This page contains JavaScript implementations of some common algorithms for handling raw eye-tracking data, such as generating fixations and managing vertical drifting, which served for the tracking part of autocomplete research. For example, IDT, attach, K-cluster.js. It also includes some data visualization script we used in internal testing. All codescripts designed to be run under NodeJs.
A user script designed to be injected into itestcloud.unipus.cn, helping individuals grade in their preferred, customized way by utilizing TensorFlow and bi-gram to simplify the grading process.
My modified version is at https://shaokangjiang.github.io/traffic-simulation/. I just add an export function to export data for each car and measuring point to csv file. I will talk them in details at here and discuss my thought.