K-Nearest Neighbor (kNN) algorithm is one of the simplest and most flexible and effective classification algorithms,
which has been widely used in many fields. Using the multi-band samples extracted from large surveys
of SDSS DR7 and UKIDSS DR3, we investigate the performance of kNN with different combinations of colors to
select quasar candidates. The color histograms of quasars and stars is helpful to select the optimal input pattern
for the classifier of kNN. The best input pattern is (u-g, g-r, r-i, i-z, z-Y, Y-J, J-H, H-K, Y-K, g-z).
In our case, the performance of kNN is assessed by different performance metrics, which indicate kNN has rather
high performance for discriminating quasars from stars. As a result, kNN is an applicable and effective method
to select quasar candidates for large sky survey projects.
We present a comparative study of implementation of supervised classification algorithms on classification of
celestial objects. Three different algorithms including Linear Discriminant Analysis (LDA), K-Dimensional Tree
(KD-tree), Support Vector Machines (SVMs) are used for classification of pointed sources from the Sloan Digital
Sky Survey (SDSS) Data Release Seven. All of them have been applied and tested on the SDSS photometric
data which are filtered by stringent conditions to make them play the best performance. Each of six performance
metrics of SVMs can achieve very high performance (99.00%). The performances of KD-tree are also very good
since six metrics are over 97.00%. Although five metrics are more than 90.00%, the performances of LDA
are relatively poor because the accuracy of positive prediction only reaches 85.98%. Moreover, we discuss what
input pattern is the best combination of different parameters for the effectiveness of these methods, respectively.
We introduce an automated method called Support Vector Machines (SVMs) for quasar selection in order to
compile an input catalogue for the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST)
and improve the efficiency of its 4000 fibers. The data are adopted from the Sloan Digital Sky Survey (SDSS)
Data Release Seven (DR7) which is the latest world release now. We carefully study the discrimination of
quasars from stars by finding the hyperplane in high-dimensional space of colors with different combinations
of model parameters in SVMs and give a clear way to find the optimal combination (C-+ = 2, C+- = 2,
kernel = RBF, gamma = 3.2). Furthermore, we investigate the performances of SVMs for the sake of
predicting the photometric redshifts of quasar candidates and get optimal model parameters of (w = 0.001,
C-+ = 1, C+- = 2, kernel = RBF, gamma = 7.5) for SVMs. Finally, the experimental results show that the
precision and the recall of SVMs for separating quasars from stars both can be over 95%. Using the optimal
model parameters, we estimate the photometric redshifts of 39353 identified quasars, and find that 72.99% of
them are consistent with the spectroscopic redshifts within |▵z| < 0.2. This approach is effective and applicable
for our problem.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.