Search

This paper proposes a Machine Learning (ML) approach to perform an Ahead-of-Time (AoT) prediction of decorated particle-board production disruptions and defects. We worked with a Portuguese company that is adopting the Industry 4.0 concept aiming to improve their decorated particleboard production planning (e.g., reducing production time and waste of materials). This company's business needs are addressed in terms of two nontrivial binary Classification tasks (production disruptions and defects). The AoT prediction is achieved by using only input attributes available before the execution of the production process. To reduce the modeling effort, we focus on Automated ML (AutoML) methods, under two main approaches: Single-Target Classification (STC) and Multi-Target Classification (MTC). The former is achieved by adopting the popular H2O AutoML tool, while the latter adopts a deep learning neural network automatically tuned by using a Bayesian search. The computational experiments adopted a realistic rolling window evaluation over recently collected industrial data (comprising 14 months). Overall, interesting predictive results were achieved by both AutoML approaches, outperforming a baseline Decision Tree method. In addition, an eXplainable Artificial Intelligence (XAI) method based on a Sensitivity Analysis (SA) was adopted, allowing the identification of the most relevant inputs, which is valuable knowledge to support the decorated particleboard production planning. [ABSTRACT FROM AUTHOR]

Nowadays, numerous organisations of different dimensions and business sectors operate in highly challenging and dynamic environments, wherein the supporting information systems (IS) are becoming increasingly complex. In this context, assistive tools capable of tackling such complexity have the potential to aid users improving their performance and effectiveness, as well as to streamline businesses' processes and promote entrepreneurial-level competitivity. Following this line of research, a web-based speech-to-term recognition approach is presented as a solution to endow IS with advanced capabilities for providing an easier (more natural) and straightforward interaction with baseline functionalities, by combining relevant techniques such as Voice Activity Detection (VAD), Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and an Ontological Database (OD), mapping the IS' functionalities and characteristics, is proposed. The developed interoperable system allows the conversion of speech to text - deriving into IS instructions - that is, in turn, submitted to on an ontological database wherein a term-based query is performed to elicit a set of available commands to be executed in the web context. These commands, fully mapped in the ontological database, are divided into three categories: a) navigation by menus/links, b) buttons interaction (e.g., submit forms) and c) completion of form fields. The proposed framework was experimentally tested in close to real conditions, resorting to an Enterprise Resource Planning (ERP) tool supplied by ERP Company. [ABSTRACT FROM AUTHOR]