Why Software-Defined Radio (SDR) Matters in
Healthcare?
Type of Article: Editorial
A.C. B. Monteiro1,
Vania V. Estrela2, Abdeldjalil Khelassi3, Yuzo Iano1,
Navid Razmjooy4, Diego T. M. Rocha2, Delcimar Martins5
1 School of Electrical and Computer Engineering (FEEC), UNICAMP,
Campinas, SP, Brazil,
2 Dep. of Telecommunications, Fluminense Federal University (UFF),
Niteroi, RJ, Brazil
3 University of Tlemcen, Algeria,
4 Department of Electrical Engineering, Tafresh University,
Tafresh, Iran,
5Observatorio Nacional, RJ, Brazil,
Abstract
Background: Wireless Body Area Networks (WBANs) have been drawing noteworthy
academic and industrial attention. A WBAN states a network dedicated to acquire
personal biomedical data via cutting-edge sensors and to transmit
healthcare-related commands to particular types of actuators intended for
health purposes. Still, different proprietary designs exist, which may lead to
biased assessments. This paper studies the role of Software-Defined Radio (SDR)
in a WBAN system for inpatient and outpatient monitoring and explains to health
professionals the importance of the SDR within WBANs.
Methods: A concern related to all wireless networks is their dependence on
hardware, which limits reprogramming or reconfiguration alternatives. If an
error happens in the equipment, firmware, or software, then, typically, there
will be no way to fix system vulnerabilities. SDR solves many fixed-hardware
problems with other benefits.
Results: SDR entails more healthcare domain dynamics with more
network convergence in agreement with the stakeholders involved. Then the SDR
perspective can bring in innovation to the healthcare subsystems’
interoperability with recombination/reprogramming of their parts, updating, and
malleability.
Conclusion: SDR technology has many utilizations in radio environments and is
becoming progressively more widespread among all kinds of users. Nowadays,
there are many frameworks to manipulate radio signals only with a computer and
an inexpensive SDR arrangement. Moreover, providing a very cheap radio receiver/transmitter
equipment, SDR devices can be merged with free software to simplify the
spectrum analyses, provide interferences detection, deliver efficient frequency
distribution assignments, test repeaters' operation while measuring their
parameters, identify spectrum intruders and characterize noise according to
frequency bands.
Keywords: Wireless Body Area Network (WBAN), Software-Defined Radio (SDR),
Internet of Things (IoT), Healthcare.
Corresponding
author: Vania V. Estrela, Dep. of
Telecommunications, Fluminense Federal University (UFF), Niteroi, RJ, Brazil
Email: vania.estrela.phd@ieee.org.
Screened
by iThenticate..©2017-2019 KNOWLEDGE KINGDOM PUBLISHING.
1.
Introduction
A Wireless Body Area Network (WBAN) is
responsible for the wireless Internet connection of independent nodes, each one
of them comprising Control Units (CUs), sensors, and actuators that are situated
in the clothes on the body or under the within the person’s body. These devices
are popularly known as wearables and permit several different topologies like a
star or multi-hop.
Figure 1. Diagram showing a WBAN.
A WBAN offers many promising new utilizations
in remote healthcare monitoring, homecare, medicine, multimedia, sports, and
several other usages, all of which take advantage of the unimpeded freedom that
a WBAN offers. E.g., an ill person can wear a WBAN consisting of sensors that
regularly measure specific biological functions, like blood pressure,
temperature, respiration, heart rate, ECG, etc. [12-14]. The benefit is that
the patient is away from bed and healthcare facilities, and move freely across
the room. If he/she is an inpatient, then this person can even leave the
hospital for a while. This paradigm change improves the patient’s Quality of
Life (QoL) and lessens hospital costs. Moreover, the data is acquired over an
extended period and within the patient’s natural environment, which offers more
valuable information, and allows for better and, occasionally, even faster
diagnosis. Along with the spread of mobile devices and wearables, the
healthcare domain has seen the rapid progress of tools intended for the
Internet of Things (IoT). Medical IoT devices include physiological monitors,
biomedical devices, medical records repositories, mobile medical apps, and
equipment for examinations like MRI, CT, and ultrasound. Several wearables for
healthcare appeared in recent times to obtain data about parameters/vital signs
such as temperature, heart rate, and acceleration to follow a person’s
activities and well-being [3]. These systems aid high-performance sports and
remote monitoring of patients [5, 6]. These practices quite often rely on the
ANT+ standard (ANT+S). This protocol lacks Bluetooth or Industry 4.0
compatibility, which has low-power consumption, with a low-transmission rate,
and exists in smartphones [7].
1.1 ANT+ Standard
The trademarked Adaptive Network Topology
(ANT+) is an open-access multicast technology for wireless sensor networks from
the ANT Wireless [1] for sports and fitness sensors.
ANT defines a Wireless Communication (WC)
protocol stack that permits hardware to utilize the 2.4 GHz Industrial,
Scientific and Medical (ISM) radio band to communicate. ANT established
standards for evidence representation, co-existence, signaling, validation, in
addition to error discovery [3]. It is conceptually akin to
Bluetooth regarding low energy despite the fact it favors its usage with
sensors.
The ANT+ ultra-low-power WC standard implements
an interoperability function. This feature supplements the underlying ANT
protocol and simplifies the networking of neighboring ANT+ devices/subsystems
to smooth the acquisition and analysis of sensory information [2]. Because
healthcare wearables demand robustness and still call for more standardization,
they may face changes, which may encounter obstacles since this standard is
proprietary, and the information is not open to the public.
Figure 2. SDR block diagram with the receiver
(lower part) and transmitter (upper part).
1.2
The Software-Defined Radio Role in Healthcare
Notwithstanding the multiple technological
advances, a new and possibly challenging concern common to all wireless
networks is the fact that their radio equipment and protocols rely mostly on
hardware. Consequently, reprogramming or reconfiguration alternatives are very
restricted. This inflexibility is bothersome because if an error happens in the
equipment, firmware, or software, then, usually, there will be no practical way
to correct the shortcoming due to the inherent system vulnerabilities. This
feature limits the hardware components' functionality and reconfigurability to
implement other WC protocols beyond the one predefined by the hardware.
Precisely, the SDR solves many of the problems described previously, along with
many other benefits. Therefore, the healthcare community necessitates better
network convergence developments in agreement with the dynamics of the
healthcare field and stakeholders involved. Meanwhile, the SDR perspective can
bring in innovation to this context with subsystems’ updating,
interoperability, combination, and malleability.
The upcoming sections are organized as follows:
Section 2 introduces the basics of Software-Defined Radio (SDR). Section 3
presents some thoughts for deploying healthcare WBANs. Future trends appear in
Section 4. This work closes with a fifth Section containing the conclusions.
2.
Software-Defined
Radio (SDR)
The Software Defined Radio (SDR) is a WC design
identified with a class of radio systems reprogrammable as well as reconfigurable
via software. Nowadays, SDR software and hardware are
available at meager prices. In terms of SDR software, most implementations are
free. An SDR device appears in Figure 2.
Ultimately, the demodulator recuperates the
original modulating signal from the Low-Noise Amplifier (LNA) output, employing
one of several alternatives. Further signal processing depends on the purpose
of the SDR equipment.
Figure 2 illustrates the SDR hardware framework
block diagram. At first, the Radiofrequency (RF) tuner filter converts the
analog signal to the Low-Noise Amplifier (LNA), then the necessary channel is
isolated and converted from analog to digital by an Analog-to-Digital Converter
(ADC). When the CPU finishes with processing, then the digital signal is
transformed into an analog signal by a Digital-to-Analog Converter (DAC) and
modulated for transmission. At the transmission path, some Power Amplification
(PA) is necessary.
While the hardware elements are indispensable
parts in the SDR rationale, the paradigm points out the need for complementary
dedicated software. Some IDEs to develop an SDR-based WBAN software employing a
computer or an FPGA or a CPU such as a Digital Signal Processor (DSP) is
needed. Nevertheless, before developing software, a hardware framework must
provide low-level interface functions. Major software IDEs are
(i) LabVIEW
by National Instruments; and
(ii) MATLAB/
Simulink/ USRP by MathWorks.
3. Some
Considerations for Deploying Healthcare WBANs
The use of WBANs is increasingly making a
difference as healthcare facilities introduce additional Wi-Fi-based
technology. WBANs are the essence of healthcare IT infrastructure, although
designing and deploying dependable Wi-Fi for present and prospect IT initiatives
can be a trial.
Healthcare personnel is becoming dependent on
interconnected mobile devices that function relentlessly and everywhere. Since
some of these devices are mission-critical, the risk of a service outage may
disrupt operations or even threaten patient safety.
The arrangements required to support an entire
IT infrastructure relying on IoT must make a serious inventory all physical and
digital impediments, understanding the information flow with the corresponding
devices/subsystems priorities to perform network connection, along with ways to
conciliate network components visibility with its management. Some of the chief
obstacles to WBANs deployments and organizations are as follows:
Coverage: Mobile
gadgets and wearables call for reliable wireless internet connectivity
regardless of the dislocations of the stakeholders. Network coverage means
devices can work everywhere. The dynamic characteristics of healthcare experts
strengthen this urgency. Healthcare personnel requires connectivity to use
communication tools even when outside of buildings.
Structural Planning:
Designing and realizing a wireless answer is more elaborate than deploying
other portions of healthcare IT infrastructure due to frequent and numerous
physical barriers, such as building materials that block RF signals. Urban
hospitals may also have to struggle with conflicting signals stemming from
other networks in the region. Healthcare facilities habitually entail
retrofitting a wireless network to their physical installations instead of
constructing edifices with particular wireless pre-requisites. Rather than
deploying a completely upgraded infrastructure altogether, Healthcare
establishments can work through departments, buildings, or systems, upgrading
one system portion at a time until finishing the entire system. Newer wireless
deployments like the IEEE 802.11ac [4] support legacy devices can still connect
to the new system, and gadgets can take advantage of the full bandwidth and
faster speeds.
Network Capacity: The
snowballing number of devices asking access to wireless networks can impact
legacy systems severely, leading to access problems. Once a healthcare
organization receives basic network coverage, it must guarantee network
robustness to fulfill the necessary expectations.
Information Quality: Data
engendered and gathered through WBANs can influence the patient's healthcare
process, which calls for a high standard to safeguard decision-making relying
on the best possible records.
Data Control: As
WBANs yield large data volumes, the necessity to manage and retain these
healthcare datasets becomes of utmost importance.
Pervasive Device Validation: Sensors
and actuators have inherent communication while being robust to hardware
constraints such as unreliable network links, limited energy reserves, and
interference. These limitations may provoke the incorrect transmission of
datasets to the stakeholders. It is essential in a healthcare realm that all
sensor measurements and actuator commands are validated to decrease false
alarms and helps to recognize possible hardware and software flaws.
Data Consistency:
Information from multiple mobile devices, media, and remote patient files need
to be acquired and examined smoothly. Within WBANs, vital patient datasets may
not arrive at their destination or contain corrupted packets after wandering
over several nodes or places as well as through many networked computers. If a
healthcare practitioner′s
portable device does not hold all known data, then the healthcare quality may
worsen.
Security: To make
WBAN transmission safe and accurate, one has to guarantee that the patient data
is secure and that each patient possesses a dedicated WBAN to avoid his/her
information to mix up with different patients. Moreover, the WBAN data must be
secure and with limited access.
Resource Availability: As
WBANs face resource-constrains because of energy, memory, communication rate,
and computational competence, security solutions from other varieties of
networks may not apply to WBANs [14, 17].
Interoperability: The
802.15.6 standard governs the WBAN configurations. These regulations outperform
current WC knowhow such as Bluetooth and ZigBee. This standard partakes the
benefits of ultra-low-power consumption, high reliability, and high-security
protection while transferring sensitive personal data. WBAN structures call for
seamless data transferences across other norms, e.g., Bluetooth, ZigBee, and
the IEEE 802.15.6 [9] standards to stimulate data exchange in a plug-and-play
fashion with scalability, guaranteed efficient migration throughout networks
and nonstop connectivity.
System Sensors and Actuators: The
WBAN sensors should have low complexity, small size, light, easy to use,
power-efficient, and reconfigurable. Furthermore, the data storage requires
some local redundancy, remote storage via cloud, access to patient data, and to
external processing via the Internet [12].
Privacy: WBANs
should not threaten the stakeholder’s freedom if facing unexpected situations
through medical usage. Confidentiality, availability, authentication,
trustworthiness, and novelty of data together with secure information
management requirements for WBAN exist in the IEEE 802.15.6 standard [5].
Interference: The
wireless links from body sensors should lessen the interference, coexist with
other WBAN devices, and allow scalability to facilitate further connection of
other network devices, especially for large-scale WBAN implementations [18].
Cost:
Healthcare consumers want low-cost health surveillance solutions with high
functionality. Cost-optimized WBAN deployments will appeal to health-conscious
people.
Monitoring:
Patients may entail different observing priorities. E.g., cardiopaths may need
checking up functions working nonstop, while elders at risk of falls may
function at a lower priority while walking or moving. The monitoring type
affects the amount of power required to sustain the WBAN framework.
Constrained Deployment: The
WBAN has to be non-intrusive, wearable, and lightweight so that it should not
alter or hinder the patient's and his/her caregiver's daily activities.
Consistent Performance: The
WBAN performance should be reliable so that sensor inputs and actuator outputs
are precise and calibrated even when the patient’s WBAN has been off for some
time, and it is switched on again. The WC links should be robust and perform
under various patients’ situations.
Quality of the Healthcare
Service: Healthcare organizations can assess their
environments for a possible wireless network upgrade employing surveys are an
option [13, 16]. A site assessment can perceive the parts that experience
problems with signal reception and transmission. Site surveys support
healthcare organizations in successfully assigning Access Points (APs)
according to the existent needs and without wasting resources on
redundant/unnecessary APs.
4. Future
Trends
The majority of the radio equipment is located
in Europe and North America, although there are stations on all continents. The
operating bands and the signal's quality may differ from one location to
another, which is understandable if the spontaneous nature of the network is
considered. Still, by accessing numerous nodes, multiple bands can be enclosed,
especially in high-density areas.
The SDR-based Internet possibilities discussed
previously point towards the following applications of the technology [11]:
Estimation of Wireless
Transmission Losses: If there is centralized control of SDR devices
deployed at strategic points to enable the signals’ comparison at reception,
then the estimation of path loss and the validation of the coverage
computations made with specialized software like RadioMobile [8] can be done.
SDR as a Service: The
healthcare corporation deploying a vast SDR network will be able to make access
available as a service to other parties with specific interests. Impact of the Geographical Site: Emitters’ locations can
be obtained from the evidence supplied by several receivers situated distantly.
If at least three of them are used, the radiofrequency source location can be
accurately determined. Nonetheless, the deployment is not straightforward with
the software presented [10].
Improvement of Shortwave
Communications: Employing remote SDR receivers make shortwave
transmissions available even from distant countries, which expands the HF
communication quality through the Internet.
Spectrum Exploring: To
listen to specific bands in faraway localities can be advantageous for many
organizations.
4.
Conclusion
SDR technology has various usages in relying on
radios and is progressively more widespread among all kinds of users. Nowadays,
there are many frameworks to manipulate radio signals employing only a computer
with a low-cost SDR arrangement to obtain an economical radio
receiver/transmitter framework. Free software helps to deploy SDRs that
simplify the spectrum analyses, afford interference detection, allocate
efficient frequency distribution, examine repeaters' operation while assessing
their parameters, pinpointing spectrum intruders besides typifying noise
according to the frequency bands [18-20].
5.
Conflict
of interest statement
We certify that there
is no conflict of interest with any financial organization in the subject
matter or materials discussed in this manuscript.
6.
Authors’
biography
Dr Vania
V. Estrela: B.Sc. degree from Federal
University of Rio de Janeiro (UFRJ) in Electrical and Computer Engineering
(ECE); M.Sc. in ECE from the Technological Institute of Aeronautics (ITA) and
Northwestern University, USA; and Ph.D. in ECE from the Illinois Institute of
Technology (IIT), Chicago, IL, USA. Taught at: DeVry University; State
University of Northern Rio de Janeiro (UENF), Rio de Janeiro (RJ), Brazil; and
for the West Zone State University (UEZO), RJ. Research interests include
signal/image/video processing, inverse problems, computational &
mathematical modeling, stochastic models, multimedia, electronic
instrumentation, machine learning and remote sensing. Reviewer for: IMAVIS
(Elsevier); Pattern Recognition (Elsevier); COMPELECENG (Elsevier); Measurement
(Elsevier); IET Image Processing; EURASIP Journal on Advances in Signal
Processing (JASP) (Springer); IEEE Journal of Biomedical and Health Informatics
(JBHI); Int’l J. of Electrical and Comp. Engineering (IJECE); Int’l Journal of
Ambient Computing and Intelligence (IJACI); Journal of Microwaves,
Optoelectronics and Electromagnetic Applications (JMOE); and SET Int'l J.
Broadcast Eng. (SET-IJBE). Engaged in topics such as technology transfer, STEM
education, environmental issues and digital inclusion. Member of IEEE, and ACM.
Editor of IJACI, EURASIP JASP, and SET-IJBE.
c: B.Sc. in Biomedicine from
Centro Universitario Amparense - UNIFIA, Brazil (2015). Currently, she pursues
a D.Sc. degreee from the Department of Communications (DECOM), Faculty of
Electrical and Computer Engineering (FEEC) at the State University of Campinas
(UNICAMP), Brazil, and she is a researcher at the Laboratory of Visual
Communications (LCV). She is also the Registration Chair and a reviewer for the
Brazilian Symposium on Technology (BTSym) and has expertise in the areas of
clinical analysis, histology, biomedical engineering, image processing and the
medical internet of things. She operates several types of electronic medical
equipment, has some knowledge on microscopy and some programming experience in
MATLAB. She has performed work, research experiments/projects, and internship
in municipal hospitals.
Dr
Abdeldjalil Khelassi: is an Associate Professor
at Tlemcen University, Algeria. He obtained his Doctor in Science (2013),
Magister (2008) and Engineer (2004) in Computer Sciences from the Department of
Computer Science at Tlemcen University. His research interest includes
cognitive systems, knowledge-based systems, case-based reasoning, distributed
reasoning, fuzzy sets theory and health science. He is the editor manager of
Medical Technologies Journal and associate editor at Electronic Physician
Journal.
Yuzo Iano: B.Sc., M.Sc., and Ph.D. degrees (1986) in Electrical Eng. at UNICAMP,
Brazil. He has been working in the technological production field, with 1
patent granted, 8 filed patent applications and 36 projects completed with
research and development agencies. He has supervised 29 doctoral theses, 49
master’s dissertations, 74 undergraduate and 48 scientific initiation works. He
has participated in more than 100 master’s examination boards, 50 doctoral
degrees, author of 2 books and more than 250 published articles. He is
currently a professor at UNICAMP, Editor-in-Chief the SET International Journal
of Broadcast Engineering and General Chair of the Brazilian Symposium on
Technology (BTSym). He has experience in Electrical Engineering, with knowledge
in Telecommunications, Electronics and Information Technology, mainly in the
field of audio-visual communications and multimedia.
Navid
Razmjooy: B.Sc. by the Ardabil
branch of IAU University/Iran (2007), M.Sc. from the Isfahan branch of IAU
University/Iran with honor in Mechatronics Engineering (2011), Ph.D. in Control
Engineering (Electrical Engineering) from the Tafresh University/Iran (2018).
Research opportunity at the Amirkabir University of Technology (2017-2018). He
is working in the following subjects: Control, interval analysis, Optimization,
Image Processing, Machine Vision, Soft Computing, Data Mining, Evolutionary
Algorithms, and System Control. He is a senior member of IEEE/USA and YRC in
the IAU/Iran. He published more than 75 papers and 3 books in English and Farsi
in peer-reviewed journals and conferences and is now a reviewer in the national
and international journals and conferences.
7.
References
[1] Fahmy, H., Mahmoud, A. (2016). Wireless Sensor Networks: Concepts,
Applications, Experimentation, and Analysis. Springer. ISBN 9789811004124
https://doi.org/10.1007/978-981-10-0412-4
[2] Khssibi, S., Idoudi, H., Van Den Bossche, A., Saidane, L. A.
(2013). Presentation and analysis of a new technology for low-power wireless
sensor network. International Journal of Digital Information and Wireless
Communications. 3 (1): 75-86
[3] Mukhopadhyay, S.C. (2014). Wearable sensors for human activity
monitoring: A review, IEEE Sensors Journal, vol. 15 (3), pp. 1321-1330, Dec.
2014. DOI: 10.1109/JSEN.2014.2370945.
https://doi.org/10.1109/JSEN.2014.2370945
[4] Fang, J., & Lu, I. (2015). Efficient channel access
scheme for multiuser parallel transmission under channel bonding in IEEE
802.11ac. IET Communications, 9, 1591-1597.
https://doi.org/10.1049/iet-com.2014.1223
[5] Huo, H., Xu, Y., Yan, H., Mubeen, S. &
Zhang, H. (2009). An elderly health care system using wireless sensor networks
at home, in 3rd Int'l Conference on Sensor Technologies and Applications, pp.
158-163, 2009. DOI: 10.1109/SENSORCOMM.2009.32.
https://doi.org/10.1109/SENSORCOMM.2009.32
PMid:19542014 PMCid:PMC2728297
[6] Weghorn, H. (2015). Efforts in developing android smartphone
sports and healthcare apps based on Bluetooth low energy and ANT+ communication
standards, in 15th International Conference on Innovations for Community
Services (I4CS), pp. 1-7. DOI: 10.1109/I4CS.2015.7294494.
https://doi.org/10.1109/I4CS.2015.7294494
[7] Khan, H., Dowling, B., Martin, K. M. (2018). Highly Efficient
Privacy-Preserving Key Agreement for Wireless Body Area Networks. 2018 17th
IEEE Int'l Conf. on Trust, Security and Privacy in Comp. and Communications/
12th IEEE Int'l Conf. on Big Data Science and Eng.
(TrustCom/BigDataSE). IEEE.
DOI:10.1109/trustcom/bigdatase.2018.00149. ISBN
9781538643884.
https://doi.org/10.1109/TrustCom/BigDataSE.2018.00149
[8] Machado-Fernández, J. R. (2015). Software defined Radio: Basic
principles and applications. Revista Facultad de Ingeniería, 24(38),
79-96.
https://doi.org/10.19053/01211129.3160
[9] Sastoque-Caro, M. A., Puerto-Leguizamón,
G.A., & C. A. Suárez-Fajardo, C.A. (2017). Opportunities to implement software defined radio in network
sensors, Rev. Fac. Ing., vol. 26 (45), pp. 137-148.
https://doi.org/10.19053/01211129.v26.n45.2017.6422
[10] Farahani, B., Firouzi, F., Chang, V. I., Badaroglu, M., Constant,
N., & Mankodiya, K. (2018). Towards fog-driven IoT eHealth: Promises and
challenges of IoT in medicine and healthcare. Future Generation Comp. Syst. 78,
pp. 659-676.
https://doi.org/10.1016/j.future.2017.04.036
[11] Sodagari, S., Bozorgchami, B., & Aghvami, H. (2018).Technologies
and challenges for cognitive radio enabled medical wireless body area networks.
IEEE Access, 6, pp. 29567-29586. https://doi.org/10.1109/ACCESS.2018.2843259
[12] Estrela, V.V., Saotome, O., Loschi, H.J.,
Hemanth, J., Farfan, W.S., Aroma, J., Saravanan, C., Grata, E.G.H. (2018). Emergency response
cyber-physical framework for landslide avoidance with sustainable electronics. Technologies,
6, 42. DOI: 10.3390/technologies6020042 https://doi.org/10.3390/technologies6020042
[13] Estrela, V.V., Monteiro, A.C., França, R.P.,
Iano, Y., Khelassi, A., & Razmjooy, N. (2018). Health 4.0 as an Application of Industry 4.0 in Healthcare
Services and Management. Medical Journal Technologies , v. 2, p. 1. DOI:
10.26415/2572-004X-vol2iss1p262-276
[14] Razmjooy, N., Khalilpour, M., Estrela, V. V., & Hermes J. Loschi.
World Cup optimization algorithm: an application for optimal control of pitch
angle in hybrid renewable PV/wind energy system (2019). In:
Marcela Quiroz, Adriana Lara, Yazmin Maldonado, Leonardo Trujillo and Oliver
Schuetze. (eds) NEO 2018: Numerical and
Evolutionary Optimization.
[15] Wang, J., Han, K., Alexandridis, A., Zilic, Z., Pang, Y., Wu, W.,
Din, S., & Jeon, G. (2018). A novel security scheme for body area networks
compatible with smart vehicles. Computer Networks, 143, 74-81.
https://doi.org/10.1016/j.comnet.2018.07.005
[16] Ashtari, S., Tofigh, F., Abolhasan, M., Lipman, J., & Ni, W.
(2019). Efficient Cellular Base Stations Sleep Mode Control Using Image
Matching. 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring), 1-7.
https://doi.org/10.1109/VTCSpring.2019.8746343
[17] He, X., Wang, K., Huang, H., Miyazaki, T., Wang, Y., & Guo, S.
(2018). Green Resource Allocation based on Deep Reinforcement Learning in
Content-Centric IoT. https://doi.org/10.1109/TETC.2018.2805718
[18] He, Y., Liang, C., Yu, F.R., Zhao, N., & Yin, H. (2017).
Optimization of cache-enabled opportunistic interference alignment wireless
networks: A big data deep reinforcement learning approach. 2017 IEEE
International Conference on Communications (ICC), 1-6. https://doi.org/10.1109/ICC.2017.7996388
[19] Wu, F., Wu, T., & Yuce, M.R. (2019). Design and implementation of a
wearable sensor network system for IoT-connected safety and health
applications. 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 87-90.
https://doi.org/10.1109/WF-IoT.2019.8767280
[20] Ali, M., & Nam, H. (2019). Optimization of spectrum utilization
in cooperative spectrum sensing. Sensors.
https://doi.org/10.3390/s19081922
PMCid:PMC6515306