The comprehensive real-time dataset is skewed. The dataset is often imbalanced and hard to classify with the existing balanced dataset. The dataset may be skewed in the range of 10:1 ratio. Due to the data imbalance and errors, the data classification accuracy rate can be reached only to 90%. The classification accuracy rate can be increased if the number of errors in dataset is minimized. Hence, in this paper, we propose to identify error in SCRUM dataset by linear neural network model. For analysis, two datasets with errors and without errors are taken and analyzed with neural network model. The model train to determine error in dataset. With the proposed method, the model determines error in dataset with 98% accuracy.
CITATION STYLE
Babu, M. C., & Pushpa, S. (2020). Imbalanced Dataset Analysis with Neural Network Model. In Lecture Notes in Electrical Engineering (Vol. 637, pp. 93–104). Springer. https://doi.org/10.1007/978-981-15-2612-1_9
Mendeley helps you to discover research relevant for your work.