---
owner:
    hid: 306
    name: Cheruvu, Murali
    url: https://github.com/bigdata-i523/hid306
paper1:
    abstract: >
        The Internet of Things, or IoT, is all about data from
        connected devices.  Millions of consumer and industrial
        devices drive IoT growth and challenge with data volume and
        variety. Big Data Analytics helps combing through these high
        volumes of complex IoT data into meaningful business insights.
    author:
        - Murali Cheruvu
    chapter: Technology
    hid:
        - 306
    status: 100%; 10/26/2017
    title: The Internet of Things and Big Data Analytics
    url: https://github.com/bigdata-i523/hid306/paper1
paper2:
    review: Nov 6 2017
    abstract: >
        The Deep Learning is unique in machine learning algorithms to
        analyze supervised and unsupervised datasets. Big Data
        challenges like high volumes, multi-dimensionality and feature
        engineering are well addressed using Deep Learning
        algorithms. Deep Leaning, with edge and distributed mesh
        computing, is best suited to handle IoT Analytics of millions
        of sensors producing petabytes of time-series data.
    author:
        - Murali Cheruvu
    chapter: Technology
    hid:
        - 306
    status: 100%; 11/4/2017
    title: Why Deep Learning matters in IoT Data Analytics?
    url: https://github.com/bigdata-i523/hid306/paper2
project:
    review: Dec 4 2017
    abstract: >
        In United States, more than 6 million residential homes sold
        in 2017. With ever-increasing demands, real estate is
        challenged with complex analysis of homes to
        provide accurate appraisals and predicting market
        fluctuations to react accordingly. Big data analytics
        helps mining the real estate data to provide valuable
        business insights. In this project, we have planned to
        analyze housing data to predict sale prices. Using well
        established datasets, with lots of exploratory variables,
        we could apply thorough exploration of the data, feature
        engineering and implement various advanced supervised
        learning algorithms, such as XGoost, Ridge, Lasso,
        Random Forest and Neural Network to
        predict accurate sale prices.
    author:
        - Murali Cheruvu
        - Anand Sriramulu
    chapter: Business
    hid:
        - 306
        - 338
    status: 100%; 12/10/2017
    title: Predicting Housing Prices
    type: latex
    url: https://github.com/bigdata-i523/hid306/project