IoT-Enabled WBAN and Machine Learning for Speech Emotion Recognition in Patients - Research overview

Aug 5, 2026

Upload by Eliana

Internet of things (IoT)-enabled wireless body area networks (WBAN) combine medical devices, wireless devices, and non-medical components for healthcare management. Speech emotion recognition (SER) extracts speakers’ emotions from speech, yet healthcare deployments face limitations including low prediction accuracy, high computational complexity, and latency in real-time inference, along with challenges in selecting effective speech features. An emotion-aware IoT-enabled WBAN framework is proposed with edge AI for real-time prediction and monitoring pre- and post-treatment changes, comparing multiple machine learning and deep learning approaches to improve performance and reduce complexity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Motivation and system integration

Speech emotion recognition background

Proposed approach and modeling

sensors Article IoT-Enabled WBAN and Machine Learning for Speech Emotion Recognition in Patients Damilola D. Olatinwo 1,*, Adnan Abu-Mahfouz 1,2, Gerhard Hancke 1,3 and Hermanus Myburgh 1 Citation: Olatinwo, D.D.; Abu-Mahfouz, A.; Hancke, G.; Myburgh, H. IoT-Enabled WBANand Machine Learning for Speech Emotion Recognition in Patients. Sensors 2023, 23, 2948. [https://](https://)[ ](https://)[doi.org/10.3390/s23062948](doi.org/10.3390/s23062948) Academic Editor: Raffaele Gravina Received: 5 February 2023 Revised: 27 February 2023 Accepted: 3 March 2023 Published: 8 March 2023 1 Department of Electrical, Electronic and Computer Engineering, University of Pretoria, Pretoria 0001, South Africa 2 Council for Scientiﬁc and Industrial Research (CSIR), Pretoria 0184, South Africa 3 Department of Computer Science, City University of Hong Kong, Hong Kong, China * Correspondence: [damibaola@gmail.com](damibaola@gmail.com) Abstract: Internet of things (IoT)-enabled wireless body area network (WBAN) is an emerging technology that combines medical devices, wireless devices, and non-medical devices for healthcare management applications. Speech emotion recognition (SER) is an active research ﬁeld in the healthcare domain and machine learning. It is a technique that can be used to automatically identify speakers' emotions from their speech. However, the SER system, especially in the healthcare domain, is confronted with a few challenges. For example, low prediction accuracy, high computational complexity, delay in real-time prediction, and how to identify appropriate features from speech. Motivated by these research gaps, we proposed an emotion-aware IoT-enabled WBAN system within the healthcare framework where data processing and long-range data transmissions are performed by an edge AI system for real-time prediction of patients' speech emotions as well as to capture the changes in emotions before and after treatment. Additionally, we investigated the effectiveness of different machine learning and deep learning algorithms in terms of performance classiﬁcation, feature extraction methods, and normalization methods. We developed a hybrid deep learning model, i.e., convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), and a regularized CNN model. We combined the models with different optimization strategies and regularization techniques to improve the prediction accuracy, reduce generalization error, and reduce the computational complexity of the neural networks in terms of their computational time, power, and space. Different experiments were performed to check the efﬁciency and effectiveness of the proposed machine learning and deep learning algorithms. The proposed models are compared with a related existing model for evaluation and validation using standard performance metrics such as prediction accuracy, precision, recall, F1 score, confusion matrix, and the differences between the actual and predicted values. The experimental results proved that one of the proposed models outperformed the existing model with an accuracy of about 98% . Keywords: IoT WBAN; machine learning; deep learning; edge AI; speech emotion; CNN; BiLSTM; standard scaler; min–max scaler; robust scaler; data augmentation; spectrograms; regularization techniques; MFCC; Mel spectrogram Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1. Introduction Due to the rapid advancement of the Internet of things (IoT) technology in various ﬁelds, ref. [1] IoT devices, IoT services, and IoT applications, IoT-enabled wireless body area network (WBAN) has gained popularity as well as new opportunities for its d

FAQs

What problem does the paper address in healthcare speech emotion recognition?

It targets challenges such as low prediction accuracy, high computational complexity, and delays for real-time inference, plus difficulty in choosing appropriate speech features.

How is the proposed IoT-enabled WBAN system used for emotion-aware monitoring?

It uses edge AI to process data and perform long-range transmissions, enabling real-time prediction of patients’ speech emotions and tracking changes before and after treatment.

Which models and evaluation metrics are used to compare methods?

The study evaluates machine learning and deep learning algorithms, including a hybrid CNN-BiLSTM model and a regularized CNN, using metrics like accuracy, precision, recall, F1 score, and confusion matrix.

Aug 5, 2026

Upload by Eliana