Richard José Duro

Richard José Duro

Auto-generated profile, based on publicly available information

Richard José Duro

Universidade da Coruña

Research Focus & Metrics

Academic Career Length

32Years (1995-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 October 2010 in IEEE Transactions on Autonomous Mental Development
Verified
Journal Article
Closed access
Francisco Bellas BouzaFrancisco Bellas Bouza
Francisco Bellas Bouza
RDRichard J. Duro
Richard J. Duro
AFAndrés Faina
Andrés Faina
DSDaniel Souto
Daniel Souto
The multilevel Darwinist brain (MDB) is a cognitive architecture that follows an evolutionary approach to provide autonomous robots with lifelong adaptation. It has been tested in real robot on-line learning scenarios obtaining successful results that reinforce the evolutionary principles that constitute the main original contribution of the MDB. This preliminary work has lead to a series of improvements in the computational implementation of the architecture so as to achieve realistic operation in real time, which was the biggest problem of the approach due to the high computational cost induced by the evolutionary algorithms that make up the MDB core. The current implementation of the architecture is able to provide an autonomous robot with real time learning capabilities and the capability for continuously adapting to changing circumstances in its world, both internal and external, with minimal intervention of the designer. This paper aims at providing an overview or the architecture and its operation and defining what is required in the path towards a real cognitive robot following a developmental strategy. The design, implementation and basic operation of the MDB cognitive architecture are presented through some successful real robot learning examples to illustrate the validity of this evolutionary approach.

8 November 2022 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
Francisco Bellas BouzaFrancisco Bellas Bouza
Francisco Bellas Bouza
SGSara Guerreiro-Santalla
Sara Guerreiro-Santalla
MNMartin Naya
Martin Naya
RDRichard J. Duro
Richard J. Duro
This paper presents a proposal of specific curriculum in Artificial Intelligence (AI) for high school students, which has been organized as a two-year subject. The curriculum was designed based on two premises. The first one is that, although the proposal is targeted to scientific programmes, the involved students and teachers do not have any previous knowledge about AI. Accordingly, the teaching units have been designed with the aim of supporting teachers in a new discipline for them and, in addition, providing an introductory level to students. The main didactical objective is to establish the fundamentals of AI from a practical perspective, learning technical concepts by using them to solve specific problems. The approach that has been followed in the teaching units is focused on developing embedded intelligence solutions, that is, programming real-world devices which interact with real environments. To this end, and to address a second fundamental premise of low investment capability at schools, it has been decided to use Smartphones as the central technological element to implement such embedded intelligence at classes. This curriculum has been developed within the Erasmus + project entitled "AI + : Developing an Artificial Intelligence Curriculum adapted to European High School". The project was carried out by a team of AI experts and high school teachers who created the teaching units, and a group of students that tested them for three years, providing feedback to make the curriculum feasible for its introduction in schools in the short-term. The main results obtained from its implementation within the project scope are presented and discussed here, with the aim of contributing to the AIEd community progress by means of a practical pilot experience. Although the curriculum has been designed and tested at European level, it has been created with a general perspective of AI education, so it can be applied worldwide.

1 July 2010 in Information Sciences
Verified
Journal Article
Closed access
RDR.J. Duro
R.J. Duro
MGManuel Grana
Manuel Grana
JAJavier de Lope Asiaín
Javier de Lope Asiaín

22 March 2010 in Sensors
Verified
Journal Article
Open access
PDF file
JVJavier Vales-Alonso
Javier Vales-Alonso
PLPablo López-Matencio
Pablo López-Matencio
Francisco Javier González-CastañoFrancisco Javier González-Castaño
Francisco Javier González-Castaño
HNHonorio Navarro-Hellín
Honorio Navarro-Hellín
PBPedro J. Baños-Guirao
Pedro J. Baños-Guirao
RDRichard Duro-Fernández
Richard Duro-Fernández
Several research programs are tackling the use of Wireless Sensor Networks (WSN) at specific fields, such as e-Health, e-Inclusion or e-Sport. This is the case of the project “Ambient Intelligence Systems Support for Athletes with Specific Profiles”, which intends to assist athletes in their training. In this paper, the main developments and outcomes from this project are described. The architecture of the system comprises a WSN deployed in the training area which provides communication with athletes’ mobile equipments, performs location tasks, and harvests environmental data (wind speed, temperature, etc.). Athletes are equipped with a monitoring unit which obtains data from their training (pulse, speed, etc.). Besides, a decision engine combines these real-time data together with static information about the training field, and from the athlete, to direct athletes’ training to fulfill some specific goal. A prototype is presented in this work for a cross country running scenario, where the objective is to maintain the heart rate (HR) of the runner in a target range. For each track, the environmental conditions (temperature of the next track), the current athlete condition (HR), and the intrinsic difficulty of the track (slopes) influence the performance of the athlete. The decision engine, implemented by means of (m; s)-splines interpolation, estimates the future HR and selects the best track in each fork of the circuit. This method achieves a success ratio in the order of 80%. Indeed, results demonstrate that if environmental information is not take into account to derive training orders, the success ratio is reduced notably.

1 November 2013 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
AFAndrés Faíña
Andrés Faíña
Francisco Bellas BouzaFrancisco Bellas Bouza
Francisco Bellas Bouza
FLFernando López-Peña
Fernando López-Peña
RDRichard J. Duro
Richard J. Duro

1 July 1999 in IEEE Transactions on Neural Networks
Verified
Journal Article
Closed access
RDR.J. Duro
R.J. Duro
JRJ.S. Reyes
J.S. Reyes
The aim of this paper is to endow a well-known structure for processing time-dependent information, synaptic delay-based ANN's, with a reliable and easy to implement algorithm suitable for training temporal decision processes. In fact, we extend the backpropagation algorithm to discrete-time feedforward networks that include adaptable internal time delays in the synapses. The structure of the network is similar to the one presented by [1], that is, in addition to the weights modeling the transmission capabilities of the synaptic connections, we model their length by means of a parameter that indicates the delay a discrete-event suffers when going from Zthe origin neuron to the target neuron through a synaptic connection. Like the weights, these delays are also trainable, and a training algorithm can be derived that is almost as simple as the backpropagation algorithm, and which is really an extension of it. We present examples of the application of these networks and algorithm to the prediction of time series and to the recognition of patterns in electrocardiographic signals. In the first case, we employ the temporal reasoning characteristics of these networks for the prediction of future values in a benchmark example of a time series: the one governed by the Mackey-Glass chaotic equation. In the second case, we provide a real life example. The problem consists in identifying different types of beats through two levels of temporal processing, one relating the morphological features which make up the beat in time and another one that relates the positions of beats in time, that is, considers rhythm characteristics of the ECG signal. In order to do this, the network receives the signal sequentially, no windowing, segmentation, or thresholding are applied.