School of Technology and Computing
Hosted by CityU’s Center for Cybersecurity Innovation and School of Technology and Computing (STC), the Applied Research Symposium is open to faculty, professionals, and students from any discipline, university, or professional organization. At the end of each quarter, any students who would like to share their projects including capstone courses will present their outcomes. This symposium will provide opportunities for students, researchers, and practitioners to discuss the influence and impact of the applied computing on the future of our planet and our society
Event details
Date: Thursday, September 9th, 2021
Time: 4:00PM-5:00PM PDT
Contact: zeyuchen@cityuniversity.edu
Advisors
DR. Sam Chung
Dean, School of Technology & Computing
AHREUM JU
Associate Faculty, School of Technology & Computing
A Synchronous Online STEM Competition with High Availability
The online education system plays an essential role in the modern world. Education organizations and businesses want to provide their assessment system based on an online education system. During the online training, GBs of data is continuously generating and being collected from the user every event. Those valuable data can be processed and analyzed to support many decisions in a second such as user state, chatting detection, and online help desk. In addition, demand from different roles, such as data analysts, data science, executives, that access to those data has increased recently. In this paper, we present the new architecture for real-time data streaming based on the existing education system and identify three challenges that need to be addressed in our architecture. First, most organizations or education areas rely on the open-source system for their learning system. Second, on top of the synchronized learning management system, we add customized solutions for improvement and customization to give real-time ability to meet the synchronized online test requirement.
for the current situation including availability, cost, technologies.
Liu, Yu-Che - M.S. Computer Science
CS 687: Computer Science Capstone
Mehta, Jayna - M.S. Computer Science
Drowsy Driver Detection with Warning System for Old Vehicles
Nowadays the major problem in the world is the increased number of road accidents. The main reason for the accident is the Driver’s sleepiness or lack of concentration. Research in driver drowsiness observing may help to reduce accidents. This paper, therefore, proposes a facial expression approach for implementing a driver’s drowsiness alert system for old vehicles which would detect and monitor the yawning and sleepiness of the driver. We use a facial landmark detector using Dlib pre-trained model to extract face and facial landmark, followed by calculation of Eye Aspect Ratio (EAR), and Mouth Aspect Ratio (MAR) to detect whether a driver is concentrated into driving. Intel’s Open-source Image processing libraries (OPENCV) are used as a primary image processing tool. EAR is analyzed by analyzing Euclidean distance between measured eye coordinates. Flask is used to create a web application and create a warning system for the drowsy driver for safety purposes. This experimental result shows better real-time performance than traditional methods.
Improved Predictive Unmanned Aerial Vehicle Maintenance Using Business Analytics and Cloud Services
The purpose of this project is to suggest adopting business analytics and cloud services to improve existing Unmanned Aerial Vehicle Maintenance.
Kim, Taejin - M.S. Computer Science
CS 687 : Computer Science Capstone
A Deep Learning Model for Multiple Apple Foliar Diseases Identification
Apple orchards are facing threats of pathogens and insects, which costs millions of dollars lost every year in the United States. The current apple disease diagnose process is based on naked eyes. The time-consuming process requires apple farmers to have professional knowledge about various apple diseases. Incorrect diagnosis will cause chemical abuse, environmental pollution, and financial loss. Because of the involution of deep learning, fast and efficient plant diseases detection powered by a deep learning model is possible. In the past few years, many high accurate deep learning models achieved high performance on apple foliar diseases classification problems. But these models have a limitation that is they only can detect a single apple disease. The paper focuses on implementing a deep learning model for multiple apple foliar diseases identification problems according to the Plant Pathology 2021 competition on Kaggle. The model achieved high accuracy on both singly and multiply apple foliar diseases identification problems.
