Fabio Narducci | CONTEXT AWARE SECURITY ANALYTICS IN COMPUTER VISION (ENGLISH)

cod. 0522500118

CONTEXT AWARE SECURITY ANALYTICS IN COMPUTER VISION (ENGLISH)

	0522500118
	COMPUTER SCIENCE
	EQF7
	COMPUTER SCIENCE
	2022/2023

CURRICULUM INTERNET OF THINGS

	OBBLIGATORIO
	YEAR OF COURSE 1
	YEAR OF DIDACTIC SYSTEM 2016
	SPRING SEMESTER

TEACHING UNITS

SSD	CFU	HOURS	ACTIVITY	TYPE OF ACTIVITY
INF/01	4	20	LESSONS	COMPULSORY SUBJECTS, CHARACTERISTIC OF THE CLASS
INF/01	5	40	LAB	COMPULSORY SUBJECTS, CHARACTERISTIC OF THE CLASS

PROFESSORS

	MICHELE NAPPI T Curriculum
	FABIO NARDUCCI Curriculum

	Objectives
	KNOWLEDGE AND UNDERSTANDING CRITICAL KNOWLEDGE OF THE FOUNDATIONS OF ARTIFICIAL INTELLIGENCE AND COMPUTER VISION APPLYING KNOWLEDGE AND UNDERSTANDING THE STUDENT WHO WILL PROFITABLY FOLLOW THE COURSE: •WILL KNOW THE MAIN ISSUES RELATED TO THE ARTIFICIAL COGNITIVE TECHNIQUES IN THE COMPUTER VISION; • WILL BE ABLE TO UNDERSTAND THE LOGIC OF THE MACHINE LEARNING AND DEEP LEARNING IN THE VIDEO ANALYTICS; • WILL BE ABLE TO CHOOSE THE TECHNIQUE BEST SUITED TO THE REFERENCE OPERATING ENVIRONMENT; • WILL BE ABLE TO USE COMPARATIVE TOOLS TO MEASURE THE PERFORMANCE OF A GIVEN TECHNIQUE IN TERMS OF EFFICIENCY AND EFFECTIVENESS; • WILL BE ABLE TO INDEPENDENTLY DESIGN AND IMPLEMENT IMPROVEMENT STRATEGIES BASED ON BASIC TECHNIQUES, IN PARTICULAR BY IDENTIFYING APPROPRIATE DESIGN SOLUTIONS FOR VIDEO ANALYTICS CONTEXT ; • WILL BE ABLE TO SUPPORT CONVERSATIONS ON TOPICS RELATED TO THE CORE ASPECTS OF THE DISCIPLINE BY USING BOTH AN APPROPRIATE SCIENTIFIC TERMINOLOGY AND THE TOOLS OF MATHEMATICAL AND GRAPHIC REPRESENTATION OF THE MAIN DESCRIBED PHENOMENA; • WILL PRODUCE MEDIUM-SIZED SOFTWARE PROJECTS IN PHYTON (ALTERNATELY IN C OR MATLAB)

KNOWLEDGE AND UNDERSTANDING

CRITICAL KNOWLEDGE OF THE FOUNDATIONS OF ARTIFICIAL INTELLIGENCE AND COMPUTER VISION

APPLYING KNOWLEDGE AND UNDERSTANDING

THE STUDENT WHO WILL PROFITABLY FOLLOW THE COURSE:
•WILL KNOW THE MAIN ISSUES RELATED TO THE ARTIFICIAL COGNITIVE TECHNIQUES IN THE COMPUTER VISION;
• WILL BE ABLE TO UNDERSTAND THE LOGIC OF THE MACHINE LEARNING AND DEEP LEARNING IN THE VIDEO ANALYTICS;
• WILL BE ABLE TO CHOOSE THE TECHNIQUE BEST SUITED TO THE REFERENCE OPERATING ENVIRONMENT;
• WILL BE ABLE TO USE COMPARATIVE TOOLS TO MEASURE THE PERFORMANCE OF A GIVEN TECHNIQUE IN TERMS OF EFFICIENCY AND EFFECTIVENESS;
• WILL BE ABLE TO INDEPENDENTLY DESIGN AND IMPLEMENT IMPROVEMENT STRATEGIES BASED ON BASIC TECHNIQUES, IN PARTICULAR BY IDENTIFYING APPROPRIATE DESIGN SOLUTIONS FOR VIDEO ANALYTICS CONTEXT ;
• WILL BE ABLE TO SUPPORT CONVERSATIONS ON TOPICS RELATED TO THE CORE ASPECTS OF THE DISCIPLINE BY USING BOTH AN APPROPRIATE SCIENTIFIC TERMINOLOGY AND THE TOOLS OF MATHEMATICAL AND GRAPHIC REPRESENTATION OF THE MAIN DESCRIBED PHENOMENA;
• WILL PRODUCE MEDIUM-SIZED SOFTWARE PROJECTS IN PHYTON (ALTERNATELY IN C OR MATLAB)

	Prerequisites
	STUDENT MUST HAVE BASIC KNOWLEDGE ABOUT BASIC ANALYSIS MATHS

	Contents
	1. ARTIFICIAL INTELLIGENCE AND COMPUTER VISION 6H LECTURE + 8LAB 2. IMAGE PROCESSING BASIC TECHNIQUES 6H LECTURE + 8 LAB 3. VISUAL CONTEXT AWARE AND TRACKING 8 LAB 4. MACHINE LEARNING AND DEEP LEARNING IN COMPUTER VISION 8H LECTURE + 8 LAB 5. VIDEO SECURITY SYSTEMS: A CASE STUDY 8 LAB

	Teaching Methods
	CLASS LECTURES INCLUDES LECTURES (4 ECTS) AND LABORATORY PROGRAMMING PRACTICE (5 ECTS). IN THE LABORATORY PRACTICE HOURS THE TEACHER WILL PROVIDE EXAMPLES OF PROGRAM WRITING (PHYTON\MATLAB\C LANGUAGE). DURING THE EXERCISES THE STUDENT WILL ADDRESS THE PROBLEM SOLVING IN THE COMPUTER VISION CONTEXT USING MACHINE LEARNING AND DEEP LEARNING. THE RESOLUTION METHOD CONSISTS IN UNDERSTANDING THE PROBLEM, IN DESIGNING A SOLUTION, AND FINALLY IN ITS IMPLEMENTATION. THE LAST PHASE INVOLVES ASSESSING THE VALIDITY OF THE SOLUTION AND VERIFYING THE CONSISTENCY AS WELL AS EFFECTIVENESS AND EFFICIENCY IN A COMPARATIVE CONTEXT.

Teaching Methods

CLASS LECTURES INCLUDES LECTURES (4 ECTS) AND LABORATORY PROGRAMMING PRACTICE (5 ECTS). IN THE LABORATORY PRACTICE HOURS THE TEACHER WILL PROVIDE EXAMPLES OF PROGRAM WRITING (PHYTON\MATLAB\C LANGUAGE). DURING THE EXERCISES THE STUDENT WILL ADDRESS THE PROBLEM SOLVING IN THE COMPUTER VISION CONTEXT USING MACHINE LEARNING AND DEEP LEARNING. THE RESOLUTION METHOD CONSISTS IN UNDERSTANDING THE PROBLEM, IN DESIGNING A SOLUTION, AND FINALLY IN ITS IMPLEMENTATION. THE LAST PHASE INVOLVES ASSESSING THE VALIDITY OF THE SOLUTION AND VERIFYING THE CONSISTENCY AS WELL AS EFFECTIVENESS AND EFFICIENCY IN A COMPARATIVE CONTEXT.

	Verification of learning
	THE EXAM IS AIMED AT EVALUATING THE STUDENT'S ABILITY TO LEARN THE BASIC PRINCIPLES OF IA AND COMPUTER VISION. THE STUDENT MUST DEMONSTRATE THAT HE HAS ACQUIRED THE ABILITY TO IDENTIFY THE MOST APPROPRIATE METHODOLOGICAL SOLUTION TO THE REFERENCE CONTEXT. THE EXAM CONSISTS OF A LABORATORY TEST AND AN ORAL INTERVIEW. IN THE LABORATORY TEST INCLUDING ALSO A HOMEWORK ACTIVITY THE STUDENT HAS TO DESIGN, IMPLEMENT AND TEST IN COMPARATIVE MODE AN INNOVATIVE SOLUTION APPLIED TO THE IA AND COMPUTER VISION. THE COMPARATIVE TEST INVOLVES SELECTING A PUBLIC DATABASE ON WHICH PERFORMANCE CAN BE MEASURED IN TERMS OF EFFICIENCY AND EFFECTIVENESS. THE SW USED FOR EXPERIMENTATION WILL BE MATLAB OR PHYTON. THE EXAM IS PASSED IF THE SCORE IS AT LEAST 18/30. THE ORAL TEST WILL CONSIST OF AN INTERVIEW WHERE THE THEORETICAL AND FORMAL TOPICS DISCUSSED IN THE COURSE WILL BE DEALT WITH. THE EVALUATION CRITERIA INCLUDE THE COMPLETENESS AND CORRECTNESS OF THE LEARNING AND THE CLARITY OF THE PRESENTATION.

Verification of learning

THE EXAM IS AIMED AT EVALUATING THE STUDENT'S ABILITY TO LEARN THE BASIC PRINCIPLES OF IA AND COMPUTER VISION. THE STUDENT MUST DEMONSTRATE THAT HE HAS ACQUIRED THE ABILITY TO IDENTIFY THE MOST APPROPRIATE METHODOLOGICAL SOLUTION TO THE REFERENCE CONTEXT.
THE EXAM CONSISTS OF A LABORATORY TEST AND AN ORAL INTERVIEW. IN THE LABORATORY TEST INCLUDING ALSO A HOMEWORK ACTIVITY THE STUDENT HAS TO DESIGN, IMPLEMENT AND TEST IN COMPARATIVE MODE AN INNOVATIVE SOLUTION APPLIED TO THE IA AND COMPUTER VISION. THE COMPARATIVE TEST INVOLVES SELECTING A PUBLIC DATABASE ON WHICH PERFORMANCE CAN BE MEASURED IN TERMS OF EFFICIENCY AND EFFECTIVENESS. THE SW USED FOR EXPERIMENTATION WILL BE MATLAB OR PHYTON. THE EXAM IS PASSED IF THE SCORE IS AT LEAST 18/30.
THE ORAL TEST WILL CONSIST OF AN INTERVIEW WHERE THE THEORETICAL AND FORMAL TOPICS DISCUSSED IN THE COURSE WILL BE DEALT WITH.
THE EVALUATION CRITERIA INCLUDE THE COMPLETENESS AND CORRECTNESS OF THE LEARNING AND THE CLARITY OF THE PRESENTATION.

	Texts
	LEARNING MATERIAL (HANDOUTS, SLIDES, EXERCISES) IS AVAILABLE ON-LINE TO THE STUDENTS. THE FOLLOWING BOOKS ARE NECESSARY FOR THE INDIVIDUAL STUDY. • ARTIFICIAL INTELLIGENCE: A MODERN APPROACH, GLOBAL EDITION, 3/E, STUART RUSSELL, PETER NORVIG, PEARSON ED • DIGITAL IMAGE PROCESSING, 4TH EDITION, RAFAEL C. GONZALEZ, RICHARD E. WOODS, PEARSON ED.

	More Information
	• TEACHING E-MAIL: MNAPPI@UNISA.IT • TEACHING WEB SITE: WWW.UNISA.IT/DOCENTI/MICHELENAPPI/INDEX

BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2024-08-21]

Fabio Narducci | CONTEXT AWARE SECURITY ANALYTICS IN COMPUTER VISION (ENGLISH)