Fall 2022 C-Day Winners

Assurant Awards

Assurant Award UC

  • UC-266 INDY-5 CompChores by Berry, Myers, Snyder, Ian
    Abstract: Getting anyone motivated to complete chores can be a chore itself! To solve this issue, our team is using Dart and Flutter to build a desktop application that pits roommates, family members, and siblings against one another to complete chores for points. The purpose of this program is to simulate competition between users in order to motivate users to complete tasks amongst the living space. To complete this task, our program will provide a place where users can create a family, create an account, join a family, create chores, complete chores, check chore history, view the family scoreboard, and view how many chores they have completed. Users will be able to change chore points based on difficulty, estimated time of completion, and priority. There will also be a way for users to check chore history in order to know which chores were completed by each person. The family will have a main homepage which will show the top three scores within the family, the chores with the highest priority, and the family ID in which users can share with one another to allow others to join the family. Then for more detail there will be a chore page, a scoreboard page, and a settings page to change account information or leave a family. All of these pages and features will allow users to create an environment amongst their peers that is not only productive but is also fun!
    Department: Computer Science
    Supervisor: Prof. Sharon Perry
    Topics: Software Engineering
    Presentation | Poster | More Information

 

Assurant Award UR

  • UR-294 A Quantum Arithmetic Logic Unit by Butler, Ethan, Phillip, Bryson, Ulrich, Benjamin G, Carroll, David
    Abstract: This paper demonstrates that a quantum version of a classical Arithmetic Logic Unit (ALU) can be implemented on a quantum circuit. It would perform the same functions as the classical ALU, with the possibility of adding quantum functions in conjunction. To create the quantum ALU, we utilized IBM’s Qiskit Python package and JuypterLab. We also used the IBM Quantum Lab to run the circuit. We believe that a quantum ALU has the potential to be faster than its classical counterpart and the ability to calculate quantum specific operations. The simple classical functions translated to a quantum circuit show a promising future for the development of a full quantum ALU with unique quantum operations.
    Department: Computer Science
    Supervisor: Senior Project Course Instructor: Prof. Sharon Perry; Project Owner: Dr. Dan Lo
    Topics: Other (explain in the comments section)
    Presentation | Poster | More Information


Undergraduate Research

First Place Under Undergraduate Research Winner

  • 1st Place: UR-269 Towards Bounding the Behavior of Deep Neural Networks by Borowski, Richard,
    Abstract: Advances in Artificial Intelligence (AI), particularly in the form of deep neural networks, have revolutionized a diverse range of fields. As neural networks become more pervasive, the need to understand the boundaries of their behavior is becoming increasingly important. For example, can we formally guarantee that an autonomous vehicle will not violate traffic laws, such as reaching excessive speeds? Towards the goal of bounding the behavior of a neural network, we propose how to bound the behavior of individual neurons by incrementally tightening formal bounds on it. We further provide a case study on classifying handwritten digits to illustrate the utility of our algorithm in terms of bounding the behavior of an individual neuron.
    Department: Computer Science
    Supervisor: Dr. Arthur Choi
    Topics: Artificial Intelligence
    Presentation | Poster | More Information

 

Second Place Undergraduate Research Winner

  • 2nd Place: UR-285 OPERATION ENDURING FREEDOM: Improving Mission Effectiveness by Identifying Trends in Successful Terrorism by Shaver, Dalton A,
    Abstract: This research examines how the characteristics of terrorist attacks predict the chance of an attack succeeding, where an attack is defined as successful if the intended attack type is carried out. Data from The Global Terrorism Database (https://www.start.umd.edu/gtd) was analyzed across three geographical missions within Operation Enduring Freedom: Trans-Sahara, Horn of Africa, and the Philippines. The three models were able to distinguish between successful and unsuccessful attacks at 78.74%, 82.11%, 74.25%, respectively. Using predicted probabilities of success obtained from each logistic regression model, the medians were plotted to compare the characteristics of terrorist attacks across missions. The coefficients for each model were analyzed to compare the odds of success for each variable level to the odds of success of the reference level for that variable. Lastly, the coordinates for successful and unsuccessful attacks as classified by the dataset was plotted to explore spatial patterns in regional maps. Many insights were gathered through analyzing Operation Enduring Freedom missions. It is shown that terrorists are substantially successful in their aims to terrorize the general populace. Attacks targeting private citizens, tourists, non-governmental organizations, and food or water supply, have the largest probability of success for the Trans-Sahara and Horn of Africa regions. Suicide attacks in the Philippines raise the chance of success, in contrast to the other two missions. The predicted probability of success when explosives and firearms are used in the Philippines is lower than the Trans-Sahara and Horn of Africa mission areas. Additionally, the odds of an attack succeeding when it involves a barricade incident with hostages is 10,491 times greater the odds of an attack succeeding when it involves bombings. By determining the specific characteristics of attacks that produce the highest probabilities of success, the effectiveness of Operation Enduring Freedom can be improved by focusing counter-terrorism training and operations on the features that predict successful attacks.
    Department: Data Science and Analytics
    Supervisor: Prof. Susan Hardy - Main Advisor, Dr. Gene Ray - Consultant Meeting, Dr. Austin Brown - Consultant Meeting
    Topics: Data/Data Analytics
    Presentation | Poster | More Information

 

Third Place Undergraduate Research Winner

  • 3d Place UR-295 Data Collection in Parkinson's VR by Weingarten, Neil E, McConnell, Ian
    Abstract: This submission is meant to show an addition to a Parkinson's simulation within VR where there are now different methods of data collection that are collected in-game. These data points are tracked and logged during gameplay, and are meant to allow researchers to make more effective use of the simulation as a tool for data collection. An example demo of the game and example files that were generated during gameplay are provided.
    Department: Software Engineering and Game Design and Development
    Supervisor: Dr. Joy Li
    Topics: Games
    Presentation | Poster | More Information


Undergraduate Capstone

First Place Undergratuare Capstone Winner

  • 1st place: UC-249 Hemorrhage by Respess, Daniel M, Brewer, Antonio S, Tran, Kenny, Li, Sandy, Watson, Rick B
    Abstract: Hemorrhage is a fast-paced FPS action game with a focus on risky gameplay and dodging enemy attacks. Fight your way through hordes of grotesque creatures and make it to the end! The player starts with limited health but can steal more from killing enemies. Then, you can unleash this stored-up health to deal massive damage to your foes! Will you choose to be an unkillable tank? Or a brutal glass cannon?
    Department: Software Engineering and Game Design and Development
    Supervisor: Dr. Joy Li
    Topics: Games
    Presentation | Poster | More Information

 

Second Place Undergraduate Capstone

  • 2nd Place UC-274 RESTful Robots by Young, Jack I, Comella, Derek M, Thomas, Sarah, Loveless, Andrew
    Abstract: The UXA-90 Robots have been sitting idle at Kennesaw State University for years. The only documentation provided were factory manuals, and there was nothing additional found online. The first step was to conduct a risk assessment and report the results to Professor Perry and Dr. Pei. The objective of the risk assessment was to determine the viability of the robots and the feasibility of three different senior project teams using them for a project. Once the risk assessment was completed and reported it was determined that all three teams could proceed with their senior projects. However, it was recommended that this team, SP-1 RED, develop a robot handling and training program and conduct training and certification of all other members of the other teams. The training and certification was conducted from September 14th through September 15th and documented online with a documentation website for all teams to reference. The robots have the ability to move, walk, see (through a webcam), hear and speak (using built in speakers and microphones). The robots consist of: * An internal mini-PC running Ubuntu 14.04 LTS * Serial-over-USB communication ports * SAM interface motor control boards * RF remote control * USB HD webcam * Internal microphone and speakers The goal of this team, SP-1 RED is to increase the accessibility and usability of the UXA-90 robot including a REST API, documentation and training.
    Department: Computer Science
    Supervisor: Prof. Sharon Perry
    Topics: Software Engineering
    Presentation | Poster | More Information

 

Third Place Undergraduate Capstone Winner

  • 3d Place: UC-296 Cybersecurity Park by Weingarten, Neil E, Hendrick, JaDante, Nowokunski, Kylie, Crawford , Tyler
    Abstract: Cybersecurity Park is an educational VR game intended for middle-school-age children that aims to demonstrate a wide range of cybersecurity concepts to the players. Such concepts include hacking ethics and types of hackers, cryptography, Trojan Horse / ransomware viruses, and authentication and authorization. These concepts are split into various mini-games that the player can freely navigate to from the hub they spawn in. For example, in the mini-game showcasing the Trojan Horse concept, players play as a knight defending a castle from evildoers. Visitors will approach the castle and ask access into the castle, and, based on the actions by the visitors, the player will choose whether or not to allow access into the castle. The player acts as a firewall, and the visitors act like applications requesting access into a computer. If a bad visitor/application is let into the castle (representing a computer), then the castle will begin to catch fire. This one of six mini-games present within this game, and video demonstrations of some of these mini-games are provided.
    Department: Software Engineering and Game Design and Development
    Supervisor: Dr. Joy Li - Supervisor, Course Instructor; Dr. Yan Huang - Owner
    Topics: Games
    Presentation | Poster | More Information

Graduate Research

First Place Graduate Research Winner

  • 1st place: GR-284 Automated Vulnerability Detection in Source Code Using Deep Neural Networks by Akter, Mst Shapna
    Abstract: One of the most important challenges in the field of a software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a large-scale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of open-source functions that point to potential exploits. We created an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. To remove the pointless components and shorten the dependency, the source code is first converted into a minimal intermediate representation. We keep the semantic and syntactic information using state-of-the-art word embedding algorithms. The embedded vectors are subsequently fed into convolutional neural networks to classify the possible vulnerabilities. Furthermore, we proposed a new neural network model which seems to overcome issues associated with traditional neural networks. To measure the performance, we used evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time.
    Department: Computer Science
    Supervisor: Dr. Dan Lo
    Topics: Artificial Intelligence
    Presentation | Poster | More Information

 

Third Place Undergraduate Research

  • 3d Place GR-241 On Training Explainable Neurons by Kennedy, Lance,
    Abstract: Neural networks have become increasingly powerful and commonplace tools for guiding decision-making. However, due to the black-box nature of many of these networks, it is often difficult to understand exactly what guides them to a certain prediction, making them dangerous to use for sensitive decision making, and making it difficult to ensure confidence in their output. For instance, a network which classifies images of dogs and cats may turn out to be flawed with little consequence, but a neural network that diagnoses the presence of diseases should be assured to make sound predictions. By understanding why a network makes the decisions it does, we can help to guarantee that the choices were made in a sensible way. However, part of the reason neural networks are considered a black-box is because it is very difficult computationally to explain how they work. In fact, individual neurons are known to be hard to explain already. In our research, we consider whether it is possible to learn an individual neuron that is explainable from the start. Unfortunately, our first result tells us that it is NP-hard to learn such a neuron. Fortunately, we have found new conditions under which we can learn an explainable neuron in pseudo-polynomial time.
    Department: Computer Science
    Supervisor: Dr. Arthur Choi
    Topics: Artificial Intelligence
    Presentation | Poster | More Information

Graduate Capstone

First Place Graduate Capstone Winner

  • 1st Place: GC-279 Geometry Matching Task for Improving The Cognitive Ability in Rehabilitation Process by owoade, samuel, Chamarthi, Ravi Teja, Kalipindi, Jeevana, Temgoua, Ghislain Dongbou
    Abstract: According to Taylor & Francis Group, LLC (2015), in the National Library of Medicine“Traumatic brain injury (TBI) impacts the lives of 1.5 to 2 million new individuals each year; 75,000 to 100,000 of these are classified as severe and will suffer enduring severe spasticity in addition to cognitive”. This game follows and respect basic and fundamental rules of brain and muscles recovery process and will help patients in their process of rehabilitation and by extension will improve their cognitive abilities.
    Department: Software Engineering and Game Design and Development
    Supervisor: Dr. Sungchul Jung
    Topics: Games
    Presentation | Poster | More Information

 

Second Place Graduate Capstone Winner

  • 2nd place: GC-250 Object Detection and Tracking: Deep Learning-based Framework with Euclidean Distance, IoU, and Hungarian Algorithm by Hossain Faruk, Md Jobair
    Abstract: Object tracking is an important basis for the logistics industry where multiple packages are moved on conveyor belts at a time. Accurate datasets and efficient benchmarks are a few of the several problems for both object detection and tracking for training the deep learning-based framework. Preparing 100% accurate correspondence between objects throughout different frames by assigning human annotated unique_attributes to train framework efficiently over ground truth data. In this research, we develop an (i) OpenCV-based framework that allows the user to assign human-annotated identification between objects and (ii) a novel application for object detection and tracking. We utilize the assigned attributes to train the deep learning model accurately and adopt various evaluation parameters including euclidean distance, intersection over union (IoU), and scale-invariant feature transform (SIFT) to measure the accuracy of an object correspondence or tracking. We also adopt the Hungarian algorithm to increase the efficiency in determining correspondences between objects and apply our framework to human-annotated ground truth datasets comprising ~1,000 images and the same amount of JSON files. Our demonstration achieved 94.53 % accuracy in object detection, finding correspondence, and object tracking. In future studies, we are aiming to apply a neural network to draw a comparison of identified accuracy.
    Department: Computer Science
    Supervisor: Dr. Selena He, Dr. Dan Lo
    Topics: Artificial Intelligence
    Presentation | Poster | More Information

 

Third Place Graduate Capstone Winner

  • 3d Place GC-312 Title - GTRI IT Service Desk System by Nwago, Koranna, Emani, Vineela, Gopi, Venkata Naga Rishita, Chatrathi, Bhavishya, Msimanga, Siphiwindoda
    Abstract: This overarching project would be web development, which would entail coding both the back end and the front end. The use of libraries is encouraged, but we must be cautious about licensing and ensure that this project remains as open-source as possible (a good open-source license ensures people can use, modify, redistribute, and sell without worry). This is a free and open-source project.
    Department: Information Technology
    Supervisor: Dr. Dr. Jack Zheng
    Topics: Other (explain in the comments section)
    Presentation | Poster | More Information
©