University of Twente Student Theses

Login
This website will be unavailable due to maintenance December 1st between 8:00 and 12:00 CET.

Airport restroom cleanliness prediction using real time user feedback data and classification techniques

Ros, K. M. (2019) Airport restroom cleanliness prediction using real time user feedback data and classification techniques.

[img] PDF
2MB
Abstract:Amsterdam Airport Schiphol aims to offer a maximized airport experience to its passengers. A main contributor to this is the cleaning of restrooms, of which the cleanliness is rated by the users. This paper reviews to what extent real-time feedback data and classification techniques can be useful in practice to predict the cleanliness of restrooms. Within this topic, different class definitions of clean and unclean are studied and a distinction is made between a combined prediction model that includes the entire environment and restroom-specific prediction models that focus only on a single restroom. The dataset is imbalanced and visualizations show that there is class overlap. The combined prediction model outperforms combined baselines but the precision is not high enough to be useful in practice. Restroom-specific prediction models of the busier restrooms outperform the combined prediction model but do not outperform simple restroom-specific baselines. Restroom-specific prediction models of the least busy restrooms perform very poor and sometimes are not even capable of correctly classifying a single unclean sample. Sampling methods do not improve the performance of the combined prediction model but do improve the performance of some of the restroom-specific prediction models, especially those with a high class imbalance. The major cause of the unsatisfying performance is not class imbalance, but the data ambiguity that leads to class overlap. To obtain prediction models that are useful in practice, the dataset should be enriched with features that are capable of distinguishing the two classes more clearly.
Item Type:Essay (Master)
Clients:
Asito B.V., Almelo, The Netherlands
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:https://purl.utwente.nl/essays/79469
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page