Ondokuz Mayıs Üniversitesi Bilgi Paketi - Ders Kataloğu

Description of Individual Course Units

Course Unit CodeCourse Unit TitleType of CourseYearSemesterECTS
RAD612 Pattern Recognition 927001 1 1 6
Level of Course Unit
Second Cycle
Objectives of the Course
This course introduces advanced subjects of digital signal and image processing as implemented in biomedical applications. Main objective of this course is to develop the students’ mathematical, scientific, and computational skills relevant to the field of biomedical signal and image processing. In the course context, biomedical data acquisition, evaluation of the characterstics, reasons and applications of preprocessing (denoising, filtering and dimension reduction), feature extraction, modeling, clustering and classification topics will be covered.To enhance students’ computational skills, Matlab projects will be assigned to student groups based on common biomedical applications.
Name of Lecturer(s)
Yrd.Doç.Dr. Nurettin ŞENYER
Learning Outcomes
  1. Bilgisayar tabanlı teşhis ve analiz uygulamalarının ve araçlarının yaygınlaşması ile birlikte tıbbi işaret ve görüntülerin değerlendirilmesi üniversitelerde ve endüstride yaygınlık kazandırılması.
  2. Özellikle, gelişen bu disiplinlerarası alanda bilgisayar mühendisliği öğrencilerine güçlü matematiksel ve algoritmik bir altyapı sağlanması.
  3. Bununla beraber işaret ve görüntü işleme, örüntü tanıma ve makine öğrenmesi konularında bilgi kazandırılması dersin en önemli katkısı olarak görülmektedir. Böylelikle öğrencilerin bu konularda ilgi ve yeteneklerinin arttırılarak akademik ve uygulamaya yönelik çalışmalarında katkıda bulunulması amaç
Mode of Delivery
Formal Education
Prerequisites and co-requisities
None
Recommended Optional Programme Components
None
Recommended or Required Reading
John L. Semmlow, “Biosignal and Medical Image Processing”, CRC Taylor and Francis, 2008.
Kayvan Najarian, Robert Splinter, “Biomedical signal and image processing”, CRC Taylor and Francis, 2005.
Sergio Cerutti, Carlo Marchesi, “Advanced Methods of Biomedical Signal Processing”, IEEE Press Series on Biomedical Engineering, 2011.
Gustavo Camps-Valls, Jose Luis Rojo-Alvarez, Manel Martinez-Ramon, “Kernel Methods in Bioengineering, Signal and Image Processing, IGI Global, 2007.
Jae S. Lim, "Two-Dimensional Signal and Image Processing", Prentice Hall, Inc., 1990.
Eugene N. Bruce, “Biomedical Signal Processing and Signal Modeling”, John Wiley and Sons, 2001
Planned Learning Activities and Teaching Methods
Language of Instruction
Work Placement(s)
None
Course Contents
Features of biomedical signal and images Transformation methods in signal and image processing Signal and image denoising methods Signal and image filtering methods Dimension reduction methods Supervised learning methods in the signal and image processing Unsupervised learning methods in the signal and image processing Learning in high dimensional space (Kernel methods)
Weekly Detailed Course Contents
Week Theoretical Practice Laboratory
1.Acquisition of biomedical signal and images and their characteristics
2.Statistical characteristics of signals (Moments, power, information, correlation…)
3.Fundementals of digital signal processing, Sampling, Quantization
4.Transformation methods I: Fourier Transform, DFT, DFT, DCT, STFT
5.Transformation methods II: Wavelet transforms
6.Fundementals of image processing, morphological and statistical feature extraction methods
7.Signal and image filtering and denoising
8.Dimension reduction and analysis methods: Linear and nonlinear methods (PCA, LDA, ICA, Isomap, Kernel-PCA, Kernel-LDA, Laplacian Eigenmaps, Diffusion Maps)
9.Analysis of signals and images using supervised learning algorithms I (Artificial Neural Networks I)
10.Midterm
11.Analysis of signals and images using supervised learning algorithms II (Artificial Neural Networks II)
12.Analysis of signals and images using supervised learning algorithms III (Artificial Neural Networks III)
13.Analysis of signals and images using supervised learning algorithms IV (Kernel methods)
14.Analysis of signals and images using unsupervised learning algorithms I (distance measures, k-means, FCM)
15.Analysis of signals and images using unsupervised learning algorithms II
16.Final exam
Assessment Methods and Criteria
Term (or Year) Learning ActivitiesQuantityWeight (%)
Midterm Examination1100
SUM100
End Of Term (or Year) Learning ActivitiesQuantityWeight (%)
Final Examination1100
SUM100
Term (or Year) Learning Activities40
End Of Term (or Year) Learning Activities60
SUM100
Workload Calculation
ActivitiesQuantityTime(hours)Total Workload(hours)
Midterm Examination155
Final Examination155
Quiz4312
Attending Lectures12336
Self Study5420
Individual Study for Homework Problems12336
Individual Study for Mid term Examination3515
Individual Study for Final Examination3721
SUM150