D.C. Wyld et al. (Eds.): Advances in Computer Science, Eng. & Appl., AISC 166, pp. 341–351.
springerlink.com
© Springer-Verlag Berlin Heidelberg 2012
Concept Adapting Real-Time Data Stream Mining
for Health Care Applications
Dipti D. Patil, Jyoti G. Mudkanna, Dnyaneshwar Rokade, and Vijay M. Wadhai
MAEER’s MIT College Of Engineering, Pune, India,
Assistant Professor, Comp. Engg. Dept.,
dipti.dpatil@yahoo.com
Abstract. Developments in sensors, miniaturization of low-power microelectron-
ics, and wireless networks are becoming a significant opportunity for improving
the quality of health care services. Vital signals like ECG, EEG, SpO2, BP etc.
can be monitor through wireless sensor networks and analyzed with the help of
data mining techniques. These real-time signals are continuous in nature and ab-
ruptly changing hence there is a need to apply an efficient and concept adapting
real-time data stream mining techniques for taking intelligent health care deci-
sions online. Because of the high speed and huge volume data set in data streams,
the traditional classification technologies are no longer applicable. The most im-
portant criteria are to solve the real-time data streams mining problem with ‘con-
cept drift’ efficiently. This paper presents the state-of-the art in this field with
growing vitality and introduces the methods for detecting concept drift in data
stream, then gives a significant summary of existing approaches to the problem of
concept drift. The work is focused on applying these real time stream mining
algorithms on vital signals of human body in health care environment.
Keywords: Real-time data stream mining, concept-drift, vital Signal processing,
Health Care.
1 Introduction
Data streams flow in and out from a computer system continuously and with varying
update rates. They are temporally ordered, fast changing, massive, and potentially in-
finite.[1][11] It may be impossible to store an entire data stream or to scan through it
multiple times due to its tremendous volume. So there is a need of analyzing this con-
tinuous data online without the overhead of storing it on a disk.
There exists a dynamic and promising field called data stream mining and know-
ledge discovery. To acquire knowledge base from raw data, emphasis is placed on in-
novative data stream mining concepts and techniques. This paper contains the general
architecture of real-time data stream mining systems (RT-DSMS), different types of
concept adapting algorithms, and finally finding useful patterns or knowledge from
real-time data. Data streams are with the characteristics dynamic, non stationary, con-
tinuous, large volume, unstoppable, infinite.
The advanced research domain in DSM system is to handle concept drift in real-
time data. While processing the data noise, errors, unwanted data, missing values
评论0
最新资源