2. Professors
  3. COLACE Francesco
  4. Teaching

COMPUTER SCIENCE FOR INDUSTRY 4.0: NETWORKING, BIG DATA MANAGEMENT AND MACHINE LEARNING

Francesco COLACE COMPUTER SCIENCE FOR INDUSTRY 4.0: NETWORKING, BIG DATA MANAGEMENT AND MACHINE LEARNING

0623000004
DIPARTIMENTO DI INGEGNERIA INDUSTRIALE
EQF7
SMART INDUSTRY ENGINEERING
2021/2022

OBBLIGATORIO
YEAR OF COURSE 1
YEAR OF DIDACTIC SYSTEM 2021
FULL ACADEMIC YEAR
CFUHOURSACTIVITY
12120LESSONS
FRANCESCO COLACE Curriculum
ALFREDO TROIANO Curriculum
Objectives
THE COURSE AIMS AT INTRODUCING THE LEADING COMPUTER SCIENCE TECHNOLOGIES AND METHODOLOGIES UNDERLYING THE INDUSTRY 4.0 FUNCTIONAL PARADIGM. IN PARTICULAR, WE WILL FIRST INTRODUCE THE PRINCIPLES THAT HAVE GUIDED AND GUIDE COMPUTER NETWORKS DEVELOPMENT. IN PARTICULAR, THE TCP/IP PROTOCOL STACK WILL BE PRESENTED, INTRODUCING ITS MAIN FUNCTIONAL CHARACTERISTICS, AND REFERENCE PROTOCOLS AND NETWORK TOPOLOGIES WILL BE DESCRIBED WITH A PARTICULAR FOCUS ON MESH NETWORKS. MOREOVER, THE COURSE INTRODUCES BASIC CONCEPTS RELATED TO CYBER SECURITY. A REVIEW OF THE MAIN METHODOLOGICAL AND PRACTICAL APPROACHES RELATED TO DISTRIBUTED PROGRAMMING AND ITS FUNCTIONAL PARADIGMS WILL CLOSE THIS PART.
AS A CONSEQUENCE OF THE INCREASING PERVASIVENESS OF IT TOOLS THAT USE THE INTERNET OF THINGS AS A FUNCTIONAL PARADIGM FOR THEIR ACTIVITIES, THERE HAS BEEN AN EXPONENTIAL INCREASE IN DATA PRODUCTION. BIG DATA, THE TERM FOR THIS DELUGE OF DATA, IS ONE OF THE MOST DISTINCTIVE ASPECTS OF THE INDUSTRY 4.0 WORLD. THEREFORE, IN THE SECOND PART OF THE COURSE, BIG DATA'S CONCEPT WILL BE INTRODUCED. WE WILL DISCUSS TRADITIONAL TECHNOLOGIES' LIMITATIONS IN CONTEXTS WHERE VOLUME, THROUGHPUT, OR TYPE MAKE CHALLENGING DATA MANAGEMENT. THE MOST WIDELY USED ARCHITECTURES, TECHNIQUES, AND TOOLS ON THE MARKET FOR THE MANAGEMENT AND PROCESSING OF THIS LARGE AMOUNT OF DATA WILL BE PRESENTED.
FINALLY, IN ITS THIRD PART, THE COURSE WILL ALSO PROVIDE THE MAIN THEORETICAL CONCEPTS OF MACHINE LEARNING AND THE TECHNIQUES AND TOOLS SUITABLE FOR APPLYING THESE APPROACHES IN AN INDUSTRIAL CONTEXT. THERE IS A FINAL PROJECT WORK IN WHICH THE PRACTICAL PART WILL USE THE PYTHON LANGUAGE AND OPEN-SOURCE SOFTWARE PACKAGES MOST WIDELY USED ON THE MARKET.
Prerequisites
THERE ARE NO PREREQUISITES.
Contents
COMPUTER NETWORKING
INTRODUCTION TO COMPUTER NETWORKS
THE TCP/IP PROTOCOL STACK
•APPLICATION LAYER
•TRANSPORT LAYER
•INTERNET LAYER
•DATA LINK LAYER
•PHYSICAL LAYER
NETWORK ARCHITECTURES
-WAN; MAN; LAN; PAN
-MESH NETWORKS IN INDUSTRIAL IOT
CYBER SECURITY
INTRODUCTION TO CYBERSECURITY AND RELATED TERMINOLOGY. INFORMATION SECURITY, PASSIVE AND ACTIVE ATTACKS, SECURITY MECHANISMS AND SERVICES
SYMMETRIC AND ASYMMETRIC ENCRYPTION SYMMETRIC ENCRYPTION SYMMETRIC ENCRYPTION MODEL AND CHARACTERISTICS, CRYPTOGRAPHIC ANALYSIS AND BRUTE FORCE ATTACKS, SYMMETRIC ENCRYPTION ALGORITHMS, SUBSTITUTION AND TRANSPOSITION TECHNIQUES. BLOCK ENCRYPTION, FEISTEL ENCRYPTION, DES, AES, 2DES, 3DES. BLOCK ENCRYPTION MODES CHANNEL AND END-TO-END ENCRYPTION, KEY DISTRIBUTION. ASYMMETRIC ENCRYPTION ASYMMETRIC ENCRYPTION MODEL AND CHARACTERISTICS, RSA. KEY DISTRIBUTION (DIFFIE-HELLMAN).
INTRUSIONS, MALWARE (VIRUSES, WORMS, ETC.), ATTACKS AND COUNTERMEASURES. DDOS, FIREWALLS, DATA PROTECTION.
BIG DATA
SOURCES AND CHARACTERISTICS. PLATFORM & ARCHITECTURES
DATABASES FOR BIG DATA
ACID, BASE, SEC AND CAP THEOREM APPROACHES
NOSQL APPROACHES
CLOUD AND BIG DATA
BIG DATA PROCESSING LANGUAGES
THE PYTHON LANGUAGE
INTRODUCTION TO BIG DATA ANALYTICS AND MANAGEMENT
MACHINE LEARNING
TECHNIQUES, ALGORITHMS AND METHODOLOGIES
ARTIFICIAL INTELLIGENCE
DEEP LEARNING
ANALYSIS OF CASE STUDIES
DATA MINING WORKSHOP WITH OPEN-SOURCE ENVIRONMENTS
Teaching Methods
THE COURSE COVERS
- LECTURES FOR A TOTAL OF 60 HOURS
- ASSISTED CLASSROOM EXERCISES: 20 HOURS. STUDENTS WILL BE ASKED TO DEVELOP, INDEPENDENTLY OR IN SMALL GROUPS, SUMMARY EXERCISES ON THE THEORETICAL TOPICS PREVIOUSLY INTRODUCED.
- LABORATORY ACTIVITIES: 40 HOURS. STUDENTS WILL BE ASKED TO DEVELOP, THROUGH A PROBLEM-SOLVING APPROACH, PROJECT WORKS RELATED TO THE MAIN TOPICS DEVELOPED IN THE THEORETICAL PART.
Verification of learning
TEACHING OBJECTIVES ACHIEVEMENT IS CERTIFIED BY AN EXAM WITH AN EVALUATION IN THIRTIETHS (THE MINIMUM LEVEL OF PASSING IS "18" AND THE MAXIMUM IS "30 CUM LAUDE"), WHICH INCLUDES AN ORAL TEST INCLUDING THE DISCUSSION OF A PROJECT WORK, PREVIOUSLY DEVELOPED, OF AN APPROXIMATE DURATION OF ONE HOUR. DURING THE EXAM, THE COMMISSION
- VERIFIES THE LEVEL OF KNOWLEDGE OF THE TOPICS COVERED IN THE THEORY LESSONS;
- VERIFIES THE ABILITY TO PRESENT ON A GIVEN TOPIC;
- VERIFIES THE AUTONOMY OF JUDGMENT IN PROPOSING THE MOST APPROPRIATE APPROACH TO ARGUING WHAT IS REQUIRED.
- ASCERTAINS THE STUDENT'S ABILITY TO IDENTIFY STRATEGIES FOR SOLVING COMPLEX PROBLEMS.
SPECIFICALLY, THE ORAL TEST CONSISTS OF THREE QUESTIONS: THE FIRST ONE CONCERNS THE PROJECT WORK AND ITS SOLUTION STRATEGY, THE SECOND AND THIRD QUESTIONS WILL FOCUS ON THE TOPICS COVERED DURING THE LECTURES (E.G., MAIN NETWORK PROTOCOLS, DISTRIBUTED ARCHITECTURES, EXAMPLES OF DISTRIBUTED PROGRAMMING, MAIN CHARACTERISTICS OF BIG DATA, BIG DATA ANALYTICS, MACHINE LEARNING TECHNIQUES). THE STUDENT REACHES THE LEVEL OF EXCELLENCE IF HE/SHE DEMONSTRATES THE ABILITY TO MAKE CONNECTIONS BETWEEN THE THEORETICAL TOPICS COVERED AND DEMONSTRATES FULL MASTERY OF THE ACTIVITIES CARRIED OUT TO DEVELOP THE WRITTEN TEST.
Texts
JAMES F. KUROSE, KEITH W. ROSS, COMPUTER NETWORKS AND THE INTERNET. A TOP-DOWN APPROACH, PEARSON
BRENDAN BURNS, DESIGNING DISTRIBUTED SYSTEMS: PATTERNS AND PARADIGMS FOR SCALABLE, RELIABLE SERVICES, O'REILLY'.
THOMAS ERL, WAJID KHATTAK, PAUL BUHLER, BIG DATA FUNDAMENTALS: CONCEPTS, DRIVERS & TECHNIQUES, PEARSON
MICHAEL MANOOCHEHRI, DATA JUST RIGHT: INTRODUCTION TO LARGE-SCALE DATA & ANALYTICS, 1ST EDITION, PEARSON
PAUL J. DEITEL, HARVEY DEITEL, INTRO TO PYTHON FOR COMPUTER SCIENCE AND DATA SCIENCE: LEARNING TO PROGRAM WITH AI, BIG DATA AND THE CLOUD, PEARSON
More Information
SUBJECT DELIVERED IN ENGLISH.
  BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2022-11-21]