IJSSER

Title: A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE AUTISM, BREAST CANCER, MELANOMA MOLE CANCER, AND PINK EYE
Authors: Nihal Boina, Jai Agarwal, Taruna Agarwal, Chloe Song, Vihaan Cherukuri, Smaran Pasupulati, Sathvik Redrouthu, Kunal Saxena, Jishnu Patel, Sri Vaishnavi Konagalla, Jay Pallepati, Rashmith Repala, Ashana Patel, Sudhit Sangela, Samarth Jain, Kinnari Chaubal, Veda Kalwala, Aneesh Sreedhara, Nihar Xavier, Yash Sonis, Anjali Sanapala, Sachin Nimmalapudi, Tanya Singhal, Avyakt Gaur, Poorvaja Gopinath, Zaakir Khan, Nikhit Rachapudi, Saketh Chintalapati, Karthik Yella, Riya Pasupulati, Zaynah Khan, Ishan Doma, Avesta Zahedi, Saranya Ganne, Aastha Sharma, Dhruv Khatod, Malachai Onwona, 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 AUTISM, BREAST CANCER, MELANOMA MOLE CANCER, AND PINK EYE." Int. j. of Social Science and Economic Research, vol. 6, no. 10, Oct. 2021, pp. 4159-4171, doi.org/10.46609/IJSSER.2021.v06i10.041. Accessed Oct. 2021. APA 6 Leddo, J. (2021, October). A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE AUTISM, BREAST CANCER, MELANOMA MOLE CANCER, AND PINK EYE. Int. j. of Social Science and Economic Research, 6(10), 4159-4171. Retrieved from doi.org/10.46609/IJSSER.2021.v06i10.041 Chicago Leddo, John. "A NOVEL META-MACHINE LEARNING PLATFORM ABLE TO AUTONOMOUSLY LEARN HOW TO DIAGNOSE AUTISM, BREAST CANCER, MELANOMA MOLE CANCER, AND PINK EYE." Int. j. of Social Science and Economic Research 6, no. 10 (October 2021), 4159-4171. Accessed October, 2021. doi.org/10.46609/IJSSER.2021.v06i10.041.
References [1]. What is autism? (n.d.). Autism Speaks. Retrieved October 8, 2021, from https://www.autismspeaks.org/what-autism [2]. CDC. (2020, March 13). Screening and diagnosis \| autism spectrum disorder (Asd) \| ncbddd. Centers for Disease Control and Prevention. https://www.cdc.gov/ncbddd/autism/screening.html [3]. CDCBreastCancer. (2021, September 22). What is breast cancer screening? Centers for Disease Control and Prevention. https://www.cdc.gov/cancer/breast/basic_info/screening.htm [4]. Melanoma of the skin statistics \| cdc. (2021, June 8). https://www.cdc.gov/cancer/skin/statistics/index.htm [5]. Reed, K. B., Brewer, J. D., Lohse, C. M., Bringe, K. E., Pruitt, C. N., & Gibson, L. E. (2012). Increasing incidence of melanoma among young adults: An epidemiological study in olmsted county, minnesota. Mayo Clinic Proceedings, 87(4), 328–334. https://doi.org/10.1016/j.mayocp.2012.01.010 [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 [8]. CDC. (2021, August 5). Protect yourself from pink eye. Centers for Disease Control and Prevention. http://www.cdc.gov/conjunctivitis/ [9]. Red eye: Causes, symptoms, treatments, prevention. (n.d.). Cleveland Clinic. Retrieved October 8, 2021, from https://my.clevelandclinic.org/health/symptoms/17690-red-eye [10]. Weber, G. (n.d.). Autistic Children Dataset [Data set]. Kaggle. https://www.kaggle.com/gpiosenka/autistic-children-data-set-traintestvalidate [11]. Shah, A. (2021). Breast Ultrasound Images Dataset [Data set]. Kaggle. https://www.kaggle.com/aryashah2k/breast-ultrasound-images-dataset [12]. Fanconi, C. (2019). Skin Cancer: Malignant vs. Benign [Data set]. Kaggle. https://www.kaggle.com/fanconic/skin-cancer-malignant-vs-benign [13]. Leddo, L. and Liang, I. (2021). Incorporating Abstract Knowledge Structures in Machine Learning: Improving Question Answering, Problem Solving and Teaching in Personal Assistants and Educational Software. International Journal of Social Science and Economic Research, 6(2), 661-673.
Abstract: One of the main goals of machine learning is to make a General Artificial Intelligence. Currently, human artificial intelligence researchers work on meticulously manipulating model parameters by hand in order to arrive at highly optimized machine learning models. In the future, a system will be needed such that a software is able to completely arrive at an optimized model to a specific topic all by itself. In this study, a novel machine learning platform was created that could learn how to diagnose a variety of diseases including autism, breast cancer, melanoma mole cancer, and pink eye without being explicitly taught to learn them. Artificial intelligence (AI) algorithms, specifically convoluted neural networks (CNN), have been employed to diagnose these skin diseases. Additionally, these algorithms were manipulated by an automated hyperparameter manipulator, using machine learning to find, sort, and train, validate, and test on a dataset all by itself. Put simply, we were able to make software capable of making its own algorithms through a meta-machine learning approach, aiming to fill 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 fitting diseases that it was not explicitly taught to learn in the first place.

IJSSER is Member of