Story

William Xue, EECS, '17

"After this internship, due to a mix of good things I saw and experienced while working for Mitsubishi Electric, I am now more inclined to consider a longer term career in Japan."

My internship project essentially consisted of developing a prototype for an idea my supervisor had.

Firstly, I was assigned with doing background research to better understand the Japanese train situation, particularly the imbalance of crowdedness in different train cars (especially during rush hours). To address this, I researched context aware technologies to gain a better idea of what was needed to come up with a solution to this problem.

Then with this newfound knowledge, I developed a model of user movement for the purpose of predicting the number of users boarding and getting off a train. With this, it became possible to develop an application that allowed passengers to compare the crowdedness of train cars and decide which cars to take from there, reducing the imbalance of crowdedness in different train cars. Finally, I implemented a prototype of this application.

I based the model off of a machine learning model I had learned at MIT. Additionally, the application was developed for Android in Java, which I gained experience with at MIT.