Embedded Machine Learning: Towards a Low-Cost Intelligent IoT edge

Shumba, Angela Tafadzwa; Montanaro, Teodoro; Sergi, Ilaria; Fachechi, Luca; Vittorio, Massimo De; Patrono, Luigi

doi:10.23919/splitech55088.2022.9854248

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deployed algorithm is composed of an encoder to compress an input sequence into a smaller dimension and a decoder that attempts to reconstruct the input sequence from the compressed data. For this work, we modified the algorithm we evaluated in [ 64 ] ( Figure 5 ) by defining and deploying the encoder and decoder as separate models, thus allowing us to access the encoder output in addition to the anomaly prediction during inference. In this way, the encoder output can be transmitted to an upper layer device containing a copy of the decoder to perform the reconstruction, resulting in a reduction in the amount of data to be transmitted by the sensor device over the implemented wireless communication channel.…”

Section: Discussionmentioning

confidence: 99%

“…We used the Google Colaboratory [ 66 ], an online notebook platform that allows browser execution of AI and ML algorithms, to design, validate, and test the algorithm. After training, validation, and testing in Google Colab, we converted the TensorFlow model into C byte arrays that we loaded onto a bare metal MCU to perform inference using the TensorFlow Lite for microcontrollers [ 56 ] and for an interpreter [ 64 ]. To verify the functionality, i.e., the reconstruction capability of the separated autoencoder, we developed the set-up illustrated in Figure 6 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging IoT-Aware Technologies and AI Techniques for Real-Time Critical Healthcare Applications

Shumba

Montanaro

Sergi

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Personalised healthcare has seen significant improvements due to the introduction of health monitoring technologies that allow wearable devices to unintrusively monitor physiological parameters such as heart health, blood pressure, sleep patterns, and blood glucose levels, among others. Additionally, utilising advanced sensing technologies based on flexible and innovative biocompatible materials in wearable devices allows high accuracy and precision measurement of biological signals. Furthermore, applying real-time Machine Learning algorithms to highly accurate physiological parameters allows precise identification of unusual patterns in the data to provide health event predictions and warnings for timely intervention. However, in the predominantly adopted architectures, health event predictions based on Machine Learning are typically obtained by leveraging Cloud infrastructures characterised by shortcomings such as delayed response times and privacy issues. Fortunately, recent works highlight that a new paradigm based on Edge Computing technologies and on-device Artificial Intelligence significantly improve the latency and privacy issues. Applying this new paradigm to personalised healthcare architectures can significantly improve their efficiency and efficacy. Therefore, this paper reviews existing IoT healthcare architectures that utilise wearable devices and subsequently presents a scalable and modular system architecture to leverage emerging technologies to solve identified shortcomings. The defined architecture includes ultrathin, skin-compatible, flexible, high precision piezoelectric sensors, low-cost communication technologies, on-device intelligence, Edge Intelligence, and Edge Computing technologies. To provide development guidelines and define a consistent reference architecture for improved scalable wearable IoT-based critical healthcare architectures, this manuscript outlines the essential functional and non-functional requirements based on deductions from existing architectures and emerging technology trends. The presented system architecture can be applied to many scenarios, including ambient assisted living, where continuous surveillance and issuance of timely warnings can afford independence to the elderly and chronically ill. We conclude that the distribution and modularity of architecture layers, local AI-based elaboration, and data packaging consistency are the more essential functional requirements for critical healthcare application use cases. We also identify fast response time, utility, comfort, and low cost as the essential non-functional requirements for the defined system architecture.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Leveraging IoT-Aware Technologies and AI Techniques for Real-Time Critical Healthcare Applications

Shumba

Montanaro

Sergi

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

On the Adoption of Modern Technologies to Fight the COVID-19 Pandemic: A Technical Synthesis of Latest Developments

Majeed

Zhang²

2023

COVID

View full text Add to dashboard Cite

In the ongoing COVID-19 pandemic, digital technologies have played a vital role to minimize the spread of COVID-19, and to control its pitfalls for the general public. Without such technologies, bringing the pandemic under control would have been tricky and slow. Consequently, exploration of pandemic status, and devising appropriate mitigation strategies would also be difficult. In this paper, we present a comprehensive analysis of community-beneficial digital technologies that were employed to fight the COVID-19 pandemic. Specifically, we demonstrate the practical applications of ten major digital technologies that have effectively served mankind in different ways during the pandemic crisis. We have chosen these technologies based on their technical significance and large-scale adoption in the COVID-19 arena. The selected technologies are the Internet of Things (IoT), artificial intelligence(AI), natural language processing(NLP), computer vision (CV), blockchain (BC), federated learning (FL), robotics, tiny machine learning (TinyML), edge computing (EC), and synthetic data (SD). For each technology, we demonstrate the working mechanism, technical applications in the context of COVID-19, and major challenges from the perspective of COVID-19. Our analysis can pave the way to understanding the roles of these digital COVID-19-fighting technologies that can be used to fight future infectious diseases to prevent global crises. Moreover, we discuss heterogeneous data that have significantly contributed to addressing multiple aspects of the ongoing pandemic when fed to the aforementioned technologies. To the best of the authors’ knowledge, this is a pioneering work on community-beneficial and transformative technologies in the context of COVID-19 with broader coverage of studies and applications.

show abstract

Embedded Machine Learning: Towards a Low-Cost Intelligent IoT edge

Cited by 2 publications

References 20 publications

Leveraging IoT-Aware Technologies and AI Techniques for Real-Time Critical Healthcare Applications

Leveraging IoT-Aware Technologies and AI Techniques for Real-Time Critical Healthcare Applications

On the Adoption of Modern Technologies to Fight the COVID-19 Pandemic: A Technical Synthesis of Latest Developments

Contact Info

Product

Resources

About