Tiziano Leidi

Prof. Dr. Tiziano Leidi

Institute of Information Systems and Networking, University of Applied Sciences and Arts of Southern Switzerland, Bioggio, Switzerland
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2022 in Clinical, Cosmetic and Investigational Dermatology
Verified
Journal Article
Open access
PDF file
AQAndrea Quattrini
Andrea Quattrini
CBClaudio Boër
Claudio Boër
Tiziano LeidiTiziano Leidi
Tiziano Leidi
RPRick Paydar
Rick Paydar
Introduction: Acne is one of the most common pathologies and affects people of all ages, genders, and ethnicities. The assessment of the type and severity status of a patient with acne should be done by a dermatologist, but the ever-increasing waiting time for an examination makes the therapy not accessible as quickly and consequently less effective. This work, born from the collaboration with CHOLLEY, a Swiss company with decades of experience in the research and production of skin care products, with the aim of developing a deep learning system that, using images produced with a mobile device, could make assessments and be as effective as a dermatologist. Methods: There are two main challenges within this task. The first is to have enough data to train a neural model. Unlike other works in the literature, it was decided not to collect a proprietary dataset, but rather to exploit the enormity of public data available in the world of face analysis. Part of Flickr-Faces-HQ (FFHQ) was re-annotated by a CHOLLEY dermatologist, producing a dataset that is sufficiently large, but still very extendable. The second challenge was to simultaneously use high-resolution images to provide the neural network with the best data quality, but at the same time to ensure that the network learned the task correctly. To prevent the network from searching for recognition patterns in some uninteresting regions of the image, a semantic segmentation model was trained to distinguish, what is a skin region possibly affected by acne and what is background and can be discarded. Results: Filtering the re-annotated dataset through the semantic segmentation model, the trained classification model achieved a final average f1 score of 60.84% in distinguishing between acne affected and unaffected faces, result that, if compared to other techniques proposed in the literature, can be considered as state-of-the-art.

2 December 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
VBValeria Bruschi
Valeria Bruschi
LGLoris Grossi
Loris Grossi
NDNefeli-Aikaterini Dourou
Nefeli-Aikaterini Dourou
AQAndrea Quattrini
Andrea Quattrini
AVAlberto Vancheri
Alberto Vancheri
SCStefania Cecchi
Stefania Cecchi
A head-related transfer function (HRTF) is a mathematical model that describes the acoustic path between a sound source and a listener’s ear. Using binaural synthesis techniques, HRTFs play a crucial role in creating immersive audio experiences through headphones or loudspeakers, using binaural synthesis techniques. HRTF measurements can be conducted either with standardised mannequins or with in-ear microphones on real subjects. However, various challenges arise in, for example, individual differences in head shape, pinnae geometry, and torso dimensions, as well as in the extensive number of measurements required for optimal audio immersion. To address these issues, numerous methods have been developed to generate new HRTFs from existing data or through computer simulations. This review paper provides an overview of the current approaches and technologies for generating, adapting, and optimising HRTFs, with a focus on physical modelling, anthropometric techniques, machine learning methods, interpolation strategies, and their practical applications.

24 October 2021 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
MMMassimo Maiolo
Massimo Maiolo
LGLorenzo Gatti
Lorenzo Gatti
DFDiego Frei
Diego Frei
Tiziano LeidiTiziano Leidi
Tiziano Leidi
MGManuel Gil
Manuel Gil
Maria AnisimovaMaria Anisimova
Maria Anisimova
Background: Current alignment tools typically lack an explicit model of indel evolution, leading to artificially short inferred alignments (i.e., over-alignment) due to inconsistencies between the indel history and the phylogeny relating the input sequences. Results: We present a new progressive multiple sequence alignment tool ProPIP. The process of insertions and deletions is described using an explicit evolutionary model—the Poisson Indel Process or PIP. The method is based on dynamic programming and is implemented in a frequentist framework. The source code can be compiled on Linux, macOS and Microsoft Windows platforms. The algorithm is implemented in C++ as standalone program. The source code is freely available on GitHub at https://github.com/acg-team/ProPIP and is distributed under the terms of the GNU GPL v3 license. Conclusions: The use of an explicit indel evolution model allows to avoid over-alignment, to infer gaps in a phylogenetically consistent way and to make inferences about the rates of insertions and deletions. Instead of the arbitrary gap penalties, the parameters used by ProPIP are the insertion and deletion rates, which have biological interpretation and are contextualized in a probabilistic environment. As a result, indel rate settings may be optimised in order to infer phylogenetically meaningful gap patterns.

22 March 2022
Verified
Book Chapter
Closed access
PDF file
DADavide Andreoletti
Davide Andreoletti
MPMarco Paoliello
Marco Paoliello
LLLuca Luceri
Luca Luceri
Tiziano LeidiTiziano Leidi
Tiziano Leidi
APAchille Peternier
Achille Peternier
Silvia GiordanoSilvia Giordano
Silvia Giordano

11 September 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MPMichela Papandrea
Michela Papandrea
APAchille Peternier
Achille Peternier
DFDiego Frei
Diego Frei
NPNicolò La Porta
Nicolò La Porta
MGMirko Gelsomini
Mirko Gelsomini
Tiziano LeidiTiziano Leidi
Tiziano Leidi
The V-Cockpit platform aims to transform the design, testing, and validation of car infotainment systems from the physical realm to virtual reality. It uniquely integrates various aspects of the creative phases—from conceptualization to evaluation—streamlining the process and reducing time and costs compared to traditional methods that focus on individual activities and rely heavily on physical prototyping. This technical note provides a comprehensive overview of the main platform’s aspects, highlighting the integration of hardware and behavioral analysis algorithms to improve user experience and detect potential design flaws early on. The V-Cockpit platform, composed of six key components, leverages virtual reality and digital twins, promising significant cost savings and enhanced design efficiency. This work details the system architecture, implementation, and first benefits of this innovative approach through the analysis of three use cases.

29 April 2024 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Closed access
MCMassimo Coluzzi
Massimo Coluzzi
ABAmos Brocco
Amos Brocco
AAAlessandro Antonucci
Alessandro Antonucci
Tiziano LeidiTiziano Leidi
Tiziano Leidi
Consistent hashing is used in distributed systems and networking applications to spread data evenly and efficiently across a cluster of nodes. In this paper, we present MementoHash, a novel consistent hashing algorithm that eliminates known limitations of state-of-the-art algorithms while keeping optimal performance and minimal memory usage. We describe the algorithm in detail, provide a pseudo-code implementation, and formally establish its solid theoretical guarantees. To measure the efficacy of MementoHash, we compare its performance, in terms of memory usage and lookup time, to that of state-of-the-art algorithms, namely, AnchorHash, DxHash, and JumpHash. Unlike JumpHash, MementoHash can handle random failures. Moreover, MementoHash does not require fixing the overall capacity of the cluster (as AnchorHash and DxHash do), allowing it to scale indefinitely. The number of removed nodes affects the performance of all the considered algorithms. Therefore, we conduct experiments considering three different scenarios: stable (no removed nodes), one-shot removals (90% of the nodes removed at once), and incremental removals. We report experimental results that averaged a varying number of nodes from ten to one million. Results indicate that our algorithm shows optimal lookup performance and minimal memory usage in its best-case scenario. It behaves better than AnchorHash and DxHash in its average-case scenario and at least as well as those two algorithms in its worst-case scenario.