Predictive Modeling of Urban Traffic Accident Severity in Türkiye's Centennial: Machine Learning Approaches for Sustainable Cities

Adem Korkmaz

Makale detayları

Predictive Modeling of Urban Traffic Accident Severity in Türkiye's Centennial: Machine Learning Approaches for Sustainable Cities

Yazarlar:

Adem Korkmaz

Yayıncı:

Ahmet FİDAN

Ana Başlıklar:

Kentsel Bilişim | Şehir ve Bölge Planlama | Coğrafi Bilgi Sistemleri

Dergi:

Kent Akademisi Vol.16 Issue Türkiye Cumhuriyetinin 100. Yılı Özel Sayısı | Special Issue for the 100th Anniversary of the Republic of Türkiye, pp.395-406

Belge Tipi:

Makale

Yayın Tarihi:

10/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001298425

pISSN:

2146-9229

Anahtar kelimeler:

Özet:

 With their far-reaching implications for public health, urban development, and societal harmony, traffic accidents remain a global challenge. As the Republic of Türkiye marks its 100th year, predicting traffic accident severity assumes critical significance, aligning with the nations aspirations for urban renewal and sustainable progress. This research harnesses the capabilities of machine learning ML to anticipate accident severities, shedding light on the critical roles of specific driver and vehicle characteristics. In-depth evaluation of various ML techniquesspanning from Random Forest RF and Gaussian Naive Bayes to k-NN, CatBoostClassifier, LightGBM, and Decision Treeswas undertaken, drawing on an expansive dataset that mirrors a spectrum of traffic situations. The RF algorithm demonstrated superior predictive prowess, with certain variables such as Engine_Capacity_CC, Age_of_Driver, Age_of_Vehicle, Day_of_Week, and Vehicle_Type emerging as decisive factors in accident outcomes. Beyond highlighting RFs potential in accident severity prediction, the study emphasizes the significance of critical determinants. These insights offer a roadmap for stakeholders to craft specialized interventions, amplify public awareness efforts, and pioneer infrastructural upgrades, culminating in a vision of enhanced road safety. Furthermore, this investigation charts a course for Türkiye to foster a sustainable urban trajectory through informed urban and traffic planning initiatives.

 With their far-reaching implications for public health, urban development, and societal harmony, traffic accidents remain a global challenge. As the Republic of Türkiye marks its 100th year, predicting traffic accident severity assumes critical significance, aligning with the nations aspirations for urban renewal and sustainable progress. This research harnesses the capabilities of machine learning ML to anticipate accident severities, shedding light on the critical roles of specific driver and vehicle characteristics. In-depth evaluation of various ML techniquesspanning from Random Forest RF and Gaussian Naive Bayes to k-NN, CatBoostClassifier, LightGBM, and Decision Treeswas undertaken, drawing on an expansive dataset that mirrors a spectrum of traffic situations. The RF algorithm demonstrated superior predictive prowess, with certain variables such as Engine_Capacity_CC, Age_of_Driver, Age_of_Vehicle, Day_of_Week, and Vehicle_Type emerging as decisive factors in accident outcomes. Beyond highlighting RFs potential in accident severity prediction, the study emphasizes the significance of critical determinants. These insights offer a roadmap for stakeholders to craft specialized interventions, amplify public awareness efforts, and pioneer infrastructural upgrades, culminating in a vision of enhanced road safety. Furthermore, this investigation charts a course for Türkiye to foster a sustainable urban trajectory through informed urban and traffic planning initiatives.

 With their far-reaching implications for public health, urban development, and societal harmony, traffic accidents remain a global challenge. As the Republic of Türkiye marks its 100th year, predicting traffic accident severity assumes critical significance, aligning with the nations aspirations for urban renewal and sustainable progress. This research harnesses the capabilities of machine learning ML to anticipate accident severities, shedding light on the critical roles of specific driver and vehicle characteristics. In-depth evaluation of various ML techniquesspanning from Random Forest RF and Gaussian Naive Bayes to k-NN, CatBoostClassifier, LightGBM, and Decision Treeswas undertaken, drawing on an expansive dataset that mirrors a spectrum of traffic situations. The RF algorithm demonstrated superior predictive prowess, with certain variables such as Engine_Capacity_CC, Age_of_Driver, Age_of_Vehicle, Day_of_Week, and Vehicle_Type emerging as decisive factors in accident outcomes. Beyond highlighting RFs potential in accident severity prediction, the study emphasizes the significance of critical determinants. These insights offer a roadmap for stakeholders to craft specialized interventions, amplify public awareness efforts, and pioneer infrastructural upgrades, culminating in a vision of enhanced road safety. Furthermore, this investigation charts a course for Türkiye to foster a sustainable urban trajectory through informed urban and traffic planning initiatives.

 Halk sağlığı, kentsel gelişim ve toplumsal uyum açısından geniş kapsamlı sonuçlarıyla trafik kazaları küresel bir sorun olmaya devam ediyor. Türkiye Cumhuriyetinin 100. yılını kutlarken, trafik kazası şiddetini tahmin etmek, ulusal kentsel yenileme ve sürdürülebilir ilerleme hedefleriyle uyumlu kritik bir öneme sahiptir. Bu araştırma, kazaların şiddetini önceden tahmin etmek için makine öğrenimi yeteneklerini kullanıyor ve belirli sürücü ve araç özelliklerinin kritik rollerini vurgulamaktadır. Random Forest RF ve Gaussian Naive Bayesten k-NN, CatBoostClassifier, LightGBM ve Decision Treesa kadar çeşitli ML tekniklerinin derinlemesine değerlendirilmesi yapılmıştır; bu, bir dizi trafik durumunu yansıtan geniş bir veri kümesiyle gerçekleştirilmiştir. RF algoritması, Engine_Capacity_CC, Age_of_Driver, Age_of_Vehicle, Day_of_Week ve Vehicle_Type gibi belirli değişkenlerin kaza sonuçlarındaki belirleyici faktörler olarak öne çıktığı üstün öngörü yeteneğiyle dikkat çekmektedir. Kazaların şiddetini tahmin etmede RFnin potansiyelini vurgulamanın ötesinde, çalışma kritik belirleyicilerin önemini vurgulamaktadır. Bu içgörüler, paydaşların özelleştirilmiş müdahaleler tasarlamaları, kamuoyu farkındalık çalışmalarını güçlendirmeleri ve altyapıyı güncellemeleri için bir yol haritası sunar; bu, gelişmiş yol güvenliği vizyonuyla sonuçlanır. Ayrıca, bu araştırma, Türkiyenin bilgilendirilmiş kentsel ve trafik planlama girişimleri aracılığıyla sürdürülebilir bir kentsel yol çizmesi için bir yol haritası sunar.

Makale detayları

Predictive Modeling of Urban Traffic Accident Severity in Türkiye's Centennial: Machine Learning Approaches for Sustainable Cities

Yazarlar:

Adem Korkmaz

Yayıncı:

Ahmet FİDAN

Ana Başlıklar:

Kentsel Bilişim | Şehir ve Bölge Planlama | Coğrafi Bilgi Sistemleri

Dergi:

Kent Akademisi Vol.16 Issue Türkiye Cumhuriyetinin 100. Yılı Özel Sayısı | Special Issue for the 100th Anniversary of the Republic of Türkiye, pp.395-406

Belge Tipi:

Makale

Yayın Tarihi:

10/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001298425

pISSN:

2146-9229

Traffic Accidents

Severity Prediction

Machine Learning

Feature Importance

Driver Attributes

Road SafetyTrafik Kazaları

Şiddet Tahmini

Makine Öğrenimi

Özellik Önemi

Sürücü Özellikleri

Yol Güvenliği

Sayı

Makale detayları

Yazarlar: Adem Korkmaz

Yayıncı: Ahmet FİDAN

Ana Başlıklar: Kentsel Bilişim | Şehir ve Bölge Planlama | Coğrafi Bilgi Sistemleri

Dergi: Kent Akademisi Vol.16 Issue Türkiye Cumhuriyetinin 100. Yılı Özel Sayısı | Special Issue for the 100th Anniversary of the Republic of Türkiye, pp.395-406

Belge Tipi: Makale

Yayın Tarihi: 10/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001298425

pISSN: 2146-9229

Sayı

Yazarlar:

Adem Korkmaz

Yayıncı:

Ahmet FİDAN

Ana Başlıklar:

Kentsel Bilişim | Şehir ve Bölge Planlama | Coğrafi Bilgi Sistemleri

Dergi:

Kent Akademisi Vol.16 Issue Türkiye Cumhuriyetinin 100. Yılı Özel Sayısı | Special Issue for the 100th Anniversary of the Republic of Türkiye, pp.395-406

Belge Tipi:

Makale

Yayın Tarihi:

10/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001298425

pISSN:

2146-9229