SciTePress - Affiliation Profile

University of Insubria, Italy

Context (please use complete words only)

Field

Sort by

26 Papers

A Replicated Study on Factors Affecting Software Understandability

Topics: Software and Service Maintenance and Evolution; Maintainability

Authors: Georgia Kapitsaki ¹ , Luigi Lavazza ² , Sandro Morasca ² and Gabriele Rotoloni ²

Affiliations: ¹ Department of Computer Science, University of Cyprus, Nicosia, Cyprus , ² Dipartimento di Scienze Teoriche e Applicate, Università degli Studi dell’Insubria, Varese, Italy

Digital Object Identifier: 10.5220/0013339500003928

Proceedings of ENASE 2025, ISBN: 978-989-758-742-9

Quick Abstract

Background. Understandability is an important characteristic of software code that can largely impact the effectiveness and cost of software maintenance. Aim. We investigate if and to what extent the characteristics of source code captured by static metrics affect understandability. Method. We replicated an empirical study which provided some insights and highlighted some code characteristics that seem to affect understandability. The replication took place in a different country and was conducted with a different set of developers, i.e., Bachelor’s students, instead of Master’s students. The same source code was used in both studies. Results. The data collected in the replication do not corroborate the results of the initial study, since no correlation between code measures and code understanding could be found. The reason seems to be that the initial study involved developers with very similar skills and experience, while the replication involved developers with quite different skills. Conclusions. Code understanding appears to be affected much more by developers’ skills than by code characteristics. The extent to which code understanding depends on code characteristics is observable only for a homogeneous population of developers. Our results can be useful for software practitioners and for future software understandability studies.

Improving Classification in Skin Lesion Analysis Through Segmentation

Topic: Medical Imaging

Authors: Mirco Gallazzi , Anwar Rehman , Silvia Corchs and Ignazio Gallo

Affiliation: Department of Theoretical and Applied Science, University of Insubria, 21100 Varese, Italy

Digital Object Identifier: 10.5220/0013247900003905

Proceedings of ICPRAM 2025, ISBN: 978-989-758-730-6

Quick Abstract

Deep Learning plays a vital role in medical imaging, especially in classification and segmentation tasks essential for diagnosing diseases from images. However, current methods often struggle to differentiate visually similar classes and accurately delineate lesion boundaries. This study builds on prior findings of classification limitations, investigating whether segmentation can improve classification performance for skin lesion analysis with Transformer-based models. We benchmarked the segmentation capabilities of the Swin Transformer, YOLOv8, and DeepLabV3 architectures on the HAM dataset, which contains 10,015 images across seven skin lesion classes. Swin outperformed others in segmentation, achieving an intersection over union of 82.75%, while YOLOv8 achieved 77.0%. However, classification experiments using classification datasets after segmenting and cropping the lesion of interest did not produce the expected improvements, with classification accuracy showing slight drops in the segmented data. For example, on the original HAM dataset, the model achieved a Test Accuracy (TA) of 84.64%, while Swin trained on segmented data showed a slight decline to a TA of 84.13%. These findings suggest that segmentation alone may not effectively support classification. Based on this, we propose future research into a sequential transfer learning approach, where segmentation knowledge could be progressively transferred to improve classification.

Access Control Integration in Sparkplug-Based Industrial Internet of Things Systems: Requirements and Open Challenges

Topic: Internet of Things

Authors: Pietro Colombo and Elena Ferrari

Affiliation: Department of Theoretical and Applied Science, University of Insubria, Via O. Rossi, 9 - 21100 Varese, Italy

Digital Object Identifier: 10.5220/0013055700003825

Proceedings of WEBIST 2024, ISBN: 978-989-758-718-4

Quick Abstract

Sparkplug (ISO, 2023) is an emerging open-source software specification that supports integrating applications and devices in Industrial Internet of Things (IIoT) systems and eases data integration. Although recently introduced, Sparkplug has rapidly gained popularity, and its specifications have already been defined as an ISO standard. However, the basic data protection features it supports could hinder the adoption of Sparkplug on a large scale. Efficient access control solutions for Sparkplug-based IIoT systems open new research challenges. In this position paper, we take the first step to fill this void by presenting key requirements for integrating access control into Sparkplug systems and discussing significant issues for developing a suitable access control framework.

GASTon: A Graph-Exploration System for Indexing, Annotating and Visualizing PubMed Articles to Enhance the Analysis of Social deTerminants of Health

Topics: Databases and Datawarehousing; Healthcare Management Systems; Data Visualization; Big Data in Healthcare; Usability and UX of Healthcare IT

Authors: Simone Bottoni ¹ , Alberto Trombetta ¹ , Flavio Bertini ² , Danilo Montesi ³ , Francesca Bonin ⁴ , Alessandra Pascale ⁴ , Martin Gleize ⁴ and Pierpaolo Tommasi ⁴

Affiliations: ¹ Department of Theoretical and Applied Sciences, University of Insubria, Varese, Italy , ² Department of Mathematical, Physical and Computer Sciences, University of Parma, Parma, Italy , ³ Department of Computer Science and Engineering, University of Bologna, Bologna, Italy , ⁴ IBM Research Europe - Dublin, Ireland

Digital Object Identifier: 10.5220/0011714900003414

Proceedings of HEALTHINF 2023/BIOSTEC, ISBN: 978-989-758-631-6

Quick Abstract

Many works have shown associations between social determinants of health (SDoH) –the social circumstances in which people live– and health-related outcomes. However, the lack of SDoH data increases the challenges in measuring and understanding their effect on people’s health and health systems. In this paper, we present GASTon, a system for the indexing, annotation, and graph-based rendering of PubMed information to enable the search and retrieval of SDoHs in scientific literature. Our work provides a way to associate specific concepts with peer-reviewed articles to simplify the search for social factors. It builds a knowledge graph based on PubMed publications and associates them with concepts extracted from the Unified Medical Language System (UMLS) Metathesaurus. GASTon allows a full-text search and graph-based navigation and supports an overview of the concepts and related publications. Moreover, the architecture allows scale-up thanks to its containerized nature and parallelization capabilities. The system is open-source under the Apache V2 license.

Semi-automatic Segmentation of MRI Brain Metastases Combining Support Vector Machine and Morphological Operators

Topics: Support Vector Machines and Kernel Methods; Applications: Image Processing and Artificial Vision, Pattern Recognition, Decision Making, Industrial and Real World Applications, Financial Applications, Neural Prostheses and Medical Applications, Neural Based Data Mining and Complex Information Process

Authors: Gloria Gonella ¹ , Elisabetta Binaghi ¹ , Paola Nocera ² and Cinzia Mordacchini ³

Affiliations: ¹ Department of Theorical and Applied Science, Insubria University, Varese and Italy , ² C. S. Health Physics, ASST dei Sette Laghi, Varese, Italy, Department of Physics, University of Milan, Milan and Italy , ³ C. S. Health Physics, ASST dei Sette Laghi, Varese and Italy

Digital Object Identifier: 10.5220/0008019304570463

Proceedings of NCTA 2019/IJCCI, ISBN: 978-989-758-384-1

Quick Abstract

The objective of this study is to develop a semi-automatic, interactive segmentation strategy for efficient and accurate brain metastases delineation on Post Gadolinium T1-weighted brain MRI images. Salient aspects of the proposed solutions are the combined use of machine learning and image processing techniques, based on Support Vector Machine and Morphological Operators respectively, to delineate pathological and healthy tissues. The overall segmentation procedure is designed to operate on a clinical setting to reduce the workload of health-care professionals but leaving to them full control of the process. The segmentation process was validated for in-house collected image data obtained from radiation therapy studies. The results prove that the allied use of SVM and Morphological Operators produces accurate segmentations, useful for their insertion in clinical practice.

Query and Product Suggestion for Price Comparison Search Engines based on Query-product Click-through Bipartite Graphs

Topics: Searching and Browsing; Personalized Web Sites and Services; Recommendation Systems; Web Interface, Web Intelligence, Big data; Data Web Mining

Authors: Lucia Noce , Ignazio Gallo and Alessandro Zamberletti

Affiliation: University of Insubria, Italy

Digital Object Identifier: 10.5220/0005753400170024

Proceedings of WEBIST 2016, ISBN: 978-989-758-186-1

Quick Abstract

Query suggestion is a technique for generating alternative queries to facilitate information seeking, and has become a needful feature that commercial search engines provide to web users. In this paper, we focus on query suggestion for price comparison search engines. In this specific domain, suggestions provided to web users need to be properly generated taking into account whether both the searched and the suggested products are still available for sale. To this end, we propose a novel approach based on a slightly variant of classical query-URL graphs: the query-product click through bipartite graph. Such graph is built using information extracted both from search engine logs and specific domain features such as categories and products popularities. Information collected from the query-product graph can be used to suggest not only related queries but also related products. The proposed model was tested on several challenging datasets, and also compared with a recent competing query suggestion approach specifically designed for price comparison engines. Our solution outperforms the competing approach, achieving higher results both in terms of relevance of the provided suggestions and coverage rates on top-8 suggestions.

Related Ontology Subjects/Areas/Topics (7)

Enterprise Information Systems	Searching and Browsing	Web Information Systems and Technologies
Personalized Web Sites and Services	Software Agents and Internet Computing	Web Interfaces and Applications
Recommendation Systems

Defining and Evaluating Software Project Success Indicators - A GQM-based Case Study

Topics: Software Metrics; Project Planning, Monitoring and Control; Quality Control and Assurance

Authors: Luigi Lavazza ¹ , Enrico Frumento ² and Riccardo Mazza ³

Affiliations: ¹ CEFRIEL and Università degli Studi dell’Insubria, Italy , ² CEFRIEL, Italy , ³ WIND, Italy

Digital Object Identifier: 10.5220/0005517301050116

Proceedings of ICSOFT-EA 2015/ICSOFT, ISBN: 978-989-758-114-4

Quick Abstract

KPI (Key Process Indicators) and success indicators are often defined in a rather generic and imprecise manner. This happens because they are defined very early in the project’s life, when little details about the project are known, or simply because the definition does not follow a systematic and effective methodology. We need to precisely define KPI and project success indicators, guarantee that the data upon which they are based can be effectively and efficiently measured, and assure that the computed indicators are adequate with respect to project objectives, and represent the viewpoints of all the involved stakeholders. A complete and coherent process for managing KPI and success indicators lifecycle –instrumented with specific techniques and tools, including the Goal/Question/Metrics (GQM) method for the definition of measures and the R statistic language and environment for analyzing data and computing indicators– was applied in the evaluation of the European research project MUSES. The MUSES case study shows that the proposed process provides an easy and well supported path to the definition and implementation of effective KPI and project success indicators.

Related Ontology Subjects/Areas/Topics (4)

Project Planning, Monitoring and Control		Software Metrics		Software Project Management
Software Engineering

An Operational Semantics for XML Fuzzy Queries

Topics: Fuzzy Information Retrieval and Data Mining; Fuzzy Information Processing, Fusion, Text Mining

Authors: Alessandro Campi ¹ , Sam Guinea ¹ and Paola Spoletini ²

Affiliations: ¹ Politecnico di Milano, Italy , ² Università dell'Insubria, Italy

Digital Object Identifier: 10.5220/0005155502050210

Proceedings of FCTA 2014/IJCCI, ISBN: 978-989-758-053-6

Quick Abstract

XML has become a widespread format for data exchange over the Internet. The current state of the art in querying XML data is represented by XPath and XQuery, both of which define binary predicates. In this paper, we advocate that binary selection can at times be restrictive due to very nature of XML, and to the uses that are made of it. We therefore suggest a querying framework, called FXPath, based on fuzzy logics. In particular, we propose the use of fuzzy predicates for the definition of more ``vague'' and softer queries. We also introduce a function called ``deep-similar'', which aims at substituting XPath's typical ``deep-equal'' function. Its goal is to provide a degree of similarity between two XML trees, assessing whether they are similar both structure-wise and content-wise. In this paper we present the formal syntax and semantics of Fuzzy XPath, and discuss implementation issues

Related Ontology Subjects/Areas/Topics (6)

Artificial Intelligence		Fuzzy Information Processing, Fusion, Text Mining		Fuzzy Systems
Computational Intelligence		Fuzzy Information Retrieval and Data Mining		Soft Computing

Automatic Segmentation of MR Brain Tumor Images using Support Vector Machine in Combination with Graph Cut

Topics: Pattern Recognition; Industrial, Financial and Medical Applications; Support Vector Machines and Applications; Image Processing and Artificial Vision Applications

Authors: Elisabetta Binaghi , Massimo Omodei , Valentina Pedoia , Sergio Balbi , Desiree Lattanzi and Emanuele Monti

Affiliation: Insubria University, Italy

Digital Object Identifier: 10.5220/0005068501520157

Proceedings of NCTA 2014/IJCCI, ISBN: 978-989-758-054-3

Quick Abstract

This work focuses the attention on the automatic segmentation of meningioma from multispectral brain Magnetic Resonance imagery. The Authors address the segmentation task by proposing a fully automatic method hierarchically structured in two phases. The preliminary unsupervised phase is based on Graph Cut framework. In the second phase, preliminary segmentation results are refined using a supervised classification based on Support Vector Machine. The overall segmentation procedure is conceived fully automatic and tailored to non-volumetric data characterized by poor inter-slice spacing, in an attempt to facilitate the insertion in clinical practice. The results obtained in this preliminary study are encouraging and prove that the segmentation benefits from the allied use of Graph Cut and Support Vector Machine frameworks.

Related Ontology Subjects/Areas/Topics (23)

Artificial Intelligence	Health Engineering and Technology Applications	Pattern Recognition
Biomedical Engineering	Human-Computer Interaction	Physiological Computing Systems
Biomedical Signal Processing	Image Processing and Artificial Vision Applications	Sensor Networks
Computational Intelligence	Industrial, Financial and Medical Applications	Signal Processing
Computer-Supported Education	Methodologies and Methods	Soft Computing
Data Manipulation	Neural Networks	Support Vector Machines and Applications
Domain Applications and Case Studies	Neurocomputing	Theory and Methods
Fuzzy Systems	Neurotechnology, Electronics and Informatics

Data Quality Evaluation of Scientific Datasets - A Case Study in a Policy Support Context

Topic: Information Quality

Authors: Antonella Zanzi ¹ and Alberto Trombetta ²

Affiliations: ¹ Università degli Studi dell’Insubria and European Commission, Italy , ² Università degli Studi dell’Insubria, Italy

Digital Object Identifier: 10.5220/0004476401670174

Proceedings of DATA 2013, ISBN: 978-989-8565-67-9

Quick Abstract

In this work we present the rule-based approach used to evaluate the quality of scientific datasets in a policy support context. The used case study refers to real datasets in a context where low data quality limits the accuracy of the analysis results and, consequently, the significance of the provided policy advice. The applied solution consists in the identification of types of constraints that can be useful as data quality rules and in the development of a software tool to evaluate a dataset on the basis of a set of rules expressed in the XML markup language. As rule types we selected some types of data constraints and dependencies already proposed in data quality works, but we experimented also the use of order dependencies and existence constraints. The case study was used to develop and test the adopted solution, which is anyway generally applicable to other contexts.

Related Ontology Subjects/Areas/Topics (3)

Data Engineering

Data Management and Quality

Information Quality

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by