An 8-channel scalable EEG acquisition SoC with fully integrated patient-specific seizure classification and recording processor

Yoo, Jerald; Yan, Lei; El-Damak, Dina; Altaf, Muhammad Awais Bin; Shoeb, Ali; Yoo, Hoi‐Jun; Chandrakasan, Anantha P.

doi:10.1109/isscc.2012.6177019

Cited by 53 publications

(36 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, all of these works make use of hardware accelerators and/or external computational devices to execute all of the processing chain using a reduced number of electrodes during the acquisition of the EEG signals. The work presented in [11] proposes an SoC for seizure detection based on an Analog Front-End (AFE) with eight channels for EEG acquisition and a digital accelerator for feature extraction and classification. This system acquires the EEG signals, extracts energy features from the eight channels and performs a linear SVM classification to detect the onset of an epileptic seizure.…”

Section: Related Workmentioning

confidence: 99%

“…The most common deeply-embedded systems for seizure detection are based on machine learning that can achieve high accuracy with a relatively small computational effort, for a limited number of electrodes. Most of these systems are based on fixed-functions ASIC designs, implementing feature extraction and pattern recognition algorithms for classification [11,12]. The main issue with machine learning approaches such as SVM is that the computational complexity significantly increases with the number of channels, making it challenging to implement these algorithms in deeply-embedded systems [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection

Montagna

Benatti

Rossi

2017

JLPEA

View full text Add to dashboard Cite

Ultra-low power operation and extreme energy efficiency are strong requirements for a number of high-growth application areas requiring near-sensor processing, including elaboration of biosignals. Parallel near-threshold computing is emerging as an approach to achieve significant improvements in energy efficiency while overcoming the performance degradation typical of low-voltage operations. In this paper, we demonstrate the capabilities of the PULP (Parallel Ultra-Low Power) platform on an algorithm for seizure detection, representative of a wide range of EEG signal processing applications. Starting from the 28-nm FD-SOI (Fully Depleted Silicon On Insulator) technology implementation of the third embodiment of the PULP architecture, we analyze the energy-efficient implementation of the seizure detection algorithm on PULP. The proposed parallel implementation exploits the dynamic voltage and frequency scaling capabilities, as well as the embedded power knobs of the PULP platform, reducing energy consumption for a seizure detection by up to 10× with respect to a sequential implementation at the nominal supply voltage and by 4.2× with respect to a sequential implementation with voltage scaling. Moreover, we analyze the trans-precision optimization of the algorithm on PULP, by means of a hybrid fixed-and floating-point implementation. This approach reduces the energy consumption by up to 43% with respect to the plain fixed-point and floating-point implementations, leveraging the requirements in terms of the precision of the kernels composing the processing chain to improve energy efficiency. Thanks to the proposed architecture and system-level approach for optimization, we demonstrate that PULP reduces energy consumption by up to 140× with respect to commercial low-power microcontrollers, being able to satisfy the real-time constraints typical of bio-medical applications, breaking the barrier of microwatts for a 50-ms complete seizure detection and a few milliwatts for a 5-ms detection latency on a fully-programmable architecture.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection

Montagna

Benatti

Rossi

2017

JLPEA

View full text Add to dashboard Cite

show abstract

“…Both physiological and pathological information could be obtained from EEG signal. The study of EEG signal has its applications in diagnosis and treatment of brain diseases, neuroscience, and cognitive science [2-3], Such as: psychogenic non-epileptic seizures [13,24] syncope, subcortical movement disorders, migraine variants, catatonia, adjunct test of brain death, etc. Saeid Sanei & J.A.Chamers, et al Cardiff University UK (2007) discussed that, EEGs cover up the way for diagnosis of many neurological disorders and other abnormalities in the human body.…”

Section: Electroencephalographicmentioning

confidence: 99%

Review on Latest Multichannel EEG Acquisition and Artifact Filtering Methods

Paradeshi¹,

Kolekar²

2016

IJCA

View full text Add to dashboard Cite

Electroencephalographic(EEG) signal records the electrical activity of the neurons near the scalp within the brain. Significant artifacts a r e introduced in the recording of EEG signals which leads to unreliable results. EEG paves the way for diagnosis of many neurological disorders and other abnormalities in the human body. The main aim of research is to get clean EEG signal with enhanced accuracy for proper diagnosis. Extensive

show abstract

“…Assuming the different noises sources during the amplification and conversion operations are not correlated, the equivalent input-referred power noise of the PG-ADC can be calculated by means of the following expression: (14) where both C C in and C A in are defined in Table I and correspond to the input capacitance C X in shown in Fig. 4.…”

Section: Noise Analysismentioning

confidence: 99%

A 515 nW, 0–18 dB Programmable Gain Analog-to-Digital Converter for In-Channel Neural Recording Interfaces

Rodríguez-Pérez

Delgado‐Restituto

Medeiro

2014

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

Abstract-This paper presents a low-area low-power SCbased Programmable-Gain Analog-to-Digital Converter (PG-ADC) suitable for in-channel neural recording applications. The PG-ADC uses a novel implementation of the binary search algorithm that is complemented with adaptive biasing techniques for power saving. It has been fabricated in a standard CMOS 130 nm technology and only occupies 0.0326 mm 2 . The PG-ADC has been optimized to operate under two different sampling modes, 27 kS/s and 90 kS/s. The former is tailored for raw data conversion of neural activity, whereas the latter is used for the onthe-fly feature extraction of neural spikes. Experimental results show that, under a voltage supply of 1.2 V, the PG-ADC obtains an ENOB of 7.56 bit (8-bit output) for both sampling modes, regardless of the gain setting. The amplification gain can be programmed from 0 to 18 dB. The power consumption of the PG-ADC at 90 kS/s is 1.52 µW with a FoM of 89.49 fJ/conv, whereas at 27 kS/s it consumes 515 nW and obtains a FoM of 98.31 fJ/conv.

show abstract

An 8-channel scalable EEG acquisition SoC with fully integrated patient-specific seizure classification and recording processor

Cited by 53 publications

References 4 publications

Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection

Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection

Review on Latest Multichannel EEG Acquisition and Artifact Filtering Methods

A 515 nW, 0–18 dB Programmable Gain Analog-to-Digital Converter for In-Channel Neural Recording Interfaces

Contact Info

Product

Resources

About