Loading...
16 results
Search Results
Now showing 1 - 10 of 16
- Context-based multi-agent recommender system, supported on IoT, for guiding the occupants of a building in case of a firePublication . Neto, Joaquim; Morais, A. Jorge; Gonçalves, Ramiro Manuel Ramos Moreira; Coelho, António LeçaThe evacuation of buildings in case of fire is a sensitive issue for civil society that also motivates the academic community to develop and study solutions to improve the efficiency of evacuating these spaces. The study of human behavior in fire emergencies has been one of the areas that have deserved the attention of researchers. However, this modeling of human behavior is difficult and complex because it depends on factors that are difficult to know and that vary from country to country. In this paper, a paradigm shift is proposed which, instead of focusing on modeling the behavior of occupants, focuses on conditioning this behavior by providing real-time information on the most efficient evacuation routes. Making this information available to occupants is possible with a solution that takes advantage of the growing use of the IoT (Internet of Things) in buildings to help occupants adapt to the environment. Supported by the IoT, multi-agent recommender systems can help users to adapt to the environment and provide the occupants with the most efficient evacuation routes. This paradigm shift is achieved through a context-based multi-agent recommender system based on contextual data obtained from IoT devices, which recommends the most efficient evacuation routes at any given time. The obtained results suggest that the proposed solution can improve the efficiency of evacuating buildings in the event of a fire; for a scenario with two hundred people following the system recommendations, the time they take to reach a safe place decreases by 17.7%.
- Sistema de recomendação Web usando agentesPublication . Morais, A. Jorge; Neto, Joaquim; Oliveira, Eugénio; Jorge, Alípio MárioO crescimento da Web trouxe vários problemas aos utilizadores. A grande quantidade de informação existente hoje em dia em alguns sítios Web torna a procura de informação útil muito difícil. Os objetivos dos proprietários dos sítios Web e dos utilizadores nem sempre coincidem. O conhecimento dos padrões de visitas dos utilizadores é crucial para que os proprietários possam transformar e adaptar o sítio Web. Este é o princípio do sítio Web adaptativo: o sítio Web adapta-se de forma a melhorar a experiência do utilizador. Alguns algoritmos foram propostos para adaptar um sítio da Web. Neste artigo, descrevemos uma proposta de um sistema de recomendação Web baseado em agentes que combina dois algoritmos: regras de associação e filtragem colaborativa. Ambos os algoritmos são incrementais e funcionam com dados binários. Os resultados mostram que, em algumas situações, a abordagem multiagente melhora a capacidade preditiva quando comparada com os agentes individuais.
- Multi-agent web recommendationsPublication . Neto, Joaquim; Morais, A. JorgeDue to the large amount of pages in Websites it is important to collect knowledge about users’ previous visits in order to provide patterns that allow the customization of the Website. In previous work we proposed a multi-agent approach using agents with two different algorithms (associative rules and collaborative filtering) and showed the results of the offline tests. Both algorithms are incremental and work with binary data. In this paper we present the results of experiments held online. Results show that this multi-agent approach combining different algorithms is capable of improving user’s satisfaction.
- Managing research or managing knowledge? A device tool for quality assurancePublication . Monteiro, António; Morais, A. Jorge; Nunes, Marlene; Dias, DianaResearch management promotes an integrated approach to identifying, capturing, evaluating, retrieving, and sharing all of a higher education institutions' research information assets. These assets may include databases, documents, policies and procedures. Conceptually linked, knowledge and research assume critical relevance as an essential tool to insuring Higher Education institutions quality. Institutions are challenged to develop robust (internal) quality assurance systems in which information about scientific production, research projects, staff curricula are considered as relevant indicators. This commitment with science and research is also visible by the opportunities promoted by institutions for the academic development of their staff. Accordingly, the assessment of research and science indicators becomes an essential step for the definition of research development programmes in HE institutions. Based on this framework, it was developed an online questionnaire to be answered by academic staff, trying to assess some science and research indicators. Trying to measure the research potential of all faculty staff, this assessment tool is organized in distinctive four dimensions, namely researcher's (i) biographic data, (ii) scientific identification, scientific outputs (books, Books' chapters, scientific paper indexed and proceedings), (iii) research project with competitive funding and (iv) suggestions to improve research production. In what concerns to the application, all faculty staff members (teachers and researchers) were invited to contribute. The results were presented and discussed personally and collectively with all academic community. These results also provide relevant Key Performance Indicators, also known as KPIs or Key Success Indicators (KSIs), that could help managers and researchers gauge the effectiveness of various functions and processes important to achieving organizational goals. If scientific research is a strategic priority to higher education institutions, this kind of KPIs could be used to help academic managers to assess whether they or their faculty/research staff are on or off target towards those goals.
- An ontology for fire building evacuationPublication . Neto, Joaquim; Morais, A. Jorge; Gonçalves, Ramiro Manuel Ramos Moreira; Coelho, António LeçaGuiding the building occupants under fire emergency to a safe place is an open research problem, and finding solutions to address the problem requires a perfect knowledge of the fire building evacuation domain. The use of ontologies to model knowledge of a domain allows a common and shared understanding of that domain, between people and heterogeneous systems. This paper presents an ontology that aims to build a knowledge model to understand the referred domain better and help develop more capable building evacuation solutions and systems. The herein proposed ontology considers the different variables and actors involved in the fire building evacuation process. We followed the Methontology methodology for its developing, and we present all the development steps, from the specification to its implementation with the Protégé tool.
- Multi-agent-based recommender systems: a literature reviewPublication . Neto, Joaquim; Morais, A. Jorge; Gonçalves, Ramiro Manuel Ramos Moreira; Coelho, António LeçaConsidering the growing volume of information and services available on the Web, it has become essential to provide Web sites and applications with tools, such as recommender systems, capable of helping their users to obtain the information and services appropriate to their interests. Due to the complexity of Web adaptation and the ability of multi-agent systems to deal with complex problems, the multi-agent systems technology have been increasing. In this paper, we present a thorough survey of the use of multi-agent-based recommender systems. The results show that the use of multi-agent systems in recommender systems is increasing. The review shows the diversity of applications of multi-agent systems in recommender systems, namely on what concerns to the diversity of domains, different types of approaches, contributing to improving the performance of the recommendation systems.
- Intelligent monitoring and management platform for the prevention of olive pests and diseases, including IoT with sensing, georeferencing and image acquisition capabilities through computer visionPublication . Alves, Adília; Morais, A. Jorge; Filipe, Vítor; Pereira, JoséClimate change affects global temperature and precipitation patterns. These effects, in turn, influence the intensity and, in some cases, the frequency of extreme environmental events, such as forest fires, hurricanes, heat waves, floods, droughts, and storms. In general, these events can be particularly conducive to the appearance of plant pests and diseases. The availability of models and a data collection system is crucial to manage pests and diseases in sustainable agricultural ecosystems. Agricultural ecosystems are known to be complex, multivariable, and unpredictable. It is important to anticipate crop pests and diseases in order to improve its control in a more ecological and economical way (e.g., precision in the use of pesticides). The development of an intelligent monitoring and management platform for the prevention of pests and diseases in olive groves at Trás-os- Montes region will be very beneficial. This platform must: a) integrate data from multiple data sources such as sensory data (e.g., temperature), biological observations (e.g., insect counts), georeferenced data (e.g., altitude) or digital images (e.g., plant images); b) systematize these data into a regional repository; c) provide relevant forecasts for pest and diseases. Convolutional Neural Networks (CNNs) can be a valuable tool for the identification and classification of images acquired by Internet of Things (IoT).
- Teoria e prática em sistemas de recomendaçãoPublication . Azambuja, Rogério Xavier de; Morais, A. Jorge; Filipe, VítorNas últimas décadas a utilização da inteligência artificial tem sido frequente no desenvolvimento de aplicações computacionais. Mais recentemente a aprendizagem automática, especialmente pelo uso da aprendizagem profunda (deep learning), tem impulsionado o crescimento e ampliado o desenvolvimento de sistemas inteligentes para diferentes domínios. No cenário atual de crescimento tecnológico estão a surgir com maior frequência os sistemas de recomendação (recommender systems) com diferentes técnicas para a filtragem de informações em grandes bases de dados. Um desafio é prover a recomendação adaptativa para mitigar a sobrecarga de informações em ambientes on-line. Este artigo revisa trabalhos anteriores e aborda alguns dos aspectos teórico-conceptuais e teórico-práticos que constituem os sistemas de recomendação, caracterizando o emprego de redes neuronais profundas (Deep Neural Network – DNN) para prover a recomendação sequencial apoiada pela recomendação baseada em sessão.
- An ontological model for fire evacuation route recommendation in buildingsPublication . Neto, Joaquim; Morais, A. Jorge; Gonçalves, Ramiro Manuel Ramos Moreira; Coelho, António LeçaGuiding the occupants of a building to a safe place is an area of research that deserves the attention of researchers. Finding solutions for the problem of guiding the building occupants requires a perfect knowledge of the fire building evacuation domain. The use of ontologies to model the knowledge of a domain allows a common and shared understanding of that domain. This paper presents an ontology that has the purpose to deepen the understanding of that domain and help develop building evacuation solutions and systems capable of guiding the occupants during a building evacuation process. The proposed ontology considers the different variables and actors involved in the fire building evacuation process. The ontology development followed the Methontology methodology, and for implementation, the Protégé tool was used. The ontological model was successfully submitted to a thorough evaluation process and is publicly available on the Web.
- Adaptive recommendation in online environmentsPublication . Azambuja, Rogério Xavier de; Morais, A. Jorge; Filipe, VítorRecommender systems form a class of Artificial Intelligence systems that aim to recommend relevant items to the users. Due to their utility, it has gained attention in several applications domains and is high demanded for research. In order to obtain successful models in the recommendation problem in non-prohibitive computational time, different heuristics, architectures and information filtering techniques are studied with different datasets. More recently, machine learning, especially through the use of deep learning, has driven growth and expanded the sequential recommender systems development. This research focuses on models for managing sequential recommendation supported by session-based recommendation. This paper presents the characterization in the specific theme and the state-of-the-art towards study object of the thesis: the adaptive recommendation to mitigate the information overload in online environments.