ADS: Applications 1

The session ADS: Applications 1 will be held on wednesday, 2019-09-18, from 14:00 to 16:00, at room 0.001. The session chair is Tias Guns.


14:00 - 14:20
Generative Adversarial Networks for Failure Prediction (23)
Shuai Zheng (Industrial AI Lab, Hitachi America Ltd), Ahmed Farahat (Industrial AI Lab, Hitachi America Ltd), Chetan Gupta (Industrial AI Lab, Hitachi America Ltd)

Prognostics and Health Management (PHM) is an emerging engineering discipline which is concerned with the analysis and prediction of equipment health and performance. One of the key challenges in PHM is to accurately predict impending failures in the equipment. In recent years, solutions for failure prediction have evolved from building complex physical models to the use of machine learning algorithms that leverage the data generated by the equipment. However, failure prediction problems pose a set of unique challenges that make direct application of traditional classification and prediction algorithms impractical. These challenges include the highly imbalanced training data, the extremely high cost of collecting more failure samples, and the complexity of the failure patterns. Traditional oversampling techniques will not be able to capture such complexity and accordingly result in overfitting the training data. This paper addresses these challenges by proposing a novel algorithm for failure prediction using Generative Adversarial Networks (GAN-FP). GAN-FP first utilizes two GAN networks to simultaneously generate training samples and build an inference network that can be used to predict failures for new samples. GAN-FP first adopts an infoGAN to generate realistic failure and non-failure samples, and initialize the weights of the first few layers of the inference network. The inference network is then tuned by optimizing a weighted loss objective using only real failure and non-failure samples. The inference network is further tuned using a second GAN whose purpose is to guarantee the consistency between the generated samples and corresponding labels. GAN-FP can be used for other imbalanced classification problems as well. Empirical evaluation on several benchmark datasets demonstrates that GAN-FP significantly outperforms existing approaches, including under-sampling, SMOTE, ADASYN, weighted loss, and infoGAN augmented training.

14:40 - 15:00
Manufacturing Dispatching using Reinforcement and Transfer Learning (225)
Shuai Zheng (Industrial AI Lab, Hitachi America Ltd), Chetan Gupta (Industrial AI Lab, Hitachi America Ltd), Susumu Serita (Industrial AI Lab, Hitachi America Ltd)

Efficient dispatching rule in manufacturing industry is key to ensure product on-time delivery and minimum past-due and inventory cost. Manufacturing, especially in the developed world, is moving towards on-demand manufacturing meaning a high mix, low volume product mix. This requires efficient dispatching that can work in dynamic and stochastic environments, meaning it allows for quick response to new orders received and can work over a disparate set of shop floor settings. In this paper we address this problem of dispatching in manufacturing. Using reinforcement learning (RL), we propose a new design to formulate the shop floor state as a 2-D matrix, incorporate job slack time into state representation, and design lateness and tardiness rewards function for dispatching purpose. However, maintaining a separate RL model for each production line on a manufacturing shop floor is costly and often infeasible. To address this, we enhance our deep RL model with an approach for dispatching policy transfer. This increases policy generalization and saves time and cost for model training and data collection. Experiments show that: (1) our approach performs the best in terms of total discounted reward and average lateness, tardiness, (2) the proposed policy transfer approach reduces training time and increases policy generalization.

15:00 - 15:20
An aggregate learning approach for interpretable semi-supervised population prediction and disaggregation using ancillary data (284)
Guillaume Derval (ICTEAM, UCLouvain), Frédéric Docquier (IRES, UCLouvain), Pierre Schaus (ICTEAM, UCLouvain)

Census data provide detailed information about population characteristics at a coarse resolution. Nevertheless, fine-grained, high-resolution mappings of population counts are increasingly needed to characterize population dynamics and to assess the consequences of climate shocks, natural disasters, investments in infrastructure, development policies, etc. Dissagregating these census is a complex machine learning, and multiple solutions have been proposed in past research. We propose in this paper to view the problem in the context of the aggregate learning paradigm, where the output value for all training points is not known, but where it is only known for aggregates of the points (i.e. in this context, for regions of pixels where a census is available). We demonstrate with a very simple and interpretable model that this method is on par, and even outperforms on some metrics, the state-of-the-art, despite its simplicity.

Reproducible Research
15:20 - 15:40
Optimizing Neural Networks for Patent Classification (619)
Louay Abdelgawad (Averbis GmbH, Freiburg), Peter Kluegl (Averbis GmbH, Freiburg), Erdan Genc (Averbis GmbH, Freiburg), Stefan Falkner (Albert-Ludwigs University of Freiburg), Frank Hutter (Albert-Ludwigs University of Freiburg)

A great number of patents is filed everyday to the patent offices worldwide. Each of these patents has to be labeled by domain experts with one or many of thousands of categories. This process is not only extremely expensive but also overwhelming for the experts, due to the considerable increase of filed patents over the years and the increasing complexity of the hierarchical categorization structure. Therefore, it is critical to automate the manual classification process using a classification model. In this paper, the automation of the task is carried out based on recent advances in deep learning for NLP and compared to customized approaches. Moreover, an extensive optimization analysis grants insights about hyperparameter importance. Our optimized convolutional neural network achieves a new state-of-the-art performance of 55.02

Reproducible Research
14:20 - 14:40
Interpreting atypical conditions in systems with deep conditional Autoencoders: the case of electrical consumption (175)
Antoine Marot (Reseau Transport Electricite R&D), Antoine Rosin (Reseau Transport Electricite R&D), Laure Crochepierre (Reseau Transport Electricite R&D; Universite de Lorraine), Benjamin Donnot (Reseau Transport Electricite R&D), Pierre Pinson (DTU Technical University of Denmark), Lydia Boudjeloud-Assala (Universite de Lorraine)

In this paper, we propose a new method to iteratively and interactively characterize new feature conditions for signals of daily French electrical consumption from our historical database, relying on Conditional Variational Autoencoders. An autoencoder first learn a compressed similarity-based representation of the signals in a latent space, in which one can select and extract well-represented expert features. Then, we successfully condition the model over the set of extracted features, as opposed to simple target label previously, to learn conditionally independent new residual latent representations. Unknown, or previously unselected factors such as atypical conditions now appear well-represented to be detected and further interpreted by experts. By applying it, we recover the appropriate known expert features and eventually discover, through adapted representations, atypical known and unknown conditions such as holidays, fuzzy non working days and weather events, which were actually related to important events that influenced consumption.

Reproducible Research

Parallel Sessions