Integrating eye-tracking technology with robust recurrent kernel online learning

This report is based on literature, Qing Song, et. Robust Recurrent Kernel Online Learning and Yanling Li, et. Integrating Eye-Tracking Technology with Robust Recurrent Kernel Online Learning. Robust recurrent kernel online learning (RRKOL) algorithm is used to investigate the integration of an eye...

全面介紹

Saved in:
書目詳細資料
主要作者: Liu, Tiange
其他作者: Song Qing
格式: Final Year Project
語言:English
出版: 2018
主題:
在線閱讀:http://hdl.handle.net/10356/74966
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Nanyang Technological University
語言: English
實物特徵
總結:This report is based on literature, Qing Song, et. Robust Recurrent Kernel Online Learning and Yanling Li, et. Integrating Eye-Tracking Technology with Robust Recurrent Kernel Online Learning. Robust recurrent kernel online learning (RRKOL) algorithm is used to investigate the integration of an eye tracking technology. In Yanling’s article, there’re four versions of model. 1. F = 1 model, also known as 1 feedback, it performs classification with a 2-selection simulation of the eye-tracking system. 2. F = 0 model, also known as no feedback, it performs classification with a 2-selection simulation of the eye-tracking system. 3. F’= 1 model, it based on F= 1 model but takes in data from a 5-selection of simulation. 4. P = 1 model, it performs recurrent prediction with 1 feedback. This project aims to repeat P = 1 model with 2-selection of simulation.