설명 가능한 합성곱 신경망을 활용한 센서 기반의 시계열 데이터 분류 모델 제안
A Proposal of Sensor-based Time Series Classification Model using Explainable Convolutional Neural Network
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
센서 데이터를 활용하여 설비의 이상 진단이 가능해졌다. 하지만 설비 이상에 대한 원인 분석은 미비한 실정이다. 본 연구에서는 센서 기반 시계열 데이터 분류 모델을 위한 해석가능한 합성곱 신경망 프레임워크를 제안한다. 연구에서 사용된 센서 기반 시계열 데이터는 실제 차량에 부착된 센서를 통해 수집되었고, 반도체의 웨이퍼 데이터는 공정 과정에서 수집되었다. 추가로 실제기계 설비에서 수집된 주기 신호 데이터를 이용 하였으며, 충분한 학습을 위해 Data augmentation 방법론인 Scaling과 Jittering을 적용하였다. 또한, 본 연구에서는 3가지 합성곱 신경망 기반 모델들을 제안하고 각각의 성능을 비교하였다. 본 연구에서는 ResNet에 Jittering을 적용한 결과 정확도95%, F1 점수 95%로 가장 뛰어난 성능을 보였으며, 기존 연구 대비 3%의 성능 향상을 보였다. 더 나아가 결과의 해석을 위한 XAI 방법론으로 Class Activation Map과 Layer Visualization을 제안하였으며, 센서 데이터 분류에 중요 영향을 끼치는 시계열 구간을 시각적으로 확인하였다.
Abstract
Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.
참고문헌 (30)
- C. Oh, "Time-series data augmentation based on interpolation", Procedia Computer Science, 175, pp.64~71 (2020)
- C. L. Yang, "Sensor classification using convolutional neural network by encoding multivariate time series as two-dimensional colored images", Sensors, 20(1), pp.168~ (2019)
- H. Ismail Fawaz, "Inceptiontime: Finding Alexnet for Time Series Classification", Data Mining and Knowledge Discovery, 34(6), pp.1936~1962 (2020)
- Y. S. Jeong, "Weighted dynamic time warping for time series classification", Pattern recognition, 44(9), pp.2231~2240 (2011)
- 안길승, "다변량 시계열 데이터 분류를 위한 특징 선택 방법", 대한산업공학회지, 43(6), pp.413~421 (2017), 대한산업공학회[DOI]
- D. Smirnov, "Time Series Classification with Recurrent Neural Networks", Advanced Analytics and Learning on Temporal Data, 8 (2018)
- M. Wenninger, "Timage–A Robust Time Series Classification Pipeline", International Conference on Artificial Neural Networks, pp.450~461 (2019), Springer
- H. Ismail Fawaz, "Deep Learning for Time Series Classification: A Review", Data Mining and Knowledge Discovery, 33(4), pp.917~963 (2019), Springer
- A. Preece, "Stakeholders in Explainable AI", ~ (2018)
- J. Zhu, "Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation", 2018 IEEE Conference on Computational Intelligence and Games (CIG), pp.1~8 (2018), IEEE
- M. Van Lent, "An explainable artificial intelligence system for small-unit tactical behavior", Proceedings of the national conference on artificial intelligence (2004)
- D. Gunning, "DARPA’s Explainable Artificial Intelligence (XAI) Program", AI Magazine, 40(2), pp.44~58 (2019)
- B. Zhou, "Learning Deep Features for Discriminative Localization", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2921~2929 (2016)
- 권상현, "밀도기반 군집화와 딥러닝을 활용한공정 주기 신호의 이상 탐지 및 분류", 대한산업공학회지, 44(6), pp.475~482 (2018), 대한산업공학회[DOI]
- B. Zhao, "Convolutional neural networks for time series classification", Journal of Systems Engineering and Electronics, 28(1), pp.162~169 (2017)
- D. Kuang, "A 1d convolutional network for leaf and time series classification", ~ (2019)
- T. Rojat, "Explainable artificial intelligence (xai) on timeseries data: A survey", ~ (2021)
- F. Oviedo, "Fast and Interpretable Classification of Small X-Ray Diffraction Datasets Using Data Augmentation and Deep Neural Networks", Npj Computational Materials, 5(1), pp.1~9 (2019), Nature Publishing Group
- N. Strodthoff, "Deep Learning for ECG Analysis:Benchmarks and Insights from PTB-XL", IEEE Journal of Biomedical and Health Informatics, 25(5), pp.1519~1528 (2020), IEEE
- K. S. Choi, "Prediction of IDH Genotype in Gliomas with Dynamic Susceptibility Contrast Perfusion MR Imaging Using an Explainable Recurrent Neural Network", Neuro-Oncology, 21(9), pp.1197~1209 (2019), Oxford University Press US
- A. A. Ismail, "Benchmarking Deep Learning Interpretability in Time Series Predictions", ~ (2020)
- G. Forestier, "Generating Synthetic Time Series to Augment Sparse Datasets", 2017 IEEE International Conference on Data Mining (ICDM), pp.865~870 (2017), IEEE
- D. Q. Goldin, "On Similarity Queries for Time-Series Data: Constraint Specification and Implementation", International Conference on Principles and Practice of Constraint Programming, pp.137~153 (1995), Springer
- T. Um, "Data Augmentation of Wearable Sensor Data for Parkinson’s Disease Monitoring Using Convolutional Neural Networks", Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp.216~220 (2017)
- Q. Wen, "Time Series Data Augmentation for Deep Learning: A Survey", ~ (2020)
- B. K. Iwana, "An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks", Plos One, 16(7), pp.e0254841~ (2021)
- F. Rosenblatt, "Perceptrons and the Theory of Brain Mechanisms" (1961), Cornell Aeronautical Lab Inc
- Z. Wang, "Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline", 2017International Joint Conference on Neural Networks (IJCNN), pp.1578~1585 (2017), IEEE
- W. Tang, "Rethinking 1d-Cnn for Time Series Classification: A Stronger Baseline", ~ (2020)
- K. He, "Deep Residual Learning for Image Recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)