Abel G. da Silva Filho

Hyperspectral images clustering on reconfigurable hardware using the k-means algorithm

Unsupervised clustering is a powerful technique for understanding multispectral and hyperspectral images, k-means being one of the most used iterative approaches. It is a simple though computationally expensive algorithm, particularly for clustering large hyperspectral images into many categories. Software implementation presents advantages such as flexibility and low cost for implementation of complex functions. However, it presents limitations, such as difficulties in exploiting parallelism for high performance applications. In order to accelerate the k-means clustering, a hardware implementation could be used. The disadvantage in this approach is that any change in the project requires previous knowledge of the hardware design process and can take several weeks to be implemented. In order to improve the design methodology, an automatic and parameterized implementation for hyperspectral images has been developed in a hardware/software codesign approach. An unsupervised clustering technique k-means that uses the Euclidian distance to calculate the pixel to centers distance was used as a case study to validate the methodology. Two implementations, a software and a hardware/software codesign one, have been implemented. Although the hardware component operates at 40 MHz, being 12.5 times less than the software operating frequency (PC), the codesign implementation was approximately 2 times faster than software one.

A partial reconfigurable architecture for controllers based on Petri nets

The digital control systems in industry has been used in most of the applications based on expensive programmable logical controllers (PLC). These systems are, in general, highly complex and slow, with an operation cycle around 10 ms. In this work, a reconfigurable logic controller (RLC) approach is presented, based on a small and low cost Xilinx Virtex-II FPGA architecture, operating as a virtual hardware machine. In this context, the main process is specified in a formal language, based on Petri nets or SFC (sequential function chart). For applications that demand more hardware than that available in the FPGA, a partial reconfiguration mechanism takes place. From the Petri net specification, the main process is split into multiple contexts, which are sequentially executed within the same FPGA, without violating the operation cycle of application.

An Ant Colony metaheuristic for energy aware application mapping on NoCs

The increasing number and complexity of tasks running on embedded systems demands more and more processors. The traditional bus based communication architecture are not scalable for high performance applications requiring a large number of processors. In this sense NoC-based MPSoC have been proposed to address these limitations. One critical problem in NoC based MPSoC is the communication costs. This cost depends on the task mapping into the processors. This paper presents an approach that uses an Ant Colony meta-heuristic to assign a set of tasks to a set of processors in a NoC-based MPSoC. The proposed approach evaluates tasks mappings while optimizing the traffic and the power consumption in the NoC. The result of applying our approach in MPEG and image segmentation applications shows that our technique was able to find a task mapping that reduces the traffic and energy consumption. Compared with the worst case solutions, our approach was able to find a task allocation that reduces the traffic and also the energy consumption of about 42% and 69% for the MPEG; and 51% and 69% for the image segmentation.

A timed Petri net approach for pre-runtime scheduling in partial and dynamic reconfigurable systems

Dynamic reconfigurable systems (DRS) offer a very interesting alternative for embedded digital systems design. Tasks scheduling within a reconfigurable environment allows the development of systems with better execution performance, chip area economy and lower power consumption. This paper describes an algorithm for design of dynamically reconfigurable systems where tasks scheduling have as prime objective the overall application performance speedup. The methodology includes the generation of an embedded controller supporting the scheduling process in a target architecture.

Ilera-Aiye: A virtual world for the development of serious games for health education and promotion in the Northeastern Brazilian countryside

The level of basic care in Brazils Unified Health System is a community-based attention model composed by Family Health Units, small teams of health professionals intended to solve low-complexity problems at a territory delimitated by a certain number of families, attended by Communitary Health Agents. Despite the large amount of social inequalities in Brazilian countryside, smartphones and tablets are becoming more widespread among rural population. According to Popular Education, the teaching-learning process is improved when the educator is part of the process as a facilitator, considering the prior knowledge of learners and their social, cultural and historical background, in a relationship mediated by affection, which can be reached by using games. This work proposes Ilera-Ayie (from Yoruba language, Land of Health), a virtual world to support 3D serious games for health education and promotion, focused on the communitary health agents and the young population of rural settlements at Brazils northeastern countryside. Non-functional requirements elicitation was performed by using participatory workshops involving participants of two rural settlements at the Northern Forest region of the State of Pernambuco, northeast of Brazil. Taking into account Popular Education and Participatory Design as theoretical backgrounds, design elements of the virtual world were defined using participatory workshops, considering identity aspects of communities, such as the local vegetation, animals, houses, historic buildings of the Brazils Empire age of slavery, and musical elements, trying to make a link between local and universal cultural elements.

Dynamical Critical Exponent for the Majority-Vote Model

We investigate the dynamical behavior of the isotropic majority-vote model on a square lattice using a combination of damage spreading and finite-size scaling methods. For initial damage D(0)≥1/2, the dynamical phase diagram exhibits a chaotic-frozen phase transition at a critical noise parameter qc=0.0818±0.0002, while for D(0)≤1/2 the damage does not propagate for any value of the models parameter 0≤q<1/2. From simulations at qc, we find that the dynamical critical exponent is z=0.65±0.05.

Developing 3D human-computer interfaces and serious games for health education in the Brazilian countryside using participatory design and popular education

The basic health care level in Brazils Unified Health System consists of a community-based attention model composed by small teams of health professionals dedicated to deal with low-complexity problems. Despite the social and economic advances experimented in the last two decades, social inequalities still persist in Brazilian countryside. However, smartphones and tablets are becoming more widespread among rural population. According to Popular Education, teaching-learning processes are specially put forward when educators assume the role of facilitators, taking into account the prior knowledge of learners, their cultural and historical background, and the real problems in which they are immersed. Popular Education claims that the interaction between educators and educands should be mediated by affection, a dimension that can be easily reached by using games. Herein this work we discuss the use of Popular Education to promote Participatory Design in order to build Ilera-Ayie, a 3D virtual world to support serious games for food and nutritional education and health promotion, and a puzzle-based minigame inserted in this virtual world, focused on the communitary health agents and the young population of rural settlements at Brazils northeastern countryside.

A methodology to design low cost mobile applications for health for rural communities using participatory design and popular education

Most of the food consumed in Brazilian cities, as in other big urban spaces, is produced by family farming. The economic sustainability of these family communities depends on the range of primary health care. The rational use of medicinal plants is recognized by the World Health Organization (WHO) as an important element of healing practices and nutrition education. Mobile health applications can contribute to both the rational use of medicinal plants and herbal medicines as to the health sustainability of family farming communities, improving the quality of primary health care in ethnic and traditional communities and the preservation of popular knowledge. This paper proposes a methodology for the development of applications for mobile devices geared to popular health education based on participatory human-computer interface design and popular education, taking into account to improve the quality of basic health care by aiding communitary health agents and popular communities at health education for the rational use of medicinal plants. As a case study we developed a basic architecture and a prototype based on Android, from the results of participatory workshops in a rural area of the North Forest in the State of Pernambuco, Brazil. The participatory workshops were designed to promote the proposed methodology of combining participatory design and popular education.

Tuning Mechanism for Two-Level Cache Hierarchy Intended for Instruction Caches and Low Energy Consumption

Configurable cache tuning architectures for embedded systems applications can dramatically reduce energy consumption. Existing state-of-the-art heuristics to efficiently explore large configurable cache design space has aimed at finding the cache configuration that yields the minimal energy consumption. However, as energy-driven cache optimizations may reach great energy reduction, the overall system performance is often penalized by considering only a single-metric energy cost function. In this paper, we propose an automated exploration mechanism for adjusting two-level cache hierarchies in order to reduce energy consumption for embedded applications, by keeping up the high performance computing. In our experiments, we applied our heuristic to 12 different benchmarks from the MiBench. The results show an average reduction of about 41% in the energy consumption for instruction caches when compared to existing heuristics and a reduction by about 25% the number of cycles needed to execute a given application

CDFG-Petri net temporal partitioning for switching context applications

Reconfigurable computing has made promising progress. The development of platforms that match the reconfigurable hardware with programmable elements, such as DSPs or microprocessors, promise great applicability in diverse areas in the future. In this article, we describe a co-design methodology for single-context and virtual hardware applications based on Petri nets for the PISH design environment. A platform description is presented as well as the reconfiguration methodology. A temporal partitioning is described, exploring different solutions for different applications with time and communication constraints.