UniCa Informatica Didattica Attività a scelta autonoma dello studente

Attività a scelta autonoma dello studente

Reading courses correntemente attivi

Referente: Fenu Gianni
CFU: 6


Instructor: Fenu Gianni

Description: This course focuses on fundamentals and possible approach to social media, social community and customer innovation including classification, profiling and recommender systems. This course is centered on the form of information filtering, that exploits past behaviors and user similarities to generate a list of information items that is really tailored to an end-user’s preferences.

Prerequisites: Data Base, Computer Networks, Data Mining.

Reference book: Francesco Ricci, Lior Rokach, Bracha Shapira “Recommender Systems Handbook”, Springer, 2016 (second edition).

Evaluation: Project Work based on autonomous reading and researching under the direction of the instructor.

Referente: Fenu Gianni
CFU: 6


Instructor: Fenu Gianni

Description: The course provides an overview of e-commerce, platform technologies, m-commerce, devices, mobility technology and standards, services and applications.

Prerequisites: Computer Networks, Networking Architecture.

Contents: Introduction to E-commerce concepts, M-commerce concepts and technologies, Wireless application development, Trust, Security, and Payment.

Reference book: Efraim Turban, Judy Whiteside, David King, Jon Outland, “Introduction to Electronic Commerce and Social Commerce”, Springer, 2016.

Evaluation: Project Work based on autonomous reading and researching under the direction of the instructor.

Referente: Riboni Daniele
CFU: 6


Instructor: Riboni Daniele

Prerequisite: Advanced Data Management (formerly Basi di Dati 2) and Data Mining

Objectives: The miniaturization of sensing and communication devices and their integration in everyday objects is turning the pervasive computing vision into reality. Nonetheless, there are several research issues to be addressed to fully realize the potential of pervasive computing. This reading course will address some key research issue in this field. After an introduction to the vision and challenges of pervasive computing, the course will address context awareness, which is a key requirement for seamlessly adapting pervasive services to the current situation of users. Then, the course will review different methods to query and mine streams of data coming from pervasive sensors. Finally, the course will discuss privacy issues in pervasive computing and possible countermeasures.

Topics:

1. Pervasive computing: vision and challenges
– Pervasive vs Mobile vs Distributed
– Scenarios and requirements

2. Context-awareness
– Object-role, spatial, and ontology-based context models
– Handling uncertainty
– Hybrid context models

3. Stream data mining
– Theoretical foundations: data-based techniques, task-based techniques
– Mining techniques: clustering, classification, frequency counting, time series analysis

4. Privacy in pervasive computing
– Pervasive computing applications, privacy threats, and requirements
– Privacy preserving approaches: access control, obfuscation, anonymity, privacy-preserving data mining
– Open issues and research challenges

References:

[1] Mahadev Satyanarayanan. Pervasive computing: vision and challenges. IEEE Personal Commun. 8(4): 10-17 (2001)

[2] Maria R. Ebling, Roy Want. Satya Revisits “Pervasive Computing: Vision and Challenges”. IEEE Pervasive Computing 16(3): 20-23 (2017)

[3] Claudio Bettini, Oliver Brdiczka, Karen Henricksen, Jadwiga Indulska, Daniela Nicklas, Anand Ranganathan, Daniele Riboni. A survey of context modelling and reasoning techniques. Pervasive and Mobile Computing 6(2): 161-180 (2010)

[4] Mohamed Medhat Gaber, Arkady B. Zaslavsky, Shonali Krishnaswamy. Mining data streams: a review. SIGMOD Record 34(2): 18-26 (2005)

[5] Claudio Bettini, Daniele Riboni. Privacy protection in pervasive systems: State of the art and technical challenges. Pervasive and Mobile Computing 17: 159-174 (2015)

Assignments: An oral test and a project development test. The oral test regards a topic chosen by the student among the ones addressed in the course. The student will also design and implement a simple prototype of a pervasive sensor-based application, regarding one of the topics addressed in the course. The project can be done either individually or by a team of students.

Referente: Riboni Daniele
CFU: 6


Instructor: Riboni Daniele

Prerequisite: Advanced Data Management (formerly Basi di Dati 2) and Data Mining

Objectives: In several application domains, including healthcare and home automation, it is important to unobtrusively monitor everyday human activities. A popular approach consists in the use of sensors to capture position, motion, interaction with objects, and contextual information. This reading course addresses the main approaches to sensor-based activity recognition, highlighting their strong and weak points. Starting from a technological point of view, the course will introduce the general structure of sensor-based activity recognition systems and discuss design issues. Data-driven activity recognition approaches will be addressed, reviewing different methods for feature extraction, supervised learning, and semi-supervised learning. The course will also discuss knowledge-based approaches based on ontological models of activities, environment, and sensors. Finally, hybrid approaches will be considered, which try to take the best of the two worlds by coupling knowledge-based and data-driven techniques.

Topics:

1. Technologies and issues.
– General structure of sensor-based activity recognition systems.
– Design issues: selection of attributes and sensors, obtrusiveness, accuracy, energy consumption, processing, flexibility.

2. Data-driven activity recognition.
– Data-driven methods: feature extraction, supervised learning, semi-supervised learning.
– Evaluation of data-driven systems.
– Research challenges.

3. Knowledge-based activity recognition.
– Knowledge-based vs data-driven activity recognition.
– Formal ontologies for human behavior recognition.
– Evaluation of knowledge-based systems.

4. Hybrid activity recognition systems.
– Hybrid statistical-ontological reasoning for activity recognition.
– Unsupervised recognition of interleaved activities through ontological and probabilistic reasoning.
– Sensor-based activity recognition through Web mining and computer vision.

References:

[1] Oscar D. Lara, Miguel A. Labrador. A Survey on Human Activity Recognition using Wearable Sensors. IEEE Communications Surveys and Tutorials 15(3): 1192-1209 (2013)

[2] Natalia Díaz Rodríguez, Manuel P. Cuéllar, Johan Lilius, Miguel Delgado Calvo-Flores. A survey on ontologies for human behavior recognition. ACM Comput. Surv. 46(4): 43:1-43:33 (2013)

[3] Daniele Riboni, Claudio Bettini. COSAR: hybrid reasoning for context-aware activity recognition. Personal and Ubiquitous Computing 15(3): 271-289 (2011)

[4] Daniele Riboni, Timo Sztyler, Gabriele Civitarese, Heiner Stuckenschmidt. Unsupervised recognition of interleaved activities of daily living through ontological and probabilistic reasoning. UbiComp 2016: 1-12

[5] Daniele Riboni, Marta Murtas. Web Mining & Computer Vision: New Partners for Object-Based Activity Recognition. WETICE 2017: 158-163

Assignments: An oral test and a project development test. The oral test regards a topic chosen by the student among the ones addressed in the course. The student will also design and implement a simple activity recognition method, and will carry on experiments using an existing dataset. The project can be done either individually or by a team of students.

Referente: Pinna Giovanni Michele
CFU: 6


Instructor: Pinna Giovanni Michele

Description: Petri net is one among several mathematical modeling formalisms for the description of distributed and concurrent systems. It is a class of discrete event dynamic system. Like industry standards such as UML activity diagrams, Business Process Model and Notation and EPCs, Petri nets offer a graphical notation for stepwise processes that include choice, iteration, and concurrent execution. Unlike these standards, Petri nets have an exact mathematical definition of their execution semantics, with a well-developed mathematical theory for process analysis. The course will be centered on the modeling capabilities of Petri nets, as well as on the complexity of various problems related to the actual modeling of systems.

Prerequisites: Good knowledge of the English language.

Contents: Petri Nets; Sequential and non sequential semantics; Abstraction and refinements; Complexity ; Deformation.

Evaluation: Autonomous reading and rehearsing under the direction of the teacher. At the end, the student will present, in a public seminar of approximately 45 minutes, some topic of the course and will answer some questions (in a question time of approximately 15 minutes).

Reference material:

  1. Petri, Carl Adam; Reisig, Wolfgang (2008). Petri net. Scholarpedia. 3 (4): 6477. doi:10.4249/scholarpedia.6477.
  2. Desel, Jörg; Juhás, Gabriel (2001). What Is a Petri Net? Informal Answers for the Informed Reader. In Ehrig, Hartmut; et al. Unifying Petri Nets. LNCS. 2128. Springerlink.com. pp. 1–25. Retrieved 2014-05-14.
  3. Esparza, Javier; Nielsen, Mogens (1995) [1994]. Decidability issues for Petri nets – a survey. Bulletin of the EATCS (Revised ed.).
  4. Murata, Tadao (April 1989). Petri Nets: Properties, Analysis and Applications. Proceedings of the IEEE. 77 (4): 541–558. doi:10.1109/5.24143. Retrieved 2014-10-13.
  5. Reisig, Wolfgang (2013), Understanding Petri Nets – Modeling Techniques, Analysis Methods, Case Studies. Springer, ISBN 978-3-642-33277-7

Referente: Pinna Giovanni Michele
CFU: 6


Instructor: Pinna Giovanni Michele

Description: Since the seminal work of Dana Scott on Data Types as lattices, domain theory plays a central role in the understanding of programming languages. The purpose of the course is to conduct the student to the knowledge of the mathematics beyond programming languages

Prerequisites: Good knowledge of the English language.

Contents: Domain theory, constructions, presentation of domains constructively.

Evaluation: Autonomous reading and rehearsing under the direction of the teacher. At the end, the student will present, in a public seminar of approximately 45 minutes, some topic of the course and will answer some questions (in a question time of approximately 15 minutes).

Reference material:

  1. G. Q. Zhang. Logic of Domains, Birkhäuser 1991
  2. G. Winskel, The formal semantics of programming languages: an introduction, MIT Press 1993

Referente: Pinna Giovanni Michele
CFU: 6


Docente: Spano Lucio Davide

Prerequisiti: Conoscenze di un corso di base di Human-Computer Interaction (IUM).

Obiettivi: Lo studente studia i fondamenti dello End User Development e le tecniche più importanti utilizzate in letteratura per permettere ad un utente non sviluppatore di automatizzare dei compiti in modo autonomo.

Programma:

  • Aspetti psicologici dello End User Development
  • Principali tecniche di interazione in ambienti di EUD
  • Applicazioni in ambienti Web
  • Applicazioni su dispositivi mobili

Testi di riferimento:

  • Lieberman, H., Paternò, F., Wulf, V. (2006). End-User Development. Springer.
  • Paternò, F., & Wulf, V. (2017). New Perspectives in End-User Development, Springer.

Modalità di verifica: Lo studente si prepara in maniera autonoma sul materiale introduttivo all’argomento e concorda con il docente un particolare campo applicativo della disciplina da approfondire, sul quale preparerà una relazione da discutere come prova finale. Il docente è disponibile per chiarimenti e suggerimenti durante l’orario di ricevimento.

Referente: Scateni Riccardo
CFU: 6


Instructor: Scateni Riccardo

Description: The course will be centered on the representation of digital geometric objects. The focus is on the manipulation of objects represented using their surfaces and will not treat the volumetric representations. It will, thus, deal with the surface representation using functions (implicit representations) or data structures for meshes (explicit representation). The problem of parameterization of the surface, in whole or in part, will be treated in deep details. This will lead to understand how a digital object can be modified either deforming its shape or just changing its representation.

Prerequisites: Geometric Algorithms and Spatial Data Structures (Algoritmi e Strutture Dati 2). Good knowledge of the English language.

Contents: Surface Representations; Mesh Data Structures; Parameterization; Remeshing; Simplification & Approximation; Deformation.

Evaluation: Autonomous reading and rehearsing under the direction of the teacher. At the end, the student will present, in a public seminar of approximately 45 minutes, the content of the course and will answer the questions in a question time of approximately 15 minutes.

Reference book: Mario Botsch, Leif Kobbelt, Mark Pauly, Pierre Alliez, Bruno Lévy. “Polygon Mesh Processing”. A K Peters, 2010.

Referente: Marchesi Michele
CFU: 6


Instructor: Marchesi Michele

Description: This reading course is focused on one of the most promising fields where Software Engineering should be applied: Blockchain applications. Blockchain technologies and cryptocurrencies, such as Bitcoin, Litecoin, and Ethereum, have attracted significant attention in recent years. The Blockchain is a decentralized ledger, shared with a peer-to-peer mechanism with no central authority, which can hold any information and can set rules on how this information is updated. The addition of new information (transactions) to the Blockchain is made by the nodes of a network through various possible consensus mechanisms. The Blockchain is a new software technology that can rely on open architectures, service oriented architectures and software-as-a-service, business models, cloud computing, global development, software applications for mobile devices.

The spreading of Blockchain oriented software products and projects definitely raises the need for the application of software engineering principles and practices specific for such software technology, and for the technologies relying on it [1].

In this course we study some aspects of Blockchain software development, and specifically the features of the software enabling main Blockchain implementations, Smart Contract development, and Blockchain applications in the field of trust management. We will also cover some economic aspects of cryptocurrency markets and mining, and the new phenomenon of ICOs (Initial Currency Offers), where new initiatives – mainly on Blockchain technology and applications – are crow-funded through Smart Contracts and existing blockchains. ICOs have exploded in 2017, gathering capitals of the order of $2 billion.

Prerequisites: Basic concepts of software engineering. Good knowledge of Java or, preferably, Python language. Good knowledge of the English language.

Contents: Introduction to Blockchain technology. The main Blockchain implementations: Bitcoin Core, Ethereum, Hyperledger Fabric. Blockchain-Oriented Software Engineering. Blockchain applications with focus on notarization, supply-chain management and certification, banking applications, ICOs (Initial Coin Offers). The business model of cryptocurrencies and ICOs.

Evaluation: Project Work based on autonomous reading and researching under the direction of the instructor. The students will present, in a public seminar of approximately 45 minutes, their Project Works.

Reference material: The teacher will guide each student through the scientific literature and to the technical material on Blockchain implementations, proposing a selection of papers and reports which are most appropriate to the student’s interests and Project Work. A preliminary list of reference material is the following:

  1. Arvind Narayanan, Joseph Bonneau, Edward Felten, Andrew Miller & Steven Goldfeder. Bitcoin and Cryptocurrency Technologies: A Comprehensive Introduction. Princeton University Press (2016).
  2. Melanie Swan. Blockchain: Blueprint for a New Economy. O’Reilly, 2015.
  3. Simone Porru, Andrea Pinna, Michele Marchesi, Roberto Tonelli. Blockchain-oriented software engineering: challenges and new directions. Proc. of the 39th Int. Conf. on Software Engineering Companion. IEEE Press, 2017.
  4. https://en.bitcoin.it/wiki/Main_Page
  5. https://ethereum.org/
  6. https://www.hyperledger.org/projects/fabric

Referente: Bartoletti Massimo
CFU: 6


Instructor: Bartoletti Massimo

Description: Through Bitcoin and other cryptocurrencies, users from all over the world can perform secure and (almost) anonymous transfers of money without the intermediation of trusted authorities. However, these new possibilities have been exploited also by cyber-criminals, who have performed, using cryptocurrencies, differents kind of illegal activities: money laundering, ransomware, financial frauds, etc. On the other side, legitimate uses of cryptocurrencies can be targeted by cyber-attacks at various levels: from the communication network, to the consensus mechanism of the blockchain, and to its application logic. Attacks at the applications level are particularly risky for those blockchain platforms which also provide smart contracts (for instance, vulnerabilities in the implementation of Ethereum smart contracts have allowed attackers to subtract several millions of dollars).

In this course we study security aspects of cryptocurrencies and smart contracts. In particular, we survey the growing scientific literature on cryptocurrencies in order to understand how illegal activities are performed, and which analysis techniques have been developed to counteract them.

Prerequisites: Knowledge of basic concepts in cryptography: asymmetric ciphers, cryptographic hash functions, digital signature schemes, authentication protocols, key distribution protocols. Good knowledge of the English language.

Contents: Introduction to cryptocurrencies, with details on Bitcoin and Ethereum. Security of consensus protocols based on proof-of-work. Security analysis of smart contracts on Bitcoin and on Ethereum. Analysis of frauds, attacks, and other illegal activities carried over on Bitcoin and Ethereum. Alternative cryptocurrencies.

Evaluation: Autonomous reading and rehearsing under the direction of the teacher. At the end, the student will present, in a public seminar of approximately 45 minutes, some topic of the course and will answer some questions (in a question time of approximately 15 minutes).

Reference material: The teacher will guide each student through the scientific literature on cryptocurrencies, proposing a selection of papers which are most appropriate to the student’s interests. A preliminary list of reference material is the following:

  1. Arvind Narayanan, Joseph Bonneau, Edward Felten, Andrew Miller & Steven Goldfeder. Bitcoin and Cryptocurrency Technologies: A Comprehensive Introduction. Princeton University Press (2016).
  2. Joseph Bonneau, Andrew Miller, Jeremy Clark, Arvind Narayanan, Joshua A. Kroll, and Edward W. Felten. 2015. SoK: Research Perspectives and Challenges for Bitcoin and Cryptocurrencies. In IEEE Security & Privacy (2015)
  3. Nicola Atzei, Massimo Bartoletti, Tiziana Cimoli. A survey of attacks on Ethereum smart contracts. In: Principles of Security and Trust (2017) https://eprint.iacr.org/2016/1007.pdf
  4. Garay, J.A., Kiayias, A., Leonardos, N.: The Bitcoin backbone protocol: Analysis and applications. In: EUROCRYPT (2015)
  5. Luu, L., Chu, D.H., Olickel, H., Saxena, P., Hobor, A.: Making smart contracts smarter. In: ACM CCS (2016) http://eprint.iacr.org/2016/633
  6. Matthias Lischke and Benjamin Fabian. 2016. Analyzing the Bitcoin network: The first four years. Future Internet 8, 1 (2016).
  7. Sarah Meiklejohn, Marjori Pomarole, Grant Jordan, Kirill Levchenko, Damon McCoy, Geoffrey M. Voelker, and Stefan Savage. 2016. A fistful of Bitcoins: characterizing payments among men with no names. Commun. ACM 59, 4 (2016)
  8. Andrychowicz, M., Dziembowski, S., Malinowski, D., Mazurek, L.: Secure multi-party computations on Bitcoin. In: IEEE Security & Privacy (2014)
  9. W. Banasik, S. Dziembowski, D. Malinowski, Efficient zero-knowledge contingent payments in cryptocurrencies without scripts, in: ESORICS (2016)

Referente: Reforgiato Recupero Diego Angelo Gaetano
CFU: 6


Instructor: Reforgiato Recupero Diego Angelo Gaetano

Description: The course provides best practices for scaling and optimizing Apache Spark

Prerequisites: Big Data (ARE2)

Contents: High performance Spark, SparkSession, DataFrame, Joins, Effectice Transformations, Working with Key/Value Data, Testing and Validation

References: High Performance Spark – Best Practice for Scaling & Optimizing Apache Spark. Holden Karau & Rachel Warren

Evaluation: Development of a project

Referente: Reforgiato Recupero Diego Angelo Gaetano
CFU: 6


Instructor: Reforgiato Recupero Diego Angelo Gaetano

Description: The course provides guides and documentation for developing on top of Zora Bot

Prerequisites: Programming in Python

Contents:

References: Documentation of Zora robot is not available online but it will be provided to the students. http://zorarobotics.be/index.php/en/zorabot-zora

Evaluation: Development of a project on top of the Zora Bot

Referente: Reforgiato Recupero Diego Angelo Gaetano
CFU: 6


Instructor: Reforgiato Recupero Diego Angelo Gaetano

Description: The course provides a description of what quantum computing is, what qubits and the operators applied on them are. Moreover, it focuses on Python libraries already created for simulation of quantum computer programming.

Prerequisites: Python Programming

Contents: Superposition, Entanglement and Reversibility
Qubits, Operators and Measurement
Teleportation, Superdense Coding and Bell’s Inequality
Examples of Quantum Circuits for Algorithms implementation

References:

  • Quantum Computing: An Applied Approach. Jack D. Hidary. Springer
  • Quantum Computing for Computer Scientists. Noson S. Yanofsky, Mirco A. Mannucci. Cambridge
  • Quantum Computer Science – An Introduction. N. David Mermin. Cambridge
  • https://www.youtube.com/watch?v=F_Riqjdh2oM&t=2959s

Evaluation: Development of a quantum circuit using Python libraries to implement a certain algorithm and description of it.

Referente: Casanova Andrea
CFU: 6


Docente: Casanova Andrea

Obiettivi: Il Corso si propone di fornire i concetti fondamentali dell’informatica medica, legati all’applicazione di metodologie e tecnologie in ambito clinico. Vengono trattati gli aspetti e le architetture dei Sistemi informativi sanitari, con enfasi sugli standard in sanità e in particolare integrazione di processi organizzativi e clinici;
Ulteriore attenzione viene rivolta ad alcuni aspetti dei sistemi informativi sanitari (e.g. il Medical record, Cartella clinica Elettronica, Fascicolo Sanitario elettronico,…)

Programma:

  • L’impatto di internet e del web2 nell’universo della sanità – il ruolo attivo del paziente (informed decision maker & acquisitore di informazioni).  (E-Health, E-Patient – Mobile-Health ecc.)
  • Informatica medica e dei sistemi informativi ospedalieri: Sistemi Formali e informali, Flussi informativi
  • I principali applicativi sanitari: ADT, LIS, RIS.
  • Integrazione e interoperabilità.
  • Il sistema informativo sanitario Regionale e nazionale (Medir, Anags, Sisar, Rtp)
  • Cartella Clinica Elettronica – Fascicolo Sanitario Elettronico
  • Standard in Sanità: Hl7, CDA2, DICOM, IHE
  • Sistemi basati su protocolli, Linee Guida, Medicina basata sull’evidenza, PDTA

Testi di riferimento:

Alberto Rosotti (2017) Informatica medica – Mcgraw-hill (concetti di base) –
Documentazione specifica di settore resa disponibile nella piattaforma Moodle

Prerequisiti: Basi di dati 2.

Valutazione: Valutazione basata sul portfolio Moodle. Lo studente, in maniera autonoma, deve preparare un approfondimento su un argomento del corso, con la supervisione del docente

Referente: Carta Salvatore Mario
CFU: 6


Instructor: Carta Salvatore Mario

Description: The course provides best practices for application of machine learning to financial markets evaluation and forecasting

Contents: Neural networks, Classification Algorithms and technologies, Time series forecasting, Big Data management

References: Computational Intelligence and Financial Markets: A Survey and Future Directions Rodolfo C.Cavalcante, Rodrigo C. Brasileiro, Victor L.F.Souza, Jarley P.Nobrega, Adriano L.I.Oliveira, Expert Systems with Applications Volume 55, 15 August 2016, Pages 194-211

Evaluation: Development of a project

Referente: Carta Salvatore Mario
CFU: 6


Docente: Carta Salvatore Mario

Prerequisiti:

  • Elaborazione ed Analisi di Immagini
  • Tecniche Avanzate di Image Processing (opzionale)

Contenuti:

  • Apprendimento di tecniche per l’elaborazione avanzata di dati e immagini;
  • Utilizzo di tecniche di apprendimento supervisionato e non supervisionato;
  • Focus su tecniche di apprendimento automatico (Deep Learning, Machine Learning, …)
  • Image Enhancement Techniques
  • Semantic Image Segmentation.

Libro di riferimento:

  • (2021) Machine Vision Inspection Systems: Image Processing, Concepts, Methodologies and Applications
  • (2021) Hybrid Image Processing Methods fo Medical Image Examination

Descrizione

Durante il corso, lo studente imparerà ad applicare tecniche avanzate di elaborazione delle immagini ad immagini mediche. Nel dettaglio, lo studente imparerà tecniche quali:

  • Pixel Clustering
  • Semantic driven segmentation
  • Image Restructuration
  • Quadtree
  • Chain Codes

L’ambito di applicazione del corso è particolarmente sentito al giorno d’oggi, in quanto, allo stato attuale, sono sempre più frequenti le applicazioni che si basano sull’utilizzo in sincrono di tecniche di AI e di Image Processing. Uno degli esempi lampanti è l’analisi delle immagini CXR (Chest X-Ray) per lo studio dei polmoni dei pazienti affetti da coronavirus. Altre potenziali applicazioni prevedono:

  • Lo studio di immagini di raggi X per analizzare fratture ossee;
  • Palm Vein recognition and segmentation;
  • Retina image analysis;
  • Face geometry analysis;
  • Lung Analysis and Segmentation.

Evaluation: Lo studente concorderà col docente un progetto e la valutazione sarà effettuata sulla base dell’esito e delle conoscenze apprese e dimostrate nello sviluppo dello stesso.

Referente: Carta Salvatore Mario
CFU: 6


Docente: Carta Salvatore Mario

Prerequisiti: Elaborazione ed Analisi di Immagini

Contenuti:

  • Apprendimento di tecniche per l’elaborazione avanzata di dati e immagini;
  • Utilizzo di tecniche di apprendimento supervisionato e non supervisionato;
  • Focus su tecniche di apprendimento automatico (Deep Learning, Machine Learning, …)
  • Utilizzo di tecniche avanzate di image processing (Image Enhancements Filters, Image Segmentation, Feature Extraction);
  • Scene Understanding.

Libro di riferimento: (2019) Learn Keras for Deep Neural Networks – Moolayil – [Apress]

Descrizione: Il corso permette allo studente di confrontarsi con le tecniche moderne di apprendimento supervisionato e non supervisionato. Tra queste si annoverano le maggiori tecnologie appartenenti al diffuso paradigma di apprendimento del deep learning. Lo studente avrà, quindi, la possibilità di studiare ed applicare tecniche estremamente utilizzate allo stato dell’arte in molteplici ambiti di applicazioni reali:

  • CNN per l’analisi di immagini e l’estrazione di caratteristiche;
  • LSTM ed RNN per l’analisi e la classificazione di serie temporali;
  • GAN per apprendere pattern e generare nuovi dati che rispettano quel pattern.

L’ambito di applicazione è la Smart Mobility, un tema di ricerca  molto analizzato e studiato al  giorno d’oggi,  in quanto nell’era dell’IoT risulta fondamentale analizzare con tecniche avanzate e performanti la notevole quantità di dati di cui si può disporre. Il connubio tra le tecniche di DL e l’ambito di cui sopra (Smart mobility) sono alla base di un ampio novero di applicazioni che ricadono nel ben più celebre ambito delle Smart Cities.

Progetti che possono essere oggetto d’esame sono:

  • Detection, Tracking e Speed Estimation dei veicoli;
  • Analisi delle anomalie stradali;
  • Trajectory Estimation;
  • Accident Prediction;
  • Model-driven traffic lights

Per le fasi di testing è possibile utilizzare CARLA,  un simulatore che permette di applicare a scenari pseudo reali, il modello sviluppato.

Evaluation: Lo studente concorderà col docente un progetto e la valutazione sarà effettuata sulla base dell’esito e delle conoscenze apprese e dimostrate nello sviluppo dello stesso.

Docente: Pes Barbara
CFU: 6

Instructor: Pes Barbara

Description: The course aims at providing a comprehensive overview of best practices and research issues in the field of feature selection.

Prerequisites: Data Mining.

Contents: Introduction to high-dimensionality; Foundations of feature selection; Review of feature selection methods; Filter, wrapper and embedded approaches; Hybrid and ensemble approaches; Robustness of feature selection algorithms; Application of feature selection to real problems; Open issues and challenges of feature selection for high-dimensional data.

Evaluation: Project work and oral discussion.

Reference Material:

  1. Bolón-Canedo V., Sánchez Maroño N., Alonso-Betanzos A., Feature Selection for High-Dimensional Data, Springer, 2015.
  2. Ian H. Witten, Eibe Frank, Mark A. Hall, Christopher J. Pal, DATA MINING: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, 2016.
  • A selection of papers from the feature selection literature.

Docente: Gianmarco Cherchi

CFU: 6

Prerequisiti: Geometric Algorithms and Spatial Data Structures (ex Algoritmi e Strutture Dati 2)

Descrizione: Nel mondo della Computer Graphics le rappresentazioni tridimensionali degli oggetti della vita reale (modelli 3D) sono l’ingrediente base di ogni algoritmo. Spesso i modelli 3D sono costituiti da una rappresentazione discretizzata della loro superficie, rappresentata tramite triangoli o quadrilateri. Tuttavia, alcuni algoritmi, come quelli che si occupano di simulazioni fisiche, hanno la necessità di lavorare sul volume interno dei modelli. In questi casi entrano in gioco le mesh volumetrice, ovvero rappresentazioni del volume interno dei modelli 3D mediante poliedri (tipicamente tetraedri e/o esaedri). In questo corso verranno studiati e affrontati gli algoritmi legati alla generazione, ottimizzazione e utilizzo delle mesh volumetriche in diversi campi della Computer Graphics. Si affronteranno le basi teoriche per poter comprendere i pregi e i difetti delle due principali famiglie di mesh volumetriche, e successivamente si entrerà nel vivo delle principali categorie di algoritmi che le utilizzano.

Materiale di riferimento:
1. T. Schneider, Y. Hu, X. Gao, J. Dumas, D. Zorin, D. Panozzo: A Large-Scale Comparison of Tetrahedral and Hexahedral Elements for Finite Element Analysis
2. S. J. Owen: A Survey of Unstructured Mesh Generation Technology
3. S.W. Cheng, T. K. Dey, Jonathan Richard Shewchuk: Delauney Mesh Generation
4. Y. Lu, R. Gadh, T.J. Tautges: Feature based hex meshing methodology: feature recognition and volume decomposition
5. T. Blacker: Meeting the Challenge for Automated Conformal Hexahedral Meshing
6. H. SI: TetGen, a Delaunay-Based Quality Tetrahedral Mesh Generator
7. Y. Hu, Q. Zhou, X. Gao, A. Jacobson, D. Zorin, D. Panozzo: Tetrahedral Meshing in the Wild
8. Altri testi forniti dal docente durante il corso.

Esame: Lo studente si prepara in maniera autonoma sul materiale introduttivo all’argomento e concorda con il docente un particolare settore della disciplina da approfondire. Al termine del corso lo studente presenterà, in un seminario di circa 45 minuti, i contenuti del corso e l’argomento approfondito, e risponderà alle domande in un question time di circa 15 minuti.

Docente: Salvatore Mario Carta

CFU: 6

Prerequisiti:

  • Programmazione a oggetti
  • Basi di dati
  • Fondamenti di Reti dei calcolatori

o in alternativa:

  • Fondamenti di programmazione web

Contenuti:

  • Utilizzo di tecnologie cloud per il supporto ad applicazioni IoT;
  • Possibile integrazione fra applicazioni IoT e altre tecnologie di particolare rilevanza applicativa: blockchain, machine learning, deep learning;
  • Utilizzo di protocolli e tecnologie hardware per implementazione di applicazioni IoT

Descrizione:

Nell'ambito del reading course, lo studente acquisirà un importante bagaglio di conoscenze e competenze nello sviluppo di sistemi Internet-of-Things end-to-end, apprendendo le principali tecniche e metodologie avanzate per la loro progettazione e implementazione.

L'attività del reading course verterà su applicazioni specifiche, preventivamente analizzate e valutate, per le quali lo studente potrà implementare particolari componenti e/o moduli. Alcuni esempi di possibili applicazioni sono: sistema IoT per la sicurezza sul lavoro; sistema IoT end-to-end per la certificazione della catena del freddo tramite blockchain; infrastruttura IoT per la gestione di cantieri edili.

Il reading course, oltre a consentire di arricchire il proprio curriculum studiorum con competenze e conoscenze in ambito Internet-of-Things di elevata spendibilità nel mondo del lavoro e/o della ricerca, si propone di stimolare la curiosità e l'interesse dello studente verso questo affascinante ambito disciplinare, in cui hardware e software si coniugano in modo fortemente creativo e applicativo, con vastissime potenzialità d'uso e diversificati scenari d'impiego.

Valutazione:

Lo studente concorderà in anticipo col docente la tematica d'interesse e il progetto da sviluppare, definendo congiuntamente requisiti e obiettivi. La valutazione terrà conto delle conoscenze apprese e dimostrate nello sviluppo del progetto, nonché del grado di completamento degli obiettivi concordati.

Questionario e social

Condividi su: