SMOTE-based method for balanced spectral nondestructive detection of moldy apple core

Zhang, Zhongxiong; Liu, Haoling; Chen, Danyan; Zhang, Junhua; Li, Hao; Shen, Maosheng; Pu, Yuge; Zhang, Zuojing; Zhao, Juan; Jin, Haiyan

doi:10.1016/j.foodcont.2022.109100

Cited by 18 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Balanced distribution and representative experimental samples were the keys to construct classification models for dried Hami jujube. Oversampling techniques combined with appropriate machine learning models can solve the class imbalance problem and further improve the classification performance of the model [ 18 ]. In this study, BL-SMOTE and ADASYN improved the model significantly, and BL-SMOTE was slightly better.…”

Section: Discussionmentioning

confidence: 99%

“…Begum et al [ 17 ] used the oversampling algorithm to process imbalance data in coal samples and demonstrated its effectiveness. Similarly, the oversampling algorithms were used for the detection of moldy apple core [ 18 ]. Still, few studies have focused on the effects of different oversampling strategies on the classification performance of the model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling

et al. 2022

Foods

View full text Add to dashboard Cite

Dried Hami jujube has great commercial and nutritional value. Starch-head and mildewed fruit are defective jujubes that pose a threat to consumer health. A novel method for detecting starch-head and mildewed fruit in dried Hami jujubes with visible/near-infrared spectroscopy was proposed. For this, the diffuse reflectance spectra in the range of 400–1100 nm of dried Hami jujubes were obtained. Borderline synthetic minority oversampling technology (BL-SMOTE) was applied to solve the problem of imbalanced sample distribution, and its effectiveness was demonstrated compared to other methods. Then, the feature variables selected by competitive adaptive reweighted sampling (CARS) were used as the input to establish the support vector machine (SVM) classification model. The parameters of SVM were optimized by the modified reptile search algorithm (MRSA). In MRSA, Tent chaotic mapping and the Gaussian random walk strategy were used to improve the optimization ability of the original reptile search algorithm (RSA). The final results showed that the MRSA-SVM method combined with BL-SMOTE had the best classification performance, and the detection accuracy reached 97.22%. In addition, the recall, precision, F1 and kappa coefficient outperform other models. Furthermore, this study provided a valuable reference for the detection of defective fruit in other fruits.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling

et al. 2022

Foods

View full text Add to dashboard Cite

show abstract

“…Data yang tidak seimbang perlu ditangani karena data tidak seimbang dapat mengakibatkan kesalahan prediksi sehingga dapat mempengaruhi akurasi model [19]. Teknik yang dapat digunakan untuk mengatasi masalah data tidak seimbang yaitu: teknik undersampling dan teknik oversampling [20]. SMOTE adalah sebuah teknik yang kurang lebih sama dengan teknik oversampling.…”

Section: Data Tidak Seimbangunclassified

“…SMOTE adalah sebuah teknik yang kurang lebih sama dengan teknik oversampling. SMOTE tidak hanya menduplikasi data yang sama akan tetapi SMOTE akan membuat data baru yang menyerupai data asli dari kelas minoritas untuk menyeimbangkan data, sehingga data baru dari kelas minoritas jauh lebih beragam [18,20]. Pengunaan SMOTE dalam data berdimensi rendah (jumlah variabel jauh lebih sedikit dibanding jumlah amatan) sangat efektif dalam penanganan kelas yang tidak seimbang, sedang pada data berdimensi tinggi (jumlah variabel jauh lebih banyak dibanding jumlah amatan) penggunaan SMOTE kurang efektif [18].…”

Section: Data Tidak Seimbangunclassified

Synthetic Minority Oversampling Technique Pada Model Logit dan Probit Status Pengangguran Terdidik

et al. 2023

View full text Add to dashboard Cite

Educated unemployment is caused by a misalignment of educational development planning and employment development, resulting in underemployed graduates from various educational institutions. Unemployment data in DKI Jakarta shows an unequal class. Unbalanced data is a severe problem of modeling because it can cause prediction errors that affect the accuracy of the resulting model. Using SMOTE to handle unbalanced data will likely increase the model’s accuracy. This study aims to find the best model for identifying the factors influencing the status of educated unemployment using logit and probit models and handling unbalanced data using SMOTE. The results showed that the independent variables that affect the status of educated unemployment in the logit and probit models are the same: age group and participation in training. The independent variables that affect the status of educated unemployment in the logit and probit models with SMOTE are also the same: age group, marital status, and participation in training. Unbalanced data handling using SMOTE can increase the balanced accuracy value significantly. Balanced accuracy values for the logit and probit models with SMOTE are higher than the logit and probit models without SMOTE. The logit model with SMOTE is the best because it has the highest balanced accuracy value compared to other models. According to the logit model with SMOTE, the educated unemployed in DKI Jakarta are young and have never married. There is a need for the government to play a role in improving the quality of educational institutions in producing graduates who meet company qualifications and can be hired by employers. Unemployed people who have attended the training, despite having a higher education, may also become unemployed. The training provided has not been able to reduce the unemployment rate. As a result, the government should be able to provide training to improve entrepreneurship skills while also providing capital in the form of business loans to reduce educated unemployment.

show abstract

“…yeni üretilen verilerin örneklem olarak alınan verilere yakın olduğu söylenebilir. İlgili yöntem sayesinde, rastgele aşırı örneklemenin sebep olduğu aşırı öğrenme ve rastgele yetersiz örneklemenin neden olduğu bilgi kaybı gibi istenmeyen durumların(Zhang et al, 2022) çözülebilmesi için yapay veriler oluşturularak veri setinin dengelenmesi sağlanır. SMOTE'nin kullanılmasındaki neden onun rastgele örnekleme yöntemlerine kıyasla sahip olduğu avantajlarıdır.…”

unclassified

Mamdani ve Sugeno Tip Bulanık Çıkarım Sistemleri ile Sosyal Medya Haber Popülerliğinin Tahmini

Atacak

ŞENCAN

2022

IJERAD

View full text Add to dashboard Cite

Haber popülerliği, internet ya da sosyal ağ sitelerinde yayınlanmış haberlerin ilgi düzeyinin ölçüsünün bir göstergesidir. Bu göstergenin değerinin bilinmesi, haber sağlayıcılarını rekabetçi ve kullanıcılar için okunabilirliği yüksek haberler yapmaya zorlar. Bu durum, hem haber servislerinin sürekliliğine hem de haber kalitesinin artırılmasına önemli katkılar sağlar. Bu yüzden, haber popülerliğini otomatik olarak tespit eden sistemlerin olması günümüzde bir ihtiyaç haline gelmiştir. Bu çalışmada, Kaliforniya Üniversitesi (KU)-Irvine Makine Öğrenmesi Deposu veri tabanından indirilen veriler bileştirilerek oluşturulmuş dengesiz veri seti ve bu veri setinden Sentetik Azınlık Örnekleme Tekniği (Synthetic Minority Oversampling Technique (SMOTE)) ile üretilen dengeli veri setine Mamdani ve Sugeno tip bulanık çıkarım sistemi temelli modeller uygulanarak haber popülerliği tahmini yapılmıştır. Haber popülerliği tahmininde çıkarım yöntemleri ve durulaştırma yöntemlerinin farklı biçimde yapılandırılmasından oluşan 6’ sı mamdani tip bulanık çıkarım sistemini ve 2’ si sugeno tip bulanık çıkarım sistemini içeren toplam 8 bulanık mantık temellli tahmin modeli kullanılmıştır. Karışıklık matrisi metrikleri ve R2 eğrileri ile performansları değerlendirilen tahmin modellerine ait deneysel sonuçlar; dengesiz ve dengeli veri setlerinin her ikisinde de tüm metrikler açısından en iyi performansı mak-min çıkarım yöntemi ve ağırlık merkezi durulaştırma yöntemini kullanan Mamdani tip bulanık çıkarım sisteminin sağladığını göstermiştir. Ayrıca yaptığımız çalışmada kullanılan modelleri literatürdeki çalışmalar ile karşılaştırdığımızda, ağırlıklı ortalama yöntemini kullanan Sugeno tip bulanık çıkarım sistemi dışındaki bulanık mantık temelli modellerin literatürdeki modellerin en iyileri kadar rekabetçi bir performans sergileyebildiği görülmüştür.

show abstract

SMOTE-based method for balanced spectral nondestructive detection of moldy apple core

Cited by 18 publications

References 43 publications

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling

Synthetic Minority Oversampling Technique Pada Model Logit dan Probit Status Pengangguran Terdidik

Mamdani ve Sugeno Tip Bulanık Çıkarım Sistemleri ile Sosyal Medya Haber Popülerliğinin Tahmini

Contact Info

Product

Resources

About