1 Introduction
-
using unlabeled data in combination with labeled data
-
generating synthetic data using generative models
-
Enhancing ML in RAW using Semi-Supervised Learning (SSL)(self-training) from the real world production plant
-
Using Generative Adversarial Networks (GANs) to increase the data sets even further with synthethic data sets
2 Related work
2.1 RARR
2.2 Quality prediction
2.3 Time series classification
-
Whole series approaches compare series using different distance measures. Best performances were reached using the Dynamic Time Warping similarity measure [18].
-
Interval based approaches use features that are time dependent and derived from intervals of each series. A promising representative of interval based approaches is the Time Series Forest (TSF) by Deng et al. [19].
-
Shapelet based models try to find unique and distinctive shapelets within time series. These shapelets (sub-sequences) are local, phase independent, and are used as a discriminative feature for another classifier [22]. Yet, according to Fawaz et al. the training complexity of shapelet algorithms is high and thus they are not competitive for bigger data sets or real world applications [20].
-
Combined transformations are ensembles of different classifiers that differ in their data representation. Example models are named Collective of Transformation-Based Ensembles (COTE) [23] or its improvement Hierarchical Vote Collective of Transformation-Based Ensembles for Time Series Classification (HIVE-COTE) [24].
2.4 Semi-supervised learning and GANs in TSC
3 Baseline quality prediction approach
3.1 Problem definition and data set
4 Experiment section
4.1 Semi-supervised approach
4.2 Semi-supervised evaluation
4.3 Synthetic data generation using GANs
4.3.1 Process expert evaluation
Expert no. | Correct | False | Accuracy (%) |
---|---|---|---|
E01 | 18 | 2 | 90 |
E02 | 6 | 14 | 30 |
E03 | 7 | 13 | 35 |
E04 | 18 | 2 | 90 |
E05 | 10 | 10 | 50 |
E06 | 18 | 2 | 90 |
E07 | 17 | 3 | 85 |
E08 | 14 | 6 | 70 |
E09 | 10 | 10 | 50 |
4.3.2 GAN model performance evaluation
4.4 Univariate data generation approach
4.5 Multivariate data generation approach
Approach | Architecture | Classifier | Accuracy (%) |
---|---|---|---|
TSTR | ACGANMTS | ROCKET | 0.477 |
TSTR | ACGANMTS | LSTM_FCN | 0.425 |
TSTR | CGANMTS | ROCKET | 0.461 |
TSTR | CGANMTS | LSTM_FCN | 0.658 |
TRTS | ACGANMTS | ROCKET | 0.499 |
TRTS | ACGANMTS | LSTM_FCN | 0.505 |
TRTS | CGANMTS | ROCKET | 0.523 |
TRTS | CGANMTS | LSTM_FCN | 0.500 |