Yapay Sinir Ağları Yöntemi ile İkinci Kuşak Akım Taşıyıcının Performans Parametrelerinin Tahmin Edilmesi

Year 2019, Volume: 1 Issue: 1, 13 - 23, 31.10.2019

Abdullah Yeşil , Ufuk Çelik , Feyzullah Temurtaş

https://doi.org/10.46387/bjesr.632631

Cited By: 1

Abstract

Bu çalışmada ikinci kuşak akım taşıyıcı (CCII) için yapay sinir
ağları ile performans parametreleri tahmin edilmiştir. Öncelikle seçilen
CCII’nin CMOS gerçeklemesindeki transistörlerin kanal boyu ve genişliği ile
kutuplama akımı sistematik olarak LTSPICE benzetim programında taratılmıştır.
Ardından CCII’nin CMOS gerçeklemesi göz önünde bulundurularak benzetim programı
aracılığıyla dört adet performans parametresi elde edilmiştir. Performans
parametrelerinin eğitimi ve tahminlemesi için yapay sinir ağları yöntemi
kullanılmıştır. Beyin sinir sisteminin bir simülasyonu olan yapay sinir ağları
(YSA) büyük verilerin işlenmesinde kullanılan algoritmalardan birisidir. Yapay
sinir ağları gerçekleştirilen tahminleme analiz sonuçlarına göre 24300 veride 19440
eğitim ile 4860 adet test verisi için ortalama mutlak yüzde hatası (MAPE) %7.33
olarak bulunmuştur.

Keywords

Aktif elemanlar, Yapay Sinir Ağları

Supporting Institution

Bandırma Onyedi Eylül Üniversitesi

Project Number

BAP-18-DF-1003-004

Thanks

Bu çalışma Bandırma Onyedi Eylül Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi tarafından desteklenmiştir. Proje Numarası: BAP-18-DF-1003-004.

Performance Parameters Estimation of Second Generation Current Conveyor with Artificial Neural Networks

Abstract

In this study, performance parameters were
estimated with artificial neural networks for the second generation current
conveyor (CCII). First, the channel length and width of the transistors in the
CMOS implementation of the selected CCII and the biasing current were
systematically scanned in the LTSPICE simulation program. Then, considering the
CMOS implementation of CCII, four performance parameters were obtained through
the simulation program. Artificial neural network method was used for training
and estimation of performance parameters. Artificial neural networks (ANNs),
which is a simulation of the brain nervous system, are one of the algorithms
used in the processing of big data. According to the estimation analysis
results of artificial neural networks, mean absolute percentage error (MAPE)
for 4860 test and 19440 training in 24300 data was found to be 7.33%.

Keywords

Active elements, Artificial Neural networks

Project Number

BAP-18-DF-1003-004

References

• [1] K. C. Smith and A. Sedra, “CC The current conveyor; A new circuit building block,” Proc. IEEE, vol. 56, no. 8, pp. 1368–1369, 1968.
• [2] A. Sedra and K. Smith, “A second-generation current conveyor and its applications,” IEEE Trans. Circuit Theory, vol. 17, no. 1, pp. 132–134, Feb. 1970.
• [3] A. Fabre, O. Saaid, F. Wiest, and C. Boucheron, “High frequency applications based on a new current controlled conveyor,” IEEE Trans. Circuits Syst. I Fundam. Theory Appl., vol. 43, no. 2, pp. 82–91, 1996.
• [4] H. O. Elwan and A. M. Soliman, “Novel CMOS differential voltage current conveyor and its applications,” IEE Proc. - Circuits, Devices Syst., vol. 144, no. 3, p. 195, Aug. 1997.
• [5] W. Chiu, S.-I. Liu, H.-W. Tsao, and J.-J. Chen, “CMOS differential difference current conveyors and their applications,” IEE Proc. - Circuits, Devices Syst., vol. 143, no. 2, p. 91, 1996.
• [6] A. A. El-Adawy, A. M. Soliman, and H. O. Elwan, “A novel fully differential current conveyor and applications for analog VLSI,” IEEE Trans. Circuits Syst. II Analog Digit. Signal Process., vol. 47, no. 4, pp. 306–313, 2000.
• [7] A. Zeki and A. Toker, “The dual-X current conveyor (DXCCII): a new active device for tunable continuous-time filters,” Int. J. Electron., vol. 89, no. 12, pp. 913–923, 2003.
• [8] C. Acar and S. Ozoguz, “A new versatile building block: current differencing buffered amplifier suitable for analog signal-processing filters,” Microelectronics J., vol. 30, no. 2, pp. 157–160, Feb. 1999.
• [9] S. Franco “Use transconductance amplifiers to make programmable active filters. Electronic Design,” vol. 24 no.19, p. 98-101, 1976.
• [10] D. Biolek, “CDTA–building block for current-mode analog signal processing,” Proc. ECCTD, vol. 3, pp. 397–400, 2003.
• [11] A. Yesil, F. Kacar, and H. Kuntman, “New simple CMOS realization of voltage differencing transconductance amplifier and its RF filter application,” Radioengineering, vol. 20, no. 3, pp. 632–637, 2011.
• [12] F. Kacar, A. Yesil, and A. Noori, “New CMOS realization of voltage differencing buffered amplifier and its biquad filter applications,” Radioengineering, vol. 21, no. 1, pp. 333–339, 2012.
• [13] F. Kacar, A. Yesil, S. Minaei, and H. Kuntman, “Positive/negative lossy/lossless grounded inductance simulators employing single VDCC and only two passive elements,” AEU - Int. J. Electron. Commun., vol. 68, no. 1, pp. 73–78, Jan. 2014.
• [14] R. G. Morris, D.O. Hebb: The Organization of Behavior, Wiley: New York; 1949. Brain Research Bulletin, vol. 50, 437,1999.
• [15] M. Caudill, “Neural Networks Primer, Part I.”, AI Expert, vol.2, no.12, p. 46–52., 1987
• [16] D.E. Rumelhart, G.E. Hinton, R.J. Williams. “Learning representations by back propagating errors.” Nature, vol.323, p.533, 1986.
• [17] J. Brownlee, “Clever Algorithms.”, 2011, lulu.com, 438 pages.
• [18] M.I. Dieste-Velasco , M. Diez-Mediavilla , and C. Alonso-Tristán “Regression and ANN Models for Electronic Circuit Design,” Complexity, 2018,
• [19] M.N. Seyman, N. Taspinar “Channel estimation based on neural network in space time block coded MIMO–OFDM system.” Digital Signal Processing, vol. 23 no.1, 275-280, 2013.
• [20] F. Temurtas, H. Temurtas, N. Yumusak, “Application of neural generalized predictive control to robotic manipulators with a cubic trajectory and random disturbances.” Robotics and Autonomous Systems, vol.54, no.1, p. 74-83, 2006.
• [21] O. Cetin, F. Temurtaş, Ş. Gülgönül, “An application of multilayer neural network on hepatitis disease diagnosis using approximations of sigmoid activation function.” Dicle Medical Journal/Dicle Tip Dergisi, vol. 42, no.2, 2015.
• [22] O. Cetin, F. Temurtaş, “Görsel Uyaranlara İlişkin Manyetoensefalografi Sinyallerinin Genelleştirilmiş Regresyon Sinir Ağı ile Sınıflandırılması.” Dicle Tıp Dergisi, vol. 46 no. 1, p. 19-25, 2019.
• [23] U. Celik, N. Yurtay, Z. Pamuk “Migraine diagnosis by using artificial neural networks and decision tree techniques.” Online Acad. J. Inf. Technol, vol. 5 no.14, p.79-89, 2014.
• [24] U. Celik, N. Yurtay, E.R. Koç, N. Tepe, H. Güllüoğlu and M. Ertaş, Diagnostic accuracy comparison of artificial immune algorithms for primary headaches. Computational and mathematical methods in medicine, 2015.
• [25] E. Arslan and A. Morgul, “Self-Biasing Current Conveyor for High Frequency Applications,” J. Circuits, Syst. Comput., vol. 21, no. 05, p. 1250039, Aug. 2012.
• [26] E. Arslan, S. Minaei, and A. Morgul, “On The Realization of High Performance Current Conveyors And Their Applications,” J. Circuits, Syst. Comput., vol. 22, no. 03, p. 1350015, Mar. 2013.
• [27] E. Arslan and A. Morgül, “Wideband current conveyor with rail to rail input stage,” ELECO, 5th Int. Conf. Electr. Electron. Eng., pp. 66–70, 2007.
• [28] E. Yuce and S. Minaei, “New CCII-based versatile structure for realizing PID controller and instrumentation amplifier,” Microelectronics J., vol. 41, no. 5, pp. 311–316, May 2010.
• [29] F. Yucel and E. Yuce, “CCII based more tunable voltage-mode all-pass filters and their quadrature oscillator applications,” AEU - Int. J. Electron. Commun., vol. 68, no. 1, pp. 1–9, 2014.
• [30] F. Yucel and E. Yuce, “A new single CCII- based voltage-mode first-order all-pass filter and its quadrature oscillator application,” Sci. Iran. Trans. D, Comput. Sci. Eng. Electr., vol. 22, no. 3, pp. 1068–1076, 2015.
• [31] M. S. Bascil, A.Y. Tesneli, F. Temurtas, F. “Multi-channel EEG signal feature extraction and pattern recognition on horizontal mental imagination task of 1-D cursor movement for brain computer interface.” Australasian physical & engineering sciences in medicine, vol.38 no.2,p. 229-239, 2015.
• [32] D.L. Chester Why two hidden layers are better than one. In: International joint conference on neural networks, p 265–268,1990
• [33] M.T. Hagan, M. Menhaj, “Training feed forward networks with the Marquardt algorithm,” IEEE Trans. Neural Netw vol. 5, p. 989–993,1994
• [34] D.E. Rumelhart, G.E. Hinton, R.J. Williams, “Learning internal representations by error propagation.” In: Rumelhart DE, McClelland J (eds) Parallel distributed processing. MIT Press, Cambridge, p. 318–362,1986.