Skip to main content

Research

Research Themes

Our current research focuses on machine learning, deep learning and data analytics to solve for any challenging science problems related to cybersecurity and social science. Particularly, we are interested in developing statistical feature modeling, big data processing, and learning-based detection system to understand, model and make sense of data generated from complex network-centric and socialtechnological systems with an emphasis on malware analysis, DNS privacy, social network analysis, marketing analytics, digital and web forensics. Below is a list of the MLDL lab projects. You can find the details of the selected projects in the Student Project page. 

  • Feature Analysis for Pet Scam Websites Clustering
  • Cryptocurrency Price Forecasting
  • Landmark Recognition for Android Application Using Deep Learning
  • Using Machine Learning for Predicting Customer Engagement on Social Media
  • Exploring Machine Learning Models for Telecom Customer Churn Prediction
  • MapReduce based string-matching algorithms for malicious domain detection
  • Emoji-Comment Relationship and User's Brand Engagement in Social Media
  • GPU-accelerated Malicious Domain Detection
  • Developing Web-based Predictive Application for Crowdfunding Campaigns
  • Efficient Clustering for User’s Brand Senti-ments Analysis on Online
  • MapReduce Design and Implementation of DNS Fingerprints for Transient User Identification
  • Efficient Clustering for User’s Brand Senti-ments Analysis on Online
  • Machine Learning-based Predictive Analytics of University Enrollment
  • Using Semi-Supervised Learning in Twitter for Labelling Cybersecurity-related Tweets 
  • EKUMiner: Machine Learning-based Predictive Analytics of University Enrollment
  • A Study of Chief Marketing Officer (CMO) Tenure with Competitive Sorting Model
Open /*deleted href=#openmobile*/