COMPULSORY TO ALL BRANCH J4PHDRM: RESEARCH METHODOLOGY Module 1 Meaning, Objectives and Characteristics of research - Research methods Vs Methodology - Types of research - Descriptive Vs. Analytical, Applied Vs. Fundamental, Quantitative Vs. Qualitative, Conceptual Vs, Empirical - Research process - Criteria of good research - Developing a research plan. Module 2: Defining the research problem - Selecting the problem - Necessity of defining the problem - Techniques involved in defining the problem - Importance of literature review in defining a problem - Survey of literature - Primary and secondary sources - Reviews, treatise, monographs- patents - web as a source - searching the web - Identifying gap areas from literature review - Development of working hypothesis. Module 3: Research design and methods ~ Research design ~ Basic Principles- Need of research design — Features of good design ~ Important concepts relating to research design ~ Observation and Facts, Laws and Theories. Prediction and explanation, Induction, Deduction, Development of Models - Developing a research plan - Exploration, Description, Diagnosis, and Experimentation - Determining experimental and sample designs. Module 4: ‘Sampling design - Steps in sampling design - Characteristics of a good sample design - Types of sample designs - Measurement and scaling techniques - Methods of data collection - Collection of primary data - Data collection instruments Module 5: Testing of hypotheses - Basic concepts - Procedure for hypotheses testing flow diagram for hypotheses testing - Data analysis with Statistical Packages ~ Correlation and Regression - Important parametric test - Chi-square test - Analysis of variance and Covariance Module 6: IPRs- Invention and Creativity. Intellectual Property-Importance and Protection of Intellectual Property Rights (IPRs) A brief summary of: Patents, Copyrights, Trademarks, IndustrialDesigns- Integrated Circuits-Geographical Indications-Establishment of WIPO-Application and Procedures Module 7: Interpretation and report writing - Techniques of interpretation - Structure and components of scientific reports - Different steps in the preparation - Layout, structure and l = Illustrations and tables - Types of report - Technical reports and thesis report wage of the REFERENCES: L 2 10. Garg, B.L., Karadia, R.. Agarwal, F. and Agarwal, U.K.. 2002, An introduction to Research Methodology. RBSA Publishers. Kothari, C.R. 1990, Research Methodology: Methods and Techniques. New Age International. 418p. Anderson, T, W., An Introduction to Multivariate Statistical Analysis, Wiley Eastern Pvt., Ltd., New Delhi Sinha, $.C. and Dhiman, A-K., 2002, Research Methodology, Ess Ess Publications. 2 volumes. Trochim, W.M-K., 2005. Research Methods: the concise knowledge base, Atomic Dog Publishing. 270p, Day, R.A., 1992,How to Write and Publish a Scientific Paper, Cambridge University Press. Fink, A., 2009, Conducting Research Literature Reviews: From the Internet to Paper. Sage Publications Coley. S.M. end Scheinberg, C. A.. 1990, "Proposal Writing", Sage Publications. Intellectual Property Rights in the Global Economy: Keith Eugene Maskus, Institute for International Economics, Washington, DC. 2000 Subbarau NR-Handbook on Intellectual Property Law and Practice-S Viswanathan Printers and Publishing Private Limited.1998ADVANCED MEDICAL IMAGE PROCESSING Subject Code IA Marks: 20 Hrs/Week & Credits Exam Marks :80 Total Lecture Hours Exam Hours: 03 Course Learning Objectives: 1, To give an idea of the state of the art in image processing by examining some of the principal arzas in which it is applied. 2. To discuss briefly the principal approaches used in digital image processing, 3. To give an overview of the components contained in a typical general purpose image processing system. 4. To understand the state of the art in enhancement techniques and how they operate on digital images. Give the students a taste of the applications of the theories taught in the subject. This will be achieved through the project and some selected lab sessions. 6. Give the students a useful skill base that would allow them to carry out farther study should they be interested and to work in the field. Fundamentals: Introduction, Fundamental steps in DIP, A simple image formation model, representing digital images, Spatial & Gray level resolution, Basic relationship between pixels. Image Enhancement: Point operations, Spatial averaging, Median filtering, Spatial low pass, high pass and band pass filtering, Histogram equalization, Transform operations. Image Compression: Huffinan coding, DFT. DCT. Wavelet coding & JPEG standard. Image segmentation: Detection of discontinuities, Edge linking and Boundary detection by local processing & global processing using Hough transform, Region based segmentation Image Representation and Description: Representation — Chain codes. polygonal approximations, signatures, boundary segments, skeletons, Boundary descriptors — Some simple descriptors, Shape numbers, Fourier descriptors, statistical moments, Regional descriptors — Some simple descriptors. topological descriptors. texture. Morphological Image Processing : Basie concepts of set theory, Logical operations involving binary images, Dilation and erosion, Opening and closing. The hit-or-miss transformation, Basic morphological algorithms 10 Hrs 10 Hrs 10 Hrs 10 Hrs 10 HrsCourse Outcomes: 1. Have an appreciation of the fundamentals of Digital image processing including the topics of filtering. transforms. and morphology. and image analysis and compression. Be able to implement basic image processing algorithms in MATLAB. 3. Evaluate and synthesize the data coding and compression techniques on images. 4. Implement and evaluate algorithms for image analysis based on segmentation, shape & texture,registration, recognition and classification. 5. Proficiently use MATLAB for implementing image processing algorithms of segmentation.registration, object recognition and classification. 6. Have a skill base necessary to further explore advanced topics of Digital Image Processing. 7. Be in a position to make a positive professional contribution in the field of Digital Image Processing. nv REFERENCE BOOKS: 1. 5 “Digital Image Processing” Rafael C. Gonzalez & Richard E. Woods, SecondEdition, Pearson Education Inc . “Fundamentals of Digital Image Processing” Anil K. Jain. Prentice Hall of India “Image Processing. Analysis and Machine Vision” Milan Sonka, Vaclav Hlavac & Roger Boyle. 2™ Edition. “Digital Image Processing” Rafael C. Gonzalez & Richard FE. Woods, First Edition. Pearson Education Inc “Practical Algorithms for Image Analysis” Description, Examples & Codes by Michael Seul, Lawrence O’Gorman, Michel J.Sammon, Cambridge University Press. “Biomedical Imaging visualization and analysis” Richard A Robb. John Wiley& sons, Inc. publication.MACHINE LEARNING TECHNIQUES [As per Choice Based Credit System (CBCS) scheme] (Effective from the academic year 2016-2017) SEMESTER - IV Subject Code T6SCS4U16SIT424__ | TA Marks 20 ‘Number of Lecture Hours) Week 4 Exam Marks | 80 Total Number of Lecture Hours 30. Exam Hours, 03 CREDITS — 04 Course objectives: This course will enable students to Explain basic concepts of learning and decision trees. © Compare and contrast neural networks and genetic algorithms © Apply the Bayesian techniques and instant based learning + Examine analytical learning and reinforced learning ‘Module -1 Teaching Hours INTRODUCTION, CONCEPT LEARNING AND DECISION TREES 10Hours Leaming Problems - Designing Learning systems. Perspectives and Issues ~ Concept Leaming ~ Version Spaces and Candidate Elimination Algorithm ~ Inductive bias — Decision Tree learning — Representation — Algorithm ~ Heuristic Space Search ‘Module -2 NEURAL NETWORKS AND GENETIC ALGORITHMS: Neural Network | 10 Hours Representation — Problems ~ Perceptrons ~ Multilayer Networks and Back Propagation Algorithms — Advanced Topics — Genetic Algorithms — Hypothesis Space Search — Genetic Programming ~ Models of Evolution and Leaming. Module - 3 BAYESIAN AND COMPUTATIONAL LEARNINGL Bayes Theorem — Concept | 10 Hours Leaning — Maximun Likelihood — Minimum Description Length Principle ~ BayesOptimal Classifier — Gibbs Algorithm — Naive Bayes Classifier Bayesian Belief Network — EM Algorithm — Probably Learning ~ Sample Complexity for Finite and Infinite Hypothesis Spaces ~ Mistake Bound Model. ‘Module-4 INSTANT BASED LEARNING AND LEARNING SET OF RULES: K- Nearest | 10 Hours Neighbor Leaming - Locally Weighted Regression — Radial Basis Functions -Case- Based Reasoning — Sequential Covering Algorithms ~ Learning Rule Sets ~ Learning First Order Rules ~ Learning Sets of First Order Rules ~ Induction as Inverted Dedetion = Inverting Resolution ‘Module-5 ANALYTICAL LEARNING AND REINFORCED LEARNING: Perfect Domain [10 Theories ~ Explanation Based Learning - Induetive-Analytical Approaches - FOCL | Hours Algorithm — Reinforcement Leaming — Task — Q-Leaming — Temporal Difference Leaming ‘Course outcomes: ‘On Completion of the course, the students will be able to ‘+ Choose the learning techniques with this basie knowledge. ‘+ Apply effectively neural networks and genetic algorithms for appropriate applications. ‘+ Apply bayesian techniques and derive effectively learning rules. © Choose and differentiate reinforcement and analytical learning techniques ‘Question paper pattern: ‘The question paper vill have ten questions. There will be 2 questions from each module, Each question will have questions covering all the topics under a module. The students will have to auswer 5 full questions, selecting one full question from esch module, Text Books: 1._Tom M. Mitchell, “Machine Leaning”, McGraw-Hill Education (INDIAN EDITION). 2013, ‘Reference Books: 1. Ethem Alpayelm, “Introduction to Machine Learmmg”, 2" Ed, PHI Learmmg Pvt. Ltd, 2013 2. T. Hastie, R Tibshirani, J. H. Friedman, “The Elements of Statistical Learning”, Springer: Ist edition. 2001PATTERN RECOGNITION [As per Choice Based Credit System (CBCS) scheme] (Effective from the academic year 2016-2017) SEMESTER - II Subject Code 16SCE252/ 16SCS252__ [TA Marks 20 ‘Number of Lecture Howrs/ Week 03 Exam Marks | 80 Total Number of Leeture Hours wD Exam Hous | 03 CREDITS — 03 Course objectives: This course will enable students to ‘* Explain various Image processing and Pattem recognition techniques. ‘© Illustrate methematical morphology necessary for Pattern recognition. ‘© Demonstrate Image Representation and description and feature extraction. ‘+ _ Explain principles of decision trees and clustering in pattem recognition, ‘Module 1 Teaching Hours Tntoduction; Definition of PR, Applications, Datasets for PR, Different paradigms for PR, Introduction t> probability, events, random variables, Joint distributions and densities. moments. Estimation mininum risk estimators. problems ‘S Hows “Module -2 Representation; Data structures for PR, Representation of clusters, proximity measures, size of patterns, Abstraction of Data set, Feature extraction, Feature selection, Evaluation ‘8 Hours: Module 3 ‘Nearest Neighbor based classifiers & Bayes classifier: Nearest neighbor algorithm, variants of NN algorithms, use of NN for transaction databases, efficient algorithms. Data seduction, prototype selection, Bayes theorem, minimum error rate classifier, estimation ‘of probabilities. estimation of probabilities. comparison with NNC. Naive bayes classifier, Bayessian belief network ‘8 Hours ‘Module-4 ‘Naive bayes classifier. Bayessian belief network Decision Trees: Introduction, DT for PR, Construction of DT. Splitting at the nodes, Over fitting & Pruning. Examples. Hidden Markov models: Markov models for classification, Hilden Markov models and classification using HMM SHows ‘Module-5 Clustering, Hierarchical (Agglomerative, single/completeaverage linkage, wards, 8 HowsPartitional (Forgy’s k-means, Tsodata), clustering large data sets, examples, Au application: Handwr:ten Digit recognition ‘Course outcomes: The students shall atle to: ‘* Explain pattem recognition principals Develop algorithms for Pattern Recognition. Develop and analyze decision tress Design the nearest neighbor classifier. Apply Decision tree and clustering techniques to various applications (Question paper pattern: The question paper will have ten questions. There will be 2 questions from each module. Each question will have questions covering all the topics under a module, The students will have to answer $ full questions, selecting one full question from each module. Text Books: 1, Pattern Reccanition ( An Introduction) , V Susheela Devi, M Narsimha Murthy, 2011 Universities Press, ISBN 978-81-7371-725-3 Pattern Recognition & Image Analysis, Earl Gose, Richard Johnsonbaugh, Steve Jost. PH ISBN-$1-203-1484-0. 1996. Reference Books: 1, Duda R. O..P.E. Hart, D.G. Stork., Pattern Classification, John Wiley and sons, 2000.