Automatic Grouping in Singular Spectrum Analysis

Kalantari, Mahdi; Hassani, Hossein

doi:10.3390/forecast1010013

Cited by 18 publications

(8 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Analisis spektrum singular (SSA) ini juga dapat digunakan untuk menguraikan rangkaian waktu musiman yang kompleks menjadi beberapa komponen yang lebih sederhana dan lebih mudah diinterpretasikan. Dalam sudut pandang machine learning, identifikasi kelompok secara manual pada SSA dapat dianggap sebagai kerugian karena adanya intervensi seorang analis yang diperlukan, sehingga pendekatan alternatif yang lebih dioptimalkan adalah dengan menerapkan metode pengelompokan otomatis (Automatic grouping) [3]. Pemodelan SSA dengan fleksibilitas dan akurasi yang baik menyebabkan penulis memilih pemodelan automatisasi SSA sebagai alat untuk meramalkan data Indeks Harga Saham Gabungan di Indonesia.…”

Section: Pendahuluanunclassified

Penerapan Metode Auto Singular Spectrum Analysis Pada Peramalan Data Indeks Harga Saham Gabungan Di Indonesia

Chrisantama

Sulandari

Sugiyanto

2022

puc

View full text Add to dashboard Cite

Keinginan dari seseorang untuk memenuhi kebutuhan serta permintaan dalamaktivitasnya setiap hari akan semakin banyak, apalagi sekarang di dalam masa kehidupanpandemik ini banyak masyarakat yang ingin meningkatkan kembali ekonomi mereka. Makadari itu diperlukan penanda dari pergerakan pasar saham untuk mengukur kinerja seluruhsaham yang tercatat di papan utama, yang merupakan asal terciptanya dari Indeks HargaSaham Gabungan (IHSG). Peramalan indeks harga saham ini penting bagi masyarakat yangingin mengukur kinerja portofolio dari investasi mereka serta bagi negara yangmengandalkan IHSG dalam menunjukkan pertumbuhan ekonomi Indonesia. Tujuan daripenelitian ini adalah menerapkan metode autoSSA yang merupakan pembuatan grup barusecara otomatis pada data yang sudah direkonstruksi untuk melihat nilai prediksi yang akandatang dari indikator yang sudah diambil. Metode autoSSA dipilih karena teknik projektifsecara tradisional tidak dapat langsung diterapkan pada sinyal one-dimensional., yangmerupakan kasus time series. Indikator IHSG yang digunakan adalah data Indeks mingguanpada tahun 2018 hingga 2020. Tahap-tahap untuk melakukan prediksi dengan metode iniantara lain membuat serta memeriksa plot data deret waktu yang telah diambil, melakukantahap dekomposisi serta merekonstruksi kembali data time series yang baru, dan akandilakukan peramalan data time series dalam 50 minggu ke depan dari model data yang telahdidapatkan untuk melihat pergerakan IHSG ke depannya. Hasil prediksi yang didapatkandari metode ini menunjukkan adanya pergantian fluktuasi secara musiman (seasonal)dengan nilai tertinggi berada di minggu ke-29 dan nilai terendah berada di minggu ke-50.

show abstract

Section: Pendahuluanunclassified

Penerapan Metode Auto Singular Spectrum Analysis Pada Peramalan Data Indeks Harga Saham Gabungan Di Indonesia

Chrisantama

Sulandari

Sugiyanto

2022

puc

View full text Add to dashboard Cite

show abstract

“…For work in this paper, we will present distance matrices by rendering the elements dµ,ν rather than wµ,ν for interpretative consistency with our k-means classifier. (Kalantari & Hassani 2019) advocated using hierarchical clustering methods which sensible but we have not explored this here. We will refer to groups defined by the distance between reconstructed trajectories for the eigenpairs.…”

Section: Separabilitymentioning

confidence: 99%

Using Multichannel Singular Spectrum Analysis to Study Galaxy Dynamics

Weinberg,

Petersen

2020

Preprint

View full text Add to dashboard Cite

N -body simulations provide most of our insight into the structure and evolution of galaxies, but our analyses of these are often heuristic and from simple statistics. We propose a method that discovers the dynamics in space and time together by finding the most correlated temporal signals in multiple time series of basis function expansion coefficients and any other data fields of interest. The method extracts the dominant trends in the spatial variation of the gravitational field along with any additional data fields through time. The mathematics of this method is known as multichannel singular spectrum analysis (M-SSA). In essence, M-SSA is a principal component analysis of the covariance of time series replicates, each lagged successively by some interval. The dominant principal component represents the trend that contains the largest fraction of the correlated signal. The next principal component is orthogonal to the first and contains the next largest fraction, and so on. Using a suite of previously analysed simulations, we find that M-SSA describes bar formation and evolution, including mode coupling and pattern-speed decay. We also analyse a new simulation tailored to study vertical oscillations of the bar using kinematic data. Additionally, and to our surprise, M-SSA uncovered some new dynamics in previously analysed simulations, underscoring the power of this new approach.

show abstract

“…Although signals can be affected by internal or external noise, which often has unknown characteristics, they can be identified if the signal and noise subspaces are accurately separated. It is known that removing noise from any signal is necessary for analyzing any time series and is helpful in properly decomposing signals [34].…”

Section: Introductionmentioning

confidence: 99%

Forecasting the COVID-19 Pandemic in Saudi Arabia Using a Modified Singular Spectrum Analysis Approach: Model Development and Data Analysis

Alharbi¹

2021

JMIRx Med

View full text Add to dashboard Cite

Background Infectious disease is one of the main issues that threatens human health worldwide. The 2019 outbreak of the new coronavirus SARS-CoV-2, which causes the disease COVID-19, has become a serious global pandemic. Many attempts have been made to forecast the spread of the disease using various methods, including time series models. Among the attempts to model the pandemic, to the best of our knowledge, no studies have used the singular spectrum analysis (SSA) technique to forecast confirmed cases. Objective The primary objective of this paper is to construct a reliable, robust, and interpretable model for describing, decomposing, and forecasting the number of confirmed cases of COVID-19 and predicting the peak of the pandemic in Saudi Arabia. Methods A modified singular spectrum analysis (SSA) approach was applied for the analysis of the COVID-19 pandemic in Saudi Arabia. We proposed this approach and developed it in our previous studies regarding the separability and grouping steps in SSA, which play important roles in reconstruction and forecasting. The modified SSA approach mainly enables us to identify the number of interpretable components required for separability, signal extraction, and noise reduction. The approach was examined using different levels of simulated and real data with different structures and signal-to-noise ratios. In this study, we examined the capability of the approach to analyze COVID-19 data. We then used vector SSA to predict new data points and the peak of the pandemic in Saudi Arabia. Results In the first stage, the confirmed daily cases on the first 42 days (March 02 to April 12, 2020) were used and analyzed to identify the value of the number of required eigenvalues (r) for separability between noise and signal. After obtaining the value of r, which was 2, and extracting the signals, vector SSA was used to predict and determine the pandemic peak. In the second stage, we updated the data and included 81 daily case values. We used the same window length and number of eigenvalues for reconstruction and forecasting of the points 90 days ahead. The results of both forecasting scenarios indicated that the peak would occur around the end of May or June 2020 and that the crisis would end between the end of June and the middle of August 2020, with a total number of infected people of approximately 330,000. Conclusions Our results confirm the impressive performance of modified SSA in analyzing COVID-19 data and selecting the value of r for identifying the signal subspace from a noisy time series and then making a reliable prediction of daily confirmed cases using the vector SSA method.

show abstract

Automatic Grouping in Singular Spectrum Analysis

Cited by 18 publications

References 48 publications

Penerapan Metode Auto Singular Spectrum Analysis Pada Peramalan Data Indeks Harga Saham Gabungan Di Indonesia

Penerapan Metode Auto Singular Spectrum Analysis Pada Peramalan Data Indeks Harga Saham Gabungan Di Indonesia

Using Multichannel Singular Spectrum Analysis to Study Galaxy Dynamics

Forecasting the COVID-19 Pandemic in Saudi Arabia Using a Modified Singular Spectrum Analysis Approach: Model Development and Data Analysis

Contact Info

Product

Resources

About