Failure and reliability prediction by support vector machines regression of time series data

Support vector machines (SVMs) have been successfully employed to solve non-linear regression and time series problems. However, SVMs have rarely been applied to forecasting software reliability. This investigation elucidates the feasibility of the use of SVMs to forecast software reliability. Simulated annealing algorithms (SA) are used to select the parameters of an SVM model. Numerical examples taken from the existing literature are used to demonstrate the performance of software reliability forecasting. The experimental results reveal that the SVM model with simulated annealing algorithms (SVMSA) results in better predictions than the other methods. Hence, the proposed model is a valid and promising alternative for forecasting software reliability.

Software reliability forecasting by support vector machines with simulated annealing algorithms

Evolutionary neural network modeling for software cumulative failure time prediction

Neural-network-based approaches for software reliability estimation using dynamic weighted combinational models

On the neural network approach in software reliability modeling

This study aimed to compare the effects of continuous hand-sewn esophagojejunostomy with barbed suture and mechanical anastomosis in total laparoscopic gastrectomy for esophagogastric junction cancer.The clinical data of 60 patients who underwent total laparoscopic total gastrectomy from January 2020 to October 2021 were collected retrospectively. Baseline data and short-term surgical results of patients in the hand-sewn anastomosis (n = 30) and mechanical anastomosis (n = 30) groups were analyzed.No significant differences were detected in the baseline data between groups. Meanwhile, the hand-sewn group had a shorter anastomosis time (21.2 ± 4.9 min vs. 27.9 ± 6.9 min, p < 0.001) and a decreased operation cost (CNY 70608.3 ± 8106.7 vs. CNY 76485.6 ± 3149.9, p = 0.001). The tumor margin distance in the hand-sewn group was longer than in the mechanical group (2.7 ± 0.4 cm vs. 2.2 ± 0.75 cm, p = 0.002). In esophagojejunostomy anastomosis, the distance between the jejunal opening and jejunal stump in the hand-sewn group was significantly shorter than that in the mechanical group (2.2 ± 0.54 cm vs. 5.7 ± 0.6 cm, p < 0.001). No significant difference was detected in the incidence of postoperative anastomotic complications.The continuous hand-sewn anastomosis with barbed suture in total laparoscopic gastrectomy for esophagogastric junction cancer is practical, safe, and cost-effective. It is also an effective supplementary technique for mechanical anastomosis. 

/pdf/comparing-intracorporeal-mechanical-anastomosis-vs-hand-sewn-igxvi4rt.pdf

Comparing intracorporeal mechanical anastomosis vs. hand-sewn esophagojejunostomy after total laparoscopic gastrectomy for esophagogastric junction cancer: a single-center study

Wei-Dong Wang

Papers

On the neural network approach in software reliability modeling

Comparing intracorporeal mechanical anastomosis vs. hand-sewn esophagojejunostomy after total laparoscopic gastrectomy for esophagogastric junction cancer: a single-center study