Embedded intelligence on FPGA: Survey, applications and challenges

KP Seng, PJ Lee, LM Ang - Electronics, 2021 - mdpi.com
Embedded intelligence (EI) is an emerging research field and has the objective to
incorporate machine learning algorithms and intelligent decision-making capabilities into …

Design possibilities and challenges of DNN models: a review on the perspective of end devices

H Hussain, PS Tamizharasan, CS Rahul - Artificial Intelligence Review, 2022 - Springer
Abstract Deep Neural Network (DNN) models for both resource-rich environments and
resource-constrained devices have become abundant in recent years. As of now, the …

A full featured configurable accelerator for object detection with YOLO

D Pestana, PR Miranda, JD Lopes, RP Duarte… - IEEE …, 2021 - ieeexplore.ieee.org
Object detection and classification is an essential task of computer vision. A very efficient
algorithm for detection and classification is YOLO (You Look Only Once). We consider …

Artificial neural network-based DTC of an induction machine with experimental implementation on FPGA

S Gdaim, A Mtibaa, MF Mimouni - Engineering Applications of Artificial …, 2023 - Elsevier
Abstract Direct Torque Control (DTC) of Induction Machine (IM) has received increasing
attention due to its high performance and low dependence on machine parameters …

Optimising deep learning at the edge for accurate hourly air quality prediction

INK Wardana, JW Gardner, SA Fahmy - Sensors, 2021 - mdpi.com
Accurate air quality monitoring requires processing of multi-dimensional, multi-location
sensor data, which has previously been considered in centralised machine learning models …

Real-time multi-task ADAS implementation on reconfigurable heterogeneous MPSoC architecture

G Tatar, S Bayar - IEEE Access, 2023 - ieeexplore.ieee.org
The rapid adoption of Advanced Driver Assistance Systems (ADAS) in modern vehicles,
aiming to elevate driving safety and experience, necessitates the real-time processing of …

Configurable 2D-3D CNNs accelerator for FPGA-based hyperspectral imagery classification

W He, Y Yang, S Mei, J Hu, W Xu… - IEEE Journal of Selected …, 2023 - ieeexplore.ieee.org
Convolutional neural network (CNN) is used efficiently for the classification of hyperspectral
imagery (HSI). Both 3-D CNN and hybrid 2D–3D CNN have better performance due to the …

Electronic nose pattern recognition engine: Design, build, and deployment

F Sun, B Wu, J Yan, S Duan, X Hu - IEEE Sensors Journal, 2022 - ieeexplore.ieee.org
The electronic nose (e-nose) consists of a sensor array, a pattern recognition engine, and
peripheral circuitry, where the pattern recognition engine performs gas classification. The …

Smart embedded system for skin cancer classification

PF Durães, MP Véstias - Future Internet, 2023 - mdpi.com
The very good results achieved with recent algorithms for image classification based on
deep learning have enabled new applications in many domains. The medical field is one …

Efficient design of pruned convolutional neural networks on fpga

M Vestias - Journal of Signal Processing Systems, 2021 - Springer
Abstract Convolutional Neural Networks (CNNs) have improved several computer vision
applications, like object detection and classification, when compared to other machine …