|
|
| JDZL7310 | Advanced Classification Algorithms | 3+0+0 | ECTS:7.5 | | Year / Semester | Spring Semester | | Level of Course | Third Cycle | | Status | Elective | | Department | DEPARTMENT of GEOMATICS ENGINEERING | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 3 hours of lectures per week | | Lecturer | Doç. Dr. Esra TUNÇ GÖRMÜŞ | | Co-Lecturer | | | Language of instruction | | | Professional practise ( internship ) | None | | | | The aim of the course: | | This lecture aims at explaining the mathematical models and theories of the latest advanced and most popular classification algorithms for classification of remotely sensed images obtained from satellites. |
| Programme Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | PO - 1 : | Classify the satellite images and produce thematic maps | 1,2,5 | 1,3, | | PO - 2 : | Learn the theoretical backgrounds of the latest and most accurate classification algorithms | 1,2 | 1, | | PO - 3 : | Learn to interpret the Matlab scripts of the classification algorithms and modify them when needed. | 5,6 | 1,3, | | PO - 4 : | Learn how to conduct accuracy assessment for classification results | 1,2 | 1,3, | | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), PO : Learning Outcome | | |
| This lecture includes the theories of advanced classification algorithms and implementations of these algorithms with Matlab scripts and software such as Erdas Imagine, Envi and Ecognition. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Introduction to classification. Concepts of pixel-based and object-based classification algorithms. Concepts of supervised and unsupervised classification. Concepts of parametric and nonparametric classification. | | | Week 2 | Concepts of digital image, pixel, band, multispectral image and hyper spectral image. Concepts of multispectral image classification and the uses of classification outputs. | | | Week 3 | Unsupervised classification. K-means and ISODATA algorithms | | | Week 4 | Supervised classification | | | Week 5 | Classical classification algorithms: Nearest neighbour, parallelpiped and maximum likelihood classification algorithms | | | Week 6 | Concept of object-based classification. Multiresolution segmentation, nearest neighbour classification algorithm | | | Week 7 | Decision trees | | | Week 8 | Neural Networks | | | Week 9 | Mid-term exam | | | Week 10 | Machine learning and ensamble classification algorithms | | | Week 11 | Bagging and boosting methods | | | Week 12 | Random forest classification algorithm | | | Week 13 | Support vector machines | | | Week 14 | Post-classification accuracy analysis | | | Week 15 | Post-classification accuracy analysis | | | Week 16 | Final exam | | | |
| 1 | John A. & Richards, 2013; Remote Sensing Digital Image Analysis: An Introduction (Fifth Edition), Springer | | | 2 | Liu, J., G. & Mason, P. 2009; Essential Image Processing and GIS for Remote Sensing. Wiley-Blackwell. | | | 3 | Mather, P. M. 2004; Computer Processing of Remotely-Sensed Images: An Introduction (Third Edition). Wiley. | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Mid-term exam | 8 | | 1 | 30 | | Homework/Assignment/Term-paper | 12 | | | 20 | | End-of-term exam | 16 | | 1 | 50 | | |
| Student Work Load and its Distribution | | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | | Yüz yüze eğitim | 3 | 14 | 42 | | Sınıf dışı çalışma | 3 | 9 | 27 | | Arasınav için hazırlık | 8 | 2 | 16 | | Arasınav | 1 | 1 | 1 | | Ödev | 4 | 4 | 16 | | Dönem sonu sınavı için hazırlık | 8 | 2 | 16 | | Dönem sonu sınavı | 1 | 1 | 1 | | Diğer 1 | 3 | 14 | 42 | | Total work load | | | 161 |
|