Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm

This study examines restroom cleanliness in public facilities, department stores, supermarkets, and schools by using water droplet volumes around washbowls as an indicator of usage. Rising cleaning costs due to labour shortages necessitate more efficient restroom maintenance. Quantifying water dropl...

Full description

Saved in:
Bibliographic Details
Main Authors: Sumio Kurose, Hironori Moriwaki, Tadao Matsunaga, Sang-Seok Lee
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769569054359552
author Sumio Kurose
Hironori Moriwaki
Tadao Matsunaga
Sang-Seok Lee
author_facet Sumio Kurose
Hironori Moriwaki
Tadao Matsunaga
Sang-Seok Lee
author_sort Sumio Kurose
collection DOAJ
description This study examines restroom cleanliness in public facilities, department stores, supermarkets, and schools by using water droplet volumes around washbowls as an indicator of usage. Rising cleaning costs due to labour shortages necessitate more efficient restroom maintenance. Quantifying water droplet accumulation and predicting cleaning schedules can help optimise cleaning frequency. To achieve this, water droplet volumes were measured at specific time intervals, with significant variations indicating increased restroom usage and potential dirt buildup. For real-world assessment, acrylic plates were placed on both sides of washbowls in public restrooms. These plates were collected every hour over five days and analysed using near-infrared photography to track changes in water droplet areas. The collected data informed the development of a prediction system based on the decision tree method, implemented via the LightGBM framework. This paper presents the developed prediction system, which utilises in situ water droplet volume measurements, and evaluates its accuracy in forecasting restroom cleaning needs.
format Article
id doaj-art-784e0d165b0a42efa065a4d94a81370f
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-784e0d165b0a42efa065a4d94a81370f2025-08-20T03:03:23ZengMDPI AGSensors1424-82202025-03-01257218610.3390/s25072186Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM AlgorithmSumio Kurose0Hironori Moriwaki1Tadao Matsunaga2Sang-Seok Lee3School of Engineering, Tottori University, 4-101 Koyama-Minami, Tottori 680-8552, JapanAsuka Bisou Co., Ltd., 296-1 Daigo, Kashihara 634-0072, JapanSchool of Engineering, Tottori University, 4-101 Koyama-Minami, Tottori 680-8552, JapanSchool of Engineering, Tottori University, 4-101 Koyama-Minami, Tottori 680-8552, JapanThis study examines restroom cleanliness in public facilities, department stores, supermarkets, and schools by using water droplet volumes around washbowls as an indicator of usage. Rising cleaning costs due to labour shortages necessitate more efficient restroom maintenance. Quantifying water droplet accumulation and predicting cleaning schedules can help optimise cleaning frequency. To achieve this, water droplet volumes were measured at specific time intervals, with significant variations indicating increased restroom usage and potential dirt buildup. For real-world assessment, acrylic plates were placed on both sides of washbowls in public restrooms. These plates were collected every hour over five days and analysed using near-infrared photography to track changes in water droplet areas. The collected data informed the development of a prediction system based on the decision tree method, implemented via the LightGBM framework. This paper presents the developed prediction system, which utilises in situ water droplet volume measurements, and evaluates its accuracy in forecasting restroom cleaning needs.https://www.mdpi.com/1424-8220/25/7/2186restroom dirtinessLightGBMdata augmentation techniqueswater droplet volume predictioncleaning schedule prediction
spellingShingle Sumio Kurose
Hironori Moriwaki
Tadao Matsunaga
Sang-Seok Lee
Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
Sensors
restroom dirtiness
LightGBM
data augmentation techniques
water droplet volume prediction
cleaning schedule prediction
title Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
title_full Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
title_fullStr Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
title_full_unstemmed Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
title_short Predicting Restroom Dirtiness Based on Water Droplet Volume Using the LightGBM Algorithm
title_sort predicting restroom dirtiness based on water droplet volume using the lightgbm algorithm
topic restroom dirtiness
LightGBM
data augmentation techniques
water droplet volume prediction
cleaning schedule prediction
url https://www.mdpi.com/1424-8220/25/7/2186
work_keys_str_mv AT sumiokurose predictingrestroomdirtinessbasedonwaterdropletvolumeusingthelightgbmalgorithm
AT hironorimoriwaki predictingrestroomdirtinessbasedonwaterdropletvolumeusingthelightgbmalgorithm
AT tadaomatsunaga predictingrestroomdirtinessbasedonwaterdropletvolumeusingthelightgbmalgorithm
AT sangseoklee predictingrestroomdirtinessbasedonwaterdropletvolumeusingthelightgbmalgorithm