Teacher: Catia Prandi (DISI, University of Bologna) Teaching period: November 3rd, 4th, 10th, 11th 2022 Total hours: 10 Assessment method: by project
The course will provide PhD students with an overview on data visualization techniques, strategies and tools, to create meaningful visualizations and make sense of data.
Topics • Introduction to Information visualization and data visualization concepts and definitions • Introduction to Data Visualization principles (e.g., color theory) • Introduction to Exploratory data analysis and fundamental graphs • Introduction to different tools and software for data visualization
Teacher: Luca Foschini, Isam Al Jawarneh (DISI, University of Bologna) Teaching period: July 18th, 19th, 22th, 25th, 27th, 29th 2022 Total hours: 15 Assessment method: by project
With most data arriving from real-world data-intensive problems being geo-referenced, it is becoming indispensable to design distributed geospatial software solutions for the large-scale management of such data. This course brings the foundational knowledge, explaining pivotal aspects pertinent to designing highly efficient distributed geospatial solutions for data-intensive applications. It covers the enabling technologies and architectures in Cloud storage and computing, including programing models (such as MapReduce and SQL-like declarative models) and algorithms from a middleware perspective.
Teacher: Andrea Melis (DISI, University of Bologna) Teaching period: July 4th, 14th, 18th, 25th 2022 Total hours: 15 Assessment method: by project
Cybersecurity is one of the main trends of recent years. While being extensively addressed in "consumers" scenarios, the security of industrial systems is not very advanced and it poses other problems such as legacy devices, time constraints, usable security for installation of devices, devices not connected to the internet, physical security, safety constraints, etc. This field has never been deeply analyzed, since these kinds of devices were thought and built in “closed” networks, where the only possible attacks were physical ones. With the advent of the fourth industrial revolution (Industry 4.0), these systems have been exposed to the public domain and the attack surface, as a consequence, it exploded. There is indeed the need of a strong security paradigm for these systems to contrast attacks which are more frequent every day. The goal of this course is to give a clear view on the implementation and research questions of cybersecurity on industrial systems. We will expose which are the current research directions and what research can do to meet with industry security standards from our industrial experience and research points of view.
Teacher: Matteo Poggi, Fabio Tosi, Pierluigi Zama Ramirez (DISI, University of Bologna) Teaching period: May - June 2022 Total hours: 20 Assessment method: by project
Computer Vision has a long history of successes in both accademia and industry. By processing an image, we can extract countless information concerning both what we are observing in a scene and where. The advent of deep learning and its wide diffusion in the last decade further booster the popularity of this broad topic, allowing to tackle tasks considered prohibitive not earlier than 10 years ago with astonishing results. In this course, we will give an overview of a subset of the most popular tasks in computer vision benefiting from rapid progresses thanks to deep learning. Through the lectures, the attendees will be introduced to some specific tasks, their state-of-the-art solutions and open challenges yet to be faced.
Teacher: Guido Borghi (DISI, University of Bologna) Teaching period: April 6th, 7th, 8th 2022 Total hours: 10 Assessment method: by project
The loss of vehicle control is a common problem, due to driving distractions, stress, fatigue and bad psycho-physical conditions. Furthermore, the future arrival of (semi-) self-driving cars and the necessary transition period, characterized by the coexistence of traditional and autonomous vehicles, is going to increase the already-high interest about driver attention monitoring systems. The course will introduce Driver Monitoring principles through Computer Vision, Deep Learning techniques and depth data. Then, we will describe learning-based methods to estimate the pose of the head and, in general, of the human body of the driver. Finally, we will see real use cases applied on modern literature datasets.
Teacher: Armir Bujari, Giuseppe Di Modica (DISI, University of Bologna) Teaching period: February 14th, 16th, 18th, 22nd, 24th 2022 Total hours: 12 Assessment method: by project
Industry 4.0 aims to revolutionize and digitize the manufacturing sector by enabling and facilitating interoperability, solution agility, flexible (re)configuration of production chain(s) while, at the same time, reducing costs by exploiting real-time data. These capabilities require linking the shop floor with data flows from/to the enterprise borders and include as core enabling technologies the Internet of Things (IoT), cloud, and edge computing key to move and execute parts of the business logic. The lecture series will discuss the transition to I4.0 and introduce some of the research opportunities and open challenges around this topic.
Teacher: Enrico Gallinucci (DISI, University of Bologna) Teaching period: January 25th-27th 2022 Total hours: 10 Assessment method: by project
The course is subdivided into three parts. In the first part, an introduction to the world of big data is given, so as to bring up to speed the students that have no prior knowledge on the subject. In the second part, an in-depth analysis of the polyglot persistence theme is given, introducing the concepts of multistores and polystores and the techniques to query heterogeneous distributed database systems. In the last part, the metadata challenge is presented to discuss the main issues related to metadata generation, maintenance, and exploitation.