Portrait of Sajjad Baghaee

Sajjad Baghaee, Ph.D. Senior Researcher, METU PI, JeoIT · CTO, FreshData

Networks, sensing and intelligent systems.

Research and engineering across IoT and cyber-physical systems, wireless networks, learning-based control and smart infrastructure — from protocol design to devices running in the field.

Research areas Projects Publications Contact
METU ERC GO-SPACE SUIT Platform JeoIT FreshData Research areas ↓

Research & engineering areas

The research page
01

Communication & networking

16 recorded works2018–2026

Protocol and flow-control design for links that are slow, intermittent or shared — including age-aware transport, goal-oriented transmission and satellite IoT access.

Age of Information · flow control · FEC · satellite / NTN · LoRaWAN
02

IoT & cyber-physical systems

19 recorded works2018–2026

End-to-end IoT and cyber-physical systems: embedded nodes, LoRa and MQTT pipelines, smart-building semantics and digital twins that are deployed and measured.

embedded · LoRa / MQTT · digital twin · smart buildings
03

AI, learning & control

11 recorded works2018–2026

Reinforcement and meta-reinforcement learning for control, surrogate simulators for faster training, and edge inference placed where the decision is made.

RL · meta-RL · HVAC control · LSTM surrogates · edge AI
04

Smart infrastructure & energy

12 recorded works2012–2026

Monitoring for electricity distribution and other infrastructure, and the energy-harvesting and sensor-network work that keeps such devices running.

smart grid · fault detection · energy harvesting · WSN
05

Wireless sensing

7 recorded works2012–2026

Device-free sensing from wireless signals: Wi-Fi channel state information for activity recognition, and magnetic and capacitive sensing for detection and localization.

Wi-Fi CSI · activity recognition · magnetic sensing · localization

Current work

All projects
Fig. 01 · IAC 2026 Figure 1 from “Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning”: Earth–Relay–Moon–Mars network
Figure 1 reproduced from S. Baghaee et al., “Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning,” 77th International Astronautical Congress (IAC 2026), 2026. View paper.
Networking research

Deep-space and delay-tolerant flow control

Goal-oriented and reinforcement-learning-based flow control for links where feedback is slow, contact windows are scheduled and disruption is the normal case, in the ERC-funded GO-SPACE project at METU.

Latest output — Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning, accepted for IAC 2026.

Funder
European Research Council
Host
METU, Ankara
Role
Senior Researcher
Since
2023
GO-SPACE
Fig. 01 · SIU 2025 Figure 1 from “AoI-Driven IoT Fault Detection for Smart Grids”: AoI-driven IoT fault detection device on a transformer
Figure 1 reproduced from S. Baghaee et al., “AoI-Driven IoT Fault Detection for Smart Grids,” 2025 33rd Signal Processing and Communications Applications Conference (SIU), 2025. View paper.
Industry · smart infrastructure

Fault monitoring for electricity distribution

An IoT fault-indicator device for distribution grids — hardware, embedded software and adaptive communication — taken from design to pilot deployment in transformer substations, and extended with edge-AI fault detection in GridAI.

Role
CTO, FreshData
Sector
Electricity distribution
Since
2023
GridAI Smart infrastructure
Fig. 02 · MipMap Digital Twin 2025 Figure 2 from “MipMap Digital Twin: A Scalable IoT-Based Framework for Smart Cities and Circular Economy”: MipMap Digital Twin Platform: Merging the physical world, real-time data, and automation for smart environments
Figure 2 reproduced from S. Baghaee and Y. Eren, “MipMap Digital Twin: A Scalable IoT-Based Framework for Smart Cities and Circular Economy,” 2025 33rd Signal Processing and Communications Applications Conference (SIU), 2025. View paper.
IoT platforms · digital twins

Environmental sensing and digital twins

SensorBox, a low-power environmental sensing platform integrating heterogeneous sensors, LoRa, edge processing and MQTT pipelines, deployed at the AE+T Department of Delft University of Technology, with digital-twin work on the MipMap platform.

Programme
TÜBİTAK 1004, SUIT
Role
PI, Work Package P9
Since
2023
MipMap digital twin IoT & cyber-physical systems

Selected projects

The projects page

  • A³L-FEC — age-aware application-layer flow control

    An application-layer flow controller using forward error correction to hold peak age below a threshold. Doctoral dissertation, preprint and a patent application.

    Networking

  • Learning-based HVAC control

    Reinforcement and meta-reinforcement learning for building climate control, with an LSTM surrogate simulator to shorten training.

    AI & control

  • Wi-Fi CSI sensing and activity recognition

    A microsecond-synchronised CSI acquisition pipeline, a public dataset and a controlled deep-learning benchmark for device-free sensing.

    Wireless sensing

  • LoRa IoT deployments at JeoIT

    Landfill environmental monitoring, facility management and an IoT-enhanced load-cell system for manufacturing, built end to end.

    Applied engineering

  • E-CROPS — energy-harvesting communication networks

    Communication and scheduling policies for networks running on harvested energy, demonstrated on a vibration-powered sensor testbed.

    Energy & WSN

  • Magnetic wireless sensor networks

    Detection, tracking and identification of ferromagnetic targets on a magnetic sensor network testbed.

    Localization

One work from each area.

37Research outputs
26Conference papers
2012–2026Span

The complete record

Recent activity

All updates

  • Deep-space flow control accepted at IAC 2026

    “Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning” is scheduled for the 77th International Astronautical Congress in Antalya, 5–9 October 2026.

    View paper IAF record

    October 2026

  • GridAI presented at EdgeSys 2026

    Edge-AI smart-grid fault detection with goal-oriented communication, presented at the 9th International Workshop on Edge Systems, Analytics and Networking in Cambridge, UK.

    View paper

    June 2026

  • SensorBox deployed at TU Delft

    Low-power environmental sensing with LoRa, edge processing and MQTT pipelines, running at the Architectural Engineering and Technology Department for occupancy-aware analytics.

    SUIT platform

    Ongoing

Background

About

Research and engineering profile, current roles and academic trajectory.

Experience

Academic research, industry leadership, applied engineering and teaching, 2008 to now.

Education

Ph.D. and M.Sc. at METU, B.Sc. in electrical engineering, with supervisors and funding.

Technical profile

Networking, embedded and IoT, machine learning and control, simulation and wireless sensing.

Working on networked, sensed or instrumented systems?

I collaborate on communication protocols, IoT and cyber-physical systems, learning-based control and applied engineering.

Get in touch About