Background: Retroperitoneoscopic donor nephrectomy (RDN) is a well-established modality for the procurement of kidneys for renal transplantation. However the learning curve of pure RDN is not yet defined. Defining the learning curve will help in proper mentorship of the new donor surgeons besides providing safety to the donors.Objective: To define the learning curve of pure RDN.Methods: We analyzed the prospectively collected data of 102 voluntary kidney donors who underwent RDN by a single surgeon between August 2012 and April 2015 at our center. The donors were classified into group A (1–34), group B (35–68), and group C (69–102) according to the chronological order of their surgery. Left RDN was performed in 28 (82%), 25 (74%), and 28 (82%) donors of group A, B, and C, respectively. Right RDN was performed in 6 (18%), 9 (26%), and 6 (18%) donors of group A, B, and C, respectively. The clinical data were analyzed for each group.Results: Statistically significant difference was observed for the mean operative time (p<0.01) and warm ischemia time (p<0.04). The operative time remained around 200 minutes after the initial 35 cases.Conclusion: The learning curve of pure RDN was 35 cases, although the mastery requires more number of cases to be performed.

This paper presents an alternative method using artificial neural network (ANN) to develop a scheduling scheme which is used to determine the makespan or cycle time of a group of jobs going through a series of stages or workstations. The common conventional method uses mathematical programming techniques and presented in Gantt charts forms. The contribution of this paper is in three fold. Firstly, the learning curve which is characterized by a coefficient is considered in the computation work. Secondly, this work is limited to small number of jobs and is useful for project based pilot runs which involve learning. Lastly, the scheduling scheme is developed in ANN as an alternate method. Extensive and successful training using the input and output vector pairs were done to establish the proposed method. Comparison was done for the tested outputs and results produced seem reliable.

Pull-out tests and corresponding curves help analyze fiber pull-out behavior, which significantly influences the tensile and flexural properties of fiber-reinforced concrete. Artificial intelligence techniques provide an efficient means to predict fiber pull-out curves. In this study, four models based on convolutional neural networks (CNN), long short-term memory networks (LSTM) and extreme gradient boosting (XGBoost) are used to predict fiber pull-out curves: CNN1D, CNN2D, LSTM, and XGBoost. A dataset of 502 experimental samples was compiled, primarily from laboratory studies conducted by one of the authors of this paper. Fiber aspect ratio, loading rate, type and quantity of cement, amount of: binder, silica fume, sand, gravel, quartz, superplasticizer, water, water to cement ratio, water to binder ratio, curing age, fiber embedded length, end-type of the fibers, pitch of spirals, number of twists, fiber inclination angle, fiber length and diameter, and concrete compressive strength are among the used input parameters. To represent the expected curve, the model output comprises 1000 pairs of data (pull-out force vs slip). Among the tested models, XGBoost demonstrated superior performance with the lowest mean absolute error (8.39) and highest R² value (0.71), making it the optimal choice for predicting fiber pull-out curves. The parameters “embedded length”, “number of twists”, “Silica fume” and “pitch of spirals” were more important and influenced the model and prediction accuracy, as can be seen from the evaluation of the feature importance graph. All in all, the proposed model provided accurate forecasts and could represent a data-based method for improving fiber-reinforced cementitious composites.