The inspiration behind David is to solve two major challenges in any mode of transport . David , a personal assistant measure the alertness index of a driver ( could be a personal / public vehicle ) based on a few questions that have been compiled after talking to experts and medical advisors from the field . The alertness index advises a driver whether he is alert enough to hit the road or should he find any alternative mode of transport . This is a crucial step , we believe , in reducing the number of driver induced errors in accidents . Another core feature of David is that it suggests a time at which a user has to depart to reach his preferred destination on his preferred time schedule , based on his preferred mode of transport . Thus David intends to provide 3 major qualities to it's end users - Alertness , safety and efficiency .

Alertness Index

Alertness index is a simple questionnaire for a driver that calculates the alertness index of the individual thereby letting him know how alert he can be in his job of driving . It asks simple questions that includes info about the amount of time he has slept , the number of hours he has spent driving in the recent past and use of alcohol and / or other alertness depriving substances . The algorithm analyses the answers given and calculates a rating that can have a maximum of 96 . A score of above 76 indicates high alertness and that the user is fit to drive . A score between 60 and 76 indicates normal alertness and the user is advised to be extra vigilant in driving and a score below 60 is considered below par and the user is advised to use alternative modes of transport or find other drivers for the same trip . The algorithm allocates weight to each answer based on the importance of the answers compiled with the help of experts in the field . End users can use this feature to significantly reduce driving errors that can lead to accidents and mishaps . The algorithm for attention index calculation can be found here


DepartBy is another core feature of the app with which a departure time is predicted to the user after he enters the source and destination addresses , preferred time of arrival expected . Separate times are given for transport by means of a personal vehicle , a cab , a shared cab and public transport . The time predicted calculates the same based on data received from Google Maps , Weather updates , Traffic updates , accident / road work info and historical data . The algorithm allocates weight to each factor considered , consolidates the result obtained and delivers time in 24 hour format for each mode of transport . DepartBy is a feature we believe can help improve the efficiency and punctuality of users using the app .

Other features

SmartBus SmartBus feature allows easy access to bus schedules, fares, trip planner, bike rack use, Smart value pass, MyConnector for regular users of the same .

ThePeopleMover ThePeopleMover feature allows easy access to Station Guide, Ride Info, passes, tickets for users of the same .

M-1 Rail M-1 Rail info allows easy access to Station stops, schedule, tickets for users of the same .

How I built it

Alertness Index was built using an algorithm that analyses the user responses and gives weight after compiling usual and normal alertness levels of individuals based on their reaction to scenarios . Depart By feature was built using Google Maps API , open weather API and other traffic APIs . The algorithm for attention index calculation can be found here

Challenges I ran into

Developing the algorithm for alertness index was the biggest challenge as it involved extensive research and data from experts in the field and common accident causes analysis . DepartBy feature , thought easier , took longer time to complete because of complexities involved in getting data from various APIs used .

What's next for David

The alertness index algorithm required rigorous testing from users and the algorithm needs to be perfected after more research , opinions and adding questions that can help us predict a better alertness Index score

Built With

+ 80 more
Share this project: