| Abstract: |
Airport Business is a “Flow Business”. Managing resources in facilitating the flow of people and goods through the airport is always the biggest challenge. For example, arrival baggage delivery, being the last step of the passenger flight journey, presents the most challenge in ensuring a superb passenger airport experience. Traditionally, baggage reclaim belts are allocated according to the flight arrival time and some other basic factors. With baggage reclaim belts loading reaching the capacity, more factors, and therefore more data, have to be taken into consideration in optimizing the allocation. Furthermore, in addition to managing the feeding of arrival bags into the reclaim belt system, ensuring even loading of bags circulating on the reclaim belts is also required to maintain and uphold the customer service. Multi-source data such as flight/origin arrival patterns, passenger profile, baggage dwelling time, seasonal factors, and historical patterns, would have to be included for consideration once they are available. This requires big data analytics. Thus, how to apply big data analytics and machine learning technologies effectively is a significant yet challenging subject. This project aims to study and develop a Big Data-Driven Airport Resource Management (BigARM) Engine for intelligent airport resource management. Initial focus is on baggage reclaim belt allocation and loading balance, but the engine would be designed with expansion capability to cover other airport resource management areas. With more generalization and business data model tuning, BigARM can also be applied in tackling similar resources management problems in other airports and industries. |
