GMT741 - ADVANCED CLASSIFICATION TECHNIQUES IN REMOTE SENS.

Course Name Code Semester Theory
(hours/week)		 Application
(hours/week)		 Credit ECTS
ADVANCED CLASSIFICATION TECHNIQUES IN REMOTE SENS. GMT741 Any Semester/Year 3 0 3 10
PrequisitesNone
Course languageEnglish
Course typeElective 
Mode of DeliveryFace-to-Face 
Learning and teaching strategiesLecture
Discussion
Question and Answer
Preparing and/or Presenting Reports
Problem Solving
 
Instructor (s)Prof.Dr.Ali ÖZGÃœN OK 
Course objectiveThe objective of the course is to teach students the advanced classification techniques in used remote sensing. 
Learning outcomes
  1. The students who successfully completed this course:
  2. apply classification methods with artificial neural networks,
  3. apply classification techniques based on fuzzy logic,
  4. apply support vector machines classification techniques,
  5. classify images using decision tree classification,
  6. classify images using random forest classification techniques,
  7. classify images using segment-based classification techniques,
  8. classify images using object-based techniques.
Course ContentMethods based on artificial neural networks. Methods based on fuzzy logic. Support vector machines (SVM) classification. Decision tree classification. Random forests classification. Image segmentation. Segment-based classification. Object-based classification. Use of texture and context. Use of ancillary data. 
ReferencesClassification Methods for Remotely Sensed Data, Tso, B. and Mather, P.M., Taylor and Francis, 2001. 

Course outline weekly

WeeksTopics
Week 1Methods based on artificial neural networks
Week 2Methods based on artificial neural networks
Week 3Methods based on fuzzy logic
Week 4Methods based on fuzzy logic
Week 5Support vector machines (SVM) classification
Week 6Decision tree classification
Week 7Random forests classification
Week 8Midterm Exam
Week 9Image segmentation
Week 10Image segmentation
Week 11Segment-based classification
Week 12Object-based classification
Week 13Use of texture and context
Week 14Use of ancillary data
Week 15Preparation for the final exam
Week 16Final Exam

Assesment methods

Course activitiesNumberPercentage
Attendance00
Laboratory00
Application00
Field activities00
Specific practical training00
Assignments410
Presentation00
Project110
Seminar00
Midterms130
Final exam150
Total100
Percentage of semester activities contributing grade succes050
Percentage of final exam contributing grade succes050
Total100

WORKLOAD AND ECTS CALCULATION

Activities Number Duration (hour) Total Work Load
Course Duration (x14) 14 3 42
Laboratory 0 0 0
Application000
Specific practical training000
Field activities000
Study Hours Out of Class (Preliminary work, reinforcement, ect)148112
Presentation / Seminar Preparation000
Project14040
Homework assignment41040
Midterms (Study duration)12525
Final Exam (Study duration) 13030
Total Workload35116289

Matrix Of The Course Learning Outcomes Versus Program Outcomes

D.9. Key Learning OutcomesContrubition level*
12345
1. Advances contemporary knowledge in the field of geomatics engineering based on novel thinking and research.    X
2. Possesses creative and critical thinking, problem solving, and decision making abilities.  X  
3. Conducts a thorough novel research from scratch independently.    X
4. Acquires interdisciplinary knowledge of common terminology and joint working culture.  X  
5. Cooperates with national and international scientific research groups.    X
6. Attains the capacity to publish an international peer-reviewed journal manuscript.    X 
7. Maintains ethical responsibility.    X 
8. Obtains the skills to teach undergraduate and graduate level courses offered in geomatics engineering.   X 
9. Conducts verbal-written communication, surveys the literature, and prepares thesis in advanced level English.   X 

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest