Artificial Intelligence in Recycling: Waste Management with Convolutional Neural Networks

Muhammed Akif Yenikaya

Makale detayları

Artificial Intelligence in Recycling: Waste Management with Convolutional Neural Networks

Yazarlar:

Muhammed Akif Yenikaya

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Sanayi Ekonomisi

Dergi:

Fiscaoeconomia Vol.9 Issue 2, pp.1225-1236

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348891

pISSN:

2564-7504

Anahtar kelimeler:

Özet:

 The rapid growth of urbanization and economic development has led to a significant increase in household waste, highlighting the necessity for developing sustainable waste management processes. Traditional waste sorting methods are based on manual processes, leading to high labor costs and low efficiency. This makes waste management systems less environmentally and economically sustainable, especially in densely populated areas. Furthermore, these methods reduce the efficiency of recycling processes and waste valuable resources by making it difficult to correctly sort waste by type. The time-consuming nature of manual methods and the risk of human error necessitate technological solutions to improve these processes. In this context, artificial intelligence-based technologies play an important role in waste management processes. Artificial intelligence reduces costs and increases efficiency by minimizing human errors through fast and accurate sorting processes. This study employed a publicly accessible dataset containing 22,564 images classified as recyclable and organic waste to train Convolutional Neural Network CNN models. The models performance was assessed using metrics such as validation accuracy and validation loss. The findings indicate that the Optimized Convolutional Neural Network OCNN model achieved superior generalization capacity with a validation accuracy of 90.41, outperforming the traditional CNN model, which attained 88.26. This study aims to increase environmental sustainability and improve economic efficiency in waste management by using innovative methods. The proposed approaches are developed to increase the efficiency of waste classification processes, thereby supporting the conservation of natural resources and promoting higher recycling rates.

 The rapid growth of urbanization and economic development has led to a significant increase in household waste, highlighting the necessity for developing sustainable waste management processes. Traditional waste sorting methods are based on manual processes, leading to high labor costs and low efficiency. This makes waste management systems less environmentally and economically sustainable, especially in densely populated areas. Furthermore, these methods reduce the efficiency of recycling processes and waste valuable resources by making it difficult to correctly sort waste by type. The time-consuming nature of manual methods and the risk of human error necessitate technological solutions to improve these processes. In this context, artificial intelligence-based technologies play an important role in waste management processes. Artificial intelligence reduces costs and increases efficiency by minimizing human errors through fast and accurate sorting processes. This study employed a publicly accessible dataset containing 22,564 images classified as recyclable and organic waste to train Convolutional Neural Network CNN models. The models performance was assessed using metrics such as validation accuracy and validation loss. The findings indicate that the Optimized Convolutional Neural Network OCNN model achieved superior generalization capacity with a validation accuracy of 90.41, outperforming the traditional CNN model, which attained 88.26. This study aims to increase environmental sustainability and improve economic efficiency in waste management by using innovative methods. The proposed approaches are developed to increase the efficiency of waste classification processes, thereby supporting the conservation of natural resources and promoting higher recycling rates.

 The rapid growth of urbanization and economic development has led to a significant increase in household waste, highlighting the necessity for developing sustainable waste management processes. Traditional waste sorting methods are based on manual processes, leading to high labor costs and low efficiency. This makes waste management systems less environmentally and economically sustainable, especially in densely populated areas. Furthermore, these methods reduce the efficiency of recycling processes and waste valuable resources by making it difficult to correctly sort waste by type. The time-consuming nature of manual methods and the risk of human error necessitate technological solutions to improve these processes. In this context, artificial intelligence-based technologies play an important role in waste management processes. Artificial intelligence reduces costs and increases efficiency by minimizing human errors through fast and accurate sorting processes. This study employed a publicly accessible dataset containing 22,564 images classified as recyclable and organic waste to train Convolutional Neural Network CNN models. The models performance was assessed using metrics such as validation accuracy and validation loss. The findings indicate that the Optimized Convolutional Neural Network OCNN model achieved superior generalization capacity with a validation accuracy of 90.41, outperforming the traditional CNN model, which attained 88.26. This study aims to increase environmental sustainability and improve economic efficiency in waste management by using innovative methods. The proposed approaches are developed to increase the efficiency of waste classification processes, thereby supporting the conservation of natural resources and promoting higher recycling rates.

 Kentleşme ve ekonomik kalkınmadaki hızlı büyüme, evsel atıklarda önemli bir artışa yol açarak sürdürülebilir atık yönetimi süreçlerinin geliştirilmesi gerekliliğini ortaya koymuştur. Geleneksel atık ayrıştırma yöntemleri manuel süreçlere dayanmakta, bu ise yüksek işçilik maliyetlerine ve düşük verimliliğe yol açmaktadır. Bu durum, özellikle yoğun nüfuslu bölgelerde atık yönetim sistemlerini çevresel ve ekonomik açıdan daha az sürdürülebilir kılmaktadır. Ayrıca, bu yöntemler geri dönüşüm süreçlerinin verimliliğini azaltmakta ve atıkların türlerine göre doğru şekilde ayrılmasını zorlaştırarak değerli kaynakları israf etmektedir. Manuel yöntemlerin zaman alıcı doğası ve insan hatası riski, bu süreçleri iyileştirmek için teknolojik çözümler gerektirmektedir. Bu bağlamda, yapay zekâ tabanlı teknolojiler, atık yönetimi süreçlerinde önemli bir rol üstlenmektedir. Yapay zekâ, hızlı ve doğru ayrıştırma süreçleri sayesinde insan hatalarını en aza indirerek maliyetleri düşürmekte ve verimliliği artırmaktadır. Bu çalışmada, Evrişimsel Sinir Ağı Convolutional Neural Network-CNN modellerini eğitmek için geri dönüştürülebilir ve organik atık olarak sınıflandırılmış 22.564 görüntü içeren halka açık bir veri kümesi kullanılmıştır. Modellerin performansı, doğrulama doğruluğu ve doğrulama kaybı gibi ölçütler kullanılarak değerlendirilmiştir. Bulgular, Optimize Edilmiş Evrişimsel Sinir Ağı Optimized Convolutional Neural Network-OCNN modelinin 90,41lik bir doğrulama doğruluğu ile üstün genelleme kapasitesi elde ettiğini ve 88,26ya ulaşan geleneksel CNN modelinden daha iyi performans gösterdiğini ortaya koymaktadır. Bu çalışma, yenilikçi yöntemler kullanarak atık yönetiminde çevresel sürdürülebilirliği artırmayı ve ekonomik verimliliği iyileştirmeyi amaçlamaktadır. Önerilen yaklaşımlar, atık sınıflandırma süreçlerinin verimliliğini artırmak, böylece doğal kaynakların korunmasını desteklemek ve daha yüksek geri dönüşüm oranlarını teşvik etmek için geliştirilmiştir.

Makale detayları

Artificial Intelligence in Recycling: Waste Management with Convolutional Neural Networks

Yazarlar:

Muhammed Akif Yenikaya

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Sanayi Ekonomisi

Dergi:

Fiscaoeconomia Vol.9 Issue 2, pp.1225-1236

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348891

pISSN:

2564-7504

Waste management

Recycling

Economic Sustainability

Digital Transformation

Artificial IntelligenceAtık Yönetimi

Geri Dönüşüm

Ekonomik Sürdürülebilirlik

Dijital Dönüşüm

Yapay Zekâ

Sayı

Makale detayları

Yazarlar: Muhammed Akif Yenikaya

Yayıncı: Ahmet Arif EREN

Ana Başlıklar: Sanayi Ekonomisi

Dergi: Fiscaoeconomia Vol.9 Issue 2, pp.1225-1236

Belge Tipi: Makale

Yayın Tarihi: 5/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001348891

pISSN: 2564-7504

Sayı

Yazarlar:

Muhammed Akif Yenikaya

Yayıncı:

Ahmet Arif EREN

Ana Başlıklar:

Sanayi Ekonomisi

Dergi:

Fiscaoeconomia Vol.9 Issue 2, pp.1225-1236

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348891

pISSN:

2564-7504