모바일 결제 시스템의 수요 예측을 위한 신경망에서 특징 선별 기법 = A Feature Selection Technique in the Neural Network for Demand Forecasting of Mobile Payment System

다국어 초록 (Multilingual Abstract)

In this paper, we present a time series prediction technique based on neural network as a methodology for forecasting service demand of mobile payment system. We propose a two-stage neural network model for the feature selection process and the prediction process. Three types of fuzzy membership functions were adopted for the representation of feature data, and a hyperbox-based neural network model is used for the evaluation of feature relevance factor. The proposed feature selection technique reduces the amount of computation and eliminates erroneous feature data in the learning data set. We evaluated the usefulness of the proposed method through experiments using two years of data obtained form actual smart campus systems.

국문 초록 (Abstract)

본 논문에서는 모바일 결제시스템의 서비스 수요예측을 위한 방법론으로서 신경망 기반의 시계열예측 기법을 제시한다. 예측에 필요한 특징 선별과정과 시계열 데이터의 예측과정을 위하여 2단계 신경망 모델을 제안하며 그 동작 특성과 알고리즘에 관해 기술한다. 특징 데이터의 표현을 위하여 3종류의 퍼지 멤버쉽함수를 적용하며, 하이퍼박스 기반의 신경망 모델을 사용하여 특징의 연관도 요소를 평가하는 방법을 제시한다. 제안된 특징 선별 기법은 예측 시스템의 계산량을 감소시키며, 학습데이터 집합에서 왜곡된 특징 데이터를 제거할 수 있게 한다. 실제 스마트캠퍼스 시스템에서 취득한 2년간의 데이터를 사용하여 실험을 수행하고 그 결과를 통하여 제안된 기법의 유용성을 평가한다.

참고문헌 (Reference)

1 Quikun Xiao, "Time series prediction using bayesian filtering model and fuzzy neural networks" 140 (140): 104-113, 2017

2 Yong-kuo Liu, "Prediction of time series of NPP operating parameters using dynamic model based on BP neural network" 85 (85): 566-575, 2015

3 Fernando Gaxiola, "Interval type-2 fuzzy weight adjustment for backpropagation neural networks with application in time series prediction" 260 (260): 1-14, 2014

4 Mohammed Falah Mohammed, "Improving the Fuzzy Min-Max neural network with a K-nearest hyperbox expansion rule for pattern classification" 52 : 135-145, 2017

5 Christopher Smith, "Evolutionary multiobjective generation of recurrent neural network ensembles for time series prediction" 143 (143): 302-311, 2014

6 Gholamali Heydari, "Chaotic time series predictin via artificial neural square fuzzy inference system," 55 (55): 461-468, 2016

7 Hicham Chaoui, "Aging prediction and state of charge estimation of a LiFePO4 battery using input timedelayed neural networks" 145 (145): 189-197, 2017

8 Epiniki I. Papageorgiou, "A two-stage model for time series prediction based on fuzzy cognitive maps and neural networks" 232 : 113-121, 2017

9 Liang Guo, "A recurrent neural network based health indicatorfor remaining useful life prediction of bearings" 240 (240): 98-109, 2017

10 Jinhai Liu, "A modified fuzzy min-max neural network for data clustering and its application on pipeline internal inspection data" 238 : 56-66, 2017