Parallel architecture to accelerate superparamagnetic clustering algorithm

• Published in: Electronics letters Vol. 56; no. 14; pp. 701 - 704
• Main Authors: Wang, Pan Ke, Chen, Chang Hao, Pun, Sio Hang, Zhang, Baijun, Mak, Peng Un, Vai, Mang I, Lei, Tim C
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 09.07.2020
• Subjects: Circuits and systems; data density; digital electronic technology; hardware architecture; Markov process; Markov processes; medical computing; Monte Carlo methods; mutual interaction energy; neurophysiology; open‐source dataset; parallel algorithms; parallel architecture; parallel architectures; parallel superparamagnetic algorithm; pattern clustering; real‐time neural spike sorting; SPC algorithm; superparamagnetic clustering algorithm; Swendsen–Wang Monte Carlo approximation technique; unsupervised classification technique; Markov process; parallel algorithms; data density; parallel architectures; Swendsen–Wang Monte Carlo approximation technique; superparamagnetic clustering algorithm; mutual interaction energy; parallel architecture; parallel superparamagnetic algorithm; SPC algorithm; Monte Carlo methods; pattern clustering; open-source dataset; real-time neural spike sorting; digital electronic technology; Markov processes; hardware architecture; neurophysiology; medical computing; unsupervised classification technique
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2020.0760

Superparamagnetic clustering (SPC) is an unsupervised classification technique in which clusters are self-organised based on data density and mutual interaction energy. Traditional SPC algorithm uses the Swendsen–Wang Monte Carlo approximation technique to significantly reduce the search space for reasonable clustering. However, Swendsen–Wang approximation is a Markov process which limits the conventional superparamagnetic technique to process data clustering in a sequential manner. Here the authors propose a parallel approach to replace the conventional appropriation to allow the algorithm to perform clustering in parallel. One synthetic and one open-source dataset were used to validate the accuracy of this parallel approach in which comparable clustering results were obtained as compared to the conventional implementation. The parallel method has an increase of clustering speed at least 8.7 times over the conventional approach, and the larger the sample size, the more increase in speed was observed. This can be explained by the higher degree of parallelism utilised for the increased data points. In addition, a hardware architecture was proposed to implement the parallel superparamagnetic algorithm using digital electronic technologies suitable for rapid or real-time neural spike sorting.