Hello! Thanks for taking the time to view my page. I am a joint Ph.D. student at the University of California, Irvine, Department of Computer Science (Donald Bren School) and San Diego State University. Previously, I completed my M.S. at the University of Nevada, Reno, Department of Computer Science and Engineering. I worked as a software engineer at World Mobile Inc.. I was a Software Engineer Intern at Tesla Inc. I received my B.S. degree in the Department of Electrical and Computer Engineering, at the University of Tabriz, Iran. I am especially interested in LLMs, Anomaly and Fraud Detection, Natural language processing and Data mining, Query processing and optimization, Distributed systems and Federated Learning.
Doctor of Philosophy, Information and Computer Science
Advisor: Dr. Amir Rahmani
Doctor of Philosophy, Computational Science
Advisor: Dr. Hajar Homayouni
Master of Science, Computer Science and Engineering
Advisor: Dr. Javad Sattarvand
Bachelor of Science, Computer Engineering
See all publications and citation counts on my Google Scholar profile.
I developed a machine learning-based prediction model for COVID-19 using the Johns Hopkins University Center for Systems Science and Engineering dataset. Using Python and deep learning techniques such as RNN and LSTM, I built a prediction model that could forecast the number of COVID-19 cases, deaths, and recoveries for different regions around the world GitHub Link
Built a system that tracks tweets and replies of some specific accounts from a specific date onwards and extracts some information. I used REST APIs to provide information about the accounts, including the conversation threads, active audiences, and sentiment analysis
Executed end-to-end machine learning on the Telco Customer Churn dataset, involving data cleaning, visualization, and categorical-to-numeric transformation. Assessed six machine learning algorithms, optimizing the Gradient Boosting Classifier for an 80% accuracy, 6% higher than the baseline. Emphasized the iterative nature of the process, adapting to evolving problem dynamics.
Utilizing machine learning techniques and social network analysis to assess the credibility of media posts on social media platforms. Developed modules for text analysis, URL consistency checks, and network analysis, enhancing the system's ability to identify and mitigate the spread of misinformation.
Implemented Time Series Data analysis using recurrent neural networks (RNNs) in both PyTorch and TensorFlow frameworks. Explored patterns like seasonality and cycles present in time series data, vital in fields like finance, economics, and weather forecasting. Utilized TensorFlow's tf.keras.layers.RNN API, employing various RNN cell types (Basic RNN, LSTM, GRU) for sequential data analysis. Demonstrated stock price prediction using Google Colaboratory, showcasing real-time series data analysis.
Developed an AutoEncoder-based anomaly detection model for Google Ads time-series data, minimizing downtime. Established role-based alerts for on-call engineers to enhance response efficiency.
Developed and implemented a machine learning solution to detect and flag potential bot accounts on social media platforms, addressing deep class imbalance through oversampling and intelligent batching strategies, and evaluating model performance based on metrics such as accuracy, false positives, false negatives, and fairness across groups.
AI-powered autonomous robotics for pet waste collection, dehydration, and garden fertilizer production with real-time health analytics.
Multi-modal AI platform for predicting patient adherence and dropout risk in clinical trials.
Revolutionizing clinical trial adherence. Harnessing multimodal data analysis and explainable AI to predict participant dropout, reduce trial failure rates, and transform healthcare innovation.
Meal planning for neurodivergent individuals. Personalized meal plans that respect your food sensitivities and make your life healthier and easier.
