Attention Mechanism for Multivariate Time Series Recurrent Model Interpretability Applied to the Ironmaking Industry

2020-07-15 · Cedric Schockaert, Reinhard Leperlier, Assaad Moawad

Data-driven model interpretability is a requirement to gain the acceptance of process engineers to rely on the prediction of a data-driven model to regulate industrial processes in the ironmaking industry. In the research presented in this paper, we focus on the development of an interpretable multivariate time series forecasting deep learning architecture for the temperature of the hot metal produced by a blast furnace. A Long Short-Term Memory (LSTM) based architecture enhanced with attention mechanism and guided backpropagation is proposed to accommodate the prediction with a local temporal interpretability for each input. Results are showing high potential for this architecture applied to blast furnace data and providing interpretability correctly reflecting the true complex variables relations dictated by the inherent blast furnace process, and with reduced prediction error compared to a recurrent-based deep learning architecture.

📄 PDF Abstract BibTeX arXiv:2007.12617

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningMultivariate Time Series Forecasting PredictionTime SeriesTime Series Analysis Time Series Forecasting

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

BRATI: Bidirectional Recurrent Attention for Time-Series Imputation

2025-01-09 · Armando Collado-Villaverde, Pablo Muñoz, Maria D. R-Moreno

Missing data in time-series analysis poses significant challenges, affecting the reliability of downstream applications. Imputation, the process of estimating missing values, has emerged as a key solution. This paper int…

Imputation Missing Values Multivariate Time Series Imputation Time Series+1

DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction

2019-04-16 · Yeqi Liu, Chuanyang Gong, Ling Yang, Yingyi Chen

Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at …

Prediction Time Series Time Series Analysis Time Series Prediction

Temporal Pattern Attention for Multivariate Time Series Forecasting

2018-09-12 · Shun-Yao Shih, Fan-Keng Sun, Hung-Yi Lee

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdepe…

Multivariate Time Series Forecasting Time Series Time Series Analysis Time Series Forecasting+1

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

2019-11-03 · CIKM ’19, November 3–7, 2019, Beijing, China 2019 11 · Siteng Huang Donglin Wang∗

Multivariate time series forecasting has attracted wide attention in areas, such as system, traffic, and finance. The difficulty of the task lies in that traditional methods fail to capture complicated nonlinear dependen…

Multivariate Time Series Forecasting Time Series Time Series Analysis Time Series Forecasting

SDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation

2024-10-04 · Amir Eskandari, Aman Anand, Drishti Sharma, Farhana Zulkernine

In various applications, the multivariate time series often suffers from missing data. This issue can significantly disrupt systems that rely on the data. Spatial and temporal dependencies can be leveraged to impute the …

Imputation Multivariate Time Series Imputation Time Series