Kian Farooghi

M.Sc. in Control Systems | Machine Learning Researcher

K.N Toosi - Tehran, Iran

4.0/4.0 Master's GPA
4 Publications in ML/Control
200+ Students Taught (RL & Control)
2 Years Industrial Experience

Education

M.Sc. in Electrical Engineering (Control)

GPA: 4.0/4.0 (18.68/20)
K. N. Toosi University of Technology, Tehran, Iran | Sep 2021 – 2023

Thesis: Forex Market Trading Strategy Based on Deep Reinforcement Learning

B.Sc. in Electrical Engineering (Control)

GPA: 3.4/4.0 (16.58/20)
University of Tabriz, Tabriz, Iran | Sep 2016 – Jul 2021

Publications

Research Interests

Reinforcement Learning Deep Learning System Identification Data-Driven Control Robotics

Determining the Most Lucrative Currency to Mine in Cryptocurrency Mining Farms

Kian Farooghi, Hamid Nemati, Hamid Khaloozadeh | Working Paper

Using heuristic optimization and deep learning for financial time series forecasting in cryptocurrency mining and blockchain applications.

Heuristic Optimization Deep Learning Financial Time Series Cryptocurrency Blockchain

Cooperative Multi-Agent Deep Reinforcement Learning for Forex Algorithmic Trading

Kian Farooghi, Hamid Khaloozadeh | International Conference on Computational Intelligence and Applications (ICCIA), 2024

Implementation of Proximal Policy Optimization for multi-agent systems in algorithmic trading.

Deep Reinforcement Learning Multi-Agent Systems PPO Algorithmic Trading Forex

Deep Learning for Bitcoin Price Prediction: The Power of Transformers and Time2Vec

Reza Lak, Kian Farooghi, Hamid Khaloozadeh | First International Conference on Computer, Electricity, Mechanics and Engineering Sciences

Leveraging transformer architectures and Time2Vec for cryptocurrency price prediction.

Transformers Attention Time2Vec Bitcoin

Tabular Dyna-Q Algorithm for Online Calculation of LQR Gains

Kian Farooghi, Mahdieh Samadi, Hamid Khaloozadeh | International Conference on Electrical Engineering and Technology (ICEET), 2023

A simulation study on reinforcement learning approaches for optimal control and data-driven control systems.

Reinforcement Learning Dyna-Q Q-Learning Optimal Control LQR

Research Experience & Academic Projects

Master's Thesis Research

K.N. Toosi University of Technology | 2021 - 2023

Forex Market Trading Strategy Based on Deep Reinforcement Learning

Developed and implemented novel deep reinforcement learning algorithms for algorithmic trading in foreign exchange markets. Led to multiple publications and demonstrated practical applications of RL in financial systems.

Deep RL Multi-Agent Systems Financial Markets Algorithm Development

Heliostat Position Control in Solar Power Plant using RL

View Project on GitHub
Spring 2024

Developed DQN agent to optimize heliostat positioning for maximizing power plant efficiency in real-time solar tracking applications.

DQN Energy Optimization Python

Deep RL Ping-Pong Player Agent

View Project on GitHub
Spring 2023

Trained an agent using PyTorch to play ping-pong using visual input from the playground, demonstrating computer vision integration with reinforcement learning.

PyTorch Visual RL Game AI

LQG Controller Design for Airplane System

Spring 2022

Implemented LQG controller using MATLAB and Simulink for Optimal Control course with Dr. Hamid Khaloozadeh.

Robust H∞ Control for Networked Systems

Fall 2021

Developed robust H∞ control strategy for Networked Control Systems (NCSs) with uncertainties in communication and system dynamics.

Professional Experience

Embedded & C# Software Engineer

Sedna Organization | Jun 2023 - Present
  • Designed and deployed comprehensive C# GUI for BLDC motor drive testing with integrated real-time data acquisition and analysis pipelines, adopted by 10+ engineers and technicians to accelerate and standardize experimental workflows
  • Implemented distributed control framework using socket programming with role-based remote access, enabling secure multi-client motor operation and monitoring across network
  • Refactored ARM Cortex-M4 (Artery F413) firmware architecture for sensorless BLDC motor drives, redesigning code structure to improve maintainability, modularity, and debugging efficiency
  • Optimized motor control algorithms and execution paths, achieving 33% faster response time and 11% reduction in execution time through systematic firmware performance tuning
  • Generalized firmware architecture across product line by replacing hard-coded configurations with dynamic Modbus-based parameter system, enabling real-time tuning of 50+ parameters including floating-point values
  • Developed microcontroller-based auto-tuning algorithm for PI controllers in BLDC motors, recognized by Iranian government as qualifying research project (equivalent to completing military service requirement)
  • View GUI Project on GitHub

Lead Software Engineer

Agrin Company | Jan 2025 - Mar 2025
  • Led team of 3 programmers to develop multi-camera surveillance platform for long-term timelapse monitoring of skyscraper construction projects
  • Designed and implemented real-time panoramic stitching algorithm, combining dual-row camera feeds into seamless wide-angle view for comprehensive site coverage
  • Developed robust TCP/IP streaming pipeline ensuring continuous transmission of stitched and raw frames to central servers with minimal latency
  • Coordinated integration of motorized camera modules, image processing, and UI control systems, employing Python for orchestration and C for performance-critical components

Teaching Experience

Head TA - Reinforcement Learning

80+ students
K.N.TU | Spring 2024 & 2023

Proposed homework questions and solved assigned problems in online class groups.

Head TA - Python Programming

45+ students
K.N.TU | Fall 2022

Graded homework and quizzes; recorded screen while coding example questions.

TA - Multivariable Control

45+ students
K.N.TU | Spring 2023

Designed and graded homework and quizzes.

TA - Game Theory

45+ students
K.N.TU | Fall 2022

Designed and graded homework assignments.

Instructor - C# Web Scraping

Online
Faradars Institute | Fall 2021

Recorded a full programming course and designed questions based on video concepts.

Technical Skills

Programming Languages:
Python, MATLAB, C (ARM/STM32), C# (.NET/WPF), Bascom, SQL, Arduino
ML/AI Frameworks:
PyTorch, Pandas, NumPy, Scikit-learn
Development Tools:
PyQt5, Selenium (C# and Python), BeautifulSoup, SQL Server Management Studio (SSMS), SQL Server, MySQL
Engineering Software:
MATLAB/Simulink, Proteus
Networking & Protocols:
Modbus, CAN, TCP/IP, UDP
Research Skills:
Deep RL (DQN, PPO, Dyna-Q), Multi-Agent Systems, System Identification, Optimal Control (LQR, LQG, H∞), Data-Driven Control
Core Competencies:
Reinforcement Learning, Deep Learning, Heuristic Optimization, Control Systems, Embedded Systems, Real-time Systems

Languages

  • English (TOEFL iBT: 109/120)
  • Kurdish (Native)
  • Persian (Bilingual)

Honors & Certifications

🏆 National Merit Recognition 2025

Microcontroller-based PI controller auto-tuning for next-generation water coolers developed for Sedna company. Approved as an alternative to compulsory military service by the Iranian government.

Certifications

  • SQL For Data Science
  • Supervised Machine Learning

References

Dr. Hamid Khaloozadeh

Department of Electrical Engineering

Khaje Nasir University of Technology

h_khaloozadeh@kntu.ac.ir

Hamid Nemati

Department of Computing Science

Umeå University

Researcher at WASP

hamid.nemati@umu.se

Dr. Amirhossain Nikoofard

Department of Electrical Engineering

Khaje Nasir University of Technology

a.nikoofard@kntu.ac.ir