Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/73561
Título: | An automated machine learning approach for predicting chemical laboratory material consumption |
Autor(es): | Silva, António João Cortez, Paulo |
Palavras-chave: | Industry 4.0 Automated Machine Learning Regression Time Series Forecasting Deep Learning |
Data: | Jun-2021 |
Editora: | Springer |
Revista: | IFIP Advances in Information and Communication Technology |
Citação: | Silva, A. J., & Cortez, P. (2021, June). An Automated Machine Learning Approach for Predicting Chemical Laboratory Material Consumption. In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 105-116). Springer |
Resumo(s): | This paper address a relevant business analytics need of a chemical company, which is adopting an Industry 4.0 transformation. In this company, quality tests are executed at the Analytical Laboratories (AL), which receive production samples and execute several instrumen- tal analyses. In order to improve the AL stock warehouse management, a Machine Learning (ML) project was developed, aiming to estimate the AL materials consumption based on week plans of sample analy- ses. Following the CRoss-Industry Standard Process for Data Mining (CRISP-DM) methodology, several iterations were executed, in which three input variable selection strategies and two sets of AL materials (top 10 and all consumed materials) were tested. To reduce the mod- eling effort, an Automated Machine Learning (AutoML) was adopted, allowing to automatically set the best ML model among six distinct re- gression algorithms. Using real data from the chemical company and a realistic rolling window evaluation, several ML train and test iterations were executed. The AutoML results were compared with two time series forecasting methods, the ARIMA methodology and a deep learning Long Short-Term Memory (LSTM) model. Overall, competitive results were achieved by the best AutoML models, particularly for the top 10 set of materials. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/73561 |
ISBN: | 9783030791490 |
DOI: | 10.1007/978-3-030-79150-6_9 |
ISSN: | 1868-4238 |
Versão da editora: | https://link.springer.com/chapter/10.1007/978-3-030-79150-6_9 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
F19_AIAI.pdf | 418,31 kB | Adobe PDF | Ver/Abrir |