Computer Science Program Projects 2021

AWS Project
Client: Commonwealth Casualty Company
Liaison: Mahan Hajianpour

Students: Jesus Garcia, Luis Lucero, Carlos Mendoza Jr, Bryan Perez, Nancy Rosa, Saul Rugama- Montenegro, Pasindu Siriwardena, Rongfeng Tan, Junli Wang
Advisor: Jiang Guo

Create a templating engine that generates policy documents from template HTML files. At runtime, templates are populated with client policy information to create documents for specific clients. Using the Java Spring framework, we were able to create a standalone web application that streamlines the document generation and management process for Commonwealth Casualty Company. Templates and documents attached to a client policy alike can then be accessed in our application, where users can modify existing templates, create new templates, or publish documents with the templates that are available to users. The web application consists of a user interface where users can add, delete, modify, and package templates, where templates are then populated with client data and turned into policy documents for CCC and their clients. Our application also gives full control of the clients that are stored in the relational database. Users have the power to add, delete, and modify clients and their policy information. The application uses Amazon Web Services to store our relational database in RDS and hosts our server in EC2, essentially hosting our application in the cloud.

Expectation from our project:
1. Create a standalone service that can be incorporated into the existing CCC application to generate documents using our Templating Engine.
2. Integrate AWS cloud services to simplify setup and allow for scalability.
3. Create comparison & version control features that enable efficient document management.

Artificial Intelligence and Data Science for Air Pollution Prediction and Visualization
Client: NASA and LA City

Students: Eric Chan, Micky Chan, Peter Gatsby, Larry Gutierrez, Jose Landa
Advisor: Mohammad Pourhomayoun

Developing AI models as well as visualization frameworks to predict and visualize air pollution in Los Angeles (various air pollutants such as PM2.5, NO2, O3, ...). In this project, we use various machine learning algorithms and visualization frameworks as well as advanced geographic information systems such as ArcGIS to visualize the results on the map. We will also develop web applications and mobile applications for the visualization framework.

Technology: AI, Data Science, machine learning, predictive models, visualization frameworks, web, and mobile apps.

Artificial Intelligence for Smart Cities
Client: TOYOTA and LA City

Students: Jason Fan, Luis Gonzalez Gutierrez, Edgar Hernandez, Gunjan Kc, Lynne Tien
Advisor: Mohammad Pourhomayoun

The City of Los Angeles is very known for its diverse cultures and timeless nightlife. However, it is also infamous for the dreaded traffic and air pollution. Hence, the City of LA and LADOT has collaborated with CSULA to apprehend these grand problems. As part of a stepping stone that Los Angeles City has taken in preparation for the Olympics 2028 whereby, we presume traffic and air pollution will worsen. Apart from preparing for the Olympics, this project is one of the many that will assist the Los Angeles City and The LA Department of Transportation (LADOT) in achieving Vision Zero, which purposes to end all traffic injuries and deaths by 2025. Thus, the objectives of this project consist of developing Artificial Intelligence (AI) based algorithms, machine learning models, and visualization frameworks that can monitor, manage or predict the traffic and air pollution data, analyzing and visualizing the results, and designing a data preprocessing pipeline whereby city engineers can use.

Technology: AI, Data Science, machine learning, predictive models, visualization frameworks, web, and mobile apps.

COVID-19 Data Analysis and Visualization
Client: Vodafone Group
Liaison: Haley Kirk

Students: Kevin Crespin Ruiz, Fredi Garcia, Kiefer Giang, John Grover Rodriguez, Jose Lopez, Kennedy Nguyen, Leo Shapiro, Abubakir Siedahmed, Isaac Villalva
Advisor: Navid Amini

In late December 2019, Chinese health authorities reported an outbreak of pneumonia of unknown origin in Wuhan, Hubei Province. Since then, the virus identified as SARS-CoV-2 or COVID-19 has spread globally, causing millions of deaths and having an enormous impact on our health systems, economies, and lifestyles. Summary: In this project, we analyze COVID-19 through data visualizations made using various tools such as Tableau, D3.js, Chart.js, and Matplotlib. We also analyze COVID-19 medical data and developed a logistic regression model using Python, Scikit Learn, and Jupyter Notebook to determine the likelihood of a patient getting hospitalized, getting admitted to an ICU (Intensive Care Unit), recovering, or dying. We also developed an Android application using Kotlin, JavaScript, and D3.js, that integrates various APIs for gathering and visualizing the latest COVID-19 numbers in the U.S and 50 of its states; it also intends to implement a Risk Calculator Tool developed by Johns Hopkins University that asserts individuals' risk of death when infected with COVID-19.

Collaborative Visualization for Solar System Treks
Client: JPL
Liaison: Emily Law

Students: Abdullah Alshebly, Stanley Do, Jose Garcia, Zipeng Guo, Johnny Lee, La France Montague, Miguel Sanchez, Christopher Smallwood, Odasys Soberanes, David Tang
Advisor: David Krum

Solar System Treks is a JPL web portal that provides NASA data from various planets, asteroids, and moons. This data is used by scientists, research partners, and the public, including students and teachers. The data includes satellite photography and 3D terrain models.  Collaborative visualization can be helpful in generating new insights, as a team of researchers or students can examine the data together and collectively generate and discuss new ideas and hypotheses. Additionally, with the need for remote work, remote learning, and social distancing due to COVID-19 precautions, remote collaboration has become increasingly important.

Trek API https://trek.nasa.gov/tiles/apidoc/

Purpose: As a means of supporting collaborative visualization, this project will develop networked visualization software that supports collaborative markup of 3D solar system terrain. The collaborative markup will include features such as the creation of waypoints, rapid navigation to waypoints, text annotations, and freely drawn “ink” annotations. The terrain would be selected from the Solar System Treks web portal and imported into the collaborative visualization application. The student capstone team will have the ability to analyze the problem and determine which technologies are best suited for developing and deploying a solution.

This capstone project would create useful tools that would support the collaborative visualization of NASA solar system data. This initial research and development would also enable a variety of future projects that could examine a variety of interesting topics involving virtual reality, augmented reality, visualization, and analytics.

Digitization of PD Onboarding & Approval Process
Client: Office of the Public Defender, LA County
Liaison: Mohammed Al Rawi

Students: Javier Garcia, Rawad Moussa, Adrian Palomares, Marlito Refuerzo Jr, Christopher Rodriguez, Tabassuma Torosa, Paul Clef Ube, Audelia Valdovinoz, Pierce Wei
Advisor: Chengyu Sun

Our Cal State LA Senior Design team is working closely with the Los Angeles County Office of the Public Defender as liaisons. The goals of this software project have shifted over the course of the 2020-2021 academic year. The project’s focus has been twofold:

(1) (Initial) Migrate PD legacy repositories in DNN and FileMaker to Salesforce architecture.

- This initially entailed some weeks of research on the Salesforce platform via the Trailhead educational portal.
- Gained an understanding of Salesforce’s capacities for platform development, data modeling, data management, data security, and building apps using cloud technologies.

(2) (Current) Digitize and automate the onboarding process and approval workflow for PD employees and contractors.

- Currently, employee/contractor internet service requests are handled in a somewhat elaborate manner. For example, employees/contractors may need to request social media access (Facebook, Twitter, LinkedIn) on their work accounts. At the moment, employees/contractors complete these requests by filling out individual PDF forms, noting the type of internet service requested, and then forwarding them to the department. This may entail completing several forms depending on the type of service requested. These forms are then manually forwarded to various parties for signing/approval.

- Our team’s solution involves migrating the request process into a more user-friendly, intuitive one using a web form. With this, contractors and employees would simply enter the relevant information one time on our clear and minimal form rather than having to parse through some of the technical jargon on the PDF files themselves. We will automate the PDF generation process using the webform so the Public Defender still gets populated files at the end.

- Importantly, upon submission, the approval/signing process would be automated as well. Relevant parties (the employee, manager, security officer, etc.) would receive emails in the appropriate order to sign the required fields on Adobe Sign.

- To meet the requirements of this software project, we have assigned team members to build the Front-end system, Back-end system, Admin functionality, and PDF population functionality. Our roles have shifted throughout the academic year according to the project’s needs.

- The Front-end system is built in Angular. It displays the web form and sends the user’s data to the back-end system.

- The Back-end system is built using Spring Boot and Hibernate. It receives employee/contractor data from the Front-end, stores it in an SQL database, and interfaces with the Adobe Sign API to populate PDFs and automate the signing process.

INART VR Project
Client: INART
Liaison: Sylke Meyer

Students: Noah Castro, Kevin Diaz-Lopez, Jessy Francisco, Steve Galvan, David Hermosillo, Kiet Hoang, Taha Kamran, Zudong Li, Daniel Ramirez Torres
Advisor: David Krum

Purpose: Creating photo-realistic virtual environments (lounges, landscapes, interior sets, etc.) and virtual characters to allow real actors to be placed into the virtual space using green screen technology. The INART project will use the Unreal Engine to create photo-realistic 3D settings to be used by Professor Meyer and the TVF students as their production sets. These virtual rooms will be used as sets for actors to interact with the world and objects in that world. The team is involved with the TVF Advanced Production to grasp a better idea of how green screens and virtual sets are used in films. Along with this, the team is looking at the implementation of animations and an A.I. system for the virtual characters.

Online Application for Street and Highway Pavements Design
Client: Department of Civil Engineering, Cal State LA

Students: Allen Atienza, Bryan Chu, Christian Esqueda, Adrian Flores, Andrew Gonzalez, Omar Juarez, Mark Kalaiji, Justin Nim, Christopher Ortega, Kayleen Ponce
Advisor: Negin Forouzesh

We are developing an online application to calculate pavement design and structures. The program then stores information on a server remotely accessed over the internet. By validating the information, a user inputs and selects, the program creates an intuitive experience everyone can use.
Deliverables: The primary deliverable is a working version of the online app (with mobile compatibility), including all the features. A data-driven design module is a secondary deliverable.

Open-Source Real-Time Video Player
Client: AT&T
Liaison: Steve Dulac

Students: Mirasol Davila, Tim Ellis, Brian Hernandez De Leon, Ashley Jetty, Wendy Joya, Israel Lopez-Diaz, Jeffrey Luu, David Melendez, Rafael Mendoza
Advisor: Negin Forouzesh

This team is working with AT&T liaisons to create an Open-Source Real-Time Video Player. We are building on top of the open-source HLS.js Github software. HLS.js is a web application that streams videos while providing a lot of useful real-time metrics and graphs about the video streaming playback. In order to further improve the features provided by HLS.js, we were given the task to implement a network throttling feature to throttle our network under different conditions such as 3G, 4G LTE, Home Broadband, etc. We are adding additional metrics and graphs to display the video start time, rebuffering ratio, average bitrate, and bandwidth conditions. Lastly, we were given the task to allow users to download an excel sheet containing all the information about the video playback for research purposes. Our proposed goal also included making our software available on Safari and Chrome and supporting HLS and DASH video files. By adding these features and metrics, companies that offer video streaming services can benefit from this software in order to collect valuable research and find new ways to improve their video streaming services.

PDF Web Viewer and Filter
Client: QTC

Students: Roman Arias, Chandel Buelna, Phoebe Castanedo, Cristian Corrales, Brandon Gonzalez, Joaquin Robles, David Sanchez, Ares Ton-That, Sean Ybarra
Advisor: Keenan Knaur

This software tool is a web PDF document viewer that allows the user to traverse through multiple documents with ease. The software retrieves a list of documents from a database and sets them up to be displayed within the web application. While the web application only displays one document at a time, it provides functionality, such as a scrolling mechanism, that will allow the user to scroll from one document onto the next. Additionally, the software provides a category filter function that will filter the list of documents to only those containing the specific category that the user has selected. Lastly, the software provides a search function that not only does look for keywords within the document that the user is looking at, but it also searches all the documents within the list, giving the user the most control when looking for specific data. 

RoboSub
Client: Civil Engineering Department and Mechanical Engineering Department, Cal State LA
Liaison: Dr. Mark Tufenkjian

Students: Albert Chew, Gabriela Cortes-Mejia, Heriberto Gonzalez, Ricardo Medina, Horacio Mondragon, Brandon Pham, Sana Shaikh, Wilson Weng, Kevin Williams
Advisor: Richard Cross

The RobSub Senior Design project is a joint project between a team of electrical and mechanical engineering students and a team of computer science students. The purpose of the project is to build a fully autonomous underwater vehicle (AUV) that will compete in an international competition. The competition consists of a sequence of different tasks and obstacles that test the AUV’s ability to detect objects, maneuver itself, and make decisions. The computer science team will design and implement the software that pilots the AUV, providing navigation, stabilization, object-detection, and task-handling capabilities.

The RoboSub project at California State University, Los Angeles is engaged in producing an Autonomous Underwater Vehicle (AUV) each year for the international RoboSub competition hosted by Robonation. The competition is held annually at the end of July at the Transducer Evaluation Center (TRANSDEC) in San Diego. The competition consists of a set of obstacles arranged in the TRANSDEC pool that each team’s submarine must navigate autonomously. This project is a joint senior design project, with a team composed of Mechanical and Electrical engineering students designing and building an Autonomous Underwater Vehicle intended for use in the competition and one composed of Computer Science Majors responsible for the software to be implemented on the AUV.

Satellite Anomaly Injection & Detection Testbed
Client: The Aerospace Corporation
Liaison: Rick Johnson, Denny Ly, Karina Martinez, Pablo Settecase

Students: Matthew Gilligan, Alex Huang, Alexander Lopez, Jerome Pineda, Vivian Sau, Samantha Simpson, Aaron Tong, Nicholas Torres, Joshua Tran
Advisor: Russ Abbott

Satellites perform a host of vital functions including communications, weather prediction, geolocation, defense, and many others. In these complicated systems, it is extremely important that accurate data flows freely between the ground and the satellite via uplinks and downlinks. When strange behaviors or anomalies occur, it is vital that the errors be identified and corrected before a disaster occurs. Sometimes these anomalies are the result of errors in the hardware or software, issues introduced by the environment, or an attack by a hacker. Effective anomaly detection techniques can help identify problems on the vehicle before they happen, which can help improve mission success.

The operation of satellites in long-term term operation is affected by many uncertain factors. Anomaly detection based on telemetry data is a critical satellite health monitoring task that is important for identifying unusual or unexpected events. The use of simulation tools allows users to configure and deploy platforms to be used in real-time environments as well as simulate any anomalies that can take place. Machine learning can be used to detect these anomalies by comparing actual observed values with the predicted intervals of telemetry data. Simulation tools can be utilized by students to develop a way to solve these complex problems using applications already being used in the industry.

For this project, we have developed software components to integrate with and utilize existing industry open-source software components to perform the tasks outlined below to:

1. Generate satellite simulation data
2. Inject anomalous scenarios into the flight system
3. Apply techniques for detecting the anomalies on board and on the ground

Outcomes from the project:

1. Software source to developed anomaly injection and detection capabilities
2. Detailed documentation on design, implementation, tests, and results from each of the anomaly scenarios
3. User manual to set up, configure, and run the OSK with the anomaly injection and detection capabilities
4. Monthly review meetings with Aerospace liaisons and final out brief to Aerospace engineers

Sidewalk Slope Monitoring System
Client: Department of Public Works and Bureau of Engineering, LA City
Liaison: Ted Allen, Alisa Blake, Miguel Grajeda, Raul Virgen

Students: Jan Bautista, Hua Chen, Abigail Garcia, Ana Guardado, Cristina Munteanu, Pabasara Navaratne, Alexis Pena, Beatriz Ruiz, Aoqian Wang
Advisor: Jungsoo (Soo) Lim

The City of Los Angeles, Bureau of Engineering maintains over 11,000 miles of sidewalks. When a segment of the sidewalk does not settle evenly or has been raised up by tree-root growth, the sidewalk becomes uneven. This can create pedestrian hazards. In addition, the City is obligated to ensure that its sidewalks conform to Federal ADA standards, which limit the extent to which a sidewalk may slope.

This is the fourth term of a multi-year project. In the last term, a rover has been successfully fabricated. Now, the rover is capable of 1) moving autonomously, 2) measuring crossing slopes and running slopes, 3) collecting GPS data, and 4) taking photo images. In this term, we will focus on developing various software that 1) lenders the photo images with slope data and GPS data, (in office) 2) processes images such as object segmenting and texture processing, 3) assists field crew while they are collecting data in the field (i.e., a user-friendly mobile app/web app). 4) In addition, develop a database schema and backend server to store and manage raw data.

Telescope Moon Trek
Client: JPL
Liaisons: Natalie Gallegos, Emily Law, Shan Malhotra

Students: Kevin Aguilera, Pavit Chawla, Jacob Frausto, Alex Lamb, Nicolas Ojeda, Albert Ramirez, Gerard Rosario, Elvira Sakalenka, Dakota Townsend
Advisor: Weronika Cwir

JPL is partnering with California State University – Los Angeles, College of Engineering, Computer Science, and Technology to build an interface between Moon Trek and telescopes amateur astronomers use to look at the Moon. When images from the telescope are routed to a laptop or a smartphone they will be annotated with names of lunar features and landmarks, local temperature, the chemical makeup of the soil – or any available information the astronomer chooses.

This team is creating a Web Application in which the user will be able to provide an image from a telescope. When feeding an image of the moon from a telescope, the application will provide additional information to the user about its moon feed. The features that are provided are important annotations such as important landing sites, local temperatures, chemical makeups of the soil – such as iron, etc.

The application goal is to obtain the additional features from the JPL’s Moon Trek portal, which already contains a vast amount of data regarding the moon. The extra annotations that the user will receive, need to be correctly correlated to the image of the moon that they’re seeing in the telescope.

To complete our main task of creating the application we must first implement important technical steps to achieve the best accuracy of annotations to the image provided by the telescope. With the help of our image registration implementation, we accurately pinpoint the user’s telescope image according to extra information of the moon gathered from JPL’s Moon Trek Portal.

The ArQive Mobile App
Clients: The ArQive & The Institute for Interactive Arts, Research, and Technology (INART) at Cal State LA
Liaisons: Zachary Vernon, Cynthia Wang

Students: Randy Arruda Jr, Balarama Carter, Richard Cruz-Silva, Abram Flores, Carlos Larios-solis, Khang Le, Brandon Lee, Casandra Pahed, Evelyn Ramirez
Advisor: John Hurley

ArQive, formerly known as GlobaltraQs, is a web and mobile application that allows anyone to post fun and interesting LGBTQ+ oriented stories, events, and other information that they find meaningful. Founded in 2014 by Dr. Cynthia Wang and Zachary Vernon. The ArQive gives users a safe platform where they can share personal, historical, and community stories, as well as have access to information about safe spaces, which all serve as valuable resources to members of the LGBTQ+ community. By providing users with the ability to place pins on the map indicating where they have been and the experiences they have lived, The ArQive gives people the ability to mark their place in the world and in history.

This year’s project for the ArQive will focus on creating iOS and Android mobile applications, as well as adding further security measures for users who choose anonymity, exploring ways to automate content moderation, enhancing gamification features to improve user engagement and linking posts to other social media sites.

Want2Remember App
Client: We2Link

Students: Kevin Benavente, Liangbin Huang, Tanya Kitchaiskulrit, Jesus Osuna, Edward Ramirez, Jesus Roman, Alejandro Salazar, Thomas Weatherell
Advisor: Zilong Ye

The We2link App, Want 2 Remember, is designed to help those with cognitive impairment and their caregivers. It is vital for the user and their caregivers to be able to keep a record of what they deem important in their lives. By implementing an online-offline mobile application that provides features such as user/location proximity with GPS and geo-tracking of supported users, we believe could better the lives of both the user and caregiver. There are also a few features that may be included, e.g., Circle of care, chat channel, provide a portal, etc. Want 2 Remember app is a mobile app currently under development for Android and iOS devices. The app is developed using the React Native framework which allows our team to develop the app for both operating systems simultaneously. The development team will be practicing a strict Agile methodology while also taking into consideration beta user feedback.