Politecnico di Torino logo
Staff

Filippo Gandino

Filippo Gandino's picture

Associate Professor (L. 240)
Department of Control and Computer Engineering (DAUIN)

  • Member of Interdepartmental Center PIC4SeR - PoliTO Interdepartmental Centre for Service Robotics

Profile

Keywords

Complex systems
Data-driven systems
Information theory
Internet of things (iot)
Machine learning
Quantum computers
Security and privacy
Wireless sensor network (wsn)

Biography

Filippo Gandino received the M.S. degree in Computer Engineering in 2005 and the Ph.D. degree in Computer Engineering in 2010 from Politecnico di Torino, Italy. He is currently an Associate Professor with the Department of Control and Computer Engineering, Politecnico di Torino. His research interests include the Internet of Things, security and privacy, machine learning, complex systems, information theory, and data-driven systems.

Scientific branch

IINF-05/A - Information Processing Systems
(Area 0009 - Industrial and information engineering)

Research topics

  • Bioinformatics, complex systems and information theory. This research line focuses on the application of computational, information-theoretic and data-driven methods to the analysis of complex biological and biomedical data, within an interdisciplinary collaboration involving expertise in the physics of complex systems. The activity addresses heterogeneous, high-dimensional and often noisy data, with the aim of extracting relevant information, identifying significant patterns and supporting the construction of structured knowledge representations. This area includes the use of measures based on entropy, informativeness, redundancy, similarity and complexity, as well as clustering, classification and pattern-analysis techniques applied to biological, genomic and biomedical data. Particular attention is devoted to transforming complex data into interpretable and usable information, distinguishing relevant signals from noise, anomalies or redundant content. This research line integrates expertise in computer science, information theory, complex systems and quantitative data analysis, with applications in bioinformatics, biomedical data analysis and the construction of information models supporting data-driven systems.
  • Games, human-computer interaction and player-experience analysis. This research line focuses on the computational study of game experience and of the interaction between players, digital systems and game environments. The goal is to develop methods and tools to observe, measure and interpret emotions, behaviours, interaction dynamics, cooperation, competition, engagement and coordination during game activities, serious games and interactive simulations. This line also aims to support interdisciplinary studies on games carried out in other fields, such as social sciences, psychology, education, interaction design, game studies and organisational studies. In this context, computational analysis can provide quantitative and data-driven tools to investigate how players interact with each other and with the system, how cooperation and competition emerge, how engagement changes over time, and how different game conditions influence behaviour, learning, decision-making and participation. The activities may use heterogeneous data, including images and videos, biometric signals, audio, text, game logs, interaction data, questionnaires and experimental annotations. Machine learning, data mining, multimodal analysis, pattern recognition and behavioural modelling techniques are applied to these data to extract useful indicators for understanding emotional states, attention, engagement, stress, frustration, collaboration, group strategies and interaction quality. This research line combines human-computer interaction, game analytics, affective computing, machine learning and multimodal data analysis, with applications in serious games, adaptive video games, interactive simulations, user-experience evaluation and the experimental study of interaction, cooperation and behaviour in game environments.
  • Precision agriculture, computer vision and machine learning. This research line focuses on the application of machine learning, computer vision and image-analysis techniques to precision agriculture. The goal is to develop automatic or semi-automatic systems capable of analysing images, videos and data acquired from sensors to support the monitoring, classification and intelligent management of crops, plants, fruits, soil and environmental conditions. The activities include automatic recognition of objects and visual patterns, image classification, detection of anomalies, defects or stress conditions, analysis of growth and ripening stages, and decision support in agricultural contexts. The use of machine learning techniques makes it possible to transform visual and sensor data into useful information for optimizing interventions, reducing waste, improving production quality and promoting more sustainable agricultural practices. This research line lies at the intersection of intelligent systems, IoT, sensing technologies, image processing and data-driven decision support, with applications in real-world scenarios of digital and sustainable agriculture.
  • Security, privacy and distributed ICT systems. This research line focuses on security and privacy in distributed ICT systems, with particular attention to the Internet of Things, wireless sensor networks, pervasive systems and infrastructures characterized by heterogeneous devices and resource constraints. The activity addresses the design and evaluation of methods to protect data, communications and processing workflows in distributed environments. Main topics include secure protocols, key management and distribution, protection mechanisms in sensor networks, security in IoT scenarios, access control, communication reliability and privacy-aware information processing. Particular attention is devoted to scenarios in which sensitive or strategic data are collected, transmitted, processed or shared by multiple devices, platforms or actors. This research line aims to develop solutions that combine efficiency, scalability, robustness and information protection, contributing to the design of secure, reliable and privacy-aware distributed systems. These competences are applicable to sensor networks, IoT, cyber-physical systems, smart infrastructures and data-processing pipelines in which information protection is a key requirement.

Skills

ERC sectors

PE6_1 - Computer architecture, pervasive computing, ubiquitous computing
PE7_8 - Networks, e.g. communication networks and nodes, Internet of Things, sensor networks, networks of robots

SDG

Goal 3: Good health and well-being

Awards and Honors

  • Best Paper Award conferred by The 6-th International Conference of Broadband and Wireless Computing, Communication and Applications (BWCCA-2011) (2011)

Teaching

Collegi of the degree programmes

Teachings

Bachelor of Science

MostraNascondi A.A. passati

Research

Research groups

Supervised PhD students

Publications

Latest publications View all publications in Porto@Iris