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.

As the benefits of Moore's Law diminish, computing performance, and efficiency gains are increasingly achieved through specializing hardware to a domain of computation. However, this limits the hardware's generality and flexibility. Field-programmable gate arrays (FPGAs), microchips which can be reprogrammed to implement arbitrary digital circuits, enable the benefits of specialization while remaining flexible. A challenge to using FPGAs is the complex computer-aided design flow required to efficiently map a computation onto an FPGA. Traditionally, these design flows are closed-source and highly specialized to a particular vendor's devices. We propose an alternate data-driven approach, which uses highly adaptable and retargettable open-source tools to target both commercial and research FPGA architectures. While challenges remain, we believe this approach makes the development of novel and commercial FPGA architectures faster and more accessible. Furthermore, it provides a path forward for industry, academia, and the open-source community to collaborate and combine their resources to advance FPGA technology.

A 35 years old man present with a skin lesion on his glans complaining of mild irritation. The condition began 3 years ago, he took wrong medication as he was diagnosed as psoriasis, mostly because the disease in it the beginning is very similar and could trick the dermatologist. He was diagnosed by the biopsy taken,Pseudo-epitheliomatous hyperkeratotic and micaceous balanitis. 5-Flouracil was given in combination with oral Acitretin, Dramatic improvement occurred in both the skin lesion and the symptoms associated.

In this paper, a low power support vector machine (SVM) training, feature extraction, and classification algorithm are hardware implemented in a neural seizure detection application. The training algorithm used is the sequential minimal optimization (SMO) algorithm. The system is implemented on different platforms: such as field programmable gate array (FPGA), Xilinx Virtex-7 and application specific integrated circuit (ASIC) using hardware-calibrated UMC 65 nm CMOS technology. The implemented training hardware is introduced as an accelerator intellectual property (IP), especially in the case of large number of training sets, such as neural seizure detection. Feature extraction and classification blocks are implemented to achieve the best trade-off between sensitivity and power consumption. The proposed seizure detection system achieves a sensitivity around 96.77% when tested with the implemented linear kernel classifier. A power consumption evaluation is performed on both the ASIC and FPGA platforms showing that the ASIC power consumption is improved by a factor of 2X when compared with the FPGA counterpart.

In this paper, two different classifiers are software and hardware implemented for neural seizure detection. The two techniques are support vector machine(SVM) and artificial neural networks(ANN). The two techniques are pretrained on software and only the classifiers are hardware implemented and tested. A comparison of the two techniques is performed on the levels of performance, energy consumption and area. The SVM is pretrained using gradient ascent (GA) algorithm, while the neural network is implemented with single hidden layer. It is found that the ANN consumes more power than the SVM by a factor of 4 with almost the same performance. However, the ANN finishes classification in much less number of clock cycles than the SVM by a factor of 34.

In this paper, different window sizes for EEG signal segmentation are investigated in order to optimize the performance of seizure detection systems. To differentiate between epileptic and non-epileptic epochs, the time axis of the EEG signal is divided into non-overlapping windows. The window period should be long enough for the lapse to be informative but not too long for it to stay stationary. Hence, the KPSS test is used to determine signal stationarity for different window sizes, then the optimal window is chosen such that it corresponds to the smallest number of non-stationary segments in the signal of interest. The seizure detection system is then applied to the piece-wise stationary segments. Compared to the exhaustive examination, it is found that the KPSS test optimal window results in the highest sensitivity.

In this paper, both linear and nonlinear features have been reviewed with linear support vector machine (SVM) classifier for neural seizure detection. The work introduced in the paper includes performance measurement through different metrics: accuracy, sensitivity, and specificity of multiple linear and nonlinear features with linear support vector machine (SVM). A comparison is performed between the performance of different combinations between 11 linear features and 9 nonlinear features to conclude the best set of features. It is found that some features enhance the detection performance greatly. Using a combination of 3 features of them, a linear SVM classifier detects seizures with sensitivity of 96.78%, specificity of 97.9%, and accuracy of 97.9%.

Objective: We compared the results of holmium laser and pneumatic intracorporeal lithotripsy for large ureteric calculi in terms of efficacy, safety and complications. Methods: The study was conducted between April 2009 and October 2010. 80 patients divided into two equally matched groups were included in a prospective randomized trial including patients with a ureteric stone size of 0.5–2 cm. A holmium laser with a 550-µm fiber was employed in the laser lithotripsy (LL) group. The Swiss Lithoclast was used in the pneumatic lithotripsy (PL) group. Results: Mean stone size was comparable in both groups, namely 13.1 mm in the PL group and 12.9 mm in the LL group. The early stone-free rate was equal in both groups, while the delayed stone-free rate was 95% in LL and 85% in PL. Stone migration occurred in 12 PL cases and in 5 LL cases. Ureteric perforation occurred in 3 LL cases and in 2 PL cases. Ureteric stricture occurred in 1 case following LL. Conclusion: Both PL and LL are effective and safe modalities in treating large ureteric stones with minor insignificant differences. A pneumatic system may be more efficient with regard to the cost-benefit ratio, which was not studied in the present work; further studies should address this issue.

The management of renal calculi following previous open surgery represents a challenge for urologists. The aim of this study is to evaluate the outcomes and safety of ureteroscopic laser retrograde intrarenal surgery (RIRS) for renal calculi following prior open renal surgery. The charts of 53 patients who underwent RIRS for renal calculi following prior open surgery for urolithiasis were reviewed. Both flexible and semi-rigid ureteroscopes were utilized together with holmium: YAG laser for stone disintegration. Intravenous urography, computed tomography (CT) and ultrasound were used to evaluate the patient, perioperatively. Stone size ranged from 5 to 32 mm (mean 14.3 mm). The mean operative time was 86 min (20-130). The overall stone-free rate was 92.4%. The overall stone-free rates after one and two-procedures were 79.2% (42 cases) and 92.4% (49 cases), respectively. Four patients (7.5%) had larger residual fragments, 2 (3.8%) of them underwent SWL, and 2 (3.8%) cases were followed up conservatively. Major complications were reported in two patients (3.8%). Stone analysis revealed calcium oxalate in 39 patients, uric acid in 5, calcium phosphate in 4, struvite in 3, and cystine in 2 cases. Ureteroscopic retrograde intrarenal surgery for renal calculi following prior open renal surgery was a minimally invasive, safe procedure with a high success rate. It is a viable alternative for PNL in managing recurrent renal calculi efficiently.

Background and objective Risks are anticipated for laryngeal mask airway (LMA) anaesthesia during nasal and sinus surgeries because blood can trickle posteriorly into the hypopharynx and contaminate the airway. This study was conducted to determine whether a LMA could provide adequate airway protection from the expected intraoperative bleeding. Methods After obtaining ethics committee approval, 60 children ASA status I or II, 1-12 years of age, and scheduled for nasal and sinus surgery were randomized to one of two groups, endotracheal tube (ETT) or LMA, with 30 patients in each. Topical lidocaine with adrenaline was used in all patients, and throat packs were used for the ETT group. The airway was examined using a fibreoptic endoscope in order to determine whether blood or tissue debris soiled the supraglottic airway or trachea. After extubation, LMAs and ETTs were examined for soiling by blood and graded on a scale of 0-3. For ETT, the grades were 0, none; 1, contamination above the mark for vocal cord depth; 2, contamination below the mark for vocal cord depth; and 3, contamination interiorly. For LMA, they were 0, no staining; 1, staining on the anterior aspect of the cuff of the LMA; 2, staining inside the cup of the LMA; and 3, staining found in the tube. Results Blood stains were found in the larynx of one child in the LMA group. In the ETT group, there were three cases of staining (two supraglottic and one in the trachea, P = 0.161). With the LMA, 12 (40%) and 18 (60%) patients had visual contamination scores of 0 and 1, respectively. With the ETT, 14 (46.7%), 10 (33.3%), and six (20%) patients had visual contamination scores of 0, 1, and 2, respectively (P = 0.0123). Conclusion LMA is a suitable method for paediatric patients undergoing sinonasal surgery because it offers airway protection from blood contamination comparable to that of a standard uncuffed ETT with throat pack.

Objective To evaluate the safety and efficacy of percutaneous suprapubic stone extraction (PSPSE) for pediatric posterior urethral stones. Methods Between July 2007 and June 2010, 54 boys presenting with acute urinary retention due to posterior urethral stones underwent PSPSE. Patients were a mean age of 66.4 months (range, 8-180 months). The stone size was 0.7-1.9 cm. Patients were placed under general anesthesia, and a 7F urethroscope was used to pushback the stone to the bladder. A 3-mm suprapubic puncture with a scalpel was performed, followed by insertion of a straight narrow hemostat through the puncture aided with cystoscopic guidance. The stone was grasped with the hemostat in its narrowest diameter and was extracted percutaneously or crushed if friable. The suprapubic puncture was closed with a single 4-0 Vicryl (Ethicon) suture. Results Intact stone retrieval was achieved in 45 patients, and the stone was crushed into minute fragments in 9 patients. Intraperitoneal extravasation developed in 1 patient that required open surgical intervention. Mean operative time was 22 minutes. Patients were monitored for up to 17 months, with complete resolution of symptoms and stone clearance. Conclusion PSPSE provides a minimally invasive approach for the extraction of urethral and bladder stones in the pediatric population. The use of a straight hemostat for suprapubic stone extraction or crushing is a good alternative to suprapubic tract dilation, with minimal morbidity.

Background: Tri-modality bladder sparing therapy in selected bladder cancer patients may be an alternatives treatment option to immediate radical cystectomy as it may result in satisfactory Quality Of Life (QOL). The present study evaluated the effects of this conservative approach versus surgical approach, i.e. Radical Cystectomy (RC) and orthotopic neobladder, on QOL of patients. Patients and methods: This is a prospective study of patients with bladder cancer in group I (using tri-modality bladder sparing therapy) and group II (using RC and orthotopic neobladder). Patients in both groups were subjected to interview NCCN-FACT FBlSI18 questionnaire, inquiring about physical and emotional disease related symptoms, treatment side effects and function and well being. SPSS version18 software was used for statistical analysis. Results: Internal consistency of the 18 items in both groups was assessed by Cronbach’s α which was adequate at 0.89 at Group I and 0.84 at Group II. Univariate analysis showed that there were statistically significant difference (p