MEC-Based Jamming-Aided Anti-Eavesdropping with Deep Reinforcement Learning for WBANs

2022 ◽  
Vol 22 (3) ◽  
pp. 1-17
Author(s):  
Guihong Chen ◽  
Xi Liu ◽  
Mohammad Shorfuzzaman ◽  
Ali Karime ◽  
Yonghua Wang ◽  
...  

Wireless body area network (WBAN) suffers secure challenges, especially the eavesdropping attack, due to constraint resources. In this article, deep reinforcement learning (DRL) and mobile edge computing (MEC) technology are adopted to formulate a DRL-MEC-based jamming-aided anti-eavesdropping (DMEC-JAE) scheme to resist the eavesdropping attack without considering the channel state information. In this scheme, a MEC sensor is chosen to send artificial jamming signals to improve the secrecy rate of the system. Power control technique is utilized to optimize the transmission power of both the source sensor and the MEC sensor to save energy. The remaining energy of the MEC sensor is concerned to ensure routine data transmission and jamming signal transmission. Additionally, the DMEC-JAE scheme integrates with transfer learning for a higher learning rate. The performance bounds of the scheme concerning the secrecy rate, energy consumption, and the utility are evaluated. Simulation results show that the DMEC-JAE scheme can approach the performance bounds with high learning speed, which outperforms the benchmark schemes.

Author(s):  
Subono . ◽  
M. Udin Harun Al Rasyid ◽  
I Gede Puja Astawa

ZigBee applications of IEEE 802.15.4 Wireless Sensor Network (WSN) with Low Rate Wireless Personal Area Network (LR-WPAN) can be integrated with e-health technology Wireless Body Area Network (WBAN). WBAN are small size and can communicate quickly making it easier for people to obtain information accurately.WBAN has a variety of functions that can help human life. It can be used in the e-health, military and sports. WBAN has the potential to be the future of wireless communication solutions. WBAN use battery as its primary power source. WBAN has limited energy and must be able to save energy consumption in order to operate for a long time. In this study, we propose a method of time scheduling called cycle sleep period (CSP) as WBAN solutions to save energy and improve energy efficiency. The CSP method is implemented in the real hardware testbed using sensor e-health includes temperature body and current sensor. We compared the performance of CSP method with duty cycle management (DCM) time scheduling-based and without using time scheduling.From the measurement results, our proposed idea has decreasingenergy consumption.Keywords: WSN, LR-WPAN, WBAN, e-health, Time Scheduling


2018 ◽  
Vol 7 (2) ◽  
pp. 34-39
Author(s):  
Pallvi . ◽  
Sunil Kumar Gupta ◽  
Rajeev Kumar Bedi

Wireless Body Area Network (WBAN) is an application of wireless sensor network (WSN). WBAN therefore forms a comprehensive collection of devices that are not only capable of providing continuous information about the health status of a person but also offers helpful details about the activities and environment of the person. In this paper, we have evaluated TDMA based MAC protocol performance through several metrics and TDMA approach is used to avoid packet collision which leads to higher packet loss rate. Reinforcement Based Clock synchronization is the solution of problem like packet collision. After clocks of WBAN sensor nodes are synchronized, data can be transferred between sensor nodes and sink efficiently and rapidly. Reinforcement learning iteratively optimizes the clock synchronization technique. Experimental results indicate that the proposed algorithm is more efficient than existing techniques.


2018 ◽  
Vol 8 (9) ◽  
pp. 1474 ◽  
Author(s):  
Chiung-An Chen ◽  
Chen Wu ◽  
Patricia Abu ◽  
Shih-Lun Chen

Data transmission of electroencephalography (EEG) signals over Wireless Body Area Network (WBAN) is currently a widely used system that comes together with challenges in terms of efficiency and effectivity. In this study, an effective Very-Large-Scale Integration (VLSI) circuit design of lossless EEG compression circuit is proposed to increase both efficiency and effectivity of EEG signal transmission over WBAN. The proposed design was realized based on a novel lossless compression algorithm which consists of an adaptive fuzzy predictor, a voting-based scheme and a tri-stage entropy encoder. The tri-stage entropy encoder is composed of a two-stage Huffman and Golomb-Rice encoders with static coding table using basic comparator and multiplexer components. A pipelining technique was incorporated to enhance the performance of the proposed design. The proposed design was fabricated using a 0.18 μm CMOS technology containing 8405 gates with 2.58 mW simulated power consumption under an operating condition of 100 MHz clock speed. The CHB-MIT Scalp EEG Database was used to test the performance of the proposed technique in terms of compression rate which yielded an average value of 2.35 for 23 channels. Compared with previously proposed hardware-oriented lossless EEG compression designs, this work provided a 14.6% increase in compression rate with a 37.3% reduction in hardware cost while maintaining a low system complexity.


Author(s):  
Shilpa Shinde ◽  
Santosh Sonavane

Background and objective: In the Wireless Body Area Network (WBAN) sensors are placed on the human body; which has various mobility patterns like seating, walking, standing and running. This mobility typically assisted with hand and leg movements on which most of the sensors are mounted. Previous studies were largely focused on simulations of WBAN mobility without focusing much on hand and leg movements. Thus for realistic studies on performance of the WBAN, it is important to consider hand and leg movements. Thus, an objective of this paper is to investigate an effect of the mobility patterns with hand movements on the throughput of the WBAN. Method: The IEEE 802.15.6 requirements are considered for WBAN design. The WBAN with star topology is used to connect three sensors and a hub. Three types of mobility viz. standing, walking and running with backward and forward hand movements is designed for simulation purpose. The throughput analysis is carried out with the three sets of simulations with standing, walking and running conditions with the speed of 0 m/s, 0.5 m/s and 3 m/s respectively. The data rate was increased from 250 Kb to 10000 Kb with AODV protocol. It is intended to investigate the effect of the hand movements and the mobility conditions on the throughput. Simulation results are analyzed with the aid of descriptive statistics. A comparative analysis between the simulated model and a mathematical model is also introduced to get more insight into the data. Results: Simulation studies showed that as the data rate is increased, throughput is also increased for all mobility conditions however, this increasing trend was discontinuous. In the standing (static) position, the throughput is found to be higher than mobility (dynamic) condition. It is found that, the throughput is better in the running condition than the walking condition. Average values of the throughput in case of the standing condition were more than that of the dynamic conditions. To validate these results, a mathematical model is created. In the mathematical model, a same trend is observed. Conclusion: Overall, it is concluded that the throughput is decreased due to mobility of the WBAN. It is understood that mathematical models have given more insight into the simulation data and confirmed the negative effect of the mobility conditions on throughput. In the future, it is proposed to investigate effect of interference on the designed network and compare the results.


Author(s):  
Suthisa Kesorn ◽  
Norakamon Wongsin ◽  
Thinnawat jangjing ◽  
Chatree Mahatthanajatuphat ◽  
Paitoon Rakluea

Sign in / Sign up

Export Citation Format

Share Document