Lightweight Convolutional Neural Networks Framework for Really Small TinyML Devices

Estrebou, César Armando; Fleming, Martín; Saavedra, Marcos David; Adra, Federico; Giusti, Armando Eduardo De

doi:10.1007/978-3-030-99170-8_1

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their MCUs’ clock speed ranges from 8 MHz to about 500 MHz, while RAM ranges from 8 KB to 320 KB, and flash memory ranges from 32 KB to 2 MB. Overall, TinyML uses low-cost devices while it efficiently consumes power and achieves a high level of performance [ 17 ]. In terms of Software, TinyML has recently attracted the interest of industry giants.…”

Section: Tinyml Overviewmentioning

confidence: 99%

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

Alajlan

Ibrahim

2023

Sensors

View full text Add to dashboard Cite

Driver drowsiness is one of the main causes of traffic accidents today. In recent years, driver drowsiness detection has suffered from issues integrating deep learning (DL) with Internet-of-things (IoT) devices due to the limited resources of IoT devices, which pose a challenge to fulfilling DL models that demand large storage and computation. Thus, there are challenges to meeting the requirements of real-time driver drowsiness detection applications that need short latency and lightweight computation. To this end, we applied Tiny Machine Learning (TinyML) to a driver drowsiness detection case study. In this paper, we first present an overview of TinyML. After conducting some preliminary experiments, we proposed five lightweight DL models that can be deployed on a microcontroller. We applied three DL models: SqueezeNet, AlexNet, and CNN. In addition, we adopted two pretrained models (MobileNet-V2 and MobileNet-V3) to find the best model in terms of size and accuracy results. After that, we applied the optimization methods to DL models using quantization. Three quantization methods were applied: quantization-aware training (QAT), full-integer quantization (FIQ), and dynamic range quantization (DRQ). The obtained results in terms of the model size show that the CNN model achieved the smallest size of 0.05 MB using the DRQ method, followed by SqueezeNet, AlexNet MobileNet-V3, and MobileNet-V2, with 0.141 MB, 0.58 MB, 1.16 MB, and 1.55 MB, respectively. The result after applying the optimization method was 0.9964 accuracy using DRQ in the MobileNet-V2 model, which outperformed the other models, followed by the SqueezeNet and AlexNet models, with 0.9951 and 0.9924 accuracies, respectively, using DRQ.

show abstract

Section: Tinyml Overviewmentioning

confidence: 99%

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

Alajlan

Ibrahim

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…TensorFlow Lite Micro (TFLM) [9], Tensor [10], Edge ML [11], and Eloquent TinyML [12] are among the libraries and frameworks that facilitate the building of machine learning models on microcontrollers. TensorFlow Lite Micro and Eloquent TinyML are the only libraries claimed to be accessible as an Arduino library and in the Arduino IDE for programming Arduino and ESP32 microcontrollers [13]. For this paper, ESP32 microcontrollers are programmed with Arduino IDE; thus, research on TinyML implementations for ESP32 will rely on the TensorFlow Lite Micro and Eloquent TinyML libraries.…”

Section: Tinyml On Esp32mentioning

confidence: 99%

“…The possibility of implementing machine learning models on the ESP32 microcontroller by implementing the TFLM library is demonstrated by implementing an Artificial Neural Network (ANN) model to predict the specific volume of moulded product parts from pressure and temperature data from sensors [14]. Eloquent TinyML is an Arduino library that simplifies the deployment of TensorFlow Lite models on compatible microcontrollers [13,14]. As of current, no research has been found on the use of AI models with Eloquent TinyML on ESP32 microcontrollers in the real world.…”

Section: Tinyml On Esp32mentioning

confidence: 99%

“…As of current, no research has been found on the use of AI models with Eloquent TinyML on ESP32 microcontrollers in the real world. Nonetheless, a method of deploying a Convolutional Neural Network (CNN) model on a Tensilica Xtensa LX6 microprocessor [15] has shown the viability of utilising different kinds of AI models on the ESP32 microcontrollers board. Tensilica Xtensa LX6 is a microcontroller implemented for the ESP32 microcontroller board family [16].…”

Section: Tinyml On Esp32mentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Wind Speed Prediction using Artificial Neural Network and Multiple Linear Regression Model using Tinyml on Esp32

2023

ARFMTS

View full text Add to dashboard Cite

show abstract

TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review

Schizas

Karras

et al. 2022

Future Internet

View full text Add to dashboard Cite

The rapid emergence of low-power embedded devices and modern machine learning (ML) algorithms has created a new Internet of Things (IoT) era where lightweight ML frameworks such as TinyML have created new opportunities for ML algorithms running within edge devices. In particular, the TinyML framework in such devices aims to deliver reduced latency, efficient bandwidth consumption, improved data security, increased privacy, lower costs and overall network cost reduction in cloud environments. Its ability to enable IoT devices to work effectively without constant connectivity to cloud services, while nevertheless providing accurate ML services, offers a viable alternative for IoT applications seeking cost-effective solutions. TinyML intends to deliver on-premises analytics that bring significant value to IoT services, particularly in environments with limited connection. This review article defines TinyML, presents an overview of its benefits and uses and provides background information based on up-to-date literature. Then, we demonstrate the TensorFlow Lite framework which supports TinyML along with analytical steps for an ML model creation. In addition, we explore the integration of TinyML with network technologies such as 5G and LPWAN. Ultimately, we anticipate that this analysis will serve as an informational pillar for the IoT/Cloud research community and pave the way for future studies.

show abstract

Lightweight Convolutional Neural Networks Framework for Really Small TinyML Devices

Cited by 3 publications

References 6 publications

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

Analysis of Wind Speed Prediction using Artificial Neural Network and Multiple Linear Regression Model using Tinyml on Esp32

TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review

Contact Info

Product

Resources

About