Massively-Parallel Bit-Serial Neural Networks for Fast Epilepsy Diagnosis: A Feasibility Study

There are about 1% of the world population suffering
from the hidden disability known as epilepsy and major developing
countries are not fully equipped to counter this problem. In order to
reduce the inconvenience and danger of epilepsy, different methods
have been researched by using a artificial neural network (ANN)
classification to distinguish epileptic waveforms from normal brain
waveforms. This paper outlines the aim of achieving massive
ANN parallelization through a dedicated hardware using bit-serial
processing. The design of this bit-serial Neural Processing Element
(NPE) is presented which implements the functionality of a complete
neuron using variable accuracy. The proposed design has been tested
taking into consideration non-idealities of a hardware ANN. The NPE
consists of a bit-serial multiplier which uses only 16 logic elements
on an Altera Cyclone IV FPGA and a bit-serial ALU as well as a
look-up table. Arrays of NPEs can be driven by a single controller
which executes the neural processing algorithm. In conclusion, the
proposed compact NPE design allows the construction of complex
hardware ANNs that can be implemented in a portable equipment
that suits the needs of a single epileptic patient in his or her daily
activities to predict the occurrences of impending tonic conic seizures.

Authors:

• Si Mon Kueh
• Tom J. Kazmierski

Keywords:

• Artificial Neural Networks
• bit-serial neural processor
• FPGA
• Neural Processing Element.

References:

[1] Y. Chen and W. du Plessis, “Neural network implementation on a fpga,”
in Africon Conference in Africa, 2002. IEEE AFRICON. 6th, vol. 1, Oct
2002, pp. 337–342 vol.1.
[2] Akin, M. and Arserim, M. A. and Kiymik, M.K. and Turkoglu, I., “A
new approach for diagnosing epilepsy by using wavelet transform and
neural networks,” in Engineering in Medicine and Biology Society, 2001.
Proceedings of the 23rd Annual International Conference of the IEEE,
vol. 2, 2001, pp. 1596–1599 vol.2.
[3] M. Freeman and J. Austin, “Designing a binary neural network
co-processor,” in Digital System Design, 2005. Proceedings. 8th
Euromicro Conference on, Aug 2005, pp. 223–226.
[4] D. Roy Chowdhury, I. Gupta, and P. Pal Chaudhuri, “A low-cost
high-capacity associative memory design using cellular automata,”
Computers, IEEE Transactions on, vol. 44, no. 10, pp. 1260–1264, Oct
1995.
[5] A. Shafer, L. Parker, and E. Swartzlander, “The fully-serial pipelined
multiplier,” in Signals, Systems and Computers (ASILOMAR), 2011
Conference Record of the Forty Fifth Asilomar Conference on, Nov 2011,
pp. 1817–1822.
[6] M. Saleheen, H. Alemzadeh, A. Cheriyan, Z. Kalbarczyk, and R. Iyer,
“An efficient embedded hardware for high accuracy detection of epileptic
seizures,” in Biomedical Engineering and Informatics (BMEI), 2010 3rd
International Conference on, vol. 5, Oct 2010, pp. 1889–1896.
[7] T. Matsumoto, Y. Shin, H. Takase, H. Kawanaka, and S. Tsuruoka,
“A learning method for extended spikeprop without redundant spikes
#x2014; automatic adjustment of hidden units,” in Soft Computing and
Intelligent Systems (SCIS), 2014 Joint 7th International Conference on
and Advanced Intelligent Systems (ISIS), 15th International Symposium
on, Dec 2014, pp. 1465–1469.
[8] H. Fang, Y. Wang, and J. He, “Spiking neural networks for cortical
neuronal spike train decoding,” Neural Computation, vol. 22, no. 4, pp.
1060–1085, April 2010.
[9] Izhikevich, E.M., “Simple model of spiking neurons,” Neural Networks,
IEEE Transactions on, vol. 14, no. 6, pp. 1569–1572, Nov 2003.
[10] Cheng-Wen Ko, Hsiao-Wen Chung , “Automatic spike detection via an
artificial neural network using raw EEG data: effects of data preparation
and implications in the limitations of online recognition,” Clinical
Neurophysiology - 1, vol. 111, no. 3, pp. 477–481, March 2000.
[11] J. Ko, C. Lu, M. Srivastava, J. Stankovic, A. Terzis, and M. Welsh,
“Wireless sensor networks for healthcare,” Proceedings of the IEEE,
vol. 98, no. 11, pp. 1947–1960, Nov 2010.
[12] B. Svensson and T. Nordstrom, “Execution of neural network algorithms
on an array of bit-serial processors,” in Pattern Recognition, 1990.
Proceedings., 10th International Conference on, vol. ii, June 1990, pp.
501–505 vol.2.
[13] T. J. Kazmierski and C. Leech, “Synthesis of application specific
processor architectures for ultra-low energy consumption,” in Small
Systems Simulation Symposium, February 2014. (Online). Available:
http://eprints.soton.ac.uk/366668/