Low-Power and Low-Cost Implementation of SVMs for Smart Sensors

Boni, Andrea; Pianegiani, F.; Petri, Dario

doi:10.1109/tim.2006.887319

Cited by 34 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 2 ] for example, SVM is adopted in maintaining a near-optimal configuration of a MANET. Also, SVMs are used in the design and development of a low-cost and energy-efficient intelligent sensor [ 94 ]. SVMs are, however, computationally and memory intensive and thus require hardware acceleration units to be effectively executed in resource-limited situations.…”

Section: Embedded Machine Learning Techniquesmentioning

confidence: 99%

“…For inference, bit precision techniques, Logarithm number representations, quantization, etc., are some optimization techniques that may be applied to fit SVM models within resource-constrained environments. In [ 94 ], Boni et al develop a model selection technique targeted at reducing SVMs for resource-constrained environments. Table 7 presents a comprehensive list of SVM optimization schemes for both the training and classification phases.…”

Section: Embedded Machine Learning Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

Ajani

Imoize

Atayero

2021

Sensors

105

View full text Add to dashboard Cite

Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.

show abstract

Section: Embedded Machine Learning Techniquesmentioning

confidence: 99%

Section: Embedded Machine Learning Techniquesmentioning

confidence: 99%

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

Ajani

Imoize

Atayero

2021

Sensors

105

View full text Add to dashboard Cite

show abstract

“…For the nonlinear classification problem, the performance of the SVM is largely determined by the estimation model. It has been shown that the SVM method can be implemented on a microcontroller with a low clock speed and limited memory size [21,22]. But the selection of the proper estimation model is necessary and the options are limited by the available computing resource [21].…”

Section: Acceptance Rates Of Steel Ball Identificationmentioning

confidence: 99%

Classification of steel balls by resonant eddy-current sensor

Dao¹,

Jeng²,

Doan³

et al. 2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

The quality and work-life of ball bearings depending on the material properties of the steel ball, hence it is necessary to carefully classify their properties for bearings and related applications. Classification of steel balls based on the subtle difference in their electromagnetic properties is presented in this paper. The conductivity and magnetic susceptibility for the steel balls of the same kind are measured to investigate the correlation with eddy-current signals. The developed eddy-current sensor works at the resonant frequency of 117 kHz with an optimal readout resistance of 15 kΩ, which helps to boost the signal level without a high-gain preamplifier. To detect the eddy-current signal, the steel ball under test moves through the pickup coil, and the recorded data are used to build the voltage probability map for the classification of the steel ball properties. Experimental results show that the steel balls with and without the hardening process can be identified by the change in the amplitude and phase of the eddy current signal, which is consistent with the observed change in the electromagnetic properties of steel balls. The built system can be applied to the related industries to check the quality of steel balls before use.

show abstract

“…Existing ML solutions for microcontrollers typically use classical ML classifiers, such as RF, SVM, and Bayesian models [17][18][19][20].…”

Section: Related Workmentioning

confidence: 99%

Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition?

Elsts

McConville

2021

Electronics

View full text Add to dashboard Cite

The last decade has seen exponential growth in the field of deep learning with deep learning on microcontrollers a new frontier for this research area. This paper presents a case study about machine learning on microcontrollers, with a focus on human activity recognition using accelerometer data. We build machine learning classifiers suitable for execution on modern microcontrollers and evaluate their performance. Specifically, we compare Random Forests (RF), a classical machine learning technique, with Convolutional Neural Networks (CNN), in terms of classification accuracy and inference speed. The results show that RF classifiers achieve similar levels of classification accuracy while being several times faster than a small custom CNN model designed for the task. The RF and the custom CNN are also several orders of magnitude faster than state-of-the-art deep learning models. On the one hand, these findings confirm the feasibility of using deep learning on modern microcontrollers. On the other hand, they cast doubt on whether deep learning is the best approach for this application, especially if high inference speed and, thus, low energy consumption is the key objective.

show abstract

Low-Power and Low-Cost Implementation of SVMs for Smart Sensors

Cited by 34 publications

References 10 publications

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

Classification of steel balls by resonant eddy-current sensor

Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition?

Contact Info

Product

Resources

About