Embedded Files
Tiny Machine Learning (TinyML)
Tiny Machine Learning (TinyML)
Implementing TinyML hardware architectures for use in agriculture and medical applications
Investigating the hardware utilization and power consumption of TinyML models
Hardware implementation of TinyML models on extremely low-cost edge devices like microcontrollers
Designing and Implementing Hardware Primitives for Deep Learning Algorithms
Designing and Implementing Hardware Primitives for Deep Learning Algorithms
Implementation of a framework for generating ideal deep learning models based on hardware specific parameters
Implementing a library of hardware modules for common deep learning operations
Implementing custom hardware accelerators for deep learning models
Exploring Open-source RISC-V Toolchain for Generating Complete SoCs
Exploring Open-source RISC-V Toolchain for Generating Complete SoCs
Estimating resource consumption and performance of the various entities in the Chipyard framework
Optimizing, customizing, and extending models in the Chipyard framework to enable ease of use
FPGA implementation of various SoC modules generated with the Chipyard framework
Custom RISC-V processor design
Lightweight Cryptography Implementation on Low-cost Devices
Lightweight Cryptography Implementation on Low-cost Devices
Hardware implementation of lightweight encryption protocols
Hardware implementation of lightweight authentication protocols
Hardware implementation of key exchange protocols
Designing compact hardware architectures for standard cryptographic protocols
Implementation of lightweight cryptographic SoCs
Research Project Collaborators and Sponsors:
Ongoing Projects
Ongoing Projects
Sponsors: the Ministry of Environment, Science and Technology (MEST), Ghana, and the National Science and Technology Council (NSTC), Zambia, under the Zambia–Ghana Bilateral Joint Call for Collaborative Research Proposals in Emerging Technologies and Development, Space Science & Technology.
Collaborating Institutions: CSIR-Institute for Scientific and Technological Information (CSIR-INSTI), University of Zambia (UNZA), Bolgatanga Technical University (BTU), Golden Valley Agricultural Research Trust (GART), and National Remote Sensing Center (NRSC)
Period: Sept. 2025 - Aug. 2028
Completed Projects
Completed Projects
Project Title: Enabling Deep Learning Inference on Low-cost Edge Devices: A Case Study of Crop Pest and Disease Identification
Sponsors: UNESCO-TWAS program (Seed Grant for African Principal Investigators) financed by the German Federal Ministry of Education and Research (BMBF).
Period: Dec. 2022 - Dec. 2024
Project Title: Deep Learning Accelerators’ Configuration Space Exploration Effect on Performance and Resource Utilization: A Gemmini Case Study
Sponsors: This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean Government (MSIT) (no. 2022-0-00394, Development of AI semiconductor for level 4 self-driving based on functional safety)
Period: Dec. 2022 - Feb. 2023
Project Title: Deep Neural Network Dataset Collection for Optimal Positioning of a Capacitive Compensated Schiffman Phase Shifter
Sponsors: This work was financially supported by the Industrial Core Technology Development Program of MOTIE/KEIT (RS-2022-00144288, Development of DRAM Interface Semiconductor Integrated with Deep Learning Accelerator).
Period: Feb. 2023 - Aug. 2023
Repositories
Repositories
Title: Next-Gen tinyML Smart Weather Station Challenge 2024 by ITU
Overview: In the face of escalating climate challenges, precise weather monitoring is crucial for community resilience and adaptation. The "Next-Gen tinyML Smart Weather Station Challenge 2024" is a beacon for innovation in environmental monitoring. Team GenStorm has designed an intelligent model for classifying rainfall intensity using the Edge Impulse platform, deployed as an Arduino library. Our weather station also records pressure and temperature, optimized for power efficiency to ensure longevity and effectiveness.
Repository:
Page updated
Google Sites
Report abuse