YAŞAR UNIVERSITY FACULTY OF ENGINEERING SOFTWARE ENGINEERING DEPARTMENT COURSE SYLLABUS Course Title Soft Computing Course Code Semester SENG368 Spring Course Hour/Week Theory 3 Practice 0 Yaşar Credit ECTS 3 5 Course Type 1. Compulsory Courses 1.1. Programme Compulsory Courses 1.2. University Compulsory Courses (UFND) 1.3. YÖK (Higher Education Council) Compulsory Courses 2. Elective Courses 2.1. Program Elective Courses X 2.2. University Elective Courses 3. Prerequisites Courses 3.1. Compulsory Prerequisites Courses 3.2. Elective Prerequisites Courses Language of Instruction English Level of Course Undergraduate Degree (First Cycle) Prerequisites Course(s) (compulsory) N/A Special Pre-Conditions of the Course (recommended) N/A Course Coordinator Assist. Prof. Dr. Mete Eminağaoğlu Mail: mete.eminagaoglu@yasar.edu.tr Web: Course Instructor(s) Assist. Prof. Dr. Mete Eminağaoğlu Mail: mete.eminagaoglu@yasar.edu.tr Web: Course Assistant(s)/Tutor (s) - Mail: Web:- Aim(s) of the Course To develop skills, knowledge and basic experience for all of the computer and software engineering students in order to design, implement and use several artificial intelligence methodologies, techniques, algorithms and related systems (such as machine learning, fuzzy logic, data mining, data analysis, evolutionary computation, optimization) in all kinds of computer and software projects such as senior projects, research projects, other IT projects and in their business life. 1. Ability to develop construction of new data processing models and software projects with simplicity, robustness and low-cost. 2. Gain knowledge about methodologies to avoid demand of over-precision in computations, expert systems, decision support systems, problem-solving and software applications. Learning Outcomes of the Course 3. Gain skills to implement several implementations, methods and models of artificial intelligence in software projects. 4. Gain knowledge and skills to analyze, prepare, cleanse, evaluate and validate mission-critical data in business applications. 5. Ability to derive solutions for complex linear and/or non-linear business and industrial problems by the aid of fuzzy logic, optimization algorithms, machine learning predictions and classifications. Course Content NP-hard and NP-complete problems. Optimization techniques and methodologies, linear and non-linear models, genetic algorithms, evolutionary computational models, multi-valued logic and predicate logic, fuzzy logic and fuzzy theory, implementation of fuzzy logic models, data mining and machine learning, data preprocessing, exploratory data analysis, prediction and estimation, classification, Bayesian Probability, Bayesian classifiers and estimators, neural networks, clustering, association rules, model evaluation techniques. COURSE OUTLINE/SCHEDULE (Weekly) Week Preliminary Preparation Methodology and Implementation (theory, practice, assignment, etc.) - theory Topics 1 Introduction to soft computing; basic concepts of artificial intelligence, decision support systems, expert systems, uncertainty and game theory in business and real life. NP-complete and NP-hard problems. 2 Propositional logic and predicate logic, Boolean logic, Students must have done the multi-valued logic. Basic models and examples of 3exercises given in the previous valued logic. course theory 3 Introduction to fuzzy logic concepts. Crisp set and fuzzy set. Basic concepts of fuzzy sets, membership functions. Basic operations on fuzzy sets, Properties of fuzzy sets, fuzzy relations. theory 4 Formulation and parameterization of fuzzy rules and Students must have done the fuzzy reasoning. Fuzzy relations and fuzzy if-then exercises given in the previous rules. Fuzzy functions and their applications by simple course examples. theory , practice 5 Basic concepts in data mining and machine learning. Students must have done the Binary and multi-classification, numerical prediction, exercises given in the previous clustering and association algorithms. Supervised and course unsupervised learning. theory 6 Data analysis, preparation and cleansing in machine learning. Different evaluation methods in machine learning. Over-fitting, cross-validation and ROC curves. Students must have done the exercises given in the previous course theory , practice 7 Bayesian probability. Naïve Bayes, Bayesian networks Students must have done the and other Bayesian classifiers and some basic exercises given in the previous numerical prediction methods in Bayesian learning. course theory , practice 8 Midterm Exam Students must study before the exam - 9 Basic concepts in artificial neural networks. Single layer perceptron and multi-layer perceptron models. Back propagation neural networks. Students must have done the exercises given in the previous course theory 10 Applications and implementations of several neural network algorithms and their evaluation methods with examples. Support vector machines with implementations and examples. Students must have done the exercises given in the previous course theory , practice 11 Decision trees and several decision tree algorithms and their implementations for classification and numerical prediction. Students must have done the exercises given in the previous course theory , practice 12 Introduction to genetic algorithms. Survival of the fittest, fitness computations, crossover, mutation, reproduction. Rank method-rank space method. Students must have done the exercises given in the previous course theory Students must have done the exercises given in the previous course 13 Random search, greedy search and downhill search Students must have done the methods and algorithms. Implementations of genetic exercises given in the previous algorithms for optimization concepts and problems. course Encoding and fitness concepts in genetic algorithms. theory , practice 14 Other evolutionary soft computing methodologies and their implementations– Part 1: Ant colony optimization Students must have done the exercises given in the previous course theory 15 Other evolutionary soft computing methodologies and their implementations– Part 2: Artificial bee colony and swarm intelligence Students must have done the exercises given in the previous course theory 16 Final Exam Students must study before the exam - Required Course Material (s) /Reading(s)/Text Book (s) Eva Volna, Introduction to Soft Computing, ISBN-13: 9788740303919, Bookboon, 2013. S. N. Sivanandam & S. N. Deepa, Principles of Soft Computing, Wiley India Pvt. Limited, 2007. Recommended Course Material (s)/Reading(s)/Other Daniel T. Larose, Discovering Knowledge in Data: An Introduction to Data Mining, John Wiley & Sons, Inc., 2005. Ian H. Witten , Eibe Frank , Mark A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, 3rd Edition, The Morgan Kaufmann Series, 2011. Lotfi A. Zadeh & Ronald R. Yager, An Introduction to Fuzzy Logic Applications in Intelligent Systems, Springer, 2012. ASSESSMENT Semester Activities/ Studies NUMBER WEIGHT in % 1 40 Quiz 3 30 Assignment (s) 2 30 Mid- Term Attendance Project Laboratory Field Studies (Technical Visits) Presentation/ Seminar Practice (Laboratory, Virtual Court, Studio Studies etc.) Other (Placement/Internship etc.) TOTAL 100 Contribution of Semester Activities/Studies to the Final Grade 60 Contribution of Final Examination/Final Project/ Dissertation to the Final Grade 40 TOTAL . 100 CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME OUTCOMES No Programme Outcomes Level of Contribution (1lowest/ 5highest) 1 1 2 3 4 To identify, formulate, and solve software engineering problems by applying knowledge of mathematics, science and engineering 2 To design and conduct scientific and engineering experiments and to analyze and interpret data 3 To identify, formulate and validate user needs and system requirements 5 4 To develop large and complex software systems as applying software engineering principles and techniques 5 To use modern engineering techniques for analysis and design 6 To recognize the importance of abstraction and modeling 7 To use efficient software engineering background for being able to follow up most recent developments in the field and other segments of life by utilizing lifelong learning principles To collect data regarding special domain knowledge in other fields and disciplines beyond the 8 computing discipline for the purposes of supporting software development in specific domains of application 9 To demonstrate efficient communication skills in written and oral forms by making use of language competences and effectively work both individually and as a team member 10 To adopt the ethical and professional responsibility and use them in professional life ECTS /STUDENT WORKLOAD ACTIVITIES NUMBER UNIT HOUR TOTAL (WORKLOAD) 14 Week 3 42 2 28 Number 8 16 Course Teaching Hour (14 weeks* total course hours) Preliminary Preparation and finalizing of course notes, further self- study 14 Assignment (s) 2 Week Presentation/ Seminars - - - Quiz and Preparation for the Quiz 3 Number 3 9 Mid- Term(s) 1 Number 10 10 Project (s) - - - Field Studies (Technical Visits, Investigate Visit etc.) - - - Practice (Laboratory, Virtual Court, Studio Studies etc.) - - Final Examination/ Final Project/ Dissertation and Preparation 1 Number Other (Placement/Internship etc.) - 12 - 12 - Total Workload 117 Total Workload/ 25 4.68 ECTS 5 ETHICAL RULES WITH REGARD TO THE COURSE (IF AVAILABLE) None. ASSESSMENT and EVALUATION METHODS: Final Grades and assessment criteria are determined according to the Yaşar University Associate Degree, Bachelor Degree and Graduate Degree Education and Examination Regulation. PREPARED BY Assist. Prof. Dr. Mete Eminağaoğlu UPDATED 03.05.2014; 22:00 APPROVED