Adaptive Dimensionality Adjustment for Online “Principal Component Analysis”

Migenda, Nico; Möller, Ralf; Schenck, Wolfram

doi:10.1007/978-3-030-33607-3_9

Cited by 4 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA juga merupakan salah satu algoritma yang dapat mengkarakterisasi subruang. Transformasi ortonormal pada PCA menghasilkan variable linear independen dari kumpulan data yang memiliki potensi untuk dikorelasikan (Migenda, Möller, and Schenck 2019). PCA juga merupakan metode statistik yang menggantikan banyak elemen asli dengan beberapa elemen penting .…”

Section: Algoritma Pcaunclassified

Implementasi Algoritma Principal Component Analysis (Pca) Dan K-Nearest Neighbor (Knn) Untuk Memprediksi Kelayakan Kredit Pengguna Smartphone Di Indonesia Pada Masa Pandemi Covid-19

Winahyu,

Saputro

2023

JUDA

View full text Add to dashboard Cite

Dalam penelitian ini, kami bertujuan untuk memprediksi kelayakan kredit pengguna smartphone di Indonesia selama masa Pandemi COVID-19 menggunakan algoritma machine learning. Algoritma Principal Component Analysis (PCA) dan K-means digunakan untuk mereduksi dimensi dataset dan mengelompokkan kelayakan kredit dari sejumlah 1050 data set responden yang terdiri dari dua belas pertanyaan kepada pengguna smartphone di Indonesia selama pandemi COVID-19. Algoritma klasifikasi K-Nearest Neighbor (KNN) juga digunakan untuk mengklasifikasikan kelayakan kredit pengguna smartphone di Indonesia. Pengujian yang dilakukan meliputi pengujian akurasi, presisi, recall, dan F1-score. Hasil dari penelitian ini menunjukkan bahwa algoritma klasifikasi K-Nearest Neighbor memiliki akurasi sebesar 0.85, presisi sebesar 0.87, recall 0.84, dan F1 score sebesar 0.85 dalam mengklasifikasikan kelayakan kredit pengguna smartphone di Indonesia pada masa pandemi COVID-19.

show abstract

Section: Algoritma Pcaunclassified

Implementasi Algoritma Principal Component Analysis (Pca) Dan K-Nearest Neighbor (Knn) Untuk Memprediksi Kelayakan Kredit Pengguna Smartphone Di Indonesia Pada Masa Pandemi Covid-19

Winahyu,

Saputro

2023

JUDA

View full text Add to dashboard Cite

show abstract

“…Streaming data is possibly subject to noise, drift or other influences, so that the optimal dimensionality has to be adjusted continuously in order to maintain the desired amount of variance in PCA. Therefore, for an online method to be effective, it is necessary to continuously add or remove dimensions with each data point when appropriate [6]. Existing methods in neural network-based PCA [7] and incremental PCA [8,9] are limited to an increment of one and are therefore unable to account for abrupt changes in data variance.…”

Section: Problem Statementmentioning

confidence: 99%

Adaptive dimensionality reduction for neural network-based online principal component analysis

2021

Self Cite

View full text Add to dashboard Cite

“Principal Component Analysis” (PCA) is an established linear technique for dimensionality reduction. It performs an orthonormal transformation to replace possibly correlated variables with a smaller set of linearly independent variables, the so-called principal components, which capture a large portion of the data variance. The problem of finding the optimal number of principal components has been widely studied for offline PCA. However, when working with streaming data, the optimal number changes continuously. This requires to update both the principal components and the dimensionality in every timestep. While the continuous update of the principal components is widely studied, the available algorithms for dimensionality adjustment are limited to an increment of one in neural network-based and incremental PCA. Therefore, existing approaches cannot account for abrupt changes in the presented data. The contribution of this work is to enable in neural network-based PCA the continuous dimensionality adjustment by an arbitrary number without the necessity to learn all principal components. A novel algorithm is presented that utilizes several PCA characteristics to adaptivly update the optimal number of principal components for neural network-based PCA. A precise estimation of the required dimensionality reduces the computational effort while ensuring that the desired amount of variance is kept. The computational complexity of the proposed algorithm is investigated and it is benchmarked in an experimental study against other neural network-based and incremental PCA approaches where it produces highly competitive results.

show abstract

Adaptive Dimensionality Reduction for Local Principal Component Analysis

Migenda

Schenck

2020

2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

View full text Add to dashboard Cite

Adaptive Dimensionality Adjustment for Online “Principal Component Analysis”

Cited by 4 publications

References 11 publications

Implementasi Algoritma Principal Component Analysis (Pca) Dan K-Nearest Neighbor (Knn) Untuk Memprediksi Kelayakan Kredit Pengguna Smartphone Di Indonesia Pada Masa Pandemi Covid-19

Implementasi Algoritma Principal Component Analysis (Pca) Dan K-Nearest Neighbor (Knn) Untuk Memprediksi Kelayakan Kredit Pengguna Smartphone Di Indonesia Pada Masa Pandemi Covid-19

Adaptive dimensionality reduction for neural network-based online principal component analysis

Adaptive Dimensionality Reduction for Local Principal Component Analysis

Contact Info

Product

Resources

About