Classification of Lubricating Oil Types Using Mid-Infrared Spectroscopy Combined with Linear Discriminant Analysis–Support Vector Machine Algorithm

Abstract

To realize the classification of lubricating oil types using mid-infrared (MIR) spectroscopy, linear discriminant analysis (LDA) was used for the dimensionality reduction of spectrum data, and the classification model was established based on the support vector machine (SVM). The spectra of the samples were pre-processed by interval selection, Savitzky–Golay smoothing, multiple scattering correction, and normalization. The Kennard–Stone algorithm (K/S) was used to construct the calibration and validation sets. The percentage of correct classification (%CC) was used to evaluate the model. This study compared the results obtained with several chemometric methods: PLS-DA, LDA, principal component analysis (PCA)-SVM, and LDA-SVM in MIR spectroscopy applications. In both calibration and verification sets, the LDA-SVM model achieved 100% favorable results. The PLS-DA analysis performed poorly. The cyclic resistance ratio (CRR) of the calibration set was classified via the LDA and PCA-SVM analysis as 100%, but the CRR of the verification set was not as good. The LDA-SVM model was superior to the other three models; it exhibited good robustness and strong generalization ability, providing a new method for the classification of lubricating oil types by MIR spectroscopy.

Sistem Rekomendasi Penerima Bantuan Sosial APBD Menggunakan Metode Support Vector Machine

“…Moch. Yazid 1 , Dian Ahkam Sani 2,* , Nanda Martyan Anggadimas 3 Program Studi Informatika, Universitas Merdeka Pasuruan, Indonesia 1 yazid@gmail.com; 2 dian.ahkam@unmerpas.ac.id; 3 Pemberian bantuan sosial APBD (Anggaran Pendapatan dan Belanja Daerah) merupakan aspek krusial dalam upaya pemerintah untuk mendukung masyarakat yang membutuhkan. Untuk meningkatkan efektivitas dan efisiensi dalam penentuan penerima bantuan, perancangan sistem rekomendasi menjadi suatu kebutuhan.…”

“…Salah satu metode klasifikasi pada machine learning yang dapat digunakan adalah metode Support Vector Machine. Metode Support Vector Machine (SVM) merupakan metode jenis supervised learning yang bekerja menggunakan pemetaan nonlinear antar variabel dan menentukan jarak menggunakan support vector sehingga proses komputasi menjadi cepat [3]. Disamping itu metode SVM juga memiliki kemampuan untuk menangani data dengan jumlah variabel yang banyak [4].…”

Selecting lubricating oil for two-stroke gasoline engines: a multi-criteria decision-making approach

“…Several recent studies on lubricant selection have been published. In [3], lubricant classification was conducted using spectral analysis, involving the use of infrared rays to examine Engineering lubricant surfaces. Complex algorithms like Support Vector Machine (SVM) and Kennard-Stone (K/S) were employed to interpret the received signals, a task demanding a high level of expertise and modern equipment.…”