A Centralized Real-Time E-Healthcare System for Remote Detection and Prediction of Epileptic Seizures - E-Healthcare Systems and Wireless Communications - page 427

or spent time to understand their daily struggles
and challenges. They also often do not understand
what designers do, the design process, and the
negotiations to create a final product that is valu-
able and manufacturable.

System for detecting and predicting epileptic
seizures on Epilepsy patients in Australia utiliz-
ing wearable wireless sensors and broadband
technologies. In addition, the chapter also pro-
vides a general description of the architecture,
required features, and implementation scenarios
of the system.

CONCLUSION AND DISCUSSION

REFERENCES The role of telecom infrastructure in remote

healthcare system is becoming more and more
important. However, in order to achieve perva-
sive healthcare services, the quality and capacity
of wireless sensor and, especially, the wireless
infrastructure are critical. While there have been
various solutions for wireless and implantable
sensor devices with reliable detection, a CRESH
for remote and mobile patients has not yet been a
topic of interest. This may partly due to the lack
of co-effort between IT engineers, healthcare
specialist, and electrical engineers to form up a
complete system. Moreover, there are still many
technical and non-technical issues such as the
capacity and reliability of broadband infrastruc-
tures, especially wireless infrastructure, and other
economical factors and legal requirements which
need to be resolved and justified. In the coming
time, the deployment of a CREHS would involve
the use of wireless sensor, wireless access points,
satellite and other mobile infrastructure such as
cellular, GSM, 3G, and 4G networks. Appreciation
to the price-to-performance ratio, many issues
regarding the cost of research and development,
cost of implementation and operation, and other
technical issues such as the capacity and reli-
ability of broadband infrastructure and wireless
technologies will be resolved in a near future.
Therefore, a nearly pervasive E-healthcare system
is absolutely feasible.
In this chapter, we present the applications,
requirements, solutions, and further research
problems for a Centralized Real-time E-Healthcare

Abibullaev, B., Kim, M. S., & Seo, H. D. (2010).
Seizure detection in temporal lobe epileptic EEGs
using the best basis wavelet functions. AUG: An
epilepsy support program. PhD thesis. Journal
of Medical Systems, 34 (4), 755-765. Hawthorn,
Australia: Swinburne University of Technology.

Angus-Leppan, H., & Parsons, L. M. (2008).
Epilepsy: Epidemiology, classification and natural
history. Medicine , 36 (11), 571-578. doi:10.1016/j.
mpmed.2008.08.003

Aslan, K., Bozdemir, H., Şahin, C., Oğulata, S. N.,
& Erol, R. (2008). A radial basis function neural
network model for classification of epilepsy using
EEG signals. Journal of Medical Systems , 32 (3),
403-408. doi:10.1007/s10916-008-9145-9

Australian Bureau of Statistics (ABS). (2010,
December 21). 3201.0 - Population by age and
sex, Australian states and territories, June 2010 .
Retrieved January 15 th , 2011, from http://www.
abs.gov.au/ AUSSTATS/ abs@.nsf/ Lookup/
3201.0Main+Features1Jun% 202010?OpenDocu-
ment

Bao, F. S., Lie, D. Y.-C., & Zhang, Y. (2008). A
new approach to automated epileptic diagnosis
using EEG and probabilistic neural network. In
Proceedings of the 2008 20 th IEEE International
Conference on Tools with Artificial Intelligence
(vol. 2, pp. 482-486).