Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library

Understanding students’ acoustic evaluation in learning environments is crucial for identifying acoustic issues, improving acoustic conditions, and enhancing academic performance. However, predictive models are not specifically tailored to predict students’ acoustic evaluations, particularly in educ...

Full description

Saved in:
Bibliographic Details
Main Authors: Dadi Zhang, Kwok-Wai Mui, Massimiliano Masullo, Ling-Tim Wong
Format: Article
Language:English
Published: MDPI AG 2024-07-01
Series:Acoustics
Subjects:
Online Access:https://www.mdpi.com/2624-599X/6/3/37
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258833849450496
author Dadi Zhang
Kwok-Wai Mui
Massimiliano Masullo
Ling-Tim Wong
author_facet Dadi Zhang
Kwok-Wai Mui
Massimiliano Masullo
Ling-Tim Wong
author_sort Dadi Zhang
collection DOAJ
description Understanding students’ acoustic evaluation in learning environments is crucial for identifying acoustic issues, improving acoustic conditions, and enhancing academic performance. However, predictive models are not specifically tailored to predict students’ acoustic evaluations, particularly in educational settings. To bridge this gap, the present study conducted a field investigation in a university library, including a measurement and questionnaire survey. Using the collected personal information, room-related parameters, and sound pressure levels as input, six machine learning models (Support Vector Machine–Radial Basis Function (SVM (RBF)), Support Vector Machine–Sigmoid (SVM (Sigmoid)), Gradient Boosting Machine (GBM), Logistic Regression (LR), Random Forest (RF), and Naïve Bayes (NB)) were trained to predict students’ acoustic acceptance/satisfaction. The performance of these models was evaluated using five metrics, allowing for a comparative analysis. The results revealed that the models better predicted acoustic acceptance than acoustic satisfaction. Notably, the RF and GBM models exhibited the highest performance, with accuracies of 0.87 and 0.84, respectively, in predicting acoustic acceptance. Conversely, the SVM models performed poorly and were not recommended for acoustic quality prediction. The findings of this study demonstrated the feasibility of employing machine learning models to predict occupants’ acoustic evaluations, thereby providing valuable insights for future acoustic assessments.
format Article
id doaj-art-79682576cb504ae0a7355ba6cc45e571
institution OA Journals
issn 2624-599X
language English
publishDate 2024-07-01
publisher MDPI AG
record_format Article
series Acoustics
spelling doaj-art-79682576cb504ae0a7355ba6cc45e5712025-08-20T01:56:01ZengMDPI AGAcoustics2624-599X2024-07-016368169710.3390/acoustics6030037Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University LibraryDadi Zhang0Kwok-Wai Mui1Massimiliano Masullo2Ling-Tim Wong3Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Architecture and Industrial Design, Università degli Studi della Campania “Luigi Vanvitelli”, 81031 Aversa, ItalyDepartment of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong, ChinaUnderstanding students’ acoustic evaluation in learning environments is crucial for identifying acoustic issues, improving acoustic conditions, and enhancing academic performance. However, predictive models are not specifically tailored to predict students’ acoustic evaluations, particularly in educational settings. To bridge this gap, the present study conducted a field investigation in a university library, including a measurement and questionnaire survey. Using the collected personal information, room-related parameters, and sound pressure levels as input, six machine learning models (Support Vector Machine–Radial Basis Function (SVM (RBF)), Support Vector Machine–Sigmoid (SVM (Sigmoid)), Gradient Boosting Machine (GBM), Logistic Regression (LR), Random Forest (RF), and Naïve Bayes (NB)) were trained to predict students’ acoustic acceptance/satisfaction. The performance of these models was evaluated using five metrics, allowing for a comparative analysis. The results revealed that the models better predicted acoustic acceptance than acoustic satisfaction. Notably, the RF and GBM models exhibited the highest performance, with accuracies of 0.87 and 0.84, respectively, in predicting acoustic acceptance. Conversely, the SVM models performed poorly and were not recommended for acoustic quality prediction. The findings of this study demonstrated the feasibility of employing machine learning models to predict occupants’ acoustic evaluations, thereby providing valuable insights for future acoustic assessments.https://www.mdpi.com/2624-599X/6/3/37acoustic evaluationmachine learningprediction modelleaning environmentfield investigationon-site measurement
spellingShingle Dadi Zhang
Kwok-Wai Mui
Massimiliano Masullo
Ling-Tim Wong
Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
Acoustics
acoustic evaluation
machine learning
prediction model
leaning environment
field investigation
on-site measurement
title Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
title_full Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
title_fullStr Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
title_full_unstemmed Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
title_short Application of Machine Learning Techniques for Predicting Students’ Acoustic Evaluation in a University Library
title_sort application of machine learning techniques for predicting students acoustic evaluation in a university library
topic acoustic evaluation
machine learning
prediction model
leaning environment
field investigation
on-site measurement
url https://www.mdpi.com/2624-599X/6/3/37
work_keys_str_mv AT dadizhang applicationofmachinelearningtechniquesforpredictingstudentsacousticevaluationinauniversitylibrary
AT kwokwaimui applicationofmachinelearningtechniquesforpredictingstudentsacousticevaluationinauniversitylibrary
AT massimilianomasullo applicationofmachinelearningtechniquesforpredictingstudentsacousticevaluationinauniversitylibrary
AT lingtimwong applicationofmachinelearningtechniquesforpredictingstudentsacousticevaluationinauniversitylibrary