IJSSER

Title: A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE ACNE AND JAUNDICE
Authors: Nihal Boina, Jai Agarwal, Taruna Agarwal, Ishita Samant, Nikhil Doma, Ishaan Saxena, Parth Patel, Ashwin Menachery, Bhargav Vantikommu, Kunal Singhal, Sai Varun Konagalla, Akshara Sanapala, Reema Patel, Sophia Nasibdar, Deepika Ravi, Sathvik Lakamsani, Mason Elkas, John Leddo
\|\| \|\|
John Leddo John Leddo is director of research at MyEdmaster.
MLA 8 Leddo, John. "A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE ACNE AND JAUNDICE." Int. j. of Social Science and Economic Research, vol. 6, no. 10, Oct. 2021, pp. 4151-4158, doi.org/10.46609/IJSSER.2021.v06i10.040. Accessed Oct. 2021. APA 6 Leddo, J. (2021, October). A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE ACNE AND JAUNDICE. Int. j. of Social Science and Economic Research, 6(10), 4151-4158. Retrieved from doi.org/10.46609/IJSSER.2021.v06i10.040 Chicago Leddo, John. "A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE ACNE AND JAUNDICE." Int. j. of Social Science and Economic Research 6, no. 10 (October 2021), 4151-4158. Accessed October, 2021. doi.org/10.46609/IJSSER.2021.v06i10.040.
References [1]. Nancy Garrick, D. D. (2016, September 1). Acne. National Institute of Arthritis and Musculoskeletal and Skin Diseases. https://www.niams.nih.gov/health-topics/acne [2]. Acne—Symptoms and causes. (n.d.). Mayo Clinic. Retrieved September 8, 2021, from https://www.mayoclinic.org/diseases-conditions/acne/symptoms-causes/syc-20368047 [3]. Jaundice. (n.d.). [Text]. Retrieved September 8, 2021, from https://medlineplus.gov/jaundice.html [4]. Kaplan, M., & Hammerman, C. (2017). 97—Hereditary contribution to neonatal hyperbilirubinemia. In R. A. Polin, S. H. Abman, D. H. Rowitch, W. E. Benitz, & W. W. Fox (Eds.), Fetal and Neonatal Physiology (Fifth Edition) (pp. 933-942.e3). Elsevier. https://doi.org/10.1016/B978-0-323-35214-7.00097-4 [5]. Infant jaundice—Symptoms and causes. (n.d.). Mayo Clinic. Retrieved September 8, 2021, from https://www.mayoclinic.org/diseases-conditions/infant-jaundice/symptoms-causes/syc-20373865 [6]. Machine learning algorithms based skin disease detection. (n.d.). ResearchGate. Retrieved September 8, 2021, from https://www.researchgate.net/publication/341372376_Machine_Learning_Algorithms_based_Skin_Disease_Detection [7]. Kaggle: Your machine learning and data science community. (n.d.). Retrieved September 8, 2021, from https://www.kaggle.com
Abstract: Acne is a skin condition caused by hair follicles that become clogged with oil and dead skin cells. Around 85% of people have experienced acne at some time in their lives, and acne is known to have heavy emotional and physical impacts on regular people. Jaundice is another type of skin condition that is noted by the yellow pigmentation of skin and whites of the eyes due to high bilirubin levels. Jaundice is rare in adults, but is significantly more common in newborn babies, with around 80% affected by it during the first week of life. Artificial intelligence (AI) algorithms, specifically convoluted neural networks (CNN), have been employed to diagnose these skin diseases. Additionally, these algorithms would be manipulated by an automated hyperparameter manipulator, using extensive machine learning to find, sort, and train, validate, and test on a dataset all by itself. Put simply, we were able to make an automated software capable of making its own state-of-the-art algorithms through a meta-machine learning approach, filling the role of an AI researcher. Additionally, the software was able to achieve consistent overall testing accuracy of at least 90%, quantifying its potential use in diagnosing skin diseases and fitting diseases that it was not explicitly taught to learn in the first place.

IJSSER is Member of