Broccoli leaf diseases classification using support  vector machine with particle swarm optimization based on feature selection

Ferdinand, Yulio; Maki, Wikky Fawwaz Al

doi:10.26555/ijain.v8i3.951

Cited by 10 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SVM is one of the machine learning methods that is easy to implement. The parameter of SVM can be explored through hyperparameters [28]. In this system, SVM is employed to classify MRI images into four classes, namely, pituitary tumor, glioma tumor, meningioma tumor, and no tumor.…”

Section: Support Vector Machinementioning

confidence: 99%

Parameter Optimization of Support Vector Machine using River Formation Dynamic on Brain Tumor Classification

Cahya Kemila,

Fawwaz Al Maki

2023

j.electron.electromedical.eng.med.inform

View full text Add to dashboard Cite

Brain tumor is a condition that can interfece with brain function due to abnormal cell growth in the brain. MRI is used as a diagnostic tool when a patient has a brain tumor. The images obtained through MRI will be analyzed by the doctor to determine the type of tumor. Therefore, it is necessary to have a system that can classify tumor types based on MRI images. The image will be extracted using the HOG method, then classified using SVM. Certain measures can be taken to improve SVM performance, such as optimizing its parameters. This research develops a system that uses a novel combination, the SVM with the River Formation Dynamic (RFD) algorithm. RFD is being used to optimize parameters of SVM (C and gamma). The basic idea of RFD is to imitate the movement of water droplets flowing from high to low areas. This research compares the accuracy produced by SVM with the accuracy produced by SVM-RFD. The result is that SVM-RFD provides the better accuracy than only using SVM. The accuracy result by SVM on the MRI dataset is 74.37%. When we compared it with SVM-RFD, the accuracy increased by 13.19% to 87.56%. Further work will be carried out on the implementation of RFD on other SVM parameters to find other parameter combinations that can improve the accuracy of SVM.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Parameter Optimization of Support Vector Machine using River Formation Dynamic on Brain Tumor Classification

Cahya Kemila,

Fawwaz Al Maki

2023

j.electron.electromedical.eng.med.inform

View full text Add to dashboard Cite

show abstract

“…SVM sendiri memiliki keunggulan yaitu bekerja lebih baik dibanding metode klasifikasi lain pada dataset bersampel kecil, tidak linier dan memiliki kelas biner (Tao, Sun and Sun, 2018). Meski begitu, SVM memiliki kelemahan ketika diterapkan pada dataset dengan kelas yang tidak seimbang karena sulit mendapatkan hyperplane pemisah optimal (Cervantes et al, 2020;Huang et al, 2021) dan tidak bekerja dengan akurat ketika terlalu banyak fitur yang tidak relevan bagi metode klasifikasi digunakan (Hamid et al, 2021;Ferdinand and Al Maki, 2022).…”

unclassified

Penyeimbangan Kelas SMOTE dan Seleksi Fitur Ensemble Filter pada Support Vector Machine untuk Klasifikasi Penyakit Liver

Nugraha,

Mazdadi,

Farmadi

et al. 2023

JTIIK

View full text Add to dashboard Cite

Liver merupakan salah satu organ penting dalam tubuh manusia yang berperan dalam proses metabolisme tubuh. Mengutip artikel dari situs American Liver Foundation, pada tahun 2020 sebanyak 51.642 orang dewasa di Amerika Serikat meninggal akibat penyakit liver. Data hasil tes fungsi liver dari laboratorium dapat digunakan untuk mendiagnosis penyakit liver. Klasifikasi penyakit liver pada pasien perlu dilakukan dengan baik karena hasilnya dapat membantu dalam diagnosis awal apakah seorang pasien mengidap penyakit liver. Berdasarkan penelitian sebelumnya, metode Support Vector Machine (SVM) paling baik dalam mengklasifikasikan pasien penyakit liver. Namun, SVM memiliki kelemahan ketika diterapkan pada dataset dengan kelas yang tidak seimbang dan tidak bekerja secara akurat ketika terlalu banyak fitur yang tidak relevan digunakan. Untuk menyeimbangkan kelas pada dataset, digunakan metode Synthetic Minority Oversampling Technique (SMOTE). Sedangkan untuk seleksi fitur dilakukan menggunakan metode Ensemble Filter, terdiri dari metode Information Gain, Gain Ratio, dan Relief-F untuk menangani fitur-fitur tidak relevan. Berdasarkan hasil pengujian, penerapan SMOTE dan Ensemble Filter pada metode klasifikasi SVM memberikan hasil terbaik dengan nilai accuracy sebesar 85% dan AUC sebesar 0,850. Pengujian tersebut dapat membuktikan jika SMOTE pada penyeimbangan kelas dan Ensemble Filter pada seleksi fitur dapat meningkatkan performa klasifikasi dari metode SVM. Abstract The liver is one of the important organs in the human body that plays a role in the body's metabolic processes. Quoting an article from the American Liver Foundation website, in 2020, as many as 51,642 adults in the United States died from liver disease. Liver function test data from the laboratory can be used to diagnose liver disease. Classification of liver disease in patients needs to be done well because the results can help in the initial diagnosis of whether a patient has liver disease. Based on previous research, the Support Vector Machine (SVM) method best classifies liver disease patients. However, SVM has weaknesses when applied to datasets with unbalanced classes and does not work accurately when too many irrelevant features are used. To class-balance the dataset, the Synthetic Minority Oversampling Technique (SMOTE) method is used. Meanwhile, feature selection is performed using the Ensemble Filter method, which consists of Information Gain, Gain Ratio, and Relief-F methods to handle irrelevant features. Based on the test results, the application of SMOTE and Ensemble Filter in SVM classification gives the best results with an accuracy value of 85% and an AUC of 0.850. The test can prove if SMOTE on class balancing and Ensemble Filter on feature selection can improve the classification performance of the SVM method.

show abstract

Optimizing ‘Explorer’ Rose Production Data with SVM in Smart Agriculture

Herrera,

Lucero-Urresta,

Ilvis

et al. 2024

IFAC-PapersOnLine

View full text Add to dashboard Cite

Broccoli leaf diseases classification using support vector machine with particle swarm optimization based on feature selection

Cited by 10 publications

References 23 publications

Parameter Optimization of Support Vector Machine using River Formation Dynamic on Brain Tumor Classification

Parameter Optimization of Support Vector Machine using River Formation Dynamic on Brain Tumor Classification

Penyeimbangan Kelas SMOTE dan Seleksi Fitur Ensemble Filter pada Support Vector Machine untuk Klasifikasi Penyakit Liver

Optimizing ‘Explorer’ Rose Production Data with SVM in Smart Agriculture

Contact Info

Product

Resources

About