Development of Applications for Mobile Devices

A.Y. 2026/2027
6
Max ECTS
48
Overall hours
SSD
INFO-01/A
Language
Italian
Learning objectives
The aim of this course is presenting advanced data management techniques in the context of mobile applications. The main topics will be: indoor positioning, activity recognition, and augmented reality.
Expected learning outcomes
The students will improve their abilities in the analysis of complex problems and in definition of the corresponding solutions with scientific methodology. The students will also acquire knowledge about three relevant topics (indoor positioning, augmented reality and activity recognition). Since these topcis are currently being investigated, the students will also improve their ability to understand scientific documents. The students will also acquire development skills by creating a prototype application with innovative aspects.
Single course

This course can be attended as a single course.

Course syllabus and organization

Single session

Responsible
Lesson period
Second four month period
Course syllabus
- Augmented reality
An introduction to the fundamental principles of Augmented Reality (AR) is provided, covering the complete development pipeline of an AR system: registration, tracking, display, environment understanding, and interaction. The teaching presents spatial reference models, pose estimation, Visual-Inertial Odometry (VIO), and Simultaneous Localization and Mapping (SLAM), as well as rendering paradigms and environment understanding techniques. Finally, the main interaction paradigms with real and virtual objects are introduced, including hit testing, 3D object manipulation, and multimodal input techniques.

- Indoor positioning
An introduction to the main challenges of Indoor Positioning is provided, covering its applications, design requirements, and the characteristics of localization systems. The teaching presents the main Indoor Positioning techniques, including computer vision, Wi-Fi, Bluetooth Low Energy (BLE), Visual-Inertial Odometry (VIO), and hybrid approaches, discussing their principles, advantages, limitations, and application scenarios. Finally, the teaching introduces probabilistic data fusion techniques for noisy localization measurements, based on Bayesian Filtering, Hidden Markov Models (HMM), and Particle Filtering, showing how heterogeneous sensor observations and environmental map information can be integrated to improve localization accuracy.

- Activity recognition
An introduction to the fundamental principles of Human Activity Recognition (HAR) is provided, covering the complete development pipeline of an activity recognition system: data acquisition, pre-processing, segmentation, feature extraction, classification, and evaluation. The teaching presents the main Machine Learning and Deep Learning algorithms, activity recognition techniques based on inertial sensors and computer vision, as well as the paradigms of pose estimation, keypoint detection, and marker-less tracking. Finally, the main methodologies for model training and evaluation are introduced, concluding with a case study.

- introduction to iOS development (including an introduction to Swift programming and to Swift UI)
An introduction to the fundamental principles of iOS application development using the Swift programming language and the SwiftUI framework is provided. The teaching presents the main language constructs, including strong typing, optionals, struct, and class, together with the imperative and declarative paradigms for user interface development. Finally, the teaching introduces the architecture of SwiftUI, state management mechanisms based on property wrappers (e.g., @State), and the principles underlying reactive user interface updates.
Prerequisites for admission
È fortemente consigliato il superamento dell'esame di Mobile Computing.
Teaching methods
Frontal teaching.
Teaching Resources
Slides are provided (on the Ariel website) for each lesson, forming the base for the study material. Within the slides, links are available to scientific papers and online resources.
Assessment methods and Criteria
Assessment

The assessment consists of two components: a theory exam and a project.

Theory

The theory exam covers all the topics presented during the teaching.

A written exam is offered during the midterm assessment (typically in May) and during the June exam session. The written exam consists of 10 multiple-choice questions (1.5 points for each correct answer) and 2 open-ended questions (up to 7 points each).

During the other exam sessions, the assessment consists of a combination of written and oral examination. The instructor assigns two or three open-ended questions, which students answer in writing. The instructor then reviews the answers in real time and may ask the student to supplement or clarify them through additional written or oral responses.

Project

To assess students' practical skills, students are required to propose a project to the instructor. The project must address one of the three topics covered in the teaching: Augmented Reality (AR), Indoor Positioning, or Human Activity Recognition (HAR). The project may be carried out individually or in pairs. Upon completion, students take an oral examination, during which they present and discuss the work they have completed.
INFO-01/A - Informatics - University credits: 6
Lessons: 48 hours