Classifying Passenger and Non-passenger Signals in Public Transportation by Analysing Mobile Device Wi-Fi Activity

Abstract

Quality of service is one factor passengers consider when deciding to use the public transportation system. Increasing the quality of service can be done in several ways, such as improving on-time arrival, reducing waiting time, and providing seat availability information. We believe that if passengers have better information for making decisions, that can increase the quality of service. This paper proposes estimating the number of passengers by analyzing signals from their Wi-Fi devices, classifying them as originating from passenger or non-passenger devices using a real-time filtering mechanism. Experimental validation was performed aboard busses of different types taking different routes. Our experimental results show that filtered data can classify passenger device signals from environmental ones with an accuracy of 75 percent, which is a promising basis for providing real-time information to passengers that improves the quality of their service.

Using passive Wi-Fi for community crowd sensing during the COVID-19 pandemic

“…Several attempts have looked at Wi-Fi as a means to infer crowd densities. Due to its non-intrusive nature, passive Wi-Fi tracking has been studied and applied in several situations in the past, ranging from university campuses [ 27 , 28 ], and tracking spectators in football stadiums [ 29 ], to small cities [ 11 ] and public transportation [ 30 , 31 ]. The motivations of these studies are diverse, some look at energy waste on scanning methods [ 27 , 32 ], others focus on realistic facility management and planning [ 33 ], and even analysing crowding factors and flock detection [ 34 ], waiting times in public transport [ 35 ], frequent paths [ 36 ], while also inferring social information, like the popularity of events [ 29 ].…”

The potential of Wi-Fi data to estimate bus passenger mobility

“…It is also not straightforward to choose the variables to determine if a signal belong to a passenger or not. Whereas signal strength and duration of the detection are most of the time preferred (Ji et al, 2017;Oransirikul et al, 2019), for Nitti et al (2020, speed would be a better indicator to determine if the object is inside the bus or not. Also, use of threshold values to select signals is more subject to ignore temporal variability.…”

UAI-FI: using artificial intelligence for automatic passenger counting through Wi-Fi and GPS data

“…TRANSPORTES | ISSN: 2237-1346 Oransirikul et al (2019) and Nitti et al (2020) included a frequency attribute, which measures the rate that packets are sent. However, de.ining this threshold is problematic because such frequency is not standardized (IEEE, 1997).…”

“…However, the parameters that .ilter the packets coming from smartphones inside the bus from outside noise are con.igured empirically, usually by setting arbitrary thresholds. This makes the application of such approaches problematic due to the complexity of estimating such limits and possible collateral effects (Oransirikul et al, 2019;Paradeda et al, 2019).…”