The website design was out first encounter in the project. It was tough at first but one team member took charge in designing and laying out the format. From that point on, the technical team was able to complete the website with ease.

This is one of the designs what the technical team had to accomplish with synchro. We first took an image of the intersection and scaled it up to match the width of the lanes in synchro. After creating the new layout of on and off ramps, we inserted the vehicle flow rates within each lane to later achieve a report that will indicate the level of service on each intersection based on the flow rate values. Synchro could also create a simulation of vehicles using the design to visually see if the intersection is creating congestion or a steady flow. From that simulation, we could change the values or road design to come up with a better level of service.

The final GEH table comparison is shown between the designs with L-9 GEH having the lowest GEH for Southbound AM & PM and Northbound AM and Existing Northbound PM.

The Surrogate Safety Assessment Model otherwise, known as SSAM, is a software application developed by the Federal Highway Administration is used to identify, classify, and evaluate traffic conflicts in the vehicle trajectory data output from microscopic traffic simulation models, such as Vissim. With the trajectory file being converted as an input for the SSAM software, SSAM draws up possible conflicts, which are: Crossing, Lane Change, and Rear End at the Palm Interchange. SSAM generates a map with these three conflicts and groups them together at the exact points on the freeway, so overlaying the map on top of the simulation network of the interchange can show visual representation.

Computer vision is a software that is able to identify certain objects with the help of the user using the polyline tool to isolate the object from the rest of the image. Some aspects that our team decided to highlight are lane markings, vehicles, and road stress. In the later run, we ran with lane markings because we had an abundance of annotations labeling the lane markings. After annotating the lane markings, we ran the save file into python to see if the super computer could identify each lane marking. The outcome of this software would help contribute with autonomous vehicles and their ability to identify certain signals to better understand the road to be able to drive safety.