Pouya Shaeri

Pouya Shaeri

About Me

I'm a PhD student in Computer Science and a research associate at Arizona State University, where I have the privilege of being mentored by Dr. Ariane Middel. I'm also a member of the ShaDE Lab (led by Dr. Middel) and collaborate on research projects focused on climate modeling and urban climate data analysis.

I'm mainly interested in urban climate modeling, data mining, machine learning, and deep learning. Currently, my work revolves around climate modeling and urban climate data analysis.

I hold a master's degree in Computer Science - Data Mining from Shahid Beheshti University, where I was mentored by Dr. Ali Katanforoush, and a bachelor's degree in Mathematics and Applications from the University of Tehran. During my master's period, my research focused on fake news detection.

If you have any questions about my work, research, or anything related to academia or programming, please feel free to reach out!

Education

 
 
 
 
 
Arizona State University logo
PhD in Computer Science
Arizona State University
2023 - Present
  • Research Area: Climate Modeling and Urban Climate Data Analysis
    • Urban Climate Modeling
    • Data Mining
    • Machine Learning
    • Deep Learning
 
 
 
 
 
Shahid Beheshti University logo
MSc in Computer Science
Shahid Beheshti University
2021-2023
  • Major: Data Mining
    • Machine Learning
    • Data Mining
    • Reinforcement Learning
    • Neural Networks
 
 
 
University of Tehran logo
BSc in Mathematics and Applications
University of Tehran
2013–2020
  • Optimization: Linear and Non-Linear
  • Algebra and Linear Numeric Algebra

Projects

WebMRT: Online Tool for Urban Temperature Prediction
Developed a web application integrating machine learning predictive models and fisheye computer graphics visualization, allowing users to input environmental parameters and receive real-time predictions of Mean Radiant Temperature (MRT) in urban settings. Published in Sustainable Cities and Society.
WebMRT logo

OpenMRT: 3D Shadow Mapping and Temperature Rendering
Reimplemented OpenMRT, a simulation framework for 3D shadow mapping and temperature surface rendering, enabling precise radiation calculations based on longwave and shortwave radiation in urban environments.
OpenMRT logo

Semi-Supervised Fake News Detection
Developed a semi-supervised deep learning model using LSTM with self-attention and sentiment encoding for detecting fake news across social media platforms. Presented at ICCKE 2023.
Fake News Detection

LRQ-Fact: Multimodal Fact-Checking Framework
Contributed to the development of LRQ-Fact, a framework for multimodal fact-checking using LLMs and VLMs to generate questions and detect misinformation, achieving improved performance and model generalizability.
LRQ-Fact Project

Gaussian Naive Bayes with Feature Selection and PCA
Implemented Gaussian Naive Bayes from scratch with Forward and Backward Feature Selection, PCA, SVM, and Decision Trees. Tested on datasets: Mobile Prices and Heart Disease, Data Mining, Spring 2022.
Gaussian Naive Bayes Project

Time-Series Interpolation and Outlier Detection
Developed time-series interpolation using Polynomial and Spline techniques for Gregorian and Lunar-Hijri calendars. Built a Python Flask API for deployment and tested with JSON datasets. Data Mining, Spring 2022.
Time-Series Interpolation Project

Linear and Nonlinear Regression with Regularization
Implemented regression and classification models with regularization and hyperparameter tuning from scratch in Python. Tested on Computers and Heart Disease datasets and visualized results. Machine Learning, Fall 2021.
Regression Project

Naive Bayes Classifier with Data Preprocessing
Implemented a Naive Bayes Classifier, with advanced data preprocessing and sample generation from probability distributions. Tested on the Titanic dataset. Machine Learning, Sharif University, Fall 2021.
Titanic Project

Publications

A Semi-supervised Fake News Detection using Sentiment Encoding and LSTM with Self-Attention

IEEE Xplore: 27 November 2023, DOI
2023 13th International Conference on Computer and Knowledge Engineering (ICCKE)
Publication date: 2023/11/1, Pages: 590-595
PDF Scholar

WebMRT: An online tool to predict summertime mean radiant temperature using machine learning

Sustainable Cities and Society, DOI
Publication date: 2024
PDF Scholar
LRQ-Fact: LLM-Generated Relevant Questions for Multimodal Fact-Checking

Computation and Language (cs.CL), DOI
Submission date: 6 Oct 2024
PDF Scholar