No abstract

Extracting information from brain signals in advanced Brain Machine Interfaces (BMI) often requires computationally demanding processing. The complexity of the algorithms traditionally employed to process multi-channel neural data, such as Principal Component Analysis (PCA), dramatically increases while scaling-up the number of channels and requires more power-hungry computational platforms. This could hinder the development of low-cost and low-power interfaces which can be used in wearable or implantable real-time systems. This work proposes a new algorithm for the detection of epileptic seizure based on compressively sensed EEG information, and its optimization on a low-power multi-core SoC for near-sensor data analytics: Mr. Wolf. With respect to traditional algorithms based on PCA, the proposed approach reduces the computational complexity by 4.4x in ARM Cortex M4-based MCU. Implementing this algorithm on Mr.Wolf platform allows to detect a seizure with 1 ms of latency after acquiring the EEG data for 1 s, within an energy budget of 18.4 µJ. A comparison with the same algorithm on a commercial MCU shows an improvement of 6.9x in performance and up to 18.4x in terms of energy efficiency.

No abstract

No abstract

This paper presents a real-time, completely automated and patient independent algorithm for detection of absence seizures in WAG/Rij rats as a valid animal model of human absence epilepsy. Single-channel EEG recordings containing totally 488 seizures from 8 WAG/Rij rats were analyzed using the real-time SWD detection algorithm. The proposed algorithms based on the variation of wavelet power to the background power in two specific frequency bands whose spectral power are highly correlated with SWDs. The wavelet powers of two specific frequency bands are calculated with a pattern-adapted mother wavelet and compared with an adaptive ratio of background power of each frequency band. The results indicate used algorithm is able to detect the whole 488 seizures within less than 1 s with sensitivity of 100%. The average precision for 1200, 1400 and 1600 point of window size was 95.2%, 98.3% and 99.17%, respectively. The present algorithm, with its high sensitivity and specificity, could be used for further studies of absence seizures in humans and rats and could be implemented as real-time system for closed loop deep brain stimulation systems.