A novel framework for deployment of CNN models using post-training quantization on microcontroller

Sailesh, M; Karuppusamy, Selvakumar; Prasanth, Associate Professor Narayanan

doi:10.1016/j.micpro.2022.104634

Cited by 5 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mainstream microcontrollers are capable enough to perform machine learning classification [26] or even run deep neural network models; for example a Convolutional Neural Network (CNN) model trained with TensorFlow can be deployed on the Cortex-M4 microcontroller. Sailesh et al [27] provided a framework that automates code generation for a CNN model on a microcontroller. However, the limited memory on IoT devices restricts the utilization of CNNs in the IoT.…”

Section: Edge Computingmentioning

confidence: 99%

Design and Implementation of an Atrial Fibrillation Detection Algorithm on the ARM Cortex-M4 Microcontroller

Żyliński,

Nassibi,

Mandic

2023

Sensors

View full text Add to dashboard Cite

At present, a medium-level microcontroller is capable of performing edge computing and can handle the computation of neural network kernel functions. This makes it possible to implement a complete end-to-end solution incorporating signal acquisition, digital signal processing, and machine learning for the classification of cardiac arrhythmias on a small wearable device. In this work, we describe the design and implementation of several classifiers for atrial fibrillation detection on a general-purpose ARM Cortex-M4 microcontroller. We used the CMSIS-DSP library, which supports Naïve Bayes and Support Vector Machine classifiers, with different kernel functions. We also developed Python scripts to automatically transfer the Python model (trained in Scikit-learn) to the C environment. To train and evaluate the models, we used part of the data from the PhysioNet/Computing in Cardiology Challenge 2020 and performed simple classification of atrial fibrillation based on heart-rate irregularity. The performance of the classifiers was tested on a general-purpose ARM Cortex-M4 microcontroller (STM32WB55RG). Our study reveals that among the tested classifiers, the SVM classifier with RBF kernel function achieves the highest accuracy of 96.9%, sensitivity of 98.4%, and specificity of 95.8%. The execution time of this classifier was 720 μs per recording. We also discuss the advantages of moving computing tasks to edge devices, including increased power efficiency of the system, improved patient data privacy and security, and reduced overall system operation costs. In addition, we highlight a problem with false-positive detection and unclear significance of device-detected atrial fibrillation.

show abstract

Section: Edge Computingmentioning

confidence: 99%

Design and Implementation of an Atrial Fibrillation Detection Algorithm on the ARM Cortex-M4 Microcontroller

Żyliński,

Nassibi,

Mandic

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Early CNN models used 64/32-bit floating points. As researchers began to study accelerators rather than GPUs, floating points were converted to fixed points to reduce computational complexity [15]- [17], and interest in quantization technology that lowered precision increased [18][19][20]. Many CNN models showed that if the precision is lowered, the hardware complexity is significantly reduced, and the accuracy reduction is negligible or low [21], [22].…”

Section: Introductionmentioning

confidence: 99%

Variable Precision Multiplier for CNN Accelerators Based on Booth Algorithm

Guem,

Kim

2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

As the utilization of CNN increases, many studies on lightweight, such as pruning, quantization, and compression, have been conducted to use CNN models in servers and edge devices. Studies have revealed that quantization greatly reduces the complexity of CNN models while lowering accuracy to a negligible level. CNN models with bit precision lowered from the existing 64/32 floating point to 16, 8, and 4 fixed points are being announced. Therefore, this paper proposes a variable precision multiplier that can select between 16 bits and 8 bits of precision. It consists of four 8-bit booth multipliers. When 16-bit multiplication is selected, the final product is calculated from four partial products, and when 8-bit multiplication is selected, four multiplications are possible simultaneously. The proposed multiplier was designed with Verilog HDL, and its function was verified in ModelSim. And it was synthesized for Altera Cyclone III EP3C16F484C6 using Quartus II 13.1.0 Web Edition. The proposed variable multiplier has increased combinational logic compared to general 8-bit/16-bit booth multipliers, and the clock speed is reduced by 65% and 82%, respectively. However, it can process four 8-bit multiplications within 1.68 times of normal 8-bit multiplication processing time and can process 16-bit multiplication within 75% of the normal 16-bit multiplication processing time. Therefore, the proposed multiplier is expected to increase speed and energy efficiency by selecting bit precision according to the layer in the CNN model.

show abstract

Near‐Infrared InGaAs Intelligent Spectral Sensor by 3D Heterogeneous Hybrid Integration

Wang

Dong

Huang

et al. 2023

Advanced Photonics Research

View full text Add to dashboard Cite

The applications of near‐infrared spectroscopy (NIRS) are limited due to the bulky size, low integration, and poor intelligence in edge computing of traditional spectrometers. In this work, the authors develop an on‐chip InGaAs intelligent spectral sensor, which consists of a linear variable filter for wavelength selection, a linear focal plane array as detector and a chip processor for neural‐network inferring, based on an advanced 3D heterogeneous hybrid‐integration. More than 200 spectral channels with a spectral resolution of 1.25% central wavelength are acquired in a wide waveband from 900 to 1700 nm. Immediate results are provided onsite for users, especially applicable to nonspecialists, owing to the embedded algorithmic model in‐sensor. As a proof of applications, the authors experimentally detect adulterating green tea and achieve a real‐time identification with accuracy better than 90%. This spectral sensor with edge‐artificial‐intelligence breaks the dependence on external algorithms and paves the way for NIRS into miniaturization, integration, and intelligence, which brings more possibilities in incorporating with the consumer devices and the Internet of Things.

show abstract

A novel framework for deployment of CNN models using post-training quantization on microcontroller

Cited by 5 publications

References 5 publications

Design and Implementation of an Atrial Fibrillation Detection Algorithm on the ARM Cortex-M4 Microcontroller

Design and Implementation of an Atrial Fibrillation Detection Algorithm on the ARM Cortex-M4 Microcontroller

Variable Precision Multiplier for CNN Accelerators Based on Booth Algorithm

Near‐Infrared InGaAs Intelligent Spectral Sensor by 3D Heterogeneous Hybrid Integration

Contact Info

Product

Resources

About