Alex Masgai, BrickSimple

BrickSimple is a software company that provides software solutions to other companies. Throughout the summer and during my senior year, I worked on quality assurance, develops, AW, and research and development in blockchain technologies.

I debugged both the hardware and the software of a new fitness app for a client, rewrote the backend for a Django website, wrote a proof-of-concept decentralized application using Node JS and Solidity, deployed a mining node in Ethereum-based network, and wrote a Python script that installs, updates and removes developmental tools. At the end of the summer portion of my internship, I presented my findings on blockchain research in a company-wide meeting.

Justin Branco, Delaware Valley Community Health

My internship at Delaware Valley Community Health (DVCH) proved to be one of the most beneficial factors of my learning experience at St. Joseph’s University. The projects I was tasked with included: managing the setup and distribution of iPads to doctors, initializing with healthcare software necessary for doctor-patient interaction, developing new plans and alternatives for patients to connect with their doctors via technology, researching new healthcare technologies that would be beneficial for DVCH to implement, and working with IS/IT professionals to deal with any ongoing software/hardware problems that DVCH might face.

My time at Delaware Valley Community Health taught me that the professional world is dynamic and fast-paced. I found myself tasked with many projects at a single time. Many of the projects had to do with our Patient Portal, which is an online hub where patients can access their health records and talk with their healthcare provider without stepping in the office. I made changes to some of the technology that DVCH has to offer their patients, including the Patient Portal and their website. A key project was updating their email scripts using HTML. Another main project was implementing iPads into a healthcare provider’s everyday routine. The use of this technology would promote a closer relationship between patient and doctor and also allow doctors to access vital healthcare software on the go.

Although not all of the projects I was tasked with were completed before my departure from DVCH, I found that my presence at the company was not only beneficial for me but to them as well. During this internship, I learned how to implement the skills I acquired in the classroom to everyday life.

Yifan Chen and Wenhao Ruan, Databricks

Thursday, April 18, 2019 (11:00 am)

Databricks is a unified analytics engine that allows rapid development of data science applications using machine learning techniques, such as classification, linear and nonlinear regression, clustering, etc. Existence of myriad sophisticated computation options, however, can become overwhelming for designers as it may not always be clear what choices can produce the best predictive model given a specific data set. Further, the mere high dimensionality of big data sets is a challenge for data scientist to gain a deep understanding of the results obtained by a utilized model.

Our research provides general guidelines for utilizing a variety of machine learning algorithms on the cloud computing platform, Databricks. Visualization is an important means for users to understand the significance of the underlying data. Therefore, it is also demonstrated how graphical tools, such as Tableau, can be used to efficiently examine results of classification or clustering. The dimensionality reduction techniques, such as Principal Component Analysis (PCA), which help reduce the number of features in a learning experiment, are also discussed.

To demonstrate the utility of Databricks tools, tow big data sets are used for performing clustering and classification. A variety of machine learning algorithms are applied to both data sets and it is shown how to obtain the most accurate learning models employing appropriate evaluation methods. During the presentation, we will introduce the workflow of conducting an ML model training and describe the method to choose the proper classification and regression algorithms.

One of the data sets will be chosen to demonstrate how we implemented unsupervised learning (K-means) on an unlabeled data set for classification (Kernel S V M) We will also briefly discuss model evaluation and time efficiency. Finally, we will present the visualization of classification after applying PCA.