Prediction of time series based on load profile using JADE technique

Hussain, Mashitah Mohd; Zakaria, Zuhaina; Rifin, Rozi; Hussin, M. Z.; Rahman, Nor Hafizah Abdul; Ilham, Nur Iqtiyani; Zain, Norlina Mohd; Sani, Maizura Mohd

doi:10.1109/icsgrc.2017.8070563

Cited by 2 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…JADE implements the fourth-order cumulant matrices to observe an expected value from the mixtures [19] representing the estimated raw matrix, where S can be estimated from the mixing matrix A, and where it is implemented in the time-series load flow situation. This estimated raw data needs to be whitened, based on the columns of orthogonal with variance.…”

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

“…Next, to explain how the JADE algorithm functions in separating the mixed data profiles, reference is made to Figure 4. Here, the mixing matrix A, is the inverse proportion to a demixing matrix, W. As explained in [19], the mixing matrix, A is Xrc × S -1 is used to estimate the value of raw matrix S. A matrix of W then needs to be calculated. The formula for estimating the original raw data S, is shown in (1).…”

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

“…Next, the data needs to be whitened using PW, the column of orthogonal with variance, as stated in [19]. In this paper, the mixing data Xrc, was transformed through Principle Component Analysis, (PCA) by rotating the PW explained in previous research [21].…”

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

“…The PW was then rotated using cumulants computation and PCA loadings so that the column vectors could be independent, called higher-order statistics. In this study, the higher-order statistics known as fourth-order cumulants (kurtosis) of equal variances in PW was calculated [19]. The equation of kurtosis is shown in (2):…”

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

See 3 more Smart Citations

Short term forecasting of electrical consumption using a neural network: joint approximate diagonal eigenvalue

Hussain

Zakaria

Dahlan

et al. 2022

IJEECS

Self Cite

View full text Add to dashboard Cite

This article aims <span lang="EN-US">to estimate the load profiling of electricity that provides information on the electrical load demand. In achieving this research implemented the neural network algorithm of joint approximate diagonalisation of eigen-matrices (JADE) to describe the load profile pattern for each point. Nowadays, utility providers claim that natural sources are used to generate power by rising consumer demands for energy. However, occasionally utility workers need to know the demand at certain location, corresponding to maintenance issues or for any shutdown area involved.<br /> A distribution pattern based on the data can be predicted based on the incoming data profile without having detailed information of certain load bus, the concept of derivatives was relevant to forecast the types of distribution data. The model was constructed with load profile information based on three different locations, and the concept of derivative was recognized, including the type of incoming data. Historical data were captured from a selected location in Malaysia that was proposed to train the JADE algorithm from three different empirical distributions of consumers, recording every 15 minutes per day. The results were analyzed based on the error measurement and compared with the real specific load distribution feeder information of needed profiles.</span>

show abstract

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

Section: Joint Approximate Diagonal Eigenvalue (Jade)mentioning

confidence: 99%

See 2 more Smart Citations

Short term forecasting of electrical consumption using a neural network: joint approximate diagonal eigenvalue

Hussain

Zakaria

Dahlan

et al. 2022

IJEECS

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the same time, considering that the micro-motion signal processed in this paper is a complex signal, the traditional independent component analysis algorithm can not process the complex signal well. Therefore, the Joint Approximate Diagonalization of Eigen-matrices separation algorithm [28] is introduced to separate the micromotion signals of each scattering point.…”

Section: G G Is Anmentioning

confidence: 99%

A Method for the Micro-Motion Signal Separation and Micro-Doppler Extraction for the Space Precession Target

Feng

Sisan

2020

IEEE Access

View full text Add to dashboard Cite

Aiming at the problem of micro-motion signal separation and micro-Doppler extraction of the precession target, a new method based on singular value decomposition (SVD) and joint approximate diagonalization of eigen-matrices (JADE) is proposed in this paper. Firstly, the micro-motion model of space precession target is established, and the micro-Doppler and scattering characteristics are analyzed to establish the echo signal model of the target. Secondly, through simplifying the signal model of scattering point and building the signal matrix of different signal lengths, the singular value ratio sequence is constructed by the method of SVD to estimate the precession period of the target. Thirdly, the singular vectors of different observation periods are extracted, the observation matrix is constructed, and then the JADE algorithm is adopted to separate the micro-motion signal of each scattering point. Finally, the clustering analysis is used to denoise the time-frequency graph and the centroid calculation is employed to extract the micro-Doppler of each scattering point. Simulation results show that this method of good robustness can effectively separate and extract the micro-Doppler of the scattering points. INDEX TERMS Micro-motion, singular value decomposition, joint approximate diagonalization of eigenmatrices, micro-Doppler extraction. XUGUANG XU was born in Xian, Shaanxi, China, in 1994. He received the B.S. degree in radar engineering in 2016 and received the M.S. degree in electronic science and engineering from Air Force Engineering University, Xi'an, China, in 2018, respectively, where he is currently pursuing the Ph.D. degree. His research interests include micro-motion signal processing and target recognition.

show abstract

Prediction of time series based on load profile using JADE technique

Cited by 2 publications

References 17 publications

Short term forecasting of electrical consumption using a neural network: joint approximate diagonal eigenvalue

Short term forecasting of electrical consumption using a neural network: joint approximate diagonal eigenvalue

A Method for the Micro-Motion Signal Separation and Micro-Doppler Extraction for the Space Precession Target

Contact Info

Product

Resources

About