Skip to main content Skip to search

News

 News

Innovation on Display at Graduate Computer Science Research Showcase

Dr. Honggang Wang, left, chair of the Graduate Department of Computer Science and Engineering, presents a certificate for outstanding presentation on Secure Web Application for Sensitive Data to cybersecurity students Joy Awoleye, center, and Elijah Laticbe. Not pictured is Christine Macharia.

By Dave DeFusco

The Katz School’s Department of Graduate Computer Science and Engineering recently hosted a dynamic presentation of graduate student research, showcasing innovative capstone projects, independent studies and other research initiatives in Artificial Intelligence, Computer Science, Cybersecurity and Data Analytics and Visualization.

“The Katz School’s graduate research presentation featured the ingenuity and dedication of its students, demonstrating their ability to tackle complex challenges with innovative solutions,” said Dr. Honggang Wang, professor and chair of the department. “From revolutionizing career services and advancing AI techniques to enhancing cybersecurity and exploring new frontiers in data visualization, these projects underscore the transformative power of research in shaping the future.”

Advancing Career Services with Data Analytics

Data analytics student Akarsha Hegde discusses her research on OutfitVisionAI.

Surya Suresh Sriraman, Shashidhar Vadla, and Prem Chand Jala, students in the M.S. in Data Analytics and Visualization program, presented their project, “On the Road to a 360-degree Student View: Building a Cloud-Data Backed Dashboard for ’s Shevet Glaubach Center for Career Strategy and Professional Development.” This initiative aims to change how the Shevet Glaubach Center leverages data to meet the needs of students, parents and university leadership. By centralizing data from multiple sources into a cloud-based warehouse, the team developed dashboards to track trends in student appointments and staff engagement, overcoming challenges such as fragmented data systems and manual reporting.

Pioneering Machine Learning Techniques

Mohammad Zubair Khan, a student in the M.S. in Artificial Intelligence, presented his research on “Dynamic Logistic Ensembles with Recursive Probability and Automatic Subset Splitting for Enhanced Binary Classification.” Addressing the challenges of datasets with inherent internal clusters, Zubair Khan’s novel approach extends traditional logistic regression by partitioning datasets into subsets and constructing an ensemble of logistic models. This method enhances classification accuracy while maintaining interpretability, offering a robust and scalable solution validated through custom datasets.

Contactless Concentration Monitoring

Cybersecurity student Shiva Kumar Arugonda gave a presentation on "A Solution to Improve Cloud's Security Posture."

Kartik Warrier, an M.S. in Cybersecurity student, introduced a pioneering project, “Towards Contactless Human Concentration Monitoring Using mmWave Signals.” By utilizing Commercial-Off-The-Shelf (COTS) mmWave devices, Warrier’s system detects concentration-related activities, such as blinking and leg shaking, overcoming limitations of traditional monitoring methods. Enhanced by advanced beamforming and frequency analysis, the system achieved a 95.3% accuracy rate in diverse environments, surpassing the typical 85% to 90% accuracy of traditional monitoring methods. This breakthrough offers applications in education, workplace productivity and cognitive health monitoring.

Data Visualization for Network Security 

A team of cybersecurity students—Yasmin Fathima, Salman Sheikh, Gokul Raju and Ahasan Divyen—discussed their project, “DataViz Forensic Data Visualization Tool.” This innovative system captures live network traffic and analyzes anomalies in TCP and ICMP data, offering network administrators real-time insights through geolocation and graphical representations. Unlike traditional tools, this system emphasizes dynamic visualization and real-time anomaly detection, enabling more proactive and efficient network management, and empowers proactive network health and security management.

Conversational AI for Career Strategy 

Data analytics students, left to right, Vivek Chinta, Mohit Kosekar, Aradhana Panchal, Priyank Tailor, Anagh Sharma and Aravind Raju.

 

Anagh Sharma and Surya Suresh Sriraman, students in the M.S. in Data Analytics and Visualization, discussed “Conversational AI for the Shevet Glaubach Center for Career Strategy and Professional Development.” By leveraging a Retrieval-Augmented Generation (RAG) framework with OpenAI GPT, the chatbot automates responses to career-related inquiries. This solution not only reduces the workload of SGC staff but provides a 24/7 resource for students, utilizing advanced tools like LangChain and Hugging Face for robust and iterative development.

Reinventing Marketing Strategies with AI 

Artificial intelligence student Mohammad Zubair Khan also presented “Optimizing Customer Targeting Using Reinforcement Learning and Neural Networks for Adaptive Marketing Strategies.” By introducing a mean-stat strategy and neural network-based cross-entropy methods, Zubair Khan’s research offers a mathematically rigorous and adaptive approach to customer targeting, validated through extensive simulations.

Game Design and Probability Theory 

Zhengnan Li’s project, “A Flexible Generalized Probability Core and Quantitative Strategy Analysis for Game Design,” explored the application of probability theory to create dynamic and engaging game levels. By modifying parameters of a generalized probability model, Li’s framework provides game designers with tools to balance difficulty and complexity, enhancing player experience.

Data analytics studebt Shashidhar Vadla presented on “On the Road to a 360-degree Student View: Building a Cloud-Data Backed Dashboard for ’s Shevet Glaubach Center for Career Strategy and Professional Development.”

Strengthening Cloud Security 

Shiva Kumar Arugonda, a student in the M.S. in Cybersecurity, tackled cloud infrastructure vulnerabilities in his project, “A Solution to Improve Cloud Infrastructure’s Security Posture.” By mimicking real-world AWS environments and implementing best practices, this project enhances security, performance and cost optimization for cloud systems.

Innovations in Bayesian Optimization 

Siddhant Anand Jadhav, a student in the M.S. in Artificial Intelligence, makes a significant contribution to the field of Bayesian Optimization with his research on “New Approaches and Comprehensive Evaluations.” By curating a diverse suite of test functions that encompass a wide range of optimization challenges, Jadhav’s work enables comprehensive evaluations and comparisons. This diversity is significant as it ensures that new methodologies are tested against varied scenarios, setting a new benchmark for the field.

GPS-Based Attendance Systems 

Xiaohang Liu and Shikshit Gupta, students in the M.S. in Artificial Intelligence, introduced the “Smart GPS Attendance Application,” a system that integrates GPS verification and calendar functionalities to streamline attendance management for educational institutions. This solution ensures accuracy and efficiency, offering a secure, paperless alternative to traditional methods.

Enhancing Video Quality Assessment 

Artificial intelligence student Ruixin Chen discussed "Mutual Information Reduction Techniques and Its Applications in Feature Engineering."

Hang Yu and Ruiming Tian, students in the M.S. in Artificial Intelligence, presented “A Dual-Path Deep Learning Framework for Video Quality Assessment.” Utilizing advanced components like PatchEmbed3D and Cross Attention, their model achieves superior results in both objective metrics and perceptual quality, setting a benchmark for AI-driven video evaluation.

Tackling Ransomware Threats 

A cybersecurity team comprising Loveth Odozor, Lynda Omini, Chandani Navadiya and Yuval Nitzen developed a “Ransomware Operational Playbook.” This comprehensive guide serves as a critical tool for incident response and mitigation, validated through tabletop exercises.

Gesture Recognition with Wi-Fi Signals 

Kalyan Roy, Shilpa Kuppili, and Veerabhadra Rao Marellapudi, students in the M.S. in Artificial Intelligence, explored touchless interaction in their project, “ML Driven Gesture Recognition Using Wi-Fi RSSI Signals for Human-Computer Interaction.” By leveraging machine learning models, their system achieves promising accuracy in classifying gestures, paving the way for noninvasive and scalable interaction solutions.

Artificial intelligence student Mohammad Zubair Khan gave a presentation on "Dynamic Logistic Ensembles with Recursive Probability and Automatic Subset Splitting for Enhanced Binary Classification."

Enhancing LSTM Predictions 

Zhengnan Li, Juan Francisco Leonhardt Chavez and Shubham Pant, students in the M.S. in Data Analytics and Visualization, discussed “Enhancing LSTM Model Predictions for Ecological Data Through Data Shuffling.” Their findings underscore the importance of data preprocessing in improving predictive accuracy, particularly for ecological forecasting.

Personalized Fashion with AI 

Akarsha Hegde and Yudhishna Kuppala, students in the M.S. in Data Analytics and Visualization, presented “OutfitVision AI,” a platform that combines advanced AI models like CLIP and Vision Transformer to offer personalized fashion recommendations. By integrating user inputs with generative AI, this project represents a pioneering step in fashion technology.

Dr. David Li, program director of the M.S. in Data Analytics and Visualization, addresses the attendees of the research forum.

Blockchain for Digital Asset Management 

Cybersecurity students Altaf Ahmed and Neha Bodupally’s project, “Digital Asset Management with Blockchain Security,” utilizes Ethereum ERC721 tokenization to safeguard digital assets, ensuring integrity and privacy through blockchain’s immutable ledger. 

Rethinking Ranking Systems 

Data Analytics student Xinyan Cui’s paper, “When a Straight-A Student Isn’t the Best: Fuzzy Ranking and Optimization from a Probabilistic Perspective,” introduces a novel theory for probabilistic ranking. This framework offers a nuanced alternative to deterministic systems, enhancing transparency and decision-making.

Feature Engineering for Machine Learning

Artificial Intelligence student Ruixin Chen presented on “Mutual Information Reduction Techniques and Its Applications in Feature Engineering.” Feature engineering is a key part of building machine learning models, and involves picking and adjusting the most useful data features to improve accuracy. Traditional methods focus on choosing features that share the most information with the target outcome; however, this paper introduces a new approach that reduces overlapping information between features.

Secure Web Application for Sensitive Data 

Cybersecurity students Joy Awoleye, Elijah Laticbe and Christine Macharia discussed "Secure Web Application for Sensitive Data," which is designed to tackle the growing cybersecurity risks that organizations face when managing sensitive information like personal, financial or healthcare data. Many web applications lack strong security measures, leaving users and organizations vulnerable to data breaches, unauthorized access and cyberattacks. This project aims to build a secure web platform that protects sensitive data by using encryption, secure authentication and compliance with data protection standards. The goal is to ensure that sensitive information remains confidential, accurate and accessible only to authorized users. 

Share

FacebookTwitterLinkedInWhat's AppEmailPrint

Follow Us