A Hybridized Fuzzy-Neural Predictive Intelligent (HFNPI) Modelling Approach-based Underlap FinFET Model

ABSTRACT

This paper presents the hybridized fuzzy-neural predictive intelligent (HFNPI) based approach for predicting FinFET model. The proposed model is an improved approach over artificial neural network (ANN) model and adaptive neuro fuzzy inference system (ANFIS) model that provides optimum model parameters. In this paper, the challenge of optimization of large number of parameters is reduced. It assesses the performance of resultant structure on the basis of selected RF figure-of-merit. Based on the application requirements, RF figure-of-merit such as f _T and f _max are used as appropriate performance parameters to analyse the device performance. The framework for the HFNPI model is underlapped FinFET structural/process parameters. The mean prediction error was found 2.8 × 10⁻⁴ GHz. The comparative analysis of HFNPI with ANN and ANFIS model is done. It is found that combination of fuzzy and neural logic shows better result rather than individual ANFIS and ANN model to redevelop the model and increase the number of inputs.

KEYWORDS:

• Compact model
• Device modelling
• Emerging device
• FinFET
• Fuzzy system
• High frequency
• MOSFET
• Multigate transistor
• Neural network
• TCAD

Acknowledgements

Special thanks to Dr Jagannath Mallik, Advanced Microwave Lab, Indian Institute of Technology, Roorkee, for kind support on technical issues.

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Savitesh M. Sharma

Savitesh Madhulika Sharma received MTech degree in VLSI design from Banasthali Vidyapeeth, Banasthali, India. She is currently pursuing PhD degree from the Electronics and Communication Engineering Department, IIT-Roorkee, Roorkee, India. Her current research interests include novel MOS-based devices, RF-FinFETs, and semiconductor device modelling.

E-mail: [email protected]

S. Dasgupta

Sudeb Dasgupta received the PhD degree from IIT-BHU, Varanasi, India, in 2000. He is currently an associate professor with the Electronics and Communication Engineering Department, IIT-Roorkee, India.

Corresponding author E-mail: [email protected]

M. V. Kartikeyan

M. V. Kartikeyan (SM’03) received the MSc and PhD degrees in physics and electronics engineering from IIT (BHU), Varanasi, India, in 1985 and 1992, respectively. Since 2009, he is a full-professor with the Department of Electronics and Communication Engineering, Indian Institute of Technology, Roorkee, India.

E-mail: [email protected]