A paper by Dr. Yimeng Sun of Kyoto College of Computer Science (KCGI) has been accepted for the 2020 IEEE 2nd Global Conference on Life Sciences and Technologies to be held at Mielparque Kyoto, Shimogyo-ku, Kyoto, March 10-12, 2020.
Dr. Sun's thesis, 'Optimized Light-Weight Convolutional Neural Networks for Histopathologic Cancer Detection' (advisor and co-presenters: Assistant Professor Fairouza Amira Binti Hamzah KCGI and Assistant Professor Badr Mochizuki), is based on his work in Kaggle, a machine learning competition in the field of AI.
Dr. Sun achieved about 98% recognition accuracy in pathological image diagnosis of cancer using EfficientNet, an image recognition model developed by Google, by improving the combination of activation function and optimization algorithm.Research on pathological diagnosis using image recognition AI is making it possible to perform diagnosis instead of doctors, and Sun's research results are also expected to be used in the medical field.