Currently studying for a master's degree in Industry 4.0 related to Cloud Computing, Machine Learning, Internet of Things IoT, Big Data, Micro-services, Systems Engineering and Databases
Experienced Software Engineer with a demonstrated history of working in the computer software industry. Skilled in JAVA, Python, PHP, C++, Hibernate, and Spring Framework.
Strong engineering professional with a Master's degree focused in Computer Software Engineering from Université Antonine.
Studies in Machine Learning, Cloud Computing, Micro-Services, Business Analytics, Databases, IoT and Systems Engineering
Apart from being a developer, I enjoy traveling, meeting new people, learning new skills as I already start improving my photography skills from watching online video tutorials and also enrolled in a salsa dance school.
Based on multiple research, public transportation is currently facing a lot of problems that drove it to the loss of attractiveness due to various reasons: the long waits at transfer points, being prevented from boarding due to crowding, the long distance that requires some people to take in order to reach the bus stop and not have the minimum requirements to satisfy disabled people's needs.
As mentioned by TCRP, Transit Cooperative Research Program, multiple criteria must be applied in order to eliminate all problems that can affect the public transportation like the spacing between other bus routes and corridors, bus stop sitting requirements, bus stop spacing requirements, passengers per hour, passengers per trip, the maximum number of standees, timed meets, or time to be spent waiting at a transfer point and bus stop consolidation.
To help respond to these criteria, our idea was born, an embedded system that can track the people waiting at the bus stop, count them, differentiate between an adult and a young person, count passengers with wheelchairs then finally analyze this data to optimize the whole bus trip. The optimization can target many layers, as the data collected can be studied and analyzed differently depending on the machine learning algorithm applied. For example, this real-time data collected can be used to know that a specific bus stop requires more buses to respond to the high demand, that multiple bus stops could be consolidated together which will result in a decrease of the bus running time and by that reducing operating costs, and many other benefits.
Technically speaking, the system is composed of two parts: the physical part and the logical one. The physical part, which will be embedded in the bus stop is mainly composed of a camera and Raspberry PI and has a role to track the different type of people waiting, count them and only send counters to the logical system due to privacy. In the other part, the logical system will collect these data, analyze them, save the result and rapidly take action.