VIP Program at Howard University (VIPatHOWARD)

Howard University

Washington, DC 20059

VIP Director: Dr. Charles Kim (CKIM@HOWARD.EDU), Professor, Electrical Engineering and Computer Science

*NOTE: From Fall 2023 semester, EE/CpE students could earn 3 credits from VIP courses (EECE101 Faculty-Student Team Project (VIP) (1 cr); EECE201 (1 cr); and EECE 302 (1 cr)) and substitute them for 1 EE/CpE elective course.  Only 1 VIP course is allowed to take in a given semester.

* How to Join?:  If you want to  join one of the teams below, contact Project Advisor (via email) or the VIP Director (Dr. Charles Kim) via email  ckim@howard.edu

 

 Any question can be directed to the VIP Director at ckim@howard.edu.  Anyone, yeah anyone, can join.

 

Project Teams

Project Team Advisor/Contact Project Description Sponsor
Intelsat Performance Bot (from Fall 2024) Dr.Anietie Andy (Computer Science)  Email: anietie.andy@howard.edu

The proposed VIP project is "Intelsat Performance Bot.”   Intelsat collects and maintains a vast amount of data points used by Network and Operations to monitor, analyze, and model operational performance to ensure connectivity service is highly available for our customers. Users outside Commercial Aviation (CA) Network and Operations teams often need answers held in the team’s data and spend significant time in meetings and/or requesting data to answer fundamental, performance-related questions. The goal of the project is to make Commercial Aviation (CA) performance data more widely available by setting up a generative AI-enabled chatbot interface with natural language processing (NLP) capabilities so users can interact / query various datasets without expertise.

Emag Playground (From Fall 2022) Dr. Su Yan (su.yan@howard.edu) Visualization of Electromnmagnetic field.  (contact Dr. Yan for more details)  
Smart Signal Detector (From Fall 2024) Advisor: Dr. Eric Seabron (Electrical Engineering) email: eric.seabron@howard.edu

Co-advisors:  Dr. Anietie Andy and Dr. Imtiaz Ahmed
Smart Signal Detector.  We want to classify the modulation type of arbitrary RF signals in a noisy environment by using Machine Learning to make the classification processing more robust, increase, accuracy, and improve processing speed. We propose exploring a variety of AI techniques and feature engineering to improve classification accuracy across a variety of modulation types. Feature engineering may include enhancement to statistical, cyclostationary, frequency domain change, principal component analysis or image (ridge, edge) features. The AI models may explore Convolutional Neural Networks (CNNs), Autoencoders, Transformer, Recurrent Neural Networks (RNN), Random Forest architectures and techniques to improve accuracy and speed. We will benchmark state of the art algorithms, as well as novel software solutions for smart signal detection on compact Intel based NPU hardware systems.
Capital One
(From Fall 2021)
Advisor: Dr. Imtiaz Ahmed (Electrical Engineering) Algorithmic and Visualization Capabilities for Machine Learning: The objective of the project is to evaluate various algorithmic and visualization tools and insights which would generate various types of visualization to support machine learning-driven analysis of large/complex data sets.  The project utilizes open source tools and publicly available data in the evaluation study.

Team Members
Amazon Freight (From Fall 2021) Advisor: This research aims to develop advanced machine learning and econometric models to tackle current days freight optimization problems. More specifically, this project focuses on the cold chain implementation in the Amazon Freight Inbound (AFI) network. Students from both Civil and Environmental Engineering and Computer Engineering are part of this research team. The project team will help Amazon to create a web-based service for cold chain shippers. The service allows shippers to send their freight pickup requests and then builds optimized execution plans for the Amazon Freight inbound process, including freight pickup, DC cross-dock, and delivery to the destination facilities. The optimization engine generates the most cost-efficient route solutions that meet the time, temperature, capacity, and operational constraints.


Team Members
Secure Smart Traffic (from Fall 2019) Advisor: Dr. Hassan Salmani (Computer Eng)
 hassan.salmani@howard.edu
The goal of the project is to realize secure smart traffic which is characterized: Driving cars on the road; base stations on the side of the road which gives road data to the cars; cars adjust position and speed among the cars on the road; there are possibilities that the communication between cars and car-station may be hacked; secure smart traffic shields the communication.
Team Members
Forming new teams Advisor: Dr. Charles Kim (Electrical Eng)  ckim@Howard.edu





Candidate Projects: (a) Predictive location of underground cable fault and  (b) Power converter in space and vehicular systems.

Students in all disciplines and all majors are encouraged to inquire about the projects and participation opportunities.  EECE101, EECE201, or EECE302 VIP course taking is optional in joining a team.





Social Sphere Machine
(From Fall 2019)
Advisor: Dr. Charles Kim (Electrical Eng)  ckim@Howard.edu Media Content Analysis for Event Prediction.  The goal of this project is to scrawl major media webpages and collects significants words regulary which, later, will be analyzed and learned to, hopefully, predict future events. Team members:
DC-Water SCADA
(from Fall 2023)
Advisor: Dr. Charles Kim (Electrical Eng)  ckim@Howard.edu

External Advisor (DC Water): Karen Green (Senior Manager)
Industrial PLC(Programmable Logic Controller) applications in DC Water.  The goal of this project is to collaborate betweem HU and DC Water for candidates for SCADA (Supervisory  Control and Data Acquaition) application positions. Team Members

Co-Manager (From Fall 2024) Advisor: Dr. Saurav Aryal (CS) and Dr. Legand Burge(saurav.aryal@howard.edu)

Production and Workforce Co-Management System: This project aims to develop a networked system which would make workforce and production management adaptable to changing situations. There is a need for efficient workforce management which runs around the product availability and, simultaneously, for seamless production plan following the workforce availability.   A networked co-management system is devised, in which the real-time production control of the field is obtained from a PLC (programmable logic controller) with pumps and valves, while the workforce-status and management is maintained in a software environment, with the two sub-systems connected through a network.   This networked system connects the production control system in the field to the workforce management system so that the production-level and the workforce-status can be both simultaneously managed.



Team Members
       

 

VIP Teams of 2019-2020, 2018-2019, 2017-2018, 2016-2017, 2015-2016.

VIP at Howard Main Webpage


MWFTR.COM