A review of on-device machine learning for IoT: An energy perspective

N Tekin, A Aris, A Acar, S Uluagac, VC Gungor - Ad Hoc Networks, 2024 - Elsevier
Recently, there has been a substantial interest in on-device Machine Learning (ML) models
to provide intelligence for the Internet of Things (IoT) applications such as image …

When object detection meets knowledge distillation: A survey

Z Li, P Xu, X Chang, L Yang, Y Zhang… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Object detection (OD) is a crucial computer vision task that has seen the development of
many algorithms and models over the years. While the performance of current OD models …

A review of AI edge devices and lightweight CNN deployment

K Sun, X Wang, X Miao, Q Zhao - Neurocomputing, 2024 - Elsevier
Abstract Artificial Intelligence of Things (AIoT) which integrates artificial intelligence (AI) and
the Internet of Things (IoT), has attracted increasing attention recently. With the remarkable …

YOLIC: An efficient method for object localization and classification on edge devices

K Su, Y Tomioka, Q Zhao, Y Liu - Image and Vision Computing, 2024 - Elsevier
In the realm of Tiny AI, we introduce “You Only Look at Interested Cells”(YOLIC), an efficient
method for object localization and classification on edge devices. Through seamlessly …

A Review of AIoT-based Edge Devices and Lightweight Deployment

K Sun, X Wang, Q Zhao - Authorea Preprints, 2023 - techrxiv.org
Artificial Intelligence of Things (AIoT) which integrates artificial intelligence (AI) and the
Internet of Things (IoT), has attracted increasing attention recently. With the remarkable …

On-road obstacle detection in real time environment using an ensemble deep learning model

A Balasundaram, A Shaik, A Prasad… - Signal, Image and Video …, 2024 - Springer
Obstacle detection on road is a challenging task in autonomous vehicle driving. Although
obstacle detection is carried out with the help of sensors which are accurate and precise in …

CMNN: Coupled modular neural network

MI Chowdhury, Q Zhao, K Su, Y Liu - IEEE Access, 2021 - ieeexplore.ieee.org
In this paper, we propose a multi-branch neural network architecture named Coupled
Modular Neural Network (CMNN). A CMNN is a network consisting of β closely coupled sub …

You only look at interested cells: Real-time object detection based on cell-wise segmentation

K Su, H Wang, IMD Chowdhury, Q Zhao… - 2020 11th …, 2020 - ieeexplore.ieee.org
In this paper, we study real-time object detection based on cell-wise segmentation. Existing
object detection methods usually focus on detecting interesting object's positions and sizes …

Comparison between block-wise detection and a modular selective approach

H Wang, K Su, IMD Chowdhunry… - 2020 11th …, 2020 - ieeexplore.ieee.org
On-road risk detection and alert system is a crucial and important task in our day to day life.
Deep Learning approaches have got much attention in solving this noble task. In this paper …

[PDF][PDF] MS-NET: モジュールの系統的選択に基づく深層ニューラルネットワークの精度向上

チョウドリエムディインティサル - u-aizu.repo.nii.ac.jp
In order to introduce Deep Neural Network (DNN)[5] let us first consider the simplest form of
a DNN, ie a shallow neural network with a single hidden layer. Once we have a basic …