullanılmaktadır. Teknolojinin gelişmesi ile hayatın her alanında özellikle tıbbi çalışmalarda [6], hassas tarım uygulamalarında [7,8], klasik ve sosyal medya [9] alanında oluşan büyük veri yapay zekâ algoritmaları ile analiz edilerek anlamlı bilgiler çıkarılmaktadır.…”