Flood Risk Analysis with Deep Learning
2024 IEEE 22nd International Symposium on Intelligent Systems and Informatics (SISY)
Sep 19, 2024DOI
Open to PhD & Research Collaboration
Pouria Maleki
AI Researcher · Electrical Engineer · Control Systems Specialist
Computer Vision & Object Detection · Reinforcement Learning · Intelligent Control · Edge AI
Top Technologist · Hamedan Province ×2Ranked 1st · M.S. Cohort 2018
Object Detection · Datasets
AI · Control
About
Engineer, researcher, and award-winning innovator
I am Pouria Maleki, an Electrical Engineer specializing in Control Systems from Hamedan, Iran. My work connects artificial intelligence, deep reinforcement learning and practical engineering challenges—from intelligent transportation to medical diagnostics.
I earned my M.S. from Bu-Ali Sina University with a 3.91/4 GPA and ranked first in my cohort. I also contributed to the development of an AI-assisted gastrointestinal lesion-detection prototype combining medical imaging, object detection and applied hardware development.
Alongside research and engineering, I teach electronics and embedded systems and enjoy turning complex concepts into practical, reproducible systems.
Biography, credentials & scholarly links5Published research works
2Public datasets
3.91/4M.S. GPA
8+Years teaching
Verified scholarly record
Publications & research citations
DOI-linked papers use verified bibliographic records checked against Crossref during build; their paper-level citation counts are refreshed by exact DOI from Semantic Scholar. Google Scholar remains the primary scholarly-profile link.
5published works
LiveDOI-linked citations
2public datasets
2021DQL M.S. thesis
Published works
Object Detection for Vehicles with Yolo
2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI)
Iranian Vehicle Images Dataset for Object Detection Algorithm
Journal of Artificial Intelligence and Data Mining (JAIDM), 12(1), 127–136
Sustainable Energy Management in Multi-Unite Cooling Systems With Fuzzy Logic and Adaptive Nonlinear Control
2023 9th International Conference on Control, Instrumentation and Automation (ICCIA)
2023DOI
Offline voice detection in smart homes
4th International Conference on Electrical Engineering, Computer, Mechanics and Artificial Intelligence
2023
Last metadata refresh: 2026-09-14
Research lineage
One research problem, multiple scientific outputs
My traffic research started with the M.S. thesis, the perception side evolved into two publications and public datasets, and the control side is now being extended into a new manuscript.
2021
M.S. thesis
Intelligent traffic-signal control with Deep Q-Learning
2024
Vehicle perception
Object detection for vehicles and emergency-vehicle classes
2024
Domain-specific data
Iranian vehicle dataset and object-detection evaluation
Now
Control-side extension
New Deep Q-Learning traffic-control manuscript being prepared for peer review
Core expertise
Capabilities demonstrated through real projects
Move across the cards: each capability reveals the tools and real projects where it has been applied.
01
Computer Vision & Object Detection
Perception systems built around real datasets and measurable evaluation
Object DetectionYOLO familyR-CNN familyOpenCVDataset DesignData Augmentation
Applied in
2 public vehicle datasets
Emergency-vehicle detection
Medical-image analysis
02
Machine Learning & Medical AI
From predictive modeling to AI-assisted diagnostic prototypes
Deep Neural NetworksCNNLSTMRandom ForestSVMModel Evaluation
Applied in
Gastrointestinal lesion-detection prototype
Flood-risk modeling
Predictive engineering systems
03
Reinforcement Learning & Decision Systems
Sequential decision-making for adaptive engineering control
Q-LearningDeep Q-Learning (DQL)Reward DesignSUMOSimulationTraffic Optimization
Applied in
M.S. thesis
Adaptive traffic-signal control
Dynamic optimization
04
Intelligent Control & Simulation
Nonlinear, fuzzy and model-based control for physical systems
MATLABSimulinkFuzzy LogicSliding ModeAdaptive ControlNonlinear Control
Applied in
Energy management
HVAC control
Renewable-energy integration
05
Embedded Systems & Edge AI
Hardware-aware prototypes where sensing, inference and control meet
C/C++STM32AVRRaspberry PiArduinoSensors & Actuators
Applied in
Offline smart-home voice control
Vehicle monitoring
Greenhouse monitoring
06
Industrial Automation & Electronics
Practical electronics, automation and engineering documentation
Siemens PLCSTEP 7PCB DesignAutoCAD ElectricalAltiumInstrumentation
Applied in
Electronics teaching
Industrial automation
Circuit & PCB design
Education & experience
Academic, teaching & professional journey
Teaching experience is calculated automatically from 2018, so the displayed duration stays current without yearly manual edits.
2021–Present
AI-Assisted Gastrointestinal Lesion Detection System
Knowledge-Based Company, Hamedan
AI algorithm development, medical-image labeling and prototype hardware development; implementation and integration details remain private to protect company IP.
2018–Present · 8+ years
Electronics Teacher
Ministry of Education, Hamedan
Teaching electricity and magnetism, circuits, PCB design, AutoCAD Electrical, AVR/ARM microcontrollers and automation-system installation.
2018–2021
M.S. Electrical Engineering · Control Systems
Bu-Ali Sina University
3.91/4 GPA and ranked first in cohort. Thesis on intelligent traffic-signal control with Deep Q-Learning, computer vision and SUMO simulation.
2012–2017
B.S. Electrical Engineering · Control Systems
Hamedan University of Technology
Thesis on energy-saving air-conditioning control with sliding-mode control and wind power.
Selected research
Research at the boundary of AI and engineering
AI-Assisted Gastrointestinal Lesion Detection System
An applied prototype for high-precision identification of polyps and suspicious gastrointestinal lesions in endoscopic imagery.
Explore case study
Intelligent Traffic Control with Deep Q-Learning
M.S. thesis research at Bu-Ali Sina University, linking vehicle perception with adaptive traffic-signal decisions in SUMO.
Explore case study
Object Detection & Vehicle Perception
Dataset engineering and object detection with the YOLO family, including dedicated emergency-vehicle classes for intelligent transportation.
Explore case study
Intelligent Energy Management
Fuzzy and adaptive nonlinear control for coordinating cooling loads with renewable energy.
Explore case studyOpen code & datasets
GitHub projects, automatically synced
Public research repositories are read at build time, so future GitHub projects can appear here without manually rewriting the portfolio.
Auto-synced from GitHub· 5 public repos
View all repositoriesIranian-Vehicle-images-dataset-for-detection
A public, domain-specific dataset of 3,000 Iranian vehicle images for YOLO-based object detection.
60updated Aug 2026
Research story & resultsTVD-dataset
A 29,759-image, seven-class vehicle benchmark with dedicated ambulance and fire-truck classes.
Jupyter Notebook10updated Sep 2025
Research story & resultsMulti-Agent-Traffic-Signal-Control
Public GitHub project
00updated Jul 2026
Latest articles
Research notes, papers & engineering insights
Research noteComputer Vision
202611 min read
Object Detection in Practice: YOLO, R-CNN and Better Dataset Design
A practical research note on choosing an object-detection approach from latency, localization, segmentation and dataset constraints—not from model-version numbers alone.
Choose an object-detection family from the deployment constraints, not from version numbers
Read articleManuscript in preparationReinforcement Learning
Current4 min read
Extending Intelligent Traffic Control with Deep Q-Learning — Work in Progress
A short update on the control-side continuation of my M.S. thesis, extending the Deep Q-Learning traffic-signal-control research before submission for peer review.
Read article
Research noteIntelligent Transportation
202610 min read
From Vehicle Detection to Smart Traffic Control: Perception, RL and Emergency Priority
A system-level view of how vehicle detection, traffic-state estimation and reinforcement learning can be connected into an adaptive intersection controller.
A smart intersection needs perception, state estimation, decision-making and control—not only a detector
Read articleAcademic references
Academic network & references
Dr. Amir Mosavi
Associate Professor
Óbuda University, Faculty of Informatics, Budapest, Hungary · TU Dresden, Faculty of Civil Engineering, Germany
amir.mosavi@kvk.uni-obuda.huDr. Hassan Khotanlou
Professor, Computer Engineering
Bu-Ali Sina University, Hamedan, Iran
khotanlou@basu.ac.irDr. Abbas Ramazani
Assistant Professor, Electrical Engineering
Bu-Ali Sina University, Hamedan, Iran
a.ramazani@basu.ac.irDr. Soheil Ganjefar
Professor, Electrical Engineering
Iran University of Science and Technology, Tehran, Iran
s_ganjefar@iust.ac.irLet’s connect
Let’s collaborate on research, PhD work and intelligent systems.
I am open to PhD opportunities, research collaborations and AI/control engineering projects.
Send email