2017
Authors
Abdolmaleki, A; Price, B; Lau, N; Reis, LP; Neumann, G;
Publication
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017
Abstract
Many stochastic search algorithms are designed to optimize a fixed objective function to learn a task, i.e., if the objective function changes slightly, for example, due to a change in the situation or context of the task, relearning is required to adapt to the new context. For instance, if we want to learn a kicking movement for a soccer robot, we have to relearn the movement for different ball locations. Such relearning is undesired as it is highly inefficient and many applications require a fast adaptation to a new context/situation. Therefore, we investigate contextual stochastic search algorithms that can learn multiple, similar tasks simultaneously. Current contextual stochastic search methods are based on policy search algorithms and suffer from premature convergence and the need for parameter tuning. In this paper, we extend the well known CMA-ES algorithm to the contextual setting and illustrate its performance on several contextual tasks. Our new algorithm, called contextual CMAES, leverages from contextual learning while it preserves all the features of standard CMA-ES such as stability, avoidance of premature convergence, step size control and a minimal amount of parameter tuning.
2017
Authors
Ferreira, DC; Reis, LP; Lopes, NV;
Publication
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
Abstract
Nanotechnology is a newand very promising area of research which will allow several new applications to be created in different fields, such as, biological, medical, environmental, military, agricultural, industrial and consumer goods. This paper focuses specifically on nanocommunications, which will allow interconnected devices, at the nano-scale, to achieve collaborative tasks, greatly changing the paradigm in the fields described. Molecular communication is a new communication paradigm which allows nanomachines to exchange information using molecules as carrier. This is the most promising nanocommunication method within nanonetworks, since it can use bio-inspired techniques, inherit from studied biological systems, which makes the connection of biologic and man-made systems a easier process. At this point, the biggest challenges in these type of nanocommunication are to establish feasible and reliable techniques that will allow information to be encoded, and mechanisms that ensure a molecular communication between different nodes. This paper focus on creating concepts and techniques to tackle these challenges, and establishing new foundations on which future work can be developed. The created concepts and techniques are then applied in an envisioned medical application, which is based on a molecular nanonetwork deployed inside the Human body. The goal of this medical application is to automatously monitor endocrine diseases using the benefits of nanonetworks, which in turn connects with the internet, thus creating a Internet of NanoThings system. The concepts and techniques developed are evaluated by performing several simulations and comparing with other researches, and the results and discussions are presented on the later sections of this paper.
2014
Authors
Costa, AP; Loureiro, MJ; Reis, LP;
Publication
Revista Lusofona de Educacao
Abstract
Software process improvement requires a team composed by highly motivated members, good working capabilities and large experience. This type of team allows the implementation of tools and techniques that help to improve communication, coordination and collaboration and cooperation, thus minimizing failures resulting from the development process. Believing on these principles the 4C model emerged as an improvement of the 3C collaboration model. This model was proposed to analyze the Hybrid Methodology for User Centered Development (HMUCD) used to develop the educational resource Courseware Sere - The Human Being and Natural Resources. The 4 model objective is to analyze and propose improvements to educational software development processes. In this study we describe the 3C collaboration model and its evolution to the 4C model. For this we present the data collection and analysis process as well as the techniques used for data analysis and used on the development of the educational resource - Courseware Sere. The 4C model allowed us to identify improvements to HMUCD by adjusting the current development methods and implementing new methods of User Centered Design.
2017
Authors
Rocha, Á; Correia, AM; Adeli, H; Reis, LP; Costanzo, S;
Publication
Advances in Intelligent Systems and Computing
Abstract
2016
Authors
Ferreira, C; Reis, LP; Santos, CP;
Publication
ROBOT 2015: SECOND IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2
Abstract
Each year thousands of people lose their lower limbs, mainly due to three causes: wars, accidents and vascular diseases. The development of prostheses is crucial to improve the quality of millions of people's lives by restoring their mobility. Lower limb prostheses can be divided into three major groups: passive, semi-active or variable damping and powered or intelligent. This contribution provides a literature review of the principal control strategies used in lower limb prostheses, i.e., the controllers used in energetically powered transfemoral and transtibial prostheses. We present a comparison of the presented literature review and the future trends of this important field. It is concluded that the use of bio-inspired concepts and continuous control combined with the other control approaches can be crucial in the improvement of prosthesis controllers, enhancing the quality of amputee's lives.
2017
Authors
Rocha, A; Correia, AMR; Adeli, H; Reis, LP; Costanzo, S;
Publication
WorldCIST (2)
Abstract
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.