Efficient Classification of Handwritten Medical Prescription Recognition using Alexnet and Analysing the Accuracy with Novel CRNN Algorithm

The ultimate purpose of this investigation is to carry out an efficient classification of handwritten medical prescription recognition by utilising a one-of-a-kind CRNN Algorithm, and then to evaluate its level of performance in contrast to that of Alexnet. A total of ten representatives from each group's sample were considered for the analysis. Under the context of this specific experiment, the Alexnet and Novel CRNN algorithm study groups are taken into consideration. Calculations were performed using the Gpower calculator, and a confidence range of 95% was applied to the results in order to arrive at the smallest possible sample size that was required for the experiment. A unique convolutional recurrent neural network with an accuracy of 91.28% and an existing Alexnet Method with an accuracy of 84.15% are compared to the findings that were obtained and examined. According to the findings, the newly developed CRNN performs classification tasks substantially better than Alexnet does, and there is a discernible and statistically significant gap between the two systems (p 0.05). In contrast to the Alexnet algorithm, the Novel CRNN technique was far more successful in accelerating the rate at which trajectory analysis could be performed.