Rogerio de Moraes Calazan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rogerio de Moraes Calazan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Nadia Nedjah
State University of Rio de Janeiro
10 shared publications - Luiza de Macedo Mourelle
State University of Rio de Janeiro
9 shared publications - Orlando Camargo Rodríguez
University of Algarve
3 shared publications - Chao Wang
University of Science and Technology of China
1 shared publication Orlando Camargo Rodríguez
LARSyS, Campus de Gambelas, University of Algarve, Faro, PT-8005-139, Portugal
1 shared publication- Pedro Mendes Diniz
Brazilian Navy Research Institute
1 shared publication
Latest Publications
- 1 June 2023
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 153 (6) , 3201
Integrating modeled environmental variability into neural network training for underwater source localization
Supervised machine learning (ML) is a powerful tool that has been applied to many fields of underwater acoustics, including acoustic inversion. ML algorithms depend on the existence of extensive labeled datasets, which are difficult to obtain for the task of underwater source localization. A feed-forward neural network (FNN) trained on imbalanced or biased data may end up suffering from a problem analogous to model mismatch in matched field processing (MFP), that is, producing incorrect results due to a difference between the environment sampled by the training data and the actual environment. To overcome this issue, physical and numerical propagation models can act as data augmentation tools to compensate for the lack of comprehensive acoustic data. This paper examines how modeled data can be effectively used for training FNNs. Mismatch tests compare the output from a FNN and MFP and show that the network becomes more robust to various kinds of mismatches when trained on diverse environments. A systematic analysis of how the training dataset's variability impacts a FNN's localization performance on experimental data is carried out. Results show that networks trained with synthetic data achieve better and more robust performance than regular MFP when environment variability is taken into account.
- 1 June 2023
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 153 (6) , 3201
Integrating modeled environmental variability into neural network training for underwater source localization
Supervised machine learning (ML) is a powerful tool that has been applied to many fields of underwater acoustics, including acoustic inversion. ML algorithms depend on the existence of extensive labeled datasets, which are difficult to obtain for the task of underwater source localization. A feed-forward neural network (FNN) trained on imbalanced or biased data may end up suffering from a problem analogous to model mismatch in matched field processing (MFP), that is, producing incorrect results due to a difference between the environment sampled by the training data and the actual environment. To overcome this issue, physical and numerical propagation models can act as data augmentation tools to compensate for the lack of comprehensive acoustic data. This paper examines how modeled data can be effectively used for training FNNs. Mismatch tests compare the output from a FNN and MFP and show that the network becomes more robust to various kinds of mismatches when trained on diverse environments. A systematic analysis of how the training dataset's variability impacts a FNN's localization performance on experimental data is carried out. Results show that networks trained with synthetic data achieve better and more robust performance than regular MFP when environment variability is taken into account.
- 1 October 2020
- Published by Springer Nature
- Vol. 12249, 485-500
Numerical Enhancements and Parallel GPU Implementation of a 3D Gaussian Beam Model
Despite the increasing performance of modern processors it is well known that the majority of models that account for 3D underwater acoustic predictions still require a high computational cost. In this context, this work presents strategies to enhance the computational performance of a ray-based 3D model. First, it is presented an optimized method for acoustic field calculations, that accounts for a large number of sensors. Second, the inherent parallelism of ray tracing and the high workload of 3D propagation are carefully considered, leading to the development of parallel algorithms for field predictions using a GPU architecture. The strategies were validated through performance analyses and comparisons with experimental data from a tank scale experiment, and the results show that model predictions are computationally efficient and accurate. The combination of numerical enhancements and parallel computing allowed to speedup model calculations for a large number of receivers.
- 1 October 2020
- Published by Springer Nature
- Vol. 12249, 485-500
Numerical Enhancements and Parallel GPU Implementation of a 3D Gaussian Beam Model
Despite the increasing performance of modern processors it is well known that the majority of models that account for 3D underwater acoustic predictions still require a high computational cost. In this context, this work presents strategies to enhance the computational performance of a ray-based 3D model. First, it is presented an optimized method for acoustic field calculations, that accounts for a large number of sensors. Second, the inherent parallelism of ray tracing and the high workload of 3D propagation are carefully considered, leading to the development of parallel algorithms for field predictions using a GPU architecture. The strategies were validated through performance analyses and comparisons with experimental data from a tank scale experiment, and the results show that model predictions are computationally efficient and accurate. The combination of numerical enhancements and parallel computing allowed to speedup model calculations for a large number of receivers.
- 1 April 2018
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 143 (4) , 2059-2065
Simplex based three-dimensional eigenray search for underwater predictions
A solution for the calculation of three-dimensional (3D) eigenrays based on Simplex optimization, implemented in a 3D Gaussian beam model, is investigated in this paper. The validation and performance of the solution were analyzed through comparisons against an equivalent (flat) two-dimensional waveguide, and against results of a tank scale experiment presented in Sturm and Korakas [(2013). J. Acoust. Soc. Am. 133(1), 108–118], in which cross-slope propagation in a wedge waveguide with a mild slope was considered. It was found that the search strategy based on Simplex optimization was able to calculate efficiently and accurately 3D eigenrays, thus providing predictions of arrival patterns along cross-slope range, which replicated elaborate patterns of mode shadow zones, intra-mode interference, and mode arrivals. A remarkable aspect of the search strategy was its ability to provide accurate values of initial eigenray elevation and azimuth, within the accuracy defined for the eigenray to arrive at the location of a given hydrophone.
- 1 April 2018
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 143 (4) , 2059-2065
Simplex based three-dimensional eigenray search for underwater predictions
A solution for the calculation of three-dimensional (3D) eigenrays based on Simplex optimization, implemented in a 3D Gaussian beam model, is investigated in this paper. The validation and performance of the solution were analyzed through comparisons against an equivalent (flat) two-dimensional waveguide, and against results of a tank scale experiment presented in Sturm and Korakas [(2013). J. Acoust. Soc. Am. 133(1), 108–118], in which cross-slope propagation in a wedge waveguide with a mild slope was considered. It was found that the search strategy based on Simplex optimization was able to calculate efficiently and accurately 3D eigenrays, thus providing predictions of arrival patterns along cross-slope range, which replicated elaborate patterns of mode shadow zones, intra-mode interference, and mode arrivals. A remarkable aspect of the search strategy was its ability to provide accurate values of initial eigenray elevation and azimuth, within the accuracy defined for the eigenray to arrive at the location of a given hydrophone.
- 29 July 2017
- Published by Springer Nature
- p. 215-224
A Fine-Grained Parallel Particle Swarm Optimization on Many-core and Multi-core Architectures
- 29 July 2017
- Published by Springer Nature
- p. 215-224
A Fine-Grained Parallel Particle Swarm Optimization on Many-core and Multi-core Architectures
- 6 July 2017
- Published by Springer Nature
- p. 43-55
Parallel Ray Tracing for Underwater Acoustic Predictions
- 6 July 2017
- Published by Springer Nature
- p. 43-55
Parallel Ray Tracing for Underwater Acoustic Predictions
- Open Access
- 31 March 2017
- Published by Springer Nature
- p. 183-190
TRACEO3D Ray Tracing Model for Underwater Noise Predictions
- 31 March 2017
- Published by Springer Nature
- p. 183-190
Open AccessTRACEO3D Ray Tracing Model for Underwater Noise Predictions
- 5 June 2015
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 44 (6) , 1173-1199
Parallel Implementations of the Cooperative Particle Swarm Optimization on Many-core and Multi-core Architectures
- 5 June 2015
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 44 (6) , 1173-1199
Parallel Implementations of the Cooperative Particle Swarm Optimization on Many-core and Multi-core Architectures
- 9 January 2015
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 59 (6) , 810-835
Particle, Dimension and Cooperation-Oriented PSO Parallelization Strategies for Efficient High-Dimension Problem Optimizations on Graphics Processing Units
Particle swarm optimization (PSO) is an evolutionary heuristics-based method used for continuous function optimization. Compared with existing stochastic methods, PSO is very robust. Nevertheless, for real-world optimizations, it requires a high computational effort. In general, parallel implementations of PSO provide better performance. However, this depends heavily on the parallelization strategy engineered as well as the number and characteristics of the exploited processors. In this paper, we analyze three different parallelization strategies: a Particle-oriented Strategy (PoS); a Dimension-oriented Strategy (DoS) and a Cooperation-oriented Strategy (CoS). PoS parallelizes the particle's work. DoS focuses on the work done with respect to each of the problem dimensions and does it in parallel. CoS subdivides the optimization problem into many simpler subproblems, each of which focuses on a distinct subset of the original problem dimensions. The optimization work for all the yielded subproblems is done in parallel. Note that in the second and third strategies, all particles act in parallel too. We map the three strategies onto a Graphics Processing Units (GPU)-based architecture. The performance of the implementations is evaluated using four benchmark functions, considering high-dimension instances. We compare the speedups achieved by the GPU-based implementations of the considered parallelization strategies to the reference sequential PSO implementation as well as to existing PSO implementation on Graphics Processing Units.
- 9 January 2015
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 59 (6) , 810-835
Particle, Dimension and Cooperation-Oriented PSO Parallelization Strategies for Efficient High-Dimension Problem Optimizations on Graphics Processing Units
Particle swarm optimization (PSO) is an evolutionary heuristics-based method used for continuous function optimization. Compared with existing stochastic methods, PSO is very robust. Nevertheless, for real-world optimizations, it requires a high computational effort. In general, parallel implementations of PSO provide better performance. However, this depends heavily on the parallelization strategy engineered as well as the number and characteristics of the exploited processors. In this paper, we analyze three different parallelization strategies: a Particle-oriented Strategy (PoS); a Dimension-oriented Strategy (DoS) and a Cooperation-oriented Strategy (CoS). PoS parallelizes the particle's work. DoS focuses on the work done with respect to each of the problem dimensions and does it in parallel. CoS subdivides the optimization problem into many simpler subproblems, each of which focuses on a distinct subset of the original problem dimensions. The optimization work for all the yielded subproblems is done in parallel. Note that in the second and third strategies, all particles act in parallel too. We map the three strategies onto a Graphics Processing Units (GPU)-based architecture. The performance of the implementations is evaluated using four benchmark functions, considering high-dimension instances. We compare the speedups achieved by the GPU-based implementations of the considered parallelization strategies to the reference sequential PSO implementation as well as to existing PSO implementation on Graphics Processing Units.
- 1 January 2014
- Published by Elsevier in Applied Soft Computing
- Vol. 14, 347-356
A hardware accelerator for Particle Swarm Optimization
- 1 January 2014
- Published by Elsevier in Applied Soft Computing
- Vol. 14, 347-356
A hardware accelerator for Particle Swarm Optimization
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 356-361
A Cooperative Parallel Particle Swarm Optimization for High-Dimension Problems on GPUs
Particle Swarm Optimization (PSO) is an evolutionary heuristics-based method used for continuous function optimization. Compared to existing stochastic methods, PSO is very robust. Nevertheless, for real-world optimizations, it requires a high computational effort. In general, parallel implementations of PSO provide better performance. However, this depends heavily on the parallelization strategy engineered as well as the number and characteristics of the exploited processors. In this paper, we propose a cooperative strategy, which consists of subdividing an optimization problem into many simpler sub problems. Each of these sub-problems focuses on a distinct subset of the original problem dimensions. The optimization work for all the selected sub-problems is done in parallel. We map the work onto a GPU-based architecture. The performance of the strategy thus implemented is evaluated for four benchmark functions with high-dimension and different complexity and compared to that yielded by other parallelization strategies.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 356-361
A Cooperative Parallel Particle Swarm Optimization for High-Dimension Problems on GPUs
Particle Swarm Optimization (PSO) is an evolutionary heuristics-based method used for continuous function optimization. Compared to existing stochastic methods, PSO is very robust. Nevertheless, for real-world optimizations, it requires a high computational effort. In general, parallel implementations of PSO provide better performance. However, this depends heavily on the parallelization strategy engineered as well as the number and characteristics of the exploited processors. In this paper, we propose a cooperative strategy, which consists of subdividing an optimization problem into many simpler sub problems. Each of these sub-problems focuses on a distinct subset of the original problem dimensions. The optimization work for all the selected sub-problems is done in parallel. We map the work onto a GPU-based architecture. The performance of the strategy thus implemented is evaluated for four benchmark functions with high-dimension and different complexity and compared to that yielded by other parallelization strategies.