11 documents found, page 1 of 2
A data drift approach to update deployed energy prediction machine learning models
Teixeira, Hélder; Matta, Arthur; Pilastri, André; Ferreira, Luís; Pereira, Pedro José; Gonçalves, Carlos; Cortez, PauloWhile there is an increasing interest in Machine Learning (ML) based solutions, scarce research has been devoted to the deployment and monitoring of ML models. In this work, we address this research gap by proposing a new data drift ML update strategy that only considers changes in the input features. Using the realistic Growing Window (GW) and Rolling Window (RW) ML deployment simulation schemes, we propose tw...
Proactive prevention of work-related musculoskeletal disorders using a motion c...
Matos, Luís Miguel; Dias, Paula; Matta, Arthur; Machado, Dário; Sampaio, Rosane; Pilastri, André; Cortez, PauloIn this paper, we propose a proactive method to prevent Work-related MusculoSkeletal Disorders (WMSDs) in manufacturing industries. The integrated method includes a Motion Capture System (MCS) for data collection, a Time Series Forecasting (TSF) module using Machine Learning (ML) algorithms, a WMSD risk assessment module based on ergonomic standards, and a safety mechanism (e.g., alarm sound). We evaluated the ...
Ahead of time prediction of decorated particleboard production disruptions and ...
Matta, Arthur; Matos, Luís Miguel; Pilastri, André; Silva, Jorge Miguel; Gomes, Miguel Bastos; Cortez, PauloThis paper proposes a Machine Learning (ML) approach to perform an Ahead-of-Time (AoT) prediction of decorated particleboard 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 ter...
Worker 4.0: A textile exoskeleton to support apparel industry
Oliveira, João; Costa, Luani; Ramôa, Ana; Silva, Ricardo; Fertuzinhos, Aureliano; Estudante, Inês; Pinheiro, João; Vale, Bruno; Pilastri, AndréSTVgoDigital project aims the transition of the textile and apparel industries to the new Industry 4.0 paradigm promoting the digitalization to increase productivity and efficiency of the entire value chain. Specifically, the PPS4 Worker 4.0 aims to develop an exoskeleton solution based on sensing and active components within a garment to support sewing operation movements that may cause injuries and/or pain in...
Machine learning for predicting production disruptions in the wood-based panels...
Afonso, Cláudia; Matta, Arthur; Matos, Luís Miguel; Gomes, Miguel Bastos; Santos, Antonina; Pilastri, André Luiz; Cortez, PauloIn this paper, we study the application of Machine Learning (ML) in detecting and predicting Ahead-of-Time (AoT) production disruptions in a Portuguese Wood-Based Panels Industry. Assuming an Industry 4.0 concept, the analyzed ML classification task presents several challenges, such as a high number of Internet of Things (IoT) sensors, high-velocity data generation and extremely imbalanced data. To solve these ...
RTSIMU: Real-Time Simulation tool for IMU sensors [Formula presented]
Dias, Paula; Matta, Arthur; Pilastri, André; Matos, Luís Miguel; Cortez, PauloA software system, called RTSIMU, was developed for analyzing worker movements in the textile industry using Inertial Measurement Units (IMUs). RTSIMU software converts raw positioning data from IMUs into quaternions, which represent orientation relative to the Earth, and further translates them into angular values of movement. To assess relevant angular values and simulate various working movements (such as ab...
An empirical study on anomaly detection algorithms for extremely imbalanced dat...
Fontes, Gonçalo; Matos, Luís Miguel; Matta, Arthur; Pilastri, André Luiz; Cortez, PauloAnomaly detection attempts to identify abnormal events that deviate from normality. Since such events are often rare, data related to this domain is usually imbalanced. In this paper, we compare diverse preprocessing and Machine Learning (ML) state-of-the-art algorithms that can be adopted within this anomaly detection context. These include two unsupervised learning algorithms, namely Isolation Forests (IF) an...
Categorical Attribute traNsformation Environment (CANE): A python module for ca...
Matos, Luís Miguel; Azevedo, João; Matta, Arthur; Pilastri, André; Cortez, Paulo; Mendes, RuiCategorical Attribute traNsformation Environment (CANE) is a simpler but powerful data categorical preprocessing Python package. The package is valuable since there is currently a large range of Machine Learning (ML) algorithms that can only be trained using numerical data (e.g., Deep Learning, Support Vector Machines) and several real-world ML applications are associated with categorical data attributes. Curre...
An intelligent decision support system for road freight transport
Carvalho, Hugo Silva; Pilastri, André Luiz; Matta, Arthur; Matos, Luís Miguel; Novais, Rui; Cortez, PauloThis paper presents an Intelligent Decision Support System (IDSS) to optimize transport and logistics activities in a set of Portuguese companies currently operating in the freight transport sector. This IDSS comprises three main modules that can be used individually or chained together, dedicated to: a geographic clustering detection of transport services; a transport driver suggestion; and a route and truck-l...
An intelligent decision support system for production planning in garments indu...
Ribeiro, Rui; Pilastri, André; Carvalho, Hugo; Matta, Arthur; Pereira, Pedro José; Rocha, Pedro; Alves, Marcelo; Cortez, PauloIn this paper, we propose an Intelligent Decision Support System (IDSS) that combines prediction and optimization for production planning. We worked with a company that provides software for the garments Industry and that had access to real-world data related with a client that works with subcontractors. Using an Automated Machine Learning (AutoML) approach, we firstly target four predictive tasks that are cruc...