Abstract

Abstract

Abstract
This paper proposes a reinforcement learning model for intelligent energy management in buildings, using a UCB1 based approach. Energy management in buildings has become a critical task in recent years, due to the incentives to the increase of energy efficiency and renewable energy sources penetration. Managing the energy consumption, generation and storage in this domain, becomes, however, an arduous task, due to the large uncertainty of the different resources, adjacent to the dynamic characteristics of this environment. In this scope, reinforcement learning is a promising solution to provide adaptiveness to the energy management methods, by learning with the on-going changes in the environment. The model proposed in this paper aims at supporting decisions on the best actions to take in each moment, regarding buildings energy management. A UCB1 based algorithm is applied, and the results are compared to those of an EXP3 approach and a simple reinforcement learning algorithm. Results show that the proposed approach is able to achieve a higher quality of results, by reaching a higher rate of successful actions identification, when compared to the other considered reference approaches.

Abstract
Conducting scientific experiments in driving simulators requires the modeling of reliable and complete road environments. These environments must provide extensive landscapes with the artifacts and natural element that can be usually found in the real world. This paper presents a method to efficiently produce models of natural vegetation. The produced models are then applied to populate existing terrain definitions, allowing the fast preparation of extensive environments with realistic landscapes. The human supervisor can interact in this generation process, in order to obtain custom landscapes definitions. After the landscape generation process, the road network definition can be then generated, producing a complete driving environment, in an integrated modeling process. The proposed method allows modeling a wide range of drive environments, with the realism and quality required to the realization of virtual training or experimental work in many terrain based activities, such driving simulators.

Abstract
Current trends in the development of remote control devices for user interaction with multimedia equipment and applications are increasingly advancing the traditional keypad-based technologies, in order to improve the functionality of remote control devices and also to enhance the user experience. Haptic feedback allows the user to have a similar sensation to that provided by conventional buttons, with the advantage of a much greater flexibility, including dynamic choice of mechanical effects capable of discriminating between different functions. However, selection of haptic feedback effects that are capable of enhancing the user experience remains a great challenge for engineers and product designers. This work is a contribution towards this goal by presenting a usability study of two technologies (eccentric rotating mass and linear resonant actuator) capable of providing different haptic feedback effects in remote control devices. A subjective evaluation study was carried out to obtain subjective scores for a significant number of haptic feedback effects. The number of preferred actuators of each type and whether haptic feedback is suitable in remote control devices for interactive multimedia, were also evaluated. The results of this study show that most users prefer an interface with haptic feedback and different scores were obtained for different haptic feedback effects, according to the characteristics and number of the actuators.

Abstract