MDP-Based MAC Protocol for WBANs in Edge-Enabled eHealth Systems

Su, Haoru; Pan, Meng-Shiuan; Chen, Huamin; Liu, Xiliang

doi:10.3390/electronics12040947

Cited by 8 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cloud server could as well be employed for data processing and predictions, but for the case of the proposed IoT WBAN SER, the data processing and predictions are performed at the network’s edge because of its numerous advantages such as closeness to the users/devices, low delay, low energy consumption, and high quality of service. Additionally, if the huge speech data generated by the audio recorder are forwarded to the cloud, this will result in unpredictable delays and would not be able to provide timely predictions due to the return delay of the remote cloud server [ 42 ]. Thus, for efficiency, the MEC forwards the predicted emotions to the cloud server and from the cloud server to a remote medical server.…”

Section: Proposed Methodsmentioning

confidence: 99%

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

Olatinwo

Abu‐Mahfouz

Hancke

et al. 2023

Sensors

View full text Add to dashboard Cite

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%.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

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

Olatinwo

Abu‐Mahfouz

Hancke

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…If no channel is available, the sensor node will back off and try again. Therefore, the main shortcoming of CSMA/CA is the wastage of energy consumption for protocol overhead and collision avoidance [32]. Despite this, the advantage of contention-based slot allocation includes low delay, low complexity, effective traffic load adaptation, and reliable WBAN data transmission.…”

Section: Wban Multiple Access Mechanismmentioning

confidence: 99%

A review of wireless body area networks

Haszerila Wan Hassan,

Mohd Ali,

Mohd Sultan

et al. 2024

IJEECS

View full text Add to dashboard Cite

<span>The widespread adoption of wireless body area network (WBAN) in healthcare presents opportunities to meet the increasing demand for medical services. WBAN enables continuous real-time (RT) monitoring through biomedical sensor nodes positioned in or around a patient's body, collecting vital physiological data. In addition, WBAN imposes stringent criteria for energy efficiency and reliability throughout data collection and transmission. This review paper places significant emphasis on the fundamental concept and essential characteristics of WBAN technology. First, the WBAN features, including architecture, sensor nodes types and network topology is presented. Then, the study explores a wide variety of communication standards and multiple access (MA) mechanism deployed in this technology. Moreover, it discusses open research and challenging issues such as heterogeneous traffic, quality of services (QoS), energy consumption, reliability, interference management, and human body movements effect. Finally, the paper is concluded, and future directions are identified in this evolving field of human health monitoring technology.</span>

show abstract

“…The mobile edge computing (MEC) network technology is applied in [9], and a multichannel MAC protocol is also designed for WBAN based on the Markov decision process (MDP). Both the channel condition and the reward value are considered in the protocol.…”

Section: Mac Protocolmentioning

confidence: 99%

“…A B C D E [9] This study applied an MEC-based network architecture and an MDP-based MAC protocol was proposed. The energy utility model and optimization problem were solved using a learning algorithm.…”

Section: Ref Authors Contributions Featuresmentioning

confidence: 99%

A Cross-Layer Media Access Control Protocol for WBANs

Zheng

Jiao

2023

Sustainability

View full text Add to dashboard Cite

Wireless body area network (WBAN) is an emerging comprehensive technology that can deeply integrate with e-health and smart sports. As a wearable network, improving the quality of network service and user experience is crucial. Due to the miniaturized design of sensors, their available energy from batteries is limited, making the extension of their lifetime a key research challenge. Existing studies have proposed methods to improve energy efficiency, but there are still limitations in addressing dynamic adaptive aspects of differential energy distribution and channel conditions. In order to further extend the lifetime of sensor nodes and networks while ensuring quality of service, and to provide a reliable transmission mechanism for heterogeneous application data, this paper presents a cross-layer optimized MAC protocol mechanism. The protocol takes into account the transmission requirements of different types of data and redesigns the superframe. To improve the lifetime of nodes, we propose an energy-adaptive adjustment mechanism considering the channel conditions. At the same time, a cooperative transmission mechanism is proposed to further enhance network lifetime. In experiments conducted on two typical networks, compared to IEEE 802.15.6, the power adjustment scheme improves the network lifetime by 2.8 to 3.7 times, and the cooperative mechanism between nodes further increases the network lifetime by 17% to 44%. Our proposed scheme effectively extends the network lifetime while ensuring quality of service, avoiding frequent battery resets for users, and effectively improving the user experience quality.

show abstract

MDP-Based MAC Protocol for WBANs in Edge-Enabled eHealth Systems

Cited by 8 publications

References 33 publications

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

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

A review of wireless body area networks

A Cross-Layer Media Access Control Protocol for WBANs

Contact Info

Product

Resources

About