Modeling quality changes in heat-processed orange juice: a comparative study of artificial neural network and multiple linear regression approaches

Asiye Akyıldız; Tüba Şimşek Mertoğlu; Nuray İnan Çınkır; Erdal Ağçam

Makale detayları

Modeling quality changes in heat-processed orange juice: a comparative study of artificial neural network and multiple linear regression approaches

Yazarlar:

Asiye Akyıldız | Tüba Şimşek Mertoğlu | Nuray İnan Çınkır | Erdal Ağçam

Yayıncı:

Harran University

Ana Başlıklar:

Meyve-Sebze Teknolojisi

Dergi:

Harran Tarım ve Gıda Bilimleri Dergisi Vol.29 Issue 2, pp.237-254

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001350134

pISSN:

2587-1358

Anahtar kelimeler:

Özet:

 The purpose of the study was to assess the prediction ability of multiple linear regression MLR and artificial neural network ANN models for the browning index, total carotenoid content, 5-hydroxymethylfurfural HMF and ascorbic acid of orange juice during storage after heat processing. For ANN models, the effect of neuron number of the hidden layer, epoch number, training algorithms and transfer functions are investigated using the trial-error method for selecting best design ANN models. The different methods stepwise and enter in multiple linear regression models were performed for detecting impact of independent variables on dependent variables. The performance of ANN and MLR models was determined through unseen data by means of statistical analysis. Regarding performance indices of ANN models for test data, overall R and R2 were recorded as follows: 0.92 and 0.84 browning index, 0.99 and 0.98 HMF, 0.92 and 0.86 ascorbic acid, 0.97 and 0.94 total carotenoid content, respectively. R and R2 values of MLR models for test data were 0.79 and 0.68 browning index, 0.94 and 0.88 HMF, 0.92 and 0.85 ascorbic acid, 0.93 and 0.90 total carotenoid content, respectively. Both models provided accurate predictions. However, the superior predictive power of ANN models is that they can learn directly from examples without calculating the parameters using statistical techniques. The results revealed that ANN models showed greater potential with high R and R2 value, and the lowest error values when compared with the MLR model, but both ANN and MLR had almost same performance for prediction of ascorbic acid.

 The purpose of the study was to assess the prediction ability of multiple linear regression MLR and artificial neural network ANN models for the browning index, total carotenoid content, 5-hydroxymethylfurfural HMF and ascorbic acid of orange juice during storage after heat processing. For ANN models, the effect of neuron number of the hidden layer, epoch number, training algorithms and transfer functions are investigated using the trial-error method for selecting best design ANN models. The different methods stepwise and enter in multiple linear regression models were performed for detecting impact of independent variables on dependent variables. The performance of ANN and MLR models was determined through unseen data by means of statistical analysis. Regarding performance indices of ANN models for test data, overall R and R2 were recorded as follows: 0.92 and 0.84 browning index, 0.99 and 0.98 HMF, 0.92 and 0.86 ascorbic acid, 0.97 and 0.94 total carotenoid content, respectively. R and R2 values of MLR models for test data were 0.79 and 0.68 browning index, 0.94 and 0.88 HMF, 0.92 and 0.85 ascorbic acid, 0.93 and 0.90 total carotenoid content, respectively. Both models provided accurate predictions. However, the superior predictive power of ANN models is that they can learn directly from examples without calculating the parameters using statistical techniques. The results revealed that ANN models showed greater potential with high R and R2 value, and the lowest error values when compared with the MLR model, but both ANN and MLR had almost same performance for prediction of ascorbic acid.

 The purpose of the study was to assess the prediction ability of multiple linear regression MLR and artificial neural network ANN models for the browning index, total carotenoid content, 5-hydroxymethylfurfural HMF and ascorbic acid of orange juice during storage after heat processing. For ANN models, the effect of neuron number of the hidden layer, epoch number, training algorithms and transfer functions are investigated using the trial-error method for selecting best design ANN models. The different methods stepwise and enter in multiple linear regression models were performed for detecting impact of independent variables on dependent variables. The performance of ANN and MLR models was determined through unseen data by means of statistical analysis. Regarding performance indices of ANN models for test data, overall R and R2 were recorded as follows: 0.92 and 0.84 browning index, 0.99 and 0.98 HMF, 0.92 and 0.86 ascorbic acid, 0.97 and 0.94 total carotenoid content, respectively. R and R2 values of MLR models for test data were 0.79 and 0.68 browning index, 0.94 and 0.88 HMF, 0.92 and 0.85 ascorbic acid, 0.93 and 0.90 total carotenoid content, respectively. Both models provided accurate predictions. However, the superior predictive power of ANN models is that they can learn directly from examples without calculating the parameters using statistical techniques. The results revealed that ANN models showed greater potential with high R and R2 value, and the lowest error values when compared with the MLR model, but both ANN and MLR had almost same performance for prediction of ascorbic acid.

 Çalışmanın amacı, ısıl işlemden sonra depolama sırasında portakal suyunun esmerleşme indeksi, 5-hidroksimetilfurfural HMF, askorbik asit ve toplam karotenoid içeriği için çoklu doğrusal regresyon MLR ve yapay sinir ağı ANN modellerinin tahmin yeteneğini değerlendirmektir. En iyi tasarım YSA modellerini seçmek için gizli katmandaki nöron sayısının, epok sayısının, eğitim algoritmalarının ve transfer fonksiyonlarının etkisi deneme-yanılma yöntemi kullanılarak araştırılmıştır. Tüm bağımsız değişkenlerin bağımlı değişkenler üzerindeki etkisini tespit etmek için çoklu doğrusal regresyon modellerindeki farklı yöntemler stepwise ve enter uygulanmıştır. ANN ve MLR modellerinin performansı istatistiksel analiz yoluyla test verileri kullanılarak değerlendirilmiştir. Test verileri için ANN modellerinin performans endekslerine ilişkin olarak, genel R ve R2 sırasıyla; 0,92 ve 0,84 esmerleşme indeksi, 0,99 ve 0,98 HMF, 0,92 ve 0,86 askorbik asit, 0,97 ve 0,94 toplam karotenoid içeriği belirlenmiştir. Test verileri için MLR modellerinin R ve R2 değerleri sırasıyla 0,79 ve 0,68 esmerleşme indeksi, 0,94 ve 0,88 HMF, 0,92 ve 0,85 askorbik asit, 0,93 ve 0,90 toplam karotenoid içeriği olarak tespit edilmiştir. YSA modellerinin üstün tahmin gücü, istatistiksel teknikler kullanarak parametreleri hesaplamaya gerek kalmadan doğrudan örneklerden öğrenebilmeleridir. Sonuçlar, ANN modelinin yüksek R ve R2 değeri, ve düşük hata değerleri ile MLR modellerine kıyasla daha büyük potansiyel göstermiştir. Askorbik asit için hem ANN hem de MLRnin tahminleme performansı neredeyse aynı düzeyde olduğu belirlenmiştir.

Makale detayları

Modeling quality changes in heat-processed orange juice: a comparative study of artificial neural network and multiple linear regression approaches

Yazarlar:

Asiye Akyıldız | Tüba Şimşek Mertoğlu | Nuray İnan Çınkır | Erdal Ağçam

Yayıncı:

Harran University

Ana Başlıklar:

Meyve-Sebze Teknolojisi

Dergi:

Harran Tarım ve Gıda Bilimleri Dergisi Vol.29 Issue 2, pp.237-254

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001350134

pISSN:

2587-1358

Artificial neural network

multiple linear regression

orange juice

color

modellingYapay sinir ağı

çoklu doğrusal regresyon

portakal suyu

renk

modelleme

Sayı

Makale detayları

Yazarlar: Asiye Akyıldız | Tüba Şimşek Mertoğlu | Nuray İnan Çınkır | Erdal Ağçam

Yayıncı: Harran University

Ana Başlıklar: Meyve-Sebze Teknolojisi

Dergi: Harran Tarım ve Gıda Bilimleri Dergisi Vol.29 Issue 2, pp.237-254

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001350134

pISSN: 2587-1358

Sayı

Yazarlar:

Asiye Akyıldız | Tüba Şimşek Mertoğlu | Nuray İnan Çınkır | Erdal Ağçam

Yayıncı:

Harran University

Ana Başlıklar:

Meyve-Sebze Teknolojisi

Dergi:

Harran Tarım ve Gıda Bilimleri Dergisi Vol.29 Issue 2, pp.237-254

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001350134

pISSN:

2587-1358