Loading...
89 results
Search Results
Now showing 1 - 10 of 89
- IV International Conference on Optimization, Learning Algorithms and Applications: Book of AbstractsPublication . Pereira, Ana I.; Fernandes, Florbela P.; Coelho, João Paulo; Teixeira, João Paulo; Lima, José; Oneto, Luca; Pacheco, Maria F.; Lopes, Rui PedroWelcome to OL2A 2025 - International Conference on Optimization, Learning Algorithms and Applications. OL2A offers a forum for the research community on optimization and learning to get together and share the latest developments and techniques, as well as to develop new paths and collaborations. OL2A provides a broad scope of presentations, covering many areas of optimization and learning and state-of the-art applications to multi-objective optimization, optimization for machine learning, machine learning for optimization, optimization and learning under uncertainty and the fourth industrial revolution. It is with great pleasure that the Organizing Committee welcomes you all to OL2A 2025!
- Optimization, Learning Algorithms and Applications (OL2A 2024) Part IPublication . Pereira, Ana I.; Fernandes, Florbela P.; Coelho, João Paulo; Teixeira, João Paulo; Lima, José; Pacheco, Maria F.; Lopes, Rui Pedro; Álvarez, Santiago T.This volume, CCIS 2280, contains the refereed proceedings of the 4th International Conference on Optimization, Learning Algorithms and Applications (OL2A 2024), a hybrid event held on July 24–26. OL2A provided a space for the research community on optimization and learning to get together and share the latest developments, trends and techniques as well as develop new paths and collaborations. OL2A had the participation of more than three hundred participants in an online and face-to-face environment throughout three days, discussing topics associated with areas such as optimization and learning and state-ofthe- art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty, and the 4th industrial revolution. Three special sessions were organized on the topics Learning Algorithms in Engineering Education, Optimization in the SDG context, and Optimization in Control Systems Design. The event accepted 41 papers. All papers were carefully reviewed and selected from 105 submissions. All the reviews were carefully carried out by a scientific committee of 115 researchers from twenty-six countries.
- Optimization, Learning Algorithms and Applications (OL2A 2024) Part IIPublication . Pereira, Ana I.; Coelho, João Paulo; Teixeira, João Paulo; Lima, José; Pacheco, Maria F.; Lopes, Rui Pedro; Álvarez, Santiago T.; Fernandes, Florbela P.This volume, CCIS 2280, contains the refereed proceedings of the 4th International Conference on Optimization, Learning Algorithms and Applications (OL2A 2024), a hybrid event held on July 24–26. OL2A provided a space for the research community on optimization and learning to get together and share the latest developments, trends and techniques as well as develop new paths and collaborations. OL2A had the participation of more than three hundred participants in an online and face-to-face environment throughout three days, discussing topics associated with areas such as optimization and learning and state-of-the- art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty, and the 4th industrial revolution. Three special sessions were organized on the topics Learning Algorithms in Engineering Education, Optimization in the SDG context, and Optimization in Control Systems Design. The event accepted 41 papers. All papers were carefully reviewed and selected from 105 submissions. All the reviews were carefully carried out by a scientific committee of 115 researchers from twenty-six countries.
- Optimization, learning algorithms and applications: first International Conference, OL2A 2021Publication . Pereira, Ana I. (Ed.); Fernandes, Florbela P. (Ed.); Coelho, João Paulo (Ed.); Teixeira, João Paulo (Ed.); Pacheco, Maria F. (Ed.); Alves, Paulo (Ed.); Lopes, Rui Pedro (Ed.)The volume CCIS 1488 contains the refereed proceedings of the International Conference on Optimization, Learning Algorithms and Applications (OL2A 2021), an event that, due to the COVID-19 pandemic, was held online. OL2A 2021 provided a space for the research community on optimization and learning to get together and share the latest developments, trends, and techniques as well as develop new paths and collaborations. OL2A 2021 had more than 400 participants in an online environment throughout the three days of the conference (July 19–21, 2021), discussing topics associated to areas such as optimization and learning and state-of-the-art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty, and the Fourth Industrial Revolution. Four special sessions were organized under the following topics: Trends in Engineering Education, Optimization in Control Systems Design, Data Visualization and Virtual Reality, and Measurements with the Internet of Things. The event had 52 accepted papers, among which 39 were full papers. All papers were carefully reviewed and selected from 134 submissions. All the reviews were carefully carried out by a Scientific Committee of 61 PhD researchers from 18 countries.
- Optimization, Learning Algorithms and Applications: Third International Conference, OL2A 2023Publication . Pereira, Ana I. (Ed.); Mendes, Armando (Ed.); Fernandes, Florbela P. (Ed.); Pacheco, Maria F. (Ed.); Coelho, João Paulo (Ed.); Lima, José (Ed.)The volumes CCIS 1981 and 1982 contains the refereed proceedings of the III International Conference on Optimization, Learning Algorithms and Applications (OL2A 2023), a hybrid event held on September 27–29. OL2A provided a space for the research community in optimization and learning to get together and share the latest developments, trends and techniques as well as develop new paths and collaborations. OL2A had the participation of more than four hundred participants in an online and face-to-face environment throughout three days, discussing topics associated with areas such as optimization and learning and state-ofthe- art applications related to multi-objective optimization, optimization for machine learning, robotics, health informatics, data analysis, optimization and learning under uncertainty and 4th industrial revolution. Six special sessions were organized under the topics Learning Algorithms in Engineering Education, Optimization in the SDG context, Optimization in Control Systems Design, Computer Vision Based on Learning Algorithms, Machine Learning and AI in Robotics and Machine Learning and Data Analysis in Internet of Things. The event had 66 accepted papers. All papers were carefully reviewed and selected from 172 submissions. All the reviews were carefully carried out by a scientific committee of 115 PhD researchers from 23 countries.
- May the force be with you: an investigation into logging methods using donkeysPublication . Rodrigues, João Brandão; Garrett, Chris; Norris, Stuart; Albuquerque, Francisco Braga; Queijo, Luis; Coelho, João Paulo; Cooke, Fiona; Judge, AndrewWorking equids represent major sources of energy worldwide, and assume an increasingly important role in line with increasing requirements for sustainable energy. The effectiveness of their contributions relies on welfare, especially in the case of donkeys that, due to their size, face more adverse working conditions compared to larger equids. In this study, heart rate and force exerted were monitored while logging using three methods: direct pull, sled, and vehicles. A swingle tree incorporating a dynamometer and data logger was developed for this project, allowing continuous recording of forces. It was hypothesized that logging techniques that suspend (partially or totally) the load from the ground, reduce the force exerted, thus reducing physical effort. This study also aimed to understand if heart rate can be used as an alternative proxy measure when pulling different loads using different methods. Results showed that the greatest force was measured during direct pull (369.66 N), requiring 20% greater force compared to the sled (299.10 N, P <0.001), and 60% greater force than the vehicle (125.11 N, P <0.001). The sled required an additional 58% of force compared to the vehicle (P <0.001). This determines vehicles are the best option for reducing the force exerted by donkeys. Affordability and skills needed to work with this technique, however, are important considerations. Sleds represent a user-friendly solution; reducing the force needed when compared to direct pull, requiring less skills and equipment. The dynamometer proved an excellent method for force monitoring. Heart rate as a proxy measure for force didn’t provide accurate data for lighter loads. Increasing load weight, followed by the increasing force requirements, correlation and explanatory power became greater, indicating that with heavier logs, or methods that display greater force requirements, heart rate may be used as a proxy method for force, but further studies are needed. Keywords: Working donkeys, dynamometer, logging techniques, heart rate, animal welfare.
- Ad-hoc network of smart sensors for mechanical load measurementPublication . Vieira, Manuel; Coelho, João Paulo; Ribeiro, J.E.Strain gauges load cells are transducers devices capable of converting changes in applied mechanical load into an electrical analog signal. Those devices have a large spectrum of applications ranging from domestic to industrial or even medical appliances just to name a few. In this work, they are used in the electronic instrumentation of a force platform that will be used to carry out the analysis and characterization of human biomechanical walking. In this platform, four load cells are installed, each one capable of measuring forces along two different axis. A total of eight strain-gauges per load cell are employed. Hence, analog signal transmission, besides requiring a large number of connection wires, is prone to interference and noise. Moreover, with this solution, scalability requires severe changes in the connection topology. In order to circumvent those problems, an alternative in-situ signal conditioning and digital data transmission system was devised. This approach, as far as investigated, presents an innovative solution to signal conditioning and data transmission for load-cells. In particular, the presented solution allows the creation of an ad-hoc network of load cells, using the I²C protocol with a master interface that allows the users to interact and change the parameters of each load cell. This instrumentation structure has been successfully tested and the obtained results are documented in this article
- Manual de boas práticas de segurança e saúde no trabalho apícola uma abordagem para uma cultura de segurança no setorPublication . Pires, Sância; Martins, Vitor Manuel Ramalheira; Igrejas, Getúlio; Coelho, João Paulo; Machado, Ana; Pereira, Ana Paula; Nunes, SofiaA qualidade das condições de trabalho é um dos fatores fundamentais para o sucesso de um sistema produtivo e, o mesmo, também se aplica ao setor apícola. Nesse âmbito, a melhoria da produtividade e da competitividade depende, necessariamente, de uma intervenção no sentido da perceção e melhoria das condições de trabalho. Neste contexto, a elaboração de um Manual de Boas Práticas de Segurança e Saúde no trabalho apícola pretende dar continuidade ao incremento e transferência de conhecimentos técnicos aos apicultores e a todos os agentes envolvidos nesta atividade, contribuindo para uma melhor estruturação do setor. Tendo em consideração a reduzida quantidade de literatura que se encontra disponível, incluindo manuais e outros documentos referentes a Boas Práticas de Segurança e Saúde no trabalho apícola, considera-se que a elaboração de um manual, não vinculativo e de caráter orientador, poderá trazer um contributo relevante e pertinente para a atividade.
- A multilayer model predictive control methodology applied to a biomass supply chain operational levelPublication . Pinho, Tatiana M.; Coelho, João Paulo; Veiga, Germano; Moreira, António Paulo G. M.; Boaventura-Cunha, JoséForest biomass has gained increasing interest in the recent years as a renewable source of energy in the context of climate changes and continuous rising of fossil fuels prices. However, due to its characteristics such as seasonality, low density, and high cost, the biomass supply chain needs further optimization to become more competitive in the current energetic market. In this sense and taking into consideration the fact that the transportation is the process that accounts for the higher parcel in the biomass supply chain costs, this work proposes a multilayer model predictive control based strategy to improve the performance of this process at the operational level. The proposed strategy aims to improve the overall supply chain performance by forecasting the system evolution using behavioural dynamic models. In this way, it is possible to react beforehand and avoid expensive impacts in the tasks execution. The methodology is composed of two interconnected levels that closely monitor the system state update, in the operational level, and delineate a new routing and scheduling plan in case of an expected deviation from the original one. By applying this approach to an experimental case study, the concept of the proposed methodology was proven. This novel strategy enables the online scheduling of the supply chain transport operation using a predictive approach.
- CONTROLO 2020: Proceedings of the 14th APCA International Conference on Automatic Control and Soft ComputingPublication . Gonçalves, José (Ed.); Braz-César, Manuel (Ed.); Coelho, João Paulo (Ed.)Going to a conference is always an opportunity to establish contacts with other researchers and to grow culturally. Often, from informal conversations fostered by the conference’s social programme, synergies are generated, leading to new ideas and partnerships. Indeed, networking is the fundamental reason for being present at any conference. Moreover, every time we visit a new country, distinct realities are observed and a kind of mild acculturation happens. Experiences gathered from travelling shape our vision of the world and promote cultural enrichment. The CONTROLO 2020 Conference was intended not only to be a scientific event, but also to give the opportunity for the control community to know Bragança, the Polytechnic Institute of Bragança, and to network face-to-face in friendly, safe, stimulating and international environment. The city was prepared to receive this scientific community, with a welcome reception at the Castle of Bragança and a gala dinner at the gardens of the Abade de Baçal Museum, providing all the participants to get in touch with some of the most important landmarks of the Bragança cultural heritage. The ideal situation would be to communicate in person but, due to the current pandemic situation, the CONTROLO 2020 Conference was forced to change to an online event. In spite of all these difficulties, the decision to maintain the date of this event has demonstrated the resilience of APCA in adapting to extreme conditions. In addition, it was also important in this decision-making, to ensure that the dissemination of the research and development works, submitted and accepted for publication, would be made public in due time. A total of 93 papers, originating from 39 different countries, were submitted for publication, from which 76 were accepted, after an evaluation process that totalled more than 300 reviews. Besides its six special sessions and a MATLAB course, the CONTROLO 2020 Conference had the honour of having five of the most relevant personalities in automatic control community in its five plenary sessions, namely professors André Preumont, Eduardo Camacho, Karl Johansson, Kevin Passino and Sebástian Dormido. We hope that all interested readers can benefit scientifically from this conference proceedings.