Student Seminar - September 2017
Welcome New and Returning Graduate Students!
We will be hosting the first installment for the new school year of our recurring Student Seminar Series. In these hour-long sessions we invite fellow ITB graduate students to give a short talk (15 minutes or less) on a CS, SE or other Science and Engineering topic of their choice. All are welcome to attend and participate in these events and refreshments will be provided.
This month's seminar will be followed by a Hike-n-Pint at the Phoenix!
These seminars will happen monthly on the Third Thursday of each month. If you would like to give a talk at one of these events please email Musa Al-hassy: firstname.lastname@example.org. These talks are meant to be a casual opportunity to meet your fellow graduate students and to improve your public speaking and networking skills, things that will be useful later on in your academic and/or professional careers.
Designing Effective PowerPoint Slides
You have likely sat through many lectures and presentations dominated by PowerPoint. While the details of the content may be covered by the PowerPoint slides, the message is often lost. Are you familiar with the phrase "death by bullet points?" How about "cognitive load in multimedia learning"? In this session (using PowerPoint), we will explore how research from applied cognition informs presentation structure and slide design. During this presentation, you will learn how to create PowerPoint slides that will increase listener's interest and comprehension, all while minimizing unnecessary cognitive load.
Driver Behavior Prediction Models on Lane Changing using Artificial Intelligence Algorithms
High accuracy of the driver behavior prediction model is beneficial to driver assistant system and fully autonomous cars.
My research proposes a lane changing prediction model based on the combined method of Supporting Vector Machine (SVM) and Artificial Neural Network (ANN) at highway lane drops. The vehicle trajectory data are from Next Generation Simulation (NGSIM) data set on U.S. Highway 101, Interstate 80 and Tsinghua University. Different classifiers are adopted and compared to predict the feasibility and suitability to change lane under certain environmental conditions. The environment data under consideration include speed difference, vehicle gap, and the positions. The best performance is the proposed combined model with improved accuracy, demonstrating the effectiveness of the proposed method and superior performance compared to other methods.