• 정보과학회 논문지
• /
• 제45권3호
• /
• pp.280-287
• /
• 2018

최근 추천시스템과 데이터 분석 분야에서 고차원 형태의 텐서를 이용하는 연구가 증가하고 있다. 이는 고차원의 데이터인 텐서 분석을 통해 더 많은 잠재 요소와 잠재 패턴을 추출가능하기 때문이다. 그러나 고차원 형태인 텐서는 크기가 방대하고 계산이 복잡하기 때문에 텐서 분해를 통해 분석해야한다. 기존 텐서 도구들인 rTensor, pyTensor와 MATLAB은 단일 시스템에서 작동하기 때문에 방대한 양의 데이터를 처리하기 어렵다. 하둡을 이용한 텐서 분해 도구들도 있지만 처리 시간이 오래 걸린다. 따라서 본 논문에서는 인 메모리 기반의 빅데이터 시스템인 아파치 스파크를 기반으로 하는 텐서 분해 도구인 S-PARAFAC을 제안한다. S-PARAFAC은 텐서 분해 방법 중 PARAFAC 분해에 초점을 맞춰 아파치 스파크에 적합하게 변형하여 텐서 분해를 빠르게 분산 처리가능 하도록 하였다. 본 논문에서는 하둡을 기반의 텐서 분해 도구와 S-PARAFAC의 성능을 비교하여 약 4~25배 정도의 좋은 성능을 보였다.

• 한국멀티미디어학회논문지
• /
• 제22권4호
• /
• pp.443-454
• /
• 2019

In recent years, there has been active research on a recommender system that considers three or more inputs in addition to users and goods, making it a multi-dimensional array, also known as a tensor. The main issue with using tensor is that there are a lot of missing values, making it sparse. In order to solve this, the tensor can be shrunk using the tensor decomposition algorithm into a lower dimensional array called a factor matrix. Then, the tensor is reconstructed by calculating factor matrices to fill original empty cells with predicted values. This is called tensor reconstruction. In this paper, we propose a user-based Top-K recommender system by normalized PARAFAC tensor reconstruction. This method involves factorization of a tensor into factor matrices and reconstructs the tensor again. Before decomposition, the original tensor is normalized based on each dimension to reduce overfitting. Using the real world dataset, this paper shows the processing of a large amount of data and implements a recommender system based on Apache Spark. In addition, this study has confirmed that the recommender performance is improved through normalization of the tensor.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.1253-1254
• /
• 2011

본 논문에서는 블로그 공간을 텐서로 표현하고, 이를 분석한다. 분석 결과에 따르면, PARAFAC 분해를 통하여 특정 주제를 나타내는 커뮤니티들을 올바르게 파악할 수 있었으며, 각 커뮤니티에서 영향력 있는 블로그들과 키워드들, 그리고 권위 있는 포스트들을 식별할 수 있었다.

• Smart Structures and Systems
• /
• 제13권2호
• /
• pp.257-280
• /
• 2014

In this paper, a novel PARAllel FACtor (PARAFAC) decomposition based Blind Source Separation (BSS) algorithm is proposed for modal identification of structures equipped with tuned mass dampers. Tuned mass dampers (TMDs) are extremely effective vibration absorbers in tall flexible structures, but prone to get de-tuned due to accidental changes in structural properties, alteration in operating conditions, and incorrect design forecasts. Presence of closely spaced modes in structures coupled with TMDs renders output-only modal identification difficult. Over the last decade, second-order BSS algorithms have shown significant promise in the area of ambient modal identification. These methods employ joint diagonalization of covariance matrices of measurements to estimate the mixing matrix (mode shape coefficients) and sources (modal responses). Recently, PARAFAC BSS model has evolved as a powerful multi-linear algebra tool for decomposing an $n^{th}$ order tensor into a number of rank-1 tensors. This method is utilized in the context of modal identification in the present study. Covariance matrices of measurements at several lags are used to form a $3^{rd}$ order tensor and then PARAFAC decomposition is employed to obtain the desired number of components, comprising of modal responses and the mixing matrix. The strong uniqueness properties of PARAFAC models enable direct source separation with fine spectral resolution even in cases where the number of sensor observations is less compared to the number of target modes, i.e., the underdetermined case. This capability is exploited to separate closely spaced modes of the TMDs using partial measurements, and subsequently to estimate modal parameters. The proposed method is validated using extensive numerical studies comprising of multi-degree-of-freedom simulation models equipped with TMDs, as well as with an experimental set-up.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권3호
• /
• pp.296-300
• /
• 2008

최근에 개발된 Nonnegative tensor factorization(NTF)는 비음수 행렬 분해(NMF)의 multiway(multilinear) 확장형이다. NTF는 CANDECOMP/PARAFAC 모델에 비음수 제약을 가한 모델이다. 본 논문에서는 Tucker 모델에 비음수 제약을 가한 nonnegative Tucker decomposition(NTD)라는 새로운 텐서 분해 모델을 제안한다. 제안된 NTD 모델을 least squares, I-divergence, $\alpha$-divergence를 이용한 여러 목적함수에 대하여 fitting하는 multiplicative update rule을 유도하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.2879-2890
• /
• 2020

In this paper, we study the estimation of angle, range and polarization parameters of a bistatic polarization sensitive frequency diverse array multiple-input multiple-output (PSFDA-MIMO) radar system. The application of polarization sensitive array in receiver is explored. A signal model of bistatic PSFDA-MIMO radar system is established. In order to utilize the multi-dimensional structure of array signals, the matched filtering radar data can be represented by a third-order tensor model. A joint estimation of the direction-of-departure (DOD), direction-of-arrival (DOA), range and polarization parameters based on parallel factor (PARAFAC) algorithm is proposed. The proposed algorithm does not need to search spectral peaks and singular value decomposition, and can obtain automatic pairing estimation. The method was compared with the existing methods, and the results show that the performance of the method is better. Therefore, the accuracy of the parameter estimation is further improved.