ENT-Lab Group

Welcome to the Embedded and Networked Things (ENT-Lab) Group!

We aim to explore the cross-cutting research problems and gaps concerning the hardware and software for networked embedded systems with extreme resource and energy constraints. These systems will significantly impact how we live and work in the near future since there will be billions of interconnected devices. This situation will create a significant demand for more bandwidth, low-power operation, sustainability, confidentiality, security, dependability, and many more. We focus on designing systems by considering these requirements and working on the problems at the intersection of embedded systems, computer architectures, energy harvesting, the internet of things, low-power wireless protocols, sensor networks, distributed algorithms, operating systems/run-times, and machine learning.

Please contact Kasim Sinan Yildirim for thesis and collaboration opportunities.

ENT-Lab offers state-of-the-art microcontroller-based computing platforms, field-programmable gate arrays (FPGAs), sensors, wireless modules, energy harvesting kits, and measurement tools to create testbeds for experimental evaluations and demonstrate real-world applications.

A more focused vision of ENT-Lab is to build and deploy networked embedded devices that can harvest ambient energy, run forever without batteries and support a wide range of green applications from remote sensing to wearables. To achieve this, ENT-Lab explores (i) ultra-low-power computation techniques and software building blocks, (ii) communication protocols, and (iii) architectural support for energy harvesting devices.

Our current research activities include:

  • Software systems and programming support for intermittent computing
  • Architectural (hardware) support for intermittent computing
  • Batteryless and intermittent networking
  • Tiny machine learning on the batteryless edge.

Open Source Releases

Please check our open-source projects.

PhD Candidates

  • Khakim Akhunov, Systems Support for Multicore Intermittent Computing
  • Muath Abu Lebdeh (co-supervised with Davide Brunelli), Spiking Neural Networks
  • Hassan Mir (co-supervised with Giovanni Iacca), Federated Learning
  • Renan Beran Kilic (co-supervised with Giovanni Iacca), Tiny Machine Learning

Internship/Master’s Thesis

External Collaborators

Past Members

  • Eren Yıldız, PhD Thesis, Systems Support for Intermittent Computing
  • Çağlar Durmaz, PhD Thesis (co-supervisor - together with Ege-SERLab), A programming language and virtual machine for developing intermittently powered systems
  • Luca Caronti, MSc Thesis (co-supervised with Davide Brunelli), Adaptive Hardware Accelerated Intermittent Deep Neural Network Inference
  • Murat Mülayim, MSc Thesis, Fast and bug-free application development for intermittently-powered devices


Undergraduate Thesis
Model Compression for Tiny Machine Learning, Pietro Farina
Distributed Machine Learning Self-Learning Pipeline for Edge Sensing Applications, Daniele Stella
Design and Implementation of a Secure Firmware-Over-The-Air System using Bluetooth Low Energy, Francesco Olivieri
The Forward-Forward Algorithm for Memory-Constrained Devices in a federated context, Federico Rubbi (co-supervised with Giovanni Iacca)
Embedded Perceptual Image Hash Application of perceptual hash functions for detecting changes in a sequence of images, Roberto Lorenzon
Tiny Federated Learning on embedded systems, Alberto Gusmeroli
Architectural Assessment - Transfer of an Embedded SW Background Task into a new Architectural Concept, Damoano Bertolini
Neuromorphic Implementation of a Spiking Neural Network on FPGA, Roberto Giordano (co-supervised with Roberto Passarone)
A Comparative Study of K-nn Algorithms for Memory-Constrained Devices, Pietro Farina
Embedding Semi-Supervised Learning on Resource-Constrained platforms, Application of machine learning technique on energy harvesting devices, Mateo Myftaraj
Runtime Monitoring for Intermittent Computing, Lorenzo Antonio Riva (co-supervised with Ivan Kurtev and Arda Goknil)
Spiking Neural Networks on Apollo3 Blue Plus microcontroller, Alice Fasoli
Continual Learning on Max78000, Application of Online Learning technique, Giovanni Lunardi (co-supervised with Davide Brunelli)
Batteryless Sensor Tags for Augmented Reality Applications, Federico Carbone
A Tiny Network Stack for Battery-free Communication, Lorenzo Canciani (co-supervised with Davide Brunelli)
Enabling Pseudo-Stackful Intermittent Threads via Automatic Code Transformation, Lijun Chen
Intermittent Two-Dimensional Discrete Cosine Transform Core simulated implementation for FPGAs, Simone Ruffini (co-supervised with Davide Brunelli)