Title: Empowering immediate healthcare insights: a deep learning chatbot with modified-CNN and SA-MGO optimisation

Authors: Sonia Rathee; Shalu Mehta; Amita Yadav; Geetika Dhand; Sachi Nandan Mohanty; Mamata Garanayak; Bijay Kumar Paikaray

Addresses: Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi, India ' Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi, India ' Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi, India ' Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi, India ' School of Computer Science and Engineering, VIT-AP University, Amaravati, Andhra Pradesh, India ' Department of Computer Science, Kalinga Institute of Social Sciences (Deemed to be University), Odisha, India ' Centre for Data Science, Department of Computer Science and Engineering, Siksha 'O' Anusandhan (Deemed to be University), Odisha, India

Abstract: This article proposes a novel deep-learning framework designed to empower a highly efficient chatbot, capable of delivering immediate responses to patients seeking information about their medical conditions before their doctor's appointment. The core of the proposed model features a modified-CNN, which incorporates enhancements through the integration of a Gaussian kernel (GK), generalised divisive normalisation (GDN) layer, and the fast Fourier transformer (FFT) for improved feature learning performance. The dataset pre-processed is fed into the modified CNN for effective information extraction. To enhance the optimisation process, the self-adaptive mountain gazelle optimiser (SA-MGO) algorithm is employed, contributing to the overall efficiency of the modified CNN by fine-tuning the parameters of the M-CNN like learning rate, epoch, momentum, and batch-size. The integration of the SA-MGO algorithm further enhances the overall performance of the modified CNN, making the chatbot a valuable resource for individuals seeking immediate insights into their health concerns.

Keywords: chatbot; modified convolutional neural network; generalised divisive normalisation layer; fast Fourier transformer; FFT; self-adaptive mountain gazelle optimiser.

DOI: 10.1504/IJES.2024.144367

International Journal of Embedded Systems, 2024 Vol.17 No.3/4, pp.267 - 284

Received: 21 Mar 2024
Accepted: 31 Oct 2024
Published online: 10 Feb 2025 *