Classification of single and double-gate nanoscale MOSFET with different dielectrics from electrical characteristics using soft computing techniques

Abstract

Near-accurate classification is possible for single and double-gate nano-MOSFETs with low and high-k dielectrics based on the experimental findings of their electrical performance. Association analysis is incorporated to identify whether class determination is at all possible based on the available 28 features obtained experimentally with 800 sample data taken for four classes of MOSFETs, and FP-Growth algorithm is used to determine highest confidence rules between different subsets of classes after population analysis of data with after applying various statistical tools like t test. ReliefF algorithm is used to generate rank-wise importance of the available feature, and multi-layer perception gives best 93.33% accuracy among other classifiers. Principal Component Analysis is incorporated for creating new predictor from the existing 28 features in this work. It is found that around 95% accuracy is achieved with best 6 transformed features taken together. It is also found out that quantum capacitance per unit gate length with lowest channel diameter and highest thickness is the best feature for this classification problem. This technique may be utilized for accurate identification of higher number of classes with different transistors having different dielectrics.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

References

  1. 1.

    Bait AA, Narkhede N, More S, Satkut A, Joshi S (2016) Performance enhancement and supression of short channel effects of 14nm double gate FETs by using gate stacked high-k dielectrics & workfunction variation. In: International conference on inventive computation technologies (ICICT), Coimbatore, pp. 1–5. https://doi.org/10.1109/INVENTIVE.2016.7824876

  2. 2.

    Goel N, Pandey MK (2017) Design device for subthreshold slope in DG fully depleted SOI MOSFET. J Nano Electron Phys 9(1):01022

    Article  Google Scholar 

  3. 3.

    Tsoukalas D, Tsamis C, Kouvatsos DN, Revva P, Tsoi E (1997) Reduction of the reverse short channel effect in thick SOI MOSFET’s. IEEE Electron Device Lett 18(3):90–92

    Article  Google Scholar 

  4. 4.

    Solomon PM, Guarini KW, Zhang Y, Chan K, Jones EC, Cohen GM, Krasnoperova A, Ronay M, Dokumaci O, Hovel HJ, Bucchignano JJ, Cabral C, Lavoie C, Ku V, Boyd DC, Petrarca K, Yoon JH, Babich IV, Treichler J, Kozlowski PM, Newbury JS, D’Emic CP, Sicina RM, Benedict J, Wong H-SP (2003) Two gates are better than one [double-gate MOSFET process]. IEEE Circuits Devices Mag 19(1):48–62

    Article  Google Scholar 

  5. 5.

    Rawat AS, Gupta SK (2017) Potential modelling and performance analysis of junctionless quadruple gate MOSFETs for analog and RF applications. Microelectron J 66:89–102

    Article  Google Scholar 

  6. 6.

    Masahara M, Matsukawa T, Ishii K, Liu Y, Nagao M, Tanoue H, Tanii T, Ohdomari I, Kanemaru S, Suzuki E (2003) Fabrication of ultrathin Si channel wall for vertical double-gate metal-oxide-semiconductor field-effect transistor (DG MOSFET) by using ion-bombardment-retarded etching (IBRE). Jpn J Appl Phys Part 1 42(4B):1916–1918

    Article  Google Scholar 

  7. 7.

    Lin X, Feng C, Zhang S, Ho WH, Chan M (2004) Characterization of double gate MOSFETs Fabricated by a simple method on a recrystallized silicon film. Solid-State Electron 48:2315–2319

    Article  Google Scholar 

  8. 8.

    Sharma A, Jain A, Pratap Y, Gupta RS (2016) Effect of High-k and vacuum dielectrics as gate stack on a junctionless cylindrical surrounding gate (JL-CSG) MOSFET. Solid State Electron 123:26–32

    Article  Google Scholar 

  9. 9.

    Zhu Y, Ye Y, Cao Y, He J, Zhang A, He H, Wang H, Ma C, Hu Y, Chan M, Zhu X (2013) Numerical study on effects of random dopant fluctuation in double gate tunneling FET. In: IEEE international conference of electron devices and solid-state circuits, Hong Kong, pp. 1–2. https://doi.org/10.1109/EDSSC.2013.6628040

  10. 10.

    Lu S, Braunstein SL (2014) Quantum decision tree classifier. Quantum Inf Process 13(3):757–770

    MathSciNet  Article  Google Scholar 

  11. 11.

    Huang H, Liu Y, Bosch LT, Cranen B, Boves L (2012) Knowledge-based quadratic discriminant analysis for phonetic classification. In: IEEE international conference on acoustics, speech and signal processing, Kyoto, pp. 4145–4148. https://doi.org/10.1109/ICASSP.2012.6288831

  12. 12.

    Zanaty EA (2012) Support vector machines (SVMs) versus multilayer perception (MLP) in data classification. Egypt Inf J 13(3):177–183

    Google Scholar 

  13. 13.

    Xu J (2011) Multi-label weighted k-nearest neighbor classifier with adaptive weight estimation. In: Lu BL, Zhang L, Kwok J (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7063. Springer, Berlin, Heidelberg

    Google Scholar 

  14. 14.

    Ploj B, Zorman M, Kokol P (2011) Border pairs method—constructive MLP learning classification algorithm. In: Bouchachia A (ed) Adaptive and intelligent systems. ICAIS 2011. Lecture notes in computer science, vol 6943. Springer, Berlin, Heidelberg

    Google Scholar 

  15. 15.

    Datta S (1997) Electronic transport in mesoscopic systems, 1st edn. Cambridge University Press, Cambridge

    Google Scholar 

  16. 16.

    Agrawal R, Imielinski T, Swami A (1993) Database mining: a performance perspective. IEEE Trans Knowl Data Eng 5(6):914–925

    Article  Google Scholar 

  17. 17.

    Agrawal R, Ghosh SP, Imielinski T, Iyer BR, Swami AN (1992) An interval classifier for database mining applications. In: VLDB, pp 560–573

  18. 18.

    http://www.cs.waikato.ac.nz/ml/weka/. Accessed 15 Jan 2018

  19. 19.

    Han J, Pei H, Mao R, Yin Y (2004) Mining frequent patterns without candidate generation: a frequent pattern tree approach. Data Min Knowl Disc 8:53–87

    MathSciNet  Article  Google Scholar 

  20. 20.

    Pirooznia M, Yang JY, Yang MY, Deng Y (2007) A comparative study of different machine learning methods on microarray gene expression data. BMC Genomics 9(Suppl 1):S13. https://doi.org/10.1186/1471-2164-9-S1-S13

    Article  Google Scholar 

  21. 21.

    Zamalloa M, Rodríguez-Fuentes LJ, Peñagarikano M, Bordel G, Uribe JB (2008) Feature selection vs. feature transformation in reducing dimensionality for speaker recognition. V Jornadas en Tecnología del Habla 45–48

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Arpan Deyasi.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Deyasi, A., Mukherjee, S., Bhattacharjee, A.K. et al. Classification of single and double-gate nanoscale MOSFET with different dielectrics from electrical characteristics using soft computing techniques. Int. j. inf. tecnol. 12, 165–174 (2020). https://doi.org/10.1007/s41870-019-00301-1

Download citation

Keywords

  • SG MOSFET
  • DG MOSFET
  • Neural network
  • Feature selection
  • Feature transformation
  • Association rules
  • High and low-k dielectrics