Josue N Rivera

I am computer scientist and aerospace engineer with an interest in machine learning and autonomy.

There is nothing more exciting to me than learning new things. Every day, I attempt to observe how our world works and explore new ways to innovate the way we live.

Resume/CV

Experience

EDUCATION

Doctor of Philosophy | Purdue University

Program: Aeronautics and Astronautics Engineering

Major: Autonomy and Control | Minor: Aerospace Systems

Honors, Leaderships and Awards:

Purdue Doctoral Fellowship: Students whose backgrounds, views, and experiences would contribute to the diversity of Purdue are considered for the Purdue Doctoral Fellowship

Highlighted Courses:

Multidisciplinary Design Optimization

Systems Analysis and Synthesis

2025

In Progress

Master of Science | University of Massachusetts Dartmouth

Program: Computer Science

Thesis: Graph Induced Lifelong Learning through Features Similarities and Dissimilarities

Highlighted Courses:

Algorithms and Complexity

Advanced Data Mining

Advanced Machine Learning

Advance Computer System

Database Design

Digital Forensic

Theoretical Computer Science

2021

Bachelor of Science | University of Massachusetts Dartmouth

Program: Computer Science

Honors, Leaderships and Awards:

Endeavor Scholar: Prestigious scholarship given for academic merit, leadership, and civic engagement

Newman Fellow: Nationwide recognition given to change-makers and public problem-solvers

29 Who Shine Award Recipient: Award given by the Dept. of Higher Education and Mass Governor to recognize 29 outstanding student graduates from the Commonwealth’s public higher education system

University Civic Engagement Award Recipient: Given to a student who made an impact on the campus

Chancellor’s List: Inducted into a list of students who have earned a GPA of 3.8 or higher

2019

Diploma | Lawrence High School (Math, Science and Technology Academy)

Honors, Leaderships and Awards: Valedictorian; L'Pin Award Recipient

2016

WORK

Graduate Research Assistant | Purdue University

Ph.D student at Dr. Dengfeng Sun's research lab
Researching machine learning-based optimal controller and scalable aerial cargo operations
Developing a data-free Hamiltonian-informed optimal neural controller for non-linear dynamical systems

August 2021 - Present

In Progress

Research Associate (Intern) | Hewlett Packard Labs

PhD R&D research associate (intern) at HPE's Large Scale Integrated Photonics (LSIP) Lab, Milpitas, California
First place technical project winner at HPE Bay Area's Best-in-Class Competition
Phototyped novel physics-informed neural network architectures to serve as surrogate for physics solvers
Developed automated test to analyzes the performance of proposed reinforcement learning methods for designing silicon photonics grating coupler
Parallelized physics simulations of gratings coupler tests

May 2022 - August 2022
May 2021 - August 2021

Graduate Teaching Assistant | University of Massachusetts Dartmouth

Teaching assistant and grader at the Computer and Information Science Department
Managed students' performance records and met regularly to review topics discussed in class
Designed learning materials with supporting tools
Courses:

CIS 180: Object-Oriented Programming I
CIS 322 (Online): Data Structures and Fundamental Algorithms
CIS 560: Theoretical Computer Science
CIS 570: Advance Computer Systems
CIS 570 (Online): Advance Computer Systems

January 2020 - May 2021

Research Fellow | University of Texas at Dallas

Worked as a researcher at the University of Texas at Dallas through the National Science Foundation Research Experiences for Undergraduate (REU) Program and under the supervision of Dr. Eric Wong
The team conducted a deep analysis on the reliability of various classical machine learning techniques, deep learning models and radiologists to provide empirical data that can either support or oppose the use of deep learning in critical situations where reliability is a priority
The research was presented by a collegue and I at 2019 REU Symposium in Washington DC

May 2019 - August 2019

Research Assistant | University of Massachusetts Dartmouth

Research assistant to Dr. Maoyuan Sun (Interests: Data Visualization and Human-Centered ML)
Worked on numerous projects including the NSF-supported research: Visualizing Data Relationships Across Multiple Views. The project investigated methods for displaying relationships in data across multiple visualizations
Developed a program to detect irregularity in a data stream

September 2017 - May 2019

Papers

Master Thesis | Graph Induced Lifelong Learning through Features Similarities and Dissimilarities

Abstract

Traditional approaches for training classical neural networks require that all possible classes that the model might encounter be sampled and presented during initial training. Such a requirement limits the domain of problems solved. For instance, building a vehicle that can traverse uncharted territories would be challenging due to the difficulty of constructing a model that can account for all unknown situations. In this thesis, we are presenting a proof-of-concept framework and technique for a novel approach to continual lifelong learning that utilizes feature similarities and dissimilarities in a given batch of data to solve never-seen-before tasks. Our approach has the advantage that it can be applied to both Euclidean data as well as graphs and can sustain notable accuracy across introductions of new classes without any retraining/rehearsal.

The heart of our technique, Lign, is the leveraging of neural network fine tuning and pruning, commonly used in transfer learning, to temporarily remove certain weights from a network that detect key features of a previously solved tasks and reuses them to understand new problems. After pruning, the neural network can be utilized as an embedder with the aid of clustering techniques to label data based on genetic learned features. Lign_MNIST (a restructured model tested on the MNIST data set) was able to demonstrate feature comparison and learning when shown unknown digits. Results were also found with other models that were tested on the CIFAR-100 and Cora data sets that provide further insights into the inner working of the technique.

2021

Book Chapter & Conference | An Educational Tool for Exploring the Pumping Lemma Property for Regular Languages

Abstract

Pumping lemma has been a very difficult topic for students to understand in a theoretical computer science course due to a lack of tool support. In this paper, we present an active learning tool called MInimum PUmping length (MIPU) educational software to explore the pumping lemma property for regular languages. For a given regular language, MIPU offers three major functionalities: determining the membership of an input string, generating a list of short strings that belong to the language, and automatically calculating the minimal pumping length of the language. The software tool has been developed to provide educational assistance to students to better understand the concepts of pumping lemma and minimum pumping length and promote active learning through hands-on practice.

Josue N. Rivera and Haiping Xu, “An Educational Tool for Exploring the Pumping Lemma Property of Regular Languages,” In H. R. Arabnia (Ed.), Advances in Software Engineering, Education, and e-Learning, Springer Nature - Research Book Series, Transactions on Computational Science & Computational Intelligence, (TCSCI), 2020.
Josue N. Rivera and Haiping Xu, “An Educational Tool for Exploring the Pumping Lemma Property of Regular Languages,” The 16th International Conference on Frontiers in Education: Computer Science and Computer Engineering (FECS’20), Las Vegas, Nevada, USA, Jul 27-30, 2020. (PDF).

2020

Research Poster | A Comparison of the Reliability between Traditional Machine Learning Techniques and Deep Learning in the Classification of Breast Cancer

Josue N. Rivera, Jacob Richard, and Ricardo Ramirez, "A Comparison of the Reliability between Traditional Machine Learning Techniques and Deep Learning in the Classification of Breast Cancer," Research Poster, 2019 Research Experiences for Undergraduates Symposium (REUS 2019), Alexandria, VA, USA, October 27-28, 2019.

2019

Portfolio

all
Machine Learning
Game Design
Web Development
Software Application

Runner-Z

Game Development

Runner-Z is a video game designed for the Intellivision console of 1979. The game incorporates modern game design concepts while working with the limitation of the hardware. The game was completely written in BASIC with some Assembly for data management.

Repository

Lign

Deep Learning Library

A graph framework that can be used to implement graph convolutional networks (GCNs), geometry machine learning, continual lifelong learning on graphs and other graph-based machine learning methods alongside PyTorch.

Repository

Porfolio

Web Development

A personal site designed to showcase current and past projects. It was built using web tools such as HTML5, CSS3 and JavaScript.

Repository

3D Geometry Foot

Machine Learning

3D Geometry Foot is an algorithm that from a few images can reconstruct a 3D model of a person foot. It was developed as a bachelor capstone project.

PIF

Neural Network Model

PIF is an encoder-decoder convolutional neural network that can generate in-between frames of a given video thus increasing frame rate. During the research, a high definition 25 fps video was increased to 50 fps without loss in resolution, reduced length of video or noticeable distortions.

Repository

SQL Engine

Database System

The project consisted of a database engine that can process SQL queries and apply standard optimization techniques like projection pushdown, selection pushdown and cross product to join conversion.

Repository

Cardiac Survival Predictor

Machine Learning

This project aims to predict patient survival of an ICU stay among those who have frequently occurring cardiac diagnoses, namely congestive heart failure and atrial fibrillation.

Repository

MIPU

Educational Application

MInimum PUmping length (MIPU) educational software is an active learning tool designed to explore the pumping lemma property for regular languages. For a given regular language, MIPU offers three major functionalities: determining the membership of an input string, generating a list of short strings that belong to the language, and automatically calculating the minimal pumping length of the language.

Repository

EZform - PerkinsHack

Application

EZform is a text reader for images with textual context that allows blind individuals to fill out forms in private. It was developed during PerkinsHack 2018.

Repository