MACHINE LEARNING-BASED ASSESSMENT AND PREDICTION OF PSYCHOACOUSTIC INDICATORS OF ROAD TRAFFIC NOISE

Şebnem Karahançer

Makale detayları

MACHINE LEARNING-BASED ASSESSMENT AND PREDICTION OF PSYCHOACOUSTIC INDICATORS OF ROAD TRAFFIC NOISE

Yazarlar:

Şebnem Karahançer

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Ulaşım ve Trafik | Ulaştırma Mühendisliği

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.13 Issue 3, pp.675-686

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001359340

pISSN:

1308-6693

Anahtar kelimeler:

Özet:

 This study explores the use of machine learning techniques to evaluate and predict psychoacoustic noise characteristics associated with pass-by road traffic events. Using a dataset comprising various acoustic and psychoacoustic parameters such as LAeq, FS50, L10, L90, and spectral indicators, a comprehensive analysis was conducted to assess their predictive potential. Gradient Boosting, Random Forest, and ARIMA models were employed for different tasks, including both classification and time-series forecasting. In addition, feature engineering techniques were used to create composite variables and enhance model input quality, while sequence-based learning methods allowed for temporal dynamics to be captured. The best-performing Gradient Boosting model achieved R²  0.63 and MAE  0.122 in predicting LAeq and FS50 indicators. The dataset used consisted of 1,200 pass-by noise events from an open-access repository, including both acoustic LAeq, L10, L90 and psychoacoustic FS50, R50, N50, S50 metrics. The results highlight the capability of machine learning not only to improve the accuracy of psychoacoustic modeling but also to support real-time, perception-aware urban noise monitoring systems. Such approaches can enable more responsive and adaptive noise management strategies in smart city planning. These findings demonstrate the potential of ML-based models to inform proactive urban noise management and public health strategies.

 This study explores the use of machine learning techniques to evaluate and predict psychoacoustic noise characteristics associated with pass-by road traffic events. Using a dataset comprising various acoustic and psychoacoustic parameters such as LAeq, FS50, L10, L90, and spectral indicators, a comprehensive analysis was conducted to assess their predictive potential. Gradient Boosting, Random Forest, and ARIMA models were employed for different tasks, including both classification and time-series forecasting. In addition, feature engineering techniques were used to create composite variables and enhance model input quality, while sequence-based learning methods allowed for temporal dynamics to be captured. The best-performing Gradient Boosting model achieved R²  0.63 and MAE  0.122 in predicting LAeq and FS50 indicators. The dataset used consisted of 1,200 pass-by noise events from an open-access repository, including both acoustic LAeq, L10, L90 and psychoacoustic FS50, R50, N50, S50 metrics. The results highlight the capability of machine learning not only to improve the accuracy of psychoacoustic modeling but also to support real-time, perception-aware urban noise monitoring systems. Such approaches can enable more responsive and adaptive noise management strategies in smart city planning. These findings demonstrate the potential of ML-based models to inform proactive urban noise management and public health strategies.

 This study explores the use of machine learning techniques to evaluate and predict psychoacoustic noise characteristics associated with pass-by road traffic events. Using a dataset comprising various acoustic and psychoacoustic parameters such as LAeq, FS50, L10, L90, and spectral indicators, a comprehensive analysis was conducted to assess their predictive potential. Gradient Boosting, Random Forest, and ARIMA models were employed for different tasks, including both classification and time-series forecasting. In addition, feature engineering techniques were used to create composite variables and enhance model input quality, while sequence-based learning methods allowed for temporal dynamics to be captured. The best-performing Gradient Boosting model achieved R²  0.63 and MAE  0.122 in predicting LAeq and FS50 indicators. The dataset used consisted of 1,200 pass-by noise events from an open-access repository, including both acoustic LAeq, L10, L90 and psychoacoustic FS50, R50, N50, S50 metrics. The results highlight the capability of machine learning not only to improve the accuracy of psychoacoustic modeling but also to support real-time, perception-aware urban noise monitoring systems. Such approaches can enable more responsive and adaptive noise management strategies in smart city planning. These findings demonstrate the potential of ML-based models to inform proactive urban noise management and public health strategies.

 Bu çalışma, yoldan geçen trafik olaylarına ait psikoakustik gürültü özelliklerini değerlendirmek ve tahmin etmek amacıyla makine öğrenimi tekniklerinin kullanımını araştırmaktadır. LAeq, FS50, L10, L90 ve spektral göstergeler gibi çeşitli akustik ve psikoakustik parametreleri içeren bir veri seti kullanılarak, bu göstergelerin tahmin gücü kapsamlı bir şekilde analiz edilmiştir. Çalışmada, sınıflandırma ve zaman serisi tahmini gibi farklı görevler için Gradient Boosting, Random Forest ve ARIMA modelleri uygulanmıştır. Ayrıca, özellik mühendisliği teknikleriyle bileşik değişkenler oluşturulmuş, model girişlerinin niteliği artırılmıştır. Zamansal örüntüleri yakalayabilen sequence-based yöntemler ile geçiş verileri üzerinde daha gerçekçi analizler yapılmıştır. Modellerin, farklı trafik ve çevre koşullarında gürültü rahatsızlığı düzeylerini tahmin etme yetenekleri de değerlendirilmiştir. Bulgular, makine öğreniminin yalnızca psikoakustik modelleme doğruluğunu artırmakla kalmayıp, aynı zamanda gerçek zamanlı, algıya duyarlı kentsel gürültü izleme sistemlerini desteklemede de güçlü bir araç olduğunu göstermektedir. Bu tür yaklaşımlar, akıllı şehir planlaması kapsamında daha esnek ve uyarlanabilir gürültü yönetim stratejilerinin geliştirilmesini mümkün kılmaktadır.

Makale detayları

MACHINE LEARNING-BASED ASSESSMENT AND PREDICTION OF PSYCHOACOUSTIC INDICATORS OF ROAD TRAFFIC NOISE

Yazarlar:

Şebnem Karahançer

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Ulaşım ve Trafik | Ulaştırma Mühendisliği

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.13 Issue 3, pp.675-686

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001359340

pISSN:

1308-6693

Psychoacoustics

Pass-by noise

Machine learning

Acoustic indicators.Psikoakustik

Geçiş Gürültüsü

Makine Öğrenimi

Akustik Göstergeler

Sayı

Makale detayları

Yazarlar: Şebnem Karahançer

Yayıncı: Süleyman Demirel University

Ana Başlıklar: Ulaşım ve Trafik | Ulaştırma Mühendisliği

Dergi: Mühendislik Bilimleri ve Tasarım Dergisi Vol.13 Issue 3, pp.675-686

Belge Tipi: Makale

Yayın Tarihi: 9/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001359340

pISSN: 1308-6693

Sayı

Yazarlar:

Şebnem Karahançer

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Ulaşım ve Trafik | Ulaştırma Mühendisliği

Dergi:

Mühendislik Bilimleri ve Tasarım Dergisi Vol.13 Issue 3, pp.675-686

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001359340

pISSN:

1308-6693