Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Vasco Amorim
  • Cargo

    Investigador Sénior
  • Desde

    01 abril 2014
003
Publicações

2024

An Overview of Explainable Artificial Intelligence in the Industry 4.0 Context

Autores
Teixeira P.; Amorim E.V.; Nagel J.; Filipe V.;

Publicação
Lecture Notes in Mechanical Engineering

Abstract
Artificial intelligence (AI) has gained significant evolution in recent years that, if properly harnessed, may meet or exceed expectations in a wide range of application fields. However, because Machine Learning (ML) models have a black-box structure, end users frequently seek explanations for the predictions made by these learning models. Through tools, approaches, and algorithms, Explainable Artificial Intelligence (XAI) gives descriptions of black-box models to better understand the models’ behaviour and underlying decision-making mechanisms. The AI development in companies enables them to participate in Industry 4.0. The need to inform users of transparent algorithms has given rise to the research field of XAI. This paper provides a brief overview and introduction to the subject of XAI while highlighting why this topic is generating more and more attention in many sectors, such as industry.

2020

Work-in-Progress: Tailoring broad-spectrum, technology-centred IEM studies

Autores
Perdicoulis, TPA; Teixeira, SF; Amorim, V; Perdicoulis, A;

Publicação
PROCEEDINGS OF THE 2020 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE (EDUCON 2020)

Abstract
For many years, industrial engineers and managers have differentiated their duties in the work environment. While this has allowed for the two specialities to operate in their respective domains, the all necessary integration required to deliver a seamless industrial operation and outcomes has been sub-optimal - particularly in cases of conflict of knowledge or power. Industrial engineering and management (IEM) has come to resolve this situation, creating a new professional field and profile, as well as a multifaceted specialisation with a practical character. The challenge to take the next step in the refinement of this relatively new reality in Portugal is placed upon the most recent IEM degree, at the University of Tras-os-Montes e Alto Douro (UTAD).

2019

Developing Training Applications for Hydrogen Emergency Response Training

Autores
Pinto, D; Peixoto, B; Goncalves, G; Melo, M; Amorim, V; Bessa, M;

Publicação
PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON GRAPHICS AND INTERACTION (ICGI 2019)

Abstract
Virtual Reality (VR) has been evolving over the years, becoming more and more accessible, in a wide area of applications. One of these areas where VR can have a major impact is training and certification. Hydrogen vehicles are becoming a reality and first responders still lack proper tools and resources to train emergency responses for the purpose. VR can play here a crucial role in ensuring a proper hydrogen emergency response training due to the advantages associated with VR training programs such as resource optimization, repeatability, and replicability. This paper proposes using VR for hydrogen emergency response training by developing a solution composed of three components: tutorial mode, training mode, and certification mode. A usability study is further conducted to evaluate its usability and user satisfaction. The results show that the use of this application regards usability and user satisfaction were extremely positive.

2017

Assessment of Microsoft Kinect in the Monitoring and Rehabilitation of Stroke Patients

Autores
Abreu, J; Rebelo, S; Paredes, H; Barroso, J; Martins, P; Reis, A; Amorim, EV; Filipe, V;

Publicação
RECENT ADVANCES IN INFORMATION SYSTEMS AND TECHNOLOGIES, VOL 2

Abstract
Telerehabilitation is an alternative way for physical therapy of stroke patients. The monitoring and correction of exercises can be done through the analysis of body movements recorded by an optical motion capture system. This paper presents a first study to assess the use of Microsoft Kinect in the monitoring and rehabilitation of patients who have suffered a stroke. A comparative study was carried out to assess the accuracy of joint angle measurement with the Microsoft Kinect (for Windows and for Xbox One) and Optitrack (TM). The results obtained in the first experiment showed a good agreement in the measurements between the three systems, in almost all movements. These results suggest that Microsoft Kinect, a low cost and markerless motion capture system, can be considered as an alternative to complex and high cost motion capture devices for the monitoring and rehabilitation of stroke patients.

2017

PROPULSION SYSTEMS MODELLING FOR MATERIALS HANDLING VEHICLES - FORKLIFTS

Autores
Moura, C; Amorim, EV;

Publicação
PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON ENERGY AND ENVIRONMENT (ICEE 2017)

Abstract
In the material handling industry, productivity is a vital driver of profitability. Efficient operation of a forklift fleet is a significant factor in determining overall warehouse productivity. Traditionally, lead-acid batteries have been the best choice for forklifts operated indoors where emissions are restricted for health and safety reasons. More recently the application of fuel cells in this type of activity has emerged, also guaranteeing operational and environmental benefits (Elgowainy et al., 2009), and it is also shown as a possible solution to increase the productivity of a warehouse (Ballard, 2013). Withing the material handling industry the increased productivity comes through range extension enabling operation of the forklift with quick refuelling, without the need for battery recharging, as well as the existence of a constant power throughout the whole work cycle (Ballard, 2013). The performance of a forklift truck powered by PEM fuel cell or a lead acid battery is modelled and investigated by conducting a parametric study (Hosseinzadeh et al., 2013). In this study as a function of the number of daily trips of a forklift is characterised its energy expenditure, with the purpose of dimensioning, in an intelligent way opt for the most efficient propulsion system. Note that the two systems currently have a very different development stage, because the use of batteries is a technology implemented much more than the fuel cells. Our objective is, according to the workload that the company demands its forklifts to adapt the propulsion system that allows obtaining a greater productivity. In this model is studied several kinds of forklifts of Class I, II and III of the 1000 to 9000 kg in a wide range of loads.

Teses
supervisionadas

2021

Data integration in shop floor for industry 4.0

Autor
Almerindo José Norinho de Oliveira

Instituição
UTAD

2017

Contributos para implementação de Parques Eólicos Offshore em águas profundas. Tecnologias e desafios

Autor
Tiago Samuel Teixeira Azevedo

Instituição
UTAD

2017

Potencial da energia solar concentrada para a produção de eletricidade em Portugal

Autor
Ana Catarina Redondo Gonçalves

Instituição
UTAD

2017

Veículos ligeiros sem emissões na Europa: projeções de mercado e consequências

Autor
Cecília Alexandra Henriques Menezes

Instituição
UTAD

2017

Sistemas fotovoltaicos: Análise comparativa de programas de modelação de energia

Autor
João Pedro Marques Natário

Instituição
UTAD