Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ22985

An Analytical Behavior On Research For Secure Analysis Of Machine Learning For Multiple Instance Against Standard Supervised Learning

Dr. Amit Kumar Chandanan

Abstract

The drug activity prediction application of the multiple-instance learning model has received a lot of recent attention. The majority of previous research on multiple-instance learning has focused on concept learning; however, the label for drug activity prediction is a real-valued affinity measurement that indicates the binding strength. On Boolean and real-valued data, we investigate the performance of our k-nearest neighbors (k-NN) extensions, Citation-kNN, and diverse density algorithm for the realvalued setting. Additionally, we offer a method for creating artificial data that is chemically accurate.

Keywords

k-NN, Machine Learning

Full Text

PDF

References

?>