iosr-JVSP   Volume-7 ~ Issue-2 ~ March-April 2017

ABSTRACT: In this paper we proposed a technique to remove eye blink artifact from electroencephalogram (EEG) using lifting wavelet transform (LWT). The LWT has been successfully used in eye blink artifact suppression form the recorded electroencephalography (EEG) signals using a data-adaptive subband filtering approach. The LWT is applied to decompose EEG signal into a finite set of subbands. The energy based subband filtering is implemented to separate the lower frequency noise components to clean the EEG signal. The energies of individual subbands respectively for EEG and fGn that of contaminated EEG are compared to derive the energy based threshold for the suppression............

Keywords: Electroencephalography, artifact reduction, stationary subspace analysis, lifting wavelet transform

[1] S. V. Ramanan, N. V. Kalpakam, J. S. Sahambi, "A novel wavelet based technique for detection and de-noising of ocular artifact in
normal and epileptic electroen-cephalogram", ICCCAS, pp. 180–183,27-29 June 2004.
[2] C. Joyce, I. Gorodnitsky, M. Kutas, "Automatic removal of eye movement and blink artifacts from EEG data using blind
component separation", Psychophysi-ology 41, 313–325, 2004.
[3] V. Krishnaveni, S. Jayaraman, S. Aravind, V. Hariharasudhan, K. Ramadoss, "Auto-matic identification and removal of ocular
artifacts from EEG using wavelet transform", Meas. Sci. Rev. 6 (4) ,45–57, 2006.
[4] Z. Wang, P. Xu, T. Liu, Y. Tian, X. Lei, D. Yao, "Robust removal of ocular arti-facts by combining independent component
analysis and system identification", Biomed. Signal Process. Control 10, 250–259, March, 2014.
[5] M. Garcia, M. Thomlinson, J. Lopez, B. Jervis, C. Mair, "Residual ocular arte-fact subsequent to ocular artefact removal from the
electroencephalogram", IEEProc. – Sci. Meas. Technol. 146, 293–298, November, 1999.

ABSTRACT: In complementary metal oxide semiconductor (CMOS) the power dissipation predominantly comprises of dynamic as well as static power. Prior to introduction of "Deep submicron technologies" it is observed that in case of technology process with feature size larger than 1micro meter, the consumption of dynamic power out of the overall power consumption of any circuit is more than 90%,while that of static power is negligible. But in the present deep submicron technologies in order to, reduce the dynamic power consumption in VLSI circuits, the power supply is being scaled down, keeping in view the principle that the dynamic power dissipated is directly proportional to the square of the supply voltage (Vdd).The threshold voltage also needs to be reduced since the supply voltage is scaled down...........

Keywords: Deep submicron, Low power, Sub-threshold leakage current, Power Gating, Threshold voltage , Transistor stacking.

[1]. H. J. M Veendrick, "Short circuit dissipation of static CMOS circuitry and its impact on the design of buffer circuits ," IEEE J. Solid-State Circuits, vol. SC-19, pp. 468–473, Aug. 1984.
[2]. R. X. Gu and M. I. Elmasry, "Power dissipation analysis and op-timization for deep submicronCMOSdigital circuits," IEEE J. Solid-State Circuits, vol. 31, pp. 707–713, May 1999.
[3]. Jun Cheol Park and Vincent J. Mooney III, Senior Member, IEEE Sleepy Stack Leakage Reduction," IEEE Transactions On Very Large Scale Integration (VLSI) Systems, vol. 14, no. 11, november 2006.
[4]. N. Hanchate and N.Ranganathan, "LECTOR: A Technique for Leakage Reduction in CMOS Circuits", IEEE Transactions on VLSI Systems, vol. 12, pp. 196-205, Feb., 2004
[5]. M. C. Johnson, D. Somasekhar, L. Y. Chiou, and K. Roy, "Leakage control with efficient use of transistor stacks in single threshold CMOS," IEEE Trans. VLSI Syst., vol. 10, pp. 1-5,Feb. 2002..

ABSTRACT: In this paper real time system identification is implemented on TMS320C6713 for speech signal using standard IEEE sentence (SP23) of NOIZEUS database with different types of real world noises at different level SNR taken from AURORA data base. The performance is measured in terms of signal to noise ratio (SNR) improvement. The implementation is done with "C' program for least mean square (LMS) and recursive least square (RLS) algorithms and processed using DSP processor with Code composer studio

Keywords: System Identification, LMS, RLS, SNR, TMS3206713

[1]. Simon Haykin " Adaptive Filter Theory" Fourth edition pearson education
[2]. V.Udayashankara " Modern digital signal processing" second edition PHI
[3]. Gaurav Saxena, SubramaniamGanesan, and Manohar Das "Real time implementation of adaptive noise cancellation" 978-1-4244-2030-8/08,2008 IEEE. PP431-436
[4]. Texas Instruments Tutorial, TMS320C6713 Hardware Designers Resource Guide",(July 2004), SPRAA33.
[5]. D. Reay, "Digital Signal Processing and Applications with the TMS320C6713 and TMS320C6416 DSK," John Wiley and Sons, Inc,Edition- 2nd 2008..

ABSTRACT: Activation functions are used to transform the mixed inputs into their corresponding output counterparts. Commonly, activation functions are used as transfer functions in engineering and research. Artificial neural networks (ANN) are the preferred choice for most studies and comparisons of activation functions. The Sigmoid Activation Function is the most common and its popularity arise from the fact that it is easy to derive, its boundedness within the unit interval, and it has mathematical properties that work well with the approximation theory. On the other hand, not so common is the Fibonacci Activation Function with similar and perhaps better features than.............

Keywords: Fibonacci Activation Function, Sigmoid Activation Function, Independent Component Analysis, Natural Gradient Algorithm.

[1]. B. Karlik and V. A. Olgac, "Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks," International Journal of Artificial Intelligence And Expert Systems (IJAE), vol. 1, no. 4, pp. 111-122, 2011.
[2]. B. DasGupta and G. Schnitger, "The Power of Approximating: A Comparison of Activation Functions," Advances in Neural Information Processing Systems, vol. 5, pp. 615-622, 1993.
[3]. N. Suttisinthong, B. Seewirote and A. Ngaopitakkul, "Selection of Proper Activation Functions in Back-propagation Neural Network algorithm for Single-Circuit Transmission Line," in Proceedings of the International MultiConference of Engineers and Computer Scientists, IMECS , Hong Kong, 2014.
[4]. L. Lei, W. Yu and W. Xing-Hui, "Natural gradient algorithm based on a class of activation functions and its applications in BSS," in Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, 2006.
[5]. J. P. Chibole, "Blind separation of two human speech signals using natural gradient algorithm by employing the assumptions of independent component analysis," in Proceedings of the 2014 International Annual Conference on Sustainable Research and Innovation, Nairobi, 2014.