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 …

Edge2train: A framework to train machine learning models (svms) on resource-constrained iot edge devices

B Sudharsan, JG Breslin, MI Ali - … of the 10th International Conference on …, 2020 - dl.acm.org
In recent years, ML (Machine Learning) models that have been trained in data centers can
often be deployed for use on edge devices. When the model deployed on these devices …

Train++: An incremental ml model training algorithm to create self-learning iot devices

B Sudharsan, P Yadav, JG Breslin… - 2021 IEEE SmartWorld …, 2021 - ieeexplore.ieee.org
The majority of Internet of Things (IoT) devices are tiny embedded systems with a micro-
controller unit (MCU) as its brain. The memory footprint (SRAM, Flash, and EEPROM) of …

Edge2guard: Botnet attacks detecting offline models for resource-constrained iot devices

B Sudharsan, D Sundaram, P Patel… - … and other Affiliated …, 2021 - ieeexplore.ieee.org
In today's IoT smart environments, dozens of MCU-based connected device types exist such
as HVAC controllers, smart meters, smoke detectors, etc. The security conditions for these …

RCE-NN: a five-stage pipeline to execute neural networks (cnns) on resource-constrained iot edge devices

B Sudharsan, JG Breslin, MI Ali - … of the 10th International Conference on …, 2020 - dl.acm.org
Microcontroller Units (MCUs) in edge devices are resource constrained due to their limited
memory footprint, fewer computation cores, and low clock speeds. These limitations …

Smart speaker design and implementation with biometric authentication and advanced voice interaction capability

B Sudharsan, P Corcoran, MI Ali - arxiv preprint arxiv:2207.10811, 2022 - arxiv.org
Advancements in semiconductor technology have reduced dimensions and cost while
improving the performance and capacity of chipsets. In addition, advancement in the AI …

An sram optimized approach for constant memory consumption and ultra-fast execution of ml classifiers on tinyml hardware

B Sudharsan, P Yadav, JG Breslin… - 2021 IEEE international …, 2021 - ieeexplore.ieee.org
With the introduction of ultra-low-power machine learning (TinyML), IoT devices are
becoming smarter as they are driven by Machine Learning (ML) models. However, any …

Enabling machine learning on the edge using sram conserving efficient neural networks execution approach

B Sudharsan, P Patel, JG Breslin, MI Ali - … 17, 2021, Proceedings, Part V 21, 2021 - Springer
Edge analytics refers to the application of data analytics and Machine Learning (ML)
algorithms on IoT devices. The concept of edge analytics is gaining popularity due to its …

A Comprehensive 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 …

Globe2train: A framework for distributed ml model training using iot devices across the globe

B Sudharsan, JG Breslin, MI Ali - 2021 IEEE SmartWorld …, 2021 - ieeexplore.ieee.org
Training a problem-solving Machine Learning (ML) model using large datasets is
computationally expensive and requires a scalable distributed training platform to complete …