An Efficient On-Demand Hardware Replacement Platform for Metamorphic Functional Processing in Edge-Centric IoT Applications

Moon, Hyeongyun; Park, Daejin

doi:10.3390/electronics10172088

Cited by 3 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted research on the real-time hardware reconfiguration of edge devices [18,19]. This real-time hardware reconfiguration research showed that the execution flow of an application can be predicted and that the hardware to be executed next to the edge device can be reconfigured in advance [20,21]. This process changes the service in real time by partially modifying the firmware of the edge device [22,23].…”

Section: Related Workmentioning

confidence: 99%

On-Cloud Linking Approach Using a Linkable Glue Layer for Metamorphic Edge Devices

Lee,

Park

2023

Electronics

Self Cite

View full text Add to dashboard Cite

As sensors operating at the edge continue to evolve, the amount of data that edge devices need to process is increasing. Cloud computing methods have been proposed to process complex data on edge devices that are powered by limited resources. However, the existing cloud computing approach, which provides services from servers determined at the compile stage on the edge, is not suitable for the metamorphic edge device proposed in this paper. Therefore, we have realized the operation of metamorphic edge devices by changing the service that accelerates the application in real time according to the surrounding environmental conditions on the edge device. The on-cloud linking approach separates the code for communication from the edge and server into a linkable glue layer. The separated communication code in the linkable glue layer is reconfigured in real time according to the environment of the edge device. To verify the computational acceleration of cloud computing and the real-time service change of the metamorphic edge device, we operated services that perform matrix multiplication operations with one process, two processes, and four processes in parallel on the edge–cloud system based on the on-cloud linking approach. Through the experiments, it was confirmed that the on-cloud linking approach changes the service provided in real time according to changes in external environmental data without changing the code built into the edge. When a square matrix operation with 1000 rows was loaded onto the proposed platform, the size of the code embedded into the edge device decreased by 8.88% and the operation time decreased by 96.7%.

show abstract

Section: Related Workmentioning

confidence: 99%

On-Cloud Linking Approach Using a Linkable Glue Layer for Metamorphic Edge Devices

Lee,

Park

2023

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The smart home is equipped with event-driven IoT sensors which are directly connected to the main edge device. The main edge device is loaded with a pre-trained model used for human activity classification and is connected to a high-performance server [32]. Step 2…”

Section: Smart Home Modelmentioning

confidence: 99%

Low-Power On-Chip Implementation of Enhanced SVM Algorithm for Sensors Fusion-Based Activity Classification in Lightweighted Edge Devices

2022

Self Cite

View full text Add to dashboard Cite

Smart homes assist users by providing convenient services from activity classification with the help of machine learning (ML) technology. However, most of the conventional high-performance ML algorithms require relatively high power consumption and memory usage due to their complex structure. Moreover, previous studies on lightweight ML/DL models for human activity classification still require relatively high resources for extremely resource-limited embedded systems; thus, they are inapplicable for smart homes’ embedded system environments. Therefore, in this study, we propose a low-power, memory-efficient, high-speed ML algorithm for smart home activity data classification suitable for an extremely resource-constrained environment. We propose a method for comprehending smart home activity data as image data, hence using the MNIST dataset as a substitute for real-world activity data. The proposed ML algorithm consists of three parts: data preprocessing, training, and classification. In data preprocessing, training data of the same label are grouped into further detailed clusters. The training process generates hyperplanes by accumulating and thresholding from each cluster of preprocessed data. Finally, the classification process classifies input data by calculating the similarity between the input data and each hyperplane using the bitwise-operation-based error function. We verified our algorithm on `Raspberry Pi 3’ and `STM32 Discovery board’ embedded systems by loading trained hyperplanes and performing classification on 1000 training data. Compared to a linear support vector machine implemented from Tensorflow Lite, the proposed algorithm improved memory usage to 15.41%, power consumption to 41.7%, performance up to 50.4%, and power per accuracy to 39.2%. Moreover, compared to a convolutional neural network model, the proposed model improved memory usage to 15.41%, power consumption to 61.17%, performance to 57.6%, and power per accuracy to 55.4%.

show abstract

“…In our previous work, we proposed a prototype of a partial firmware replacement for a run-time network model [21][22][23][24][25]. This technique involves selecting a model corresponding to the input data domain from a memory-limited device.…”

Section: Related Workmentioning

confidence: 99%

Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices

Kwon

Park

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

On-device artificial intelligence has attracted attention globally, and attempts to combine the internet of things and TinyML (machine learning) applications are increasing. Although most edge devices have limited resources, time and energy costs are important when running TinyML applications. In this paper, we propose a structure in which the part that preprocesses externally input data in the TinyML application is distributed to the hardware. These processes are performed using software in the microcontroller unit of an edge device. Furthermore, resistor–transistor logic, which perform not only windowing using the Hann function, but also acquire audio raw data, is added to the inter-integrated circuit sound module that collects audio data in the voice-recognition application. As a result of the experiment, the windowing function was excluded from the TinyML application of the embedded board. When the length of the hardware-implemented Hann window is 80 and the quantization degree is 2−5, the exclusion causes a decrease in the execution time of the front-end function and energy consumption by 8.06% and 3.27%, respectively.

show abstract

An Efficient On-Demand Hardware Replacement Platform for Metamorphic Functional Processing in Edge-Centric IoT Applications

Cited by 3 publications

References 44 publications

On-Cloud Linking Approach Using a Linkable Glue Layer for Metamorphic Edge Devices

On-Cloud Linking Approach Using a Linkable Glue Layer for Metamorphic Edge Devices

Low-Power On-Chip Implementation of Enhanced SVM Algorithm for Sensors Fusion-Based Activity Classification in Lightweighted Edge Devices

Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices

Contact Info

Product

Resources

About