COURSE SYLLABUS

MULTI-SENSOR DATA FUSION

1	Course Title:	MULTI-SENSOR DATA FUSION
2	Course Code:	BM5140
3	Type of Course:	Optional
4	Level of Course:	Second Cycle
5	Year of Study:	1
6	Semester:	2
7	ECTS Credits Allocated:	6
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:	Undergraduate Level Probability and Statistics Knowledge
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Prof. Dr. KEMAL FİDANBOYLU
16	Course Lecturers:	-
17	Contactinformation of the Course Coordinator:	e-posta: kfidan@uludag.edu.tr Uludağ Üniversitesi, Bilgisayar Mühendisliği Bölümü Görükle Kampüsü, 16059 Nilüfer, Bursa
18	Website:
19	Objective of the Course:	To provide the students with knowledge about basic principles and applications of multi-sensor data fusion.
20	Contribution of the Course to Professional Development	Engineering Science: 85%; Engineering Design: 15%

Learning Outcomes:

1	Define multi-sensor data fusion strategies;
2	Classify different types of sensors;
3	Describe the architectures of fusion networks;
4	Explain several sensor representational formats such as spatial alignment, temporal alignment, semantic alignment and radiometric normalization;
5	Examine Bayesian inference methods;
6	Investigate different concepts of parameter estimation;
7	Explain the principles of robust parameter estimation;
8	Examine different sequential Bayesian interfaces such as recursive filters, Kalman filters, particle filters and multi-sensor multi-temporal data fusion;
9	Discuss different approaches for pattern recognition;
10	Explain the fundamentals of ensemble learning and sensor management;

22	Course Content:

Week	Theoretical	Practical
1	Introduction: Multi-sensor data fusion strategies; Formal framework; Catastrophic fusion; Organization.
2	Sensors: Smart sensors; Logical sensors; Interface file systems; Sensor observation; Sensor characteristics; Sensor model.
3	Architecture: Fusion mode; Simple Fusion networks; Network topologies.
4	Common Representation Format: Spatial temporal transformation; Geographical information system; Common representational format; Subspace methods; Multiple training sets.
5	Spatial Alignment: Image registration; Mutual information; Optical flow; Feature based image registration; Resample/Interpolation; Pairwise transformation; Uncertainity estimation; Image fusion; Mosaic images.
6	Temporal Alignment: Dynamic time warping; Dynamic programming; One sided dynamic time warping algorithm; Multiple time series.
7	Semantic Alignment: Assignment matrix; Clustering algorithm; Clustering ensembles.
8	Radiometric Normalization: Scales of measurement; Degree of similarity scales; Radiometric normalization functions; Binarization; Parametric normalization functions; Fuzzy normalization functions; Ranking; Conversion to probabilities.
9	Bayesian Inference: Bayesian analysis; Probability model; A posteriori distribution; Guassian mixture model; Model selection; Markov chain Monte Carlo computation.
10	Parameter Estimation: Bayesian curve fitting; Maximum likelihood; Least squares; Linear Guassian model; Generalized Millman formula.
11	Robust Statistics: Outliers; Robust parameter estimation; Classical robust estimators; Robust subspace techniques; Robust subspace in computer vision.
12	Robust Statistics: Outliers; Robust parameter estimation; Classical robust estimators; Robust subspace techniques; Robust subspace in computer vision.
13	Bayesian Decision Theory: Pattern recognition; Naive Bayes’ classifer; Variants; Multiple Naive Bayes’ classifiers; Error estimation; Pairwise Naive Bayes’ classifiers.
14	Ensemble Learning: Bayesian framework; Empirical framework; Diversity tecniques; Diversity measures; Classifier types; Combination strategies; Simple combiners; Meta-learners; Boosting. Sensor Management: Hierarchical Classification; Sensor management techiques.

23	Textbooks, References and/or Other Materials:	H.B. Mitchel, Data Fusion: Concepts and Ideas, 2nd Ed., Springer-Verlag 2012.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	1	20
Quiz	0	0
Homeworks, Performances	1	20
Final Exam	1	60
Total	3	100
Contribution of Term (Year) Learning Activities to Success Grade		40
Contribution of Final Exam to Success Grade		60
Total		100
Measurement and Evaluation Techniques Used in the Course	Classical problem-solving ability will be measured in midterm and final exams. The project will include research, simulation, report writing and presentation on a subject related to the course content.
Information	All exam and project evaluations will be made over 100. It will then be multiplied by the respective contribution percentage and the overall course grade will be obtained out of 100.

ECTS / WORK LOAD TABLE

Activites	NUMBER	TIME [Hour]	Total WorkLoad [Hour]
Theoretical	14	3	42
Practicals/Labs	0	0	0
Self Study and Preparation	14	5	70
Homeworks, Performances	1	33	33
Projects	0	0	0
Field Studies	0	0	0
Midtermexams	1	15	15
Others	0	0	0
Final Exams	1	20	20
Total WorkLoad			180
Total workload/ 30 hr			6
ECTS Credit of the Course			6

CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

	PQ1	PQ2	PQ3	PQ4	PQ5	PQ6
LO1	5	3	3	2	2	2
LO2	5	4	4	2	2	2
LO3	5	4	4	2	2	2
LO4	5	4	4	2	2	2
LO5	5	4	4	2	2	2
LO6	5	4	4	2	2	2
LO7	5	4	4	2	2	2
LO8	5	4	4	2	2	2
LO9	5	4	4	2	2	2
LO10	5	4	4	2	2	2

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High