Browsing by Author "Marreiros, Goreti"
Now showing 1 - 10 of 46
Results Per Page
Sort Options
- ABS4GD: a multi-agent system that simulates group decision processes considering emotional and argumentative aspectsPublication . Marreiros, Goreti; Santos, Ricardo; Ramos, Carlos; Neves, José; Bulas-Cruz, JoséEmotion although being an important factor in our every day life it is many times forgotten in the development of systems to be used by persons. In this work we present an architecture for a ubiquitous group decision support system able to support persons in group decision processes. The system considers the emotional factors of the intervenient participants, as well as the argumentation between them. Particular attention will be taken to one of components of this system: the multi-agent simulator, modeling the human participants, considering emotional characteristics, and allowing the exchanges of hypothetic arguments among the participants.
- Agent based simulation for group formationPublication . Marreiros, Goreti; Santos, Ricardo; Ramos, Carlos; Neves, JoséGroup decision making plays an important role in today’s organisations. The impact of decision making is so high and complex, that rarely the decision making process is made just by one individual. The simulation of group decision making through a Multi-Agent System is a very interesting research topic. The purpose of this paper it to specify the actors involved in the simulation of a group decision, to present a model to the process of group formation and to describe the approach made to implement that model. In the group formation model it is considered the existence of incomplete and negative information, which was identified as crucial to make the simulation closer to the reality.
- Agent Based Simulation for Group FormationPublication . Marreiros, Goreti; Santos, Ricardo; Ramos, Carlos; Neves, JoséGroup decision making plays an important role in today’s organisations. The impact of decision making is so high and complex, that rarely the decision making process is made just by one individual. The simulation of group decision making through a Multi-Agent System is a very interesting research topic. The purpose of this paper it to specify the actors involved in the simulation of a group decision, to present a model to the process of group formation and to describe the approach made to implement that model. In the group formation model it is considered the existence of incomplete and negative information, which was identified as crucial to make the simulation closer to the reality.
- AIRDOC: Smart mobile application for individualized support and monitoring of respiratory function and sounds of patients with chronic osbtructive diseasePublication . Almeida, Rute; Amaral, Rita; Jácome, Cristina; Martinho, Diogo; Vieira-Marques, Pedro; Jacinto, Tiago; Ferreira, Ana; Almeida, Ana; Martins, Constantino; Pereira, Mariana; Pereira, Ana; Valente, José; Almeida, Rafael; Vieira, Ana; Amaral, Rita; Sá-Sousa, Ana; Gonçalves, Ivânia; Rodrigues, Pedro; Alves-Correia, Magna; Freitas, Alberto; Marreiros, GoretiCurrent tools for self-management of chronic obstructive respiratory diseases (CORD) are difficult to use, not individualized and requiring laborious analysis by health professionals, discouraging their use in healthcare. There is an opportunity for cost-effective and easy-to-disseminate advanced technological solutions directed to patients and attractive to different stakeholders. The strategy of AIRDOC is to develop and integrate self-monitoring and self-managing tools, making use of the smartphone's presence in everyday life. AIRDOC intends to innovate on: i) technologies for remote monitoring of respiratory function and computerized lung auscultation; ii) coaching solutions, integrating psychoeducation, gamification and disease management support systems; and iii) management of personal health data, focusing on security, privacy and interoperability. It is expected that AIRDOC results will contribute for the innovation in CORD healthcare, with increased patient involvement and empowerment while providing quality prospective information for better clinical decisions, allowing more efficient and sustainable healthcare delivery.
- Ambient intelligence in emotion based ubiquitous decision makingPublication . Marreiros, Goreti; Santos, Ricardo; Ramos, Carlos; Neves, José; Novais, Paulo; Machado, José; Bulas-Cruz, JoséAs the time goes on, it is a question of common sense to involve in the process of decision making people scattered around the globe. Groups are created in a formal or informal way, exchange ideas or engage in a process of argumentation and counterargumentation, negotiate, cooperate, collaborate or even discuss techniques and/or methodologies for problem solving. In this work it is proposed an agent-based architecture to support a ubiquitous group decision support system, i.e. based on the concept of agent, which is able to exhibit intelligent, and emotional-aware behaviour, and support argumentation, through interaction with individual persons or groups. It is enforced the paradigm of Mixed Initiative Systems, so the initiative is to be pushed by human users and/or intelligent agents.
- An emotional and context-aware model for adapting RSS news to users and groupsPublication . Vinagre, Eugénia; Marreiros, Goreti; Ramos, Carlos; Figueiredo, LinoThe exhibition of information does not always attend to the preferences and characteristics of the users, nor the context that involves the user. With the aim of overcoming this gap, we propose an emotional context-aware model for adapting information contents to users and groups. The proposed model is based on OCC and Big Five models to handle emotion and personality respectively. The idea is to adapt the representation of the information in order to maximize the positive emotional valences and minimize the negatives. To evaluate the proposed model it was developed a prototype for adapting RSS news to users and group of users.
- An Intelligent Coaching Prototype for Elderly CarePublication . Martinho, Diogo; Crista, Vítor; Carneiro, João; Corchado, Juan Manuel; Marreiros, GoretiThe world ageing problem is prompting new sustainable ways to support elderly people. As such, it is important to promote personalized and intelligent ways to assure the active and healthy ageing of the population. Technological breakthroughs have led to the development of personalized healthcare systems, capable of monitoring and providing feedback on different aspects that can improve the health of the elderly person. Furthermore, defining motivational strategies to persuade the elderly person to be healthier and stay connected to such systems is also fundamental. In this work, a coaching system is presented, especially designed to support elderly people and motivate them to pursue healthier ways of living. To do this, a coaching application is developed using both a cognitive virtual assistant to directly interact with the elderly person and provide feedback on his/her current health condition, and several gamification techniques to motivate the elderly person to stay engaged with the application. Additionally, a set of simulations were performed to validate the proposed system in terms of the support and feedback provided to the user according to his progress, and through interactions with the cognitive assistant.
- Anomaly Detection on Natural Language Processing to Improve Predictions on Tourist PreferencesPublication . Meira, Jorge; Carneiro, João; Bolón-Canedo, Verónica; Alonso-Betanzos, Amparo; Novais, Paulo; Marreiros, GoretiArgumentation-based dialogue models have shown to be appropriate for decision contexts in which it is intended to overcome the lack of interaction between decision-makers, either because they are dispersed, they are too many, or they are simply not even known. However, to support decision processes with argumentation-based dialogue models, it is necessary to have knowledge of certain aspects that are specific to each decision-maker, such as preferences, interests, and limitations, among others. Failure to obtain this knowledge could ruin the model’s success. In this work, we sought to facilitate the information acquisition process by studying strategies to automatically predict the tourists’ preferences (ratings) in relation to points of interest based on their reviews. We explored different Machine Learning methods to predict users’ ratings. We used Natural Language Processing strategies to predict whether a review is positive or negative and the rating assigned by users on a scale of 1 to 5. We then applied supervised methods such as Logistic Regression, Random Forest, Decision Trees, K-Nearest Neighbors, and Recurrent Neural Networks to determine whether a tourist likes/dislikes a given point of interest. We also used a distinctive approach in this field through unsupervised techniques for anomaly detection problems. The goal was to improve the supervised model in identifying only those tourists who truly like or dislike a particular point of interest, in which the main objective is not to identify everyone, but fundamentally not to fail those who are identified in those conditions. The experiments carried out showed that the developed models could predict with high accuracy whether a review is positive or negative but have some difficulty in accurately predicting the rating assigned by users. Unsupervised method Local Outlier Factor improved the results, reducing Logistic Regression false positives with an associated cost of increasing false negatives.
- Applying Data Mining Techniques to Improve Breast Cancer DiagnosisPublication . Diz, Joana; Marreiros, Goreti; Freitas, AlbertoIn the field of breast cancer research, and more than ever, new computer aided diagnosis based systems have been developed aiming to reduce diagnostic tests false-positives. Within this work, we present a data mining based approach which might support oncologists in the process of breast cancer classification and diagnosis. The present study aims to compare two breast cancer datasets and find the best methods in predicting benign/malignant lesions, breast density classification, and even for finding identification (mass / microcalcification distinction). To carry out these tasks, two matrices of texture features extraction were implemented using Matlab, and classified using data mining algorithms, on WEKA. Results revealed good percentages of accuracy for each class: 89.3 to 64.7 % - benign/malignant; 75.8 to 78.3 % - dense/fatty tissue; 71.0 to 83.1 % - finding identification. Among the different tests classifiers, Naive Bayes was the best to identify masses texture, and Random Forests was the first or second best classifier for the majority of tested groups.
- Artificial intelligence in digital mental healthPublication . Lopes Martins, Constantino; Martinho, Diogo; Marreiros, Goreti; Conceição, Luís; Faria, Luiz; Simões De Almeida, RaquelThe prevention of diseases considered a scourge of our society, as for example mental illness, particularly anxiety disorders and depressive states, is a primary and urgent goal today and a priority axis of the EU. Mental illness includes many clinical conditions associated with several changes that include limitations related with social interaction or several tasks such as sleeping through the night, doing homework, making friends, thinking capacity and reality understanding, deficits in communication skills, and difficulties in developing appropriate emotional and behavioural response. Artificial intelligence has gained a prominent role in the management and delivery of healthcare. There is a growth in mobile devices applied to health with high mobility, connectivity, and processing capacity. This chapter provides an analysis of the actual trends regarding the main problems that can be dealt with using AI in mental healthcare and the corresponding main techniques used to deal with these problems. Additionally, some case studies for using AI for mental health care are described.