Search

In this paper, a high-sensitivity low-cost power-aware Support Vector Machine (SVM) training and classification based system, is hardware implemented for a neural seizure detection application. The training accelerator algorithm, adopted in this work, is the sequential minimal optimization (SMO). System blocks are implemented to achieve the best trade-off between sensitivity and the consumption of area and power. The proposed seizure detection system achieves 98.38% sensitivity when tested with the implemented linear kernel classifier. The system is implemented on different platforms: such as Field Programmable Gate Array (FPGA) Xilinx Virtex-7 board and Application Specific Integrated Circuit (ASIC) using hardware-calibrated UMC 65nm CMOS technology. A power consumption evaluation is performed on both the ASIC and FPGA platforms showing that the ASIC power consumption is lower by at least 65% when compared with the FPGA counterpart. A power-aware system is implemented with FPGAs by the adoption of the Dynamic Partial Reconfiguration (DPR) technique that allows the dynamic operation of the system based on power level available to the system at the expense of degradation of the system accuracy. The proposed system exploits the advantages of DPR technology in FPGAs to switch between two proposed designs providing a decrease of 64% in power consumption.

Objectives: The recurrence of pediatric nephrolithiasis, the morbidity of repeated open surgical treatment as well as our experience in percutaneous nephrolithotomy (PNL) in adult patients, all derived us to shift to PNL for managing renal stones >1.5 cm in pediatric patients. Our aim of this study is to evaluate the safety and efficacy of PNL in pediatric patients. Materials and Methods: During the period of the month between May 2011 and April 2013, 38 children (47 renal units) underwent PNL for renal stones 1.5-5 cm in length. Patient demographics, stone characteristics, and clinical outcome were prospectively studied. Data of those who underwent conventional and tubeless PNL were compared. Median follow-up period was 12 months (range: 6-24). Results: The median age at presentation was 8-year (range: 3-12). The operative time ranged from 30 to 120 min (median 90). Overall stone clearance rate was 91.5% after single PNL. The median hospital stay was 3 days. Auxiliary procedures were successful for the remaining 4 patients (nephroscopic clearance in one and shockwave lithotripsy in 3). Tubeless PNL was performed in 17 renal units with a comparable outcome to conventional ones. The perioperative complications were noted in 5/47 (10.6%) of all procedures (Clavien Grade II in 4 and Clavien Grade IIIa in 1) and were managed conservatively. Conclusions: Percutaneous nephrolithotomy for renal stones in pediatric patients is safe and feasible if performed by a well-experienced endourologist. Tubeless PNL is a better choice for children.