Implementation of machine learning algorithm in embedded devices

Dudak, Juraj; Kebísek, Michal; Gašpar, Gabriel; Fabo, Peter

doi:10.1109/me49197.2020.9286705

Cited by 10 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the recent advances in microcontroller-related technologies, embedded Machine Learning has gained momentum and demonstrated its capabilities in different areas. For instance, Dudak et al [ 50 ] implemented a neural network model in an STM32L4x microcontroller for motion detection purposes, enabling it to recognize six basic movements in three axes. Healthcare has its fair share of embedded Machine Learning applications.…”

Section: Related Workmentioning

confidence: 99%

An Integrated Artificial Intelligence of Things Environment for River Flood Prevention

Boulouard

Ouaissa

et al. 2022

Sensors

View full text Add to dashboard Cite

River floods are listed among the natural disasters that can directly influence different aspects of life, ranging from human lives, to economy, infrastructure, agriculture, etc. Organizations are investing heavily in research to find more efficient approaches to prevent them. The Artificial Intelligence of Things (AIoT) is a recent concept that combines the best of both Artificial Intelligence and Internet of Things, and has already demonstrated its capabilities in different fields. In this paper, we introduce an AIoT architecture where river flood sensors, in each region, can transmit their data via the LoRaWAN to their closest local broadcast center. The latter will relay the collected data via 4G/5G to a centralized cloud server that will analyze the data, predict the status of the rivers countrywide using an efficient Artificial Intelligence approach, and thus, help prevent eventual floods. This approach has proven its efficiency at every level. On the one hand, the LoRaWAN-based communication between sensor nodes and broadcast centers has provided a lower energy consumption and a wider range. On the other hand, the Artificial Intelligence-based data analysis has provided better river flood predictions.

show abstract

Section: Related Workmentioning

confidence: 99%

An Integrated Artificial Intelligence of Things Environment for River Flood Prevention

Boulouard

Ouaissa

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Це в першу чергу пояснюється наявністю безкоштовних програмних платформ (фреймворків) з широким функціоналом для створення та навчання нейронних мереж. Прикладами таких платформ є Tensorflow [15] та Keras [16], які використовуються не тільки для розпізнавання мови, а й зображень та інформації з сенсорів [17,18].…”

Section: вступunclassified

Analysis of the Microcontroller Resources Using Specifics for Speech Recognition

Ryzhova

Onykiienko

2022

Microsyst., Electron. & Acoust.

View full text Add to dashboard Cite

The use of neural networks for information recognition, in particular, voice, expands the functional capabilities of embedded systems on microcontrollers. But it is necessary to take into account the limitations of the microcontroller resources. The purpose of the work is to analyze the impact of voice processing parameters and neural network architecture on the degree of microcontroller resources usage. To do this, a database of samples of the keyword, samples of other words and voices, and samples of noise are created, the probability of recognizing the keyword among other words and noises is evaluated, the dependence of the amount of memory used on the microcontroller and the decision-making time on the number MFC coefficients is established, the dependence of the amount of used memory of the microcontroller and the decision-making time on the type of convolutional neural network is established also. During the experiment, the Arduino Nano 33 BLE Sense development board was used. The neural network model was built and trained on the Edge Impulse software platform. To conduct the experiment, three groups of data with the names "hello", "unknown", "noise" were created. The group "hello" contains 94 examples of the word "hello" in English, spoken by a female voice. The "unknown" group contains 167 examples of other words pronounced by both female and male voices. The "noise" group contains 166 samples of noise and random sounds. According to Edge Impulse's recommendation, 80% of the samples from each of the data groups were used to train the neural network model, and 20% of the samples were used for testing. Analysis of the results shows that with an increase in the number of MFC coefficients and, accordingly, the accuracy of keyword recognition, the amount of program memory occupied by the code increases by 480 bytes (less than 1%). For the nRF52840 microcontroller, this is not a significant increase. The amount of RAM used during the experiment did not change. Although the calculation time of the accuracy of the code word definition increased by only 14 ms (less than 5%) with the increase in the number of MFC coefficients, the calculation procedure is quite long (approximately 0.3 s) compared to the sound sample length of 1 s. This can be a certain limitation when processing a sound signal with 32-bit microcontrollers. To analyze phrases or sentences, it is necessary to use more powerful microcontrollers or microprocessors. Based on the results of experimental research, it can be stated that the computing resources of 32-bit microcontrollers are quite sufficient for recognizing voice commands with the possibility of pre-digital processing of the sound signal, in particular, the use of low-frequency cepstral coefficients. The selection of the number of coefficients does not significantly affect the amount of used FLASH and RAM memory of the nRF52840 microcontroller. The comparison results show the superiority of the 2D network in the accuracy of the keyword definition for both 12 and 13 MFC coefficients. The use of a one-dimensional convolutional neural network for voice sample recognition in the conducted experiment provides memory savings of approximately 5%. The quality of keyword recognition with the number of MFC coefficients of 12 is approximately 0.7. For 17 MFC coefficients, the recognition quality is already 0.97. The amount of RAM used in the case of the 2D network has decreased slightly. Voice sample processing time for both types of networks is practically the same. Thus, 1D convolutional neural networks have certain advantages in microcontroller applications for voice processing and recognition. The limitation of voice recognition on the microcontroller is the sufficiently long processing time of the sound sample (approximately 0.3 s) with the duration of the sample itself being 1 s, this can be explained by a sufficiently low clock frequency of 64 MHz. Increasing the clock frequency will reduce the calculation time.

show abstract

“…Subsequently, test the system in different aspects, taking into account for use in physiotherapy, where it could find a wide application in thermo-diagnostics, either as a primary or complementary method. Based on the review of available technologies and our previous experience with 1-wire based solutions [18]- [21], we chose the contact method using DS18B20 [22] digital thermometers as a measurement technology. Such sensors have various uses in temperature measurements [23]- [25].…”

Section: Introductionmentioning

confidence: 99%