A Minimally Invasive Low-Power Platform for Real-Time Brain Computer Interaction Based on Canonical Correlation Analysis

IEEE Trans. Parallel Distrib. Syst.

et al. 2022

Self Cite

Recent applications in low-power (1-20 mW) near-sensor computing require the adoption of floating-point arithmetic to reconcile high precision results with a wide dynamic range. In this paper, we propose a low-power multi-core computing cluster that leverages the fined-grained tunable principles of transprecision computing to provide support to near-sensor applications at a minimum power budget. Our solution -based on the open-source RISC-V architecture -combines parallelization and sub-word vectorization with a dedicated interconnect design capable of sharing floating-point units (FPUs) among the cores. On top of this architecture, we provide a full-fledged software stack support, including a parallel low-level runtime, a compilation toolchain, and a high-level programming model, with the aim to support the development of end-to-end applications. We performed an exhaustive exploration of the design space of the transprecision cluster on a cycle-accurate FPGA emulator, varying the number of cores and FPUs to maximize performance. Orthogonally, we performed a vertical exploration to identify the most efficient solutions in terms of non-functional requirements (operating frequency, power, and area). We conducted an experimental assessment on a set of benchmarks representative of the near-sensor processing domain, complementing the timing results with a post place-&-route analysis of the power consumption. A comparison with the state-of-the-art shows that our solution outperforms the competitors in energy efficiency, reaching a peak of 97 Gflop/s/W on single-precision scalars and 162 Gflop/s/W on half-precision vectors. Finally, a real-life use case demonstrates the effectiveness of our approach in fulfilling accuracy constraints.

Section: Case Study: Cca-based Brain-computer Interfacementioning

confidence: 99%

A Low-Power Transprecision Floating-Point Cluster for Efficient Near-Sensor Data Analytics

Montagna

Mach

IEEE Trans. Parallel Distrib. Syst.

et al. 2022

Self Cite

“…Custom active electrodes are used to make signal quality resilient to the higher contact impedance of dry electrodes with respect to wet electrodes with skin preparation. As single-ended amplification stages with gain higher than one limit the rejection of common mode noise [11], only signal buffering is performed on the active electrode by an Operational Amplifier (O.A.) connected as a unity-gain buffer.…”

Section: System Descriptionmentioning

confidence: 99%

Towards a Wearable Interface for Food Quality Grading Through ERP Analysis

Guermandi

2019 IEEE International Symposium on Circuits and Systems (ISCAS)

Brunelli

et al. 2019

Sensory evaluation is used to assess the consumer acceptance of foods or other consumer products, so as to improve industrial processes and marketing strategies. The procedures currently involved are time-consuming because they require a statistical approach from measurements and feedback reports from a wide set of evaluators under a well-established measurement setup. In this paper, we propose to collect directly the signal of the perceived quality of the food from Event-related potentials (ERPs) that are the outcome of the processing of visual stimuli. This permits to narrow the number of evaluators since errors related to psychological factors are by-passed. We present the design of a wearable system for ERP measurement and we present preliminary results on the use of ERP to give a quantitative measure to the appearance of a food product. The system is developed to be wearable and our experiments demonstrate that is possible to use it to identify and classify the grade of acceptance of the food.

“…On the algorithmic side, steady-state evoked potentials are traditionally computed from the power spectrum at the tag frequency, often normalized by the power spectrum at neighboring frequency bins [3,4,8]. Another up-and-coming technique, very successful in the field of SSVEP-based BCI systems, is Canonical Correlation Analysis (CCA) [14][15][16]. CCA presents appealing features for processing SSVEP signals: it potentially provides infinite frequency resolution; as an intrinsically multivariate analysis, it does not require an explicit channel selection strategy; it can correlate EEG with several harmonics (together with central frequency) while conveying the information in a single output.…”

Section: Introductionmentioning

confidence: 99%

Efficient Low-Frequency SSVEP Detection with Wearable EEG Using Normalized Canonical Correlation Analysis

Kartsch

Kumaravel

et al. 2022

Sensors

Self Cite

Recent studies show that the integrity of core perceptual and cognitive functions may be tested in a short time with Steady-State Visual Evoked Potentials (SSVEP) with low stimulation frequencies, between 1 and 10 Hz. Wearable EEG systems provide unique opportunities to test these brain functions on diverse populations in out-of-the-lab conditions. However, they also pose significant challenges as the number of EEG channels is typically limited, and the recording conditions might induce high noise levels, particularly for low frequencies. Here we tested the performance of Normalized Canonical Correlation Analysis (NCCA), a frequency-normalized version of CCA, to quantify SSVEP from wearable EEG data with stimulation frequencies ranging from 1 to 10 Hz. We validated NCCA on data collected with an 8-channel wearable wireless EEG system based on BioWolf, a compact, ultra-light, ultra-low-power recording platform. The results show that NCCA correctly and rapidly detects SSVEP at the stimulation frequency within a few cycles of stimulation, even at the lowest frequency (4 s recordings are sufficient for a stimulation frequency of 1 Hz), outperforming a state-of-the-art normalized power spectral measure. Importantly, no preliminary artifact correction or channel selection was required. Potential applications of these results to research and clinical studies are discussed.