A5072426521- Parallel Computing and Optimization Techniques
- Embedded Systems Design Techniques
- Effects of Environmental Stressors on Livestock
- Interconnection Networks and Systems
- Irrigation Practices and Water Management
- IoT and Edge/Fog Computing
- Machine Learning in Bioinformatics
- Animal Behavior and Welfare Studies
- Distributed and Parallel Computing Systems
- Advanced Data Storage Technologies
- Genomics and Phylogenetic Studies
- Algorithms and Data Compression
- Meat and Animal Product Quality
- Energy Efficient Wireless Sensor Networks
- Milk Quality and Mastitis in Dairy Cows
- VLSI and FPGA Design Techniques
- Enzyme Production and Characterization
- Thermoregulation and physiological responses
- Soil Mechanics and Vehicle Dynamics
- Seismic Imaging and Inversion Techniques
- Real-Time Systems Scheduling
- Polysaccharides and Plant Cell Walls
- Advanced Numerical Methods in Computational Mathematics
- Sugarcane Cultivation and Processing
- Botanical Research and Applications
Universidade Federal Rural de Pernambuco
2013-2024
Universidade Federal de Pernambuco
2008-2024
Universidade de Pernambuco
2012
Centro Universitário da Cidade
2008
The use of precision livestock has increased due to the need improve efficiency and productivity required by high food demand. Monitoring cattle behavior is a fundamental requirement for sustainable development quality control inputs industry. In this regard, there are several proposed solutions in decision-making. work, we present survey on monitoring classifying behavior. After selection, analyzed 17 papers extract synthesize information related devices, sensors, behaviors, pre-processing...
Precision agriculture requires accurate methods for classifying crops and soil cover in agricultural production areas. The study aims to evaluate three machine learning-based classifiers identify intercropped forage cactus cultivation irrigated areas using Unmanned Aerial Vehicles (UAV). It conducted a comparative analysis between multispectral visible Red-Green-Blue (RGB) sampling, followed by the efficiency of Gaussian Mixture Model (GMM), K-Nearest Neighbors (KNN), Random Forest (RF)...
Rapid and sensitive identification of illicit drugs has been a challenge requires new methods. This study proposes newly developed electronic nose (e-nose) based on commercially available gas sensors to provide nondestructive, rapid, low cost, portable solution for in situ detection marijuana samples. Samples seized marijuana, pseudo-narcotic cigarettes were analyzed. Principal component analysis (PCA), soft independent modeling class analogies (SIMCA), successive projection algorithm-linear...
Energy consumption is one of the great villains in high-performance processing when applied to large clusters that continuously run certain applications. Seismic migration applications are targets this type processing, since feature denotes a need apply complex models evaluate drilling petroleum wells. This work describes an analysis tool energy seismic application FPGA architecture for real Brazilian industry. A comparative study with traditional multi-core and GPGPU architectures performed...
Hardware accelerators like GPGPUs and FPGAs have been used as an alternative to conventional CPU architectures in scientific computing applications shown considerable speed-ups on them. In this context, work presents FPGA-based solution that explores efficiently the data reuse spatial time domain parallelism for first computational stage of reverse migration (RTM) algorithm, seismic modelling. We also implemented same algorithm some CPUs GPGPU our results showed approach can be a feasible...
Mastitis is a disease that considered an obstacle in dairy farming. Some methods of diagnosing mastitis have been used effectively over the years, but with associated relative cost reduces producer’s profit. In this context, sector needs tools offer early, safe, and non-invasive diagnosis direct producer to apply resources confirm clinical picture, minimizing monitoring herd. The objective study was develop predictive methodology based on sequential knowledge transfer for automatic detection...
Recently, the manufactures of supercomputers have made use FPGAs to accelerate scientific applications [16][17]. Traditionally, were used only on non-scientific applications. The main reasons for this fact are: floating-point computation complexity; FPGA logic cells are not sufficient cores implementation; complexity prevents them operate high frequencies.
The recent evolution of the programmable logic devices, such as FPGAs (Field Programmable Gate Array), associated with growing demand for performance improvements in scientific computing applications, has attracted attention supercomputers vendors. They have been developing hybrid platforms that links general-purpose processors co-processors based on FPGAs, aiming acceleration.
This paper presents the Human-Centered Design process (HCD) applied in context of educational games using open data about cultural aspects city Recife. The main objective work is collaborative development an application for smartphones, entitled "Recife Games", which provides entertaining way to learn Recife culture. methodology was based on HCD Toolkit and Jakob Nielsen's usability criteria heuristics. We also used two interaction design techniques, Skeumorfism Flat Design. includes steps...
Hardware accelerators like GPGPUs and FPGAs have been used as an alternative for the conventional computing architectures (CPUs) in scientific applications shown considerable speed-ups. In this context, poster presents a solution that takes advantage from FPGA's flexibility to explore efficiently data reuse, parallelization both time space domains first processing stage of RTM (Reverse Time Migration) algorithm, seismic modeling.
Hardware accelerators such as GPGPUs and FPGAs have been used an alternative to the conventional CPU in scientific computing applications shown significant performance improvements. In this context, work presents FPGA-based solution that explores efficiently reuse of data parallelization both space time domains for first computational stage RTM (Reverse Time Migration) algorithm, seismic modeling. We also implemented same algorithm architectures GPGPU our results demonstrate approach can be...
This paper presents a Design Space Exploration(DSE) methodology based on temporal partitioning strategy for mapping of massive computational dataflow problems into FPGAs. In this approach the FPGAs work as co-processors in hypothetic reconfigurable computing architecture. The is Tabu Search strategies and libraries IP-cores. allows Exploration optimization implementation FPGA pre-runtime analysis. Results DSE technique, synthetic benchmarks, have reached very good performance sometimes...
The comparison of DNA sequences is a classic problem in molecular biology. Forensic applications uses this for personal identication. For instance, the USA, CODES system has today 14.9 million proles stored on its database. To accelerate recurrent task to query into similar databases, work presents hardware acclerator parallel alignment multiple sequences, aiming maximum throughput. proposed accelerator architecture optimizes use resources, data access strategy and, as result, memory...
The comparison of DNA sequences is a classic problem in molecular biology. Forensic applications uses this for personal identication. For instance, the USA, CODIS system has today 14.9 million proles stored on its database. To accelerate recurrent task to query into similar databases, work presents hardware acderator parallel alignment multiple sequences, aiming maximum throughput Each these alignments done using Needleman-Wunsch algorithm which represents an optimal global technique...
The comparison of DNA sequences is a classic problem in molecular biology. Forensic applications uses this for personal identication. For instance, the USA, CODES system has today 14.9 million proles stored on its database. To accelerate recurrent task to query into similar databases, work presents hardware acclerator parallel alignment multiple sequences, aiming maximum throughput. proposed accelerator architecture optimizes use resources, data access strategy and, as result, memory...