SciTePress - Affiliation Profile

University of Trieste, Italy

Context (please use complete words only)

Field

Sort by

9 Papers

Loads Estimation using Deep Learning Techniques in Consumer Washing Machines

Topics: Industry Related Applications; Deep Learning and Neural Networks

Authors: Alexander Babichev ¹ , Vittorio Casagrande ² , Luca Della Schiava ¹ , Gianfranco Fenu ³ , Imola Fodor ¹ , Enrico Marson ¹ , Felice Andrea Pellegrino ³ , Gilberto Pin ¹ , Erica Salvato ³ , Michele Toppano ¹ and Davide Zorzenon ⁴

Affiliations: ¹ Electrolux Italia S.p.A., Porcia, 33080, Italy , ² Department of Electrical and Electronic Engineering, University College London, U.K. , ³ Department of Engineering and Architecture, University of Trieste, Italy , ⁴ Technische Universität Berlin, Control Systems Group, Einsteinufer 17, D-10587 Berlin, Germany

Digital Object Identifier: 10.5220/0008935104250432

Proceedings of ICPRAM 2020, ISBN: 978-989-758-397-1

Quick Abstract

Home appliances are nowadays present in every house. In order to ensure a suitable level of maintenance, manufacturers strive to design a method to estimate the wear of the single electrical parts composing an appliance without providing it with a large number of expensive sensors. With this in mind, our goal consists in inferring the status of the electrical actuators of a washing machine, given the measures of electrical signals at the plug, which carry an aggregate information. The approach is end-to-end, i.e. it does not require any feature extraction and thus it can be easily generalized to other appliances. Two different techniques have been investigated: Convolutional Neural Networks and Long Short-Term Memories. These tools are trained and tested on data collected on four different washing machines.

Mosaic Images Segmentation using U-net

Topics: Deep Learning and Neural Networks; Image and Video Analysis and Understanding

Authors: Gianfranco Fenu , Eric Medvet , Daniele Panfilo and Felice Andrea Pellegrino

Affiliation: Dipartimento di Ingegneria e Architettura, Università degli Studi di Trieste, Trieste, Italy

Digital Object Identifier: 10.5220/0008967404850492

Proceedings of ICPRAM 2020, ISBN: 978-989-758-397-1

Quick Abstract

We consider the task of segmentation of images of mosaics, where the goal is to segment the image in such a way that each region corresponds exactly to one tile of the mosaic. We propose to use a recent deep learning technique based on a kind of convolutional neural networks, called U-net, that proved to be effective in segmentation tasks. Our method includes a preprocessing phase that allows to learn a U-net despite the scarcity of labeled data, which reflects the peculiarity of the task, in which manual annotation is, in general, costly. We experimentally evaluate our method and compare it against the few other methods for mosaic images segmentation using a set of performance indexes, previously proposed for this task, computed using 11 images of real mosaics. In our results, U-net compares favorably with previous methods. Interestingly, the considered methods make errors of different kinds, consistently with the fact that they are based on different assumptions and techniques. This finding suggests that combining different approaches might lead to an even more effective segmentation.

Topics: Knowledge Acquisition and Representation; Advanced Learning Methods; Machine Learning Methods; Deep Learning and Neural Networks

Authors: Alessio Ansuini ¹ , Eric Medvet ² , Felice Andrea Pellegrino ² and Marco Zullich ²

Affiliations: ¹ International School for Advanced Studies, Trieste, Italy , ² Dipartimento di Ingegneria e Architettura, Università degli Studi di Trieste, Trieste, Italy

Digital Object Identifier: 10.5220/0008960300520059

Proceedings of ICPRAM 2020, ISBN: 978-989-758-397-1

Quick Abstract

During the last few decades, artificial neural networks (ANN) have achieved an enormous success in regression and classification tasks. The empirical success has not been matched with an equally strong theoretical understanding of such models, as some of their working principles (training dynamics, generalization properties, and the structure of inner representations) still remain largely unknown. It is, for example, particularly difficult to reconcile the well known fact that ANNs achieve remarkable levels of generalization also in conditions of severe over-parametrization. In our work, we explore a recent network compression technique, called Iterative Magnitude Pruning (IMP), and apply it to convolutional neural networks (CNN). The pruned and unpruned models are compared layer-wise with Canonical Correlation Analysis (CCA). Our results show a high similarity between layers of pruned and unpruned CNNs in the first convolutional layers and in the fully-connected layer, while for the intermediate convolutional layers the similarity is significantly lower. This suggests that, although in intermediate layers representation in pruned and unpruned networks is markedly different, in the last part the fully-connected layers act as pivots, producing not only similar performances but also similar representations of the data, despite the large difference in the number of parameters involved.

Impact of Code Obfuscation on Android Malware Detection based on Static and Dynamic Analysis

Topics: Malware Detection; Data Mining and Knowledge Discovery

Authors: Alessandro Bacci ¹ , Alberto Bartoli ¹ , Fabio Martinelli ² , Eric Medvet ¹ , Francesco Mercaldo ² and Corrado Aaron Visaggio ³

Affiliations: ¹ Università degli Studi di Trieste, Italy , ² Consiglio Nazionale delle Ricerche, Italy , ³ Università degli Studi del Sannio, Italy

Digital Object Identifier: 10.5220/0006642503790385

Proceedings of ICISSP 2018, ISBN: 978-989-758-282-0

Quick Abstract

The huge diffusion of malware in mobile platform is plaguing users. New malware proliferates at a very fast pace: as a matter of fact, to evade the signature-based mechanism implemented in current antimalware, the application of trivial obfuscation techniques to existing malware is sufficient. In this paper, we show how the application of several morphing techniques affects the effectiveness of two widespread malware detection approaches based on Machine Learning coupled respectively with static and dynamic analysis. We demonstrate experimentally that dynamic analysis-based detection performs equally well in evaluating obfuscated and non-obfuscated malware. On the other hand, static analysis-based detection is more accurate on non-obfuscated samples but is greatly negatively affected by obfuscation: however, we also show that this effect can be mitigated by using obfuscated samples also in the learning phase.

VizMal: A Visualization Tool for Analyzing the Behavior of Android Malware

Authors: Alessandro Bacci ¹ , Fabio Martinelli ² , Eric Medvet ¹ and Francesco Mercaldo ²

Affiliations: ¹ Università degli Studi di Trieste, Italy , ² Consiglio Nazionale delle Ricerche, Italy

Digital Object Identifier: 10.5220/0006665005170525

Proceedings of ForSE 2018, ISBN: 978-989-758-282-0

Quick Abstract

Malware signature extraction is currently a manual and a time-consuming process. As a matter of fact, security analysts have to manually inspect samples under analysis in order to find the malicious behavior. From research side, current literature is lacking of methods focused on the malicious behavior localization: designed approaches basically mark an entire application as malware or non-malware (i.e., take a binary decision) without knowledge about the malicious behavior localization inside the analysed sample. In this paper, with the twofold aim of assisting the malware analyst in the inspection process and of pushing the research community in malicious behavior localization, we propose VizMal, a tool for visualizing the dynamic trace of an Android application which highlights the portions of the application which look potentially malicious. VizMal performs a detailed analysis of the application activities showing for each second of the execution whether the behavior exhibited is legitimate or malicious. The analyst may hence visualize at a glance when at to which degree an application execution looks malicious.

Yet Another Automated OLAP Workload Analyzer: Principles, and Experiences

Topics: Data Warehouses and OLAP; Performance Evaluation and Benchmarking

Authors: Alfredo Cuzzocrea ¹ , Rim Moussa ² and Enzo Mumolo ³

Affiliations: ¹ University of Trieste and ICAR-CNR, Italy , ² LaTICE and University of Carthage, Tunisia , ³ University of Trieste, Italy

Digital Object Identifier: 10.5220/0006812202930298

Proceedings of ICEIS 2018, ISBN: 978-989-758-298-1

Quick Abstract

In order to tune a data warehouse workload, we need automated recommenders on when and how (i) to partition data and (ii) to deploy summary structures such as derived attributes, aggregate tables, and (iii) to build OLAP indexes. In this paper, we share our experience of implementation of an OLAP workload analyzer, which exhaustively enumerates all materialized views, indexes and fragmentation schemas candidates. As a case of study, we consider TPC-DS benchmark -the de-facto industry standard benchmark for measuring the performance of decision support solutions including.

Related Ontology Subjects/Areas/Topics (4)

Data Warehouses and OLAP		Enterprise Information Systems		Performance Evaluation and Benchmarking
Databases and Information Systems Integration

On the Assessment of Segmentation Methods for Images of Mosaics

Topics: Segmentation and Grouping; Imaging for Cultural Heritage (Modeling/Simulation, Virtual Restoration)

Authors: Gianfranco Fenu ¹ , Nikita Jain ² , Eric Medvet ¹ , Felice Andrea Pellegrino ¹ and Myriam Pilutti Namer ³

Affiliations: ¹ University of Trieste, Italy , ² Delhi Technological University, India , ³ Ca' Foscari University of Venice, Italy

Digital Object Identifier: 10.5220/0005310101300137

Proceedings of VISAPP 2015/VISIGRAPP, ISBN: 978-989-758-091-8

Quick Abstract

The present paper deals with automatic segmentation of mosaics, whose aim is obtaining a digital representation of the mosaic where the shape of each tile is recovered. This is an important step, for instance, for preserving ancient mosaics. By using a ground-truth consisting of a set of manually annotated mosaics, we objectively compare the performance of some existing recent segmentation methods, based on a simple error metric taking into account precision, recall and the error on the number of tiles. Moreover, we introduce some mosaic-specific hardness estimators (namely some indexes of how difficult is the task of segmenting a particular mosaic image). The results show that the only segmentation algorithm specifically designed for mosaics performs better than the general purpose algorithms. However, the problem of segmentation of mosaics appears still partially unresolved and further work is needed for exploiting the specificity of mosaics in designing new segmentation algorithms.

Related Ontology Subjects/Areas/Topics (5)

Applications and Services		Image and Video Analysis		Segmentation and Grouping
Computer Vision, Visualization and Computer Graphics		Imaging for Cultural Heritage (Modeling/Simulation, Virtual Restoration)

Progressive Co-adaptation in Human-Machine Interaction

Topics: Vision, Recognition and Reconstruction; Human-Robots Interfaces; Human-Machine Interfaces; Cognitive Robotics

Authors: Paolo Gallina ¹ , Nicola Bellotto ² and Massimiliano Di Luca ³

Affiliations: ¹ University of Trieste, Italy , ² University of Lincoln, United Kingdom , ³ University of Birmingham, United Kingdom

Digital Object Identifier: 10.5220/0005561003620368

Proceedings of ICINCO 2015, ISBN: 978-989-758-123-6

Quick Abstract

In this paper we discuss the concept of co-adaptation between a human operator and a machine interface and we summarize its application with emphasis on two different domains, teleoperation and assistive technology. The analysis of the literature reveals that only in a few cases the possibility of a temporal evolution of the co-adaptation parameters has been considered. In particular, it has been overlooked the role of time-related indexes that capture changes in motor and cognitive abilities of the human operator. We argue that for a more effective long-term co-adaptation process, the interface should be able to predict and adjust its parameters according to the evolution of human skills and performance. We thus propose a novel approach termed progressive co-adaptation, whereby human performance is continuously monitored and the system makes inferences about changes in the users' cognitive and motor skills. We illustrate the features of progressive co-adaptation in two possible applications, robotic telemanipulation and active vision for the visually impaired.

Related Ontology Subjects/Areas/Topics (8)

Agents	Human-Machine Interfaces	Robotics and Automation
Artificial Intelligence	Human-Robots Interfaces	Vision, Recognition and Reconstruction
Cognitive Robotics	Informatics in Control, Automation and Robotics

A Metamodelling Approach to the Management of Intermodal Transportation Networks

Authors: Valentina Boschian ¹ , Mariagrazia Dotoli ² , Maria Pia Fanti ² , Giorgio Iacobellis ² and Walter Ukovich ¹

Affiliations: ¹ University of Trieste, Italy , ² Politecnico di Bari, Italy

Digital Object Identifier: 10.5220/0002271800960105

Proceedings of Workshop IVC & ITS 2009/ICINCO, ISBN: 978-989-674-003-0

Quick Abstract

The paper develops a novel and broad metamodel of a generic Intermodal Transportation Network (ITN), devoted to provide a reference model for the real time management and control of such systems. In order to take operational decisions, the presented model describes in detail the ITN structure and dynamic evolution that is updated on the basis of the information obtained in real time by modern information and communication technologies tools. The proposed metamodelling approach consists in employing a top down procedure and is based on the UML formalism, a graphic and textual modelling language intended to describe systems from structural and dynamics viewpoints. Hence, the paper models a generic ITN starting from the network description and shows as an example the metamodel of one of the most important nodes that compose it: the port subsystem. To this aim, we present the main UML dia-grams describing the structure and dynamics of a case study

Context (please use complete words only)

Field

Sort by

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by