Abstract The progress made in the field of medicine and the consequent increase in the prospect of life have contributed to rise people's interest towards a healthier lifestyle. Fitness activity is becoming a must for those who aspire to live more and better. However, this should be accompanied by additional good practices to safeguard individuals' life from risks that could undermine their health. Most of these risks are linked to personal, surrounding, and contextual conditions that technology can detect and monitor. Recommender systems can adequately support fitness activity by performing data analyzes aimed at identifying possible risk factors for users, starting from their physiological data and those related to the closest context where they are. This article introduces the architecture of a recommender system called App4Health in the context related to both mobile crowd sensing and wellness. The App4Health architecture consists of a smart application platform, capable of interfacing and managing data from heterogeneous edge sources, such as mobile phones, IoT, and sensors. The analysis result consists of the semantic generation of healthy behavioral conducts to the user as Telegram BOT messages. For evaluating the proposed solution, the article also provides a case study and a testbed. The testbed consists of a comparative stress test of two edge software components of the App4Health's architecture in order to identify the performance degradation threshold of these components, assuming that they can be deployed on edge‐level hardware devices with different technical specifications and configurations.

Abstract Trial excessive duration is a common problem in Juridical systems worldwide, even if some countries seem to be more affected by it than others. The European Council has provided metrics and statistics to identify this problem and has pointed out solutions, such as the simplification of norms and the digitization of Juridical procedures. The Italian Telematic Civil Process (TCP) is an example of this digitization effort that has surely positively influenced the duration of Trials, their traceability and general complexity. However, there are still many possible actions that can be taken to simplify the work of Judges and Chancellors, and to support their daily operations in dealing with several Trials at once, and with the consistent number of documents that are involved in them. This paper presents a toolchain and a related methodology for the management of documentation attached to Trials, based on semantic technologies and Natural Language Processing techniques, which will help Judges in faster assessing the situation of each Trial they follow, and will also provide the means to identify potential correlations among different Juridical procedures. The methodology is tested against a case study, i.e. the compensation requests related to road accidents, which has been provided and described by Domain Experts from the Italian Ministry of Justice.

Through the digitalisation of Civil Trials and the implementation of the Telematic Civil Process framework, the Italian Ministry of Justice has amassed a wealth of data covering all facets of modern Trials. While data availability has surged, the focus now lies in actively analysing this data to optimise Trials and curtail their duration. This paper, with a strong emphasis on its outcomes, delves into the analysis of data from the Court of Livorno. It seeks to pinpoint specific events within the Trial workflow that significantly extend Trial durations. Notably, Domain Experts have identified a set of events, intending to validate their pivotal role in recognising critical Trials. Leveraging Machine Learning techniques, the paper evaluates multiple binary classifiers to proactively identify potentially critical Trials, empowering Judges to mitigate future issues. The study has yielded a remarkable 80% accuracy rate in predicting Trials exceeding acceptable duration thresholds.

This paper focuses on exploring and comparing different machine learning algorithms in the context of diabetes management.The aim is to understand their characteristics, mathematical foundations, and practical implications specifically for predicting blood glucose levels.The study provides an overview of the algorithms, with a particular emphasis on deep learning techniques such as Long Short-Term Memory Networks.Efficiency is a crucial factor in practical machine learning applications, especially in the context of diabetes management.Therefore, the paper investigates the tradeoff between accuracy, resource utilisation, time consumption, and computational power requirements, aiming to identify the optimal balance.By analysing these algorithms, the research uncovers their distinct behaviours and highlights their dissimilarities, even when their analytical underpinnings may appear similar.

Abstract The adoption of the business process model notation for the description of internal workflows and procedures by both public administrations and private organizations is steadily growing, thanks to the simplicity of the standard and its consistent expressivity. However, the lack of semantic support from BPMN can pose important limitations to its efficient use, as ambiguities in task definitions and communications can lead to misinterpretations. Furthermore, there is the need to validate the BPMNs, to check their adherence to regulations, especially in public administration, and to verify their conformance to security and privacy constraints. In this work, we present SemPrAnn, a semantic annotation tool for BPMN that, exploiting domain ontologies and logical rules, provides the possibility to unambiguously identify concepts in workflows and to run inferential engines against them to enforce the rules. The manuscript presents the methodology applied for the implementation of the tool, the tool itself with its exposed functionalities, and a case study demonstrating its current capabilities.

Abstract Patients afflicted by multiple sclerosis experience a relapsing-remitting course in about 85% of the cases. Furthermore, after a 10/15-year period their situation tends to worse, resulting in what is considered the second phase of multiple sclerosis. While treatments are now available to reduce the symptoms and slow down the progression of the disease, the administration of drugs must be adapted to the course of the disease, and predicting relapsing periods and the worsening of the symptoms can greatly improve the outcome of the treatment. For this reason, indicators such as the patient-reported outcome measures (PROMs) have been largely used to support early diagnosis and prediction of future relapsing periods in patients affected by multiple sclerosis. However, such indicators are insufficient, as the prediction they provide is often not accurate enough. In this paper, machine learning techniques have been applied to data obtained from clinical trial, in order to improve the prediction capabilities and provide doctors with an additional instrument to evaluate the clinical situation of patients. After the application of correlation indicators and the use of principal component analysis for the reduction of the dimensionality of the feature space, classification algorithms have been applied and compared, in order to identify the best suiting one for our purposes. After the application of re-balance algorithms, the accuracy of the machine learning-based prediction system reaches 79%, demonstrating the capability of the framework to correctly predict future progression of disability.

To run proper Big Data Analytics, small and medium enterprises (SMEs) need to acquire expertise, hardware and software, which often translates to relevant initial investments for activities not directly connected to the company's business. To reduce such investments, the TOREADOR project proposes a Big Data Analytics framework which supports users in devising their own Big Data solutions by keeping the inherent costs at a minimum, and leveraging pre-existent knowledge and expertise. Among the objectives of the TOREADOR framework is supporting developers in parallelizing and deploying their Big Data algorithms, in order to develop their own analytics solutions. This paper describes the Code-Based approach, adopted within the TOREADOR framework to parallelize users' algorithms and deploy them on distributed platforms, via the annotation of parallelizable code portions with parallelization primitives. The approach, which relies on the guidance of Parallel Patterns to implement the parallelization, and on Skeletons to automatically build execution and deployment templates, is realized through a source-to-source Compiler, also described in the present paper.

During the past years the Cloud Computing offer has exponentially grown, with new Cloud providers, platforms and services being introduced in the IT market. The extreme variety of services, often providing non uniform and incompatible interfaces, makes it hard for customers to decide how to develop, or even worse to migrate, their own application into the Cloud. This situation can only get worse when customers want to exploit services from different providers, because of the portability and interoperability issues that often arise. In this paper we propose a uniform, integrated, machine-readable, semantic representation of cloud services, patterns, appliances and their compositions. Our approach aims at supporting the development of new applications for the Cloud environment, using semantic models and automatic reasoning to enhance potability and interoperability when multiple platforms are involved. In particular, the proposed reasoning procedure allows to: perform automatic discovery of Cloud services and Appliances; map between agnostic and vendor dependent Cloud Patterns and Services; automatically enrich the semantic knowledge base.

Nowadays, most of the information available on the web is in Natural Language. Extracting such knowledge from Natural Language text is an essential work and a very remarkable research topic in the Semantic Web field. The logic programming language Prolog, based on the definite-clause formalism, is a useful tool for implementing a Natural Language Processing (NLP) systems. However, web-based services for NLP have also been developed recently, and they represent an important alternative to be considered. In this paper we present the comparison between two different approaches in NLP, for the automatic creation of an OWL ontology supporting the semantic annotation of text. The first one is a pure Prolog approach, based on grammar and logic analysis rules. The second one is based on Watson Relationship Extraction service of IBM Cloud platform Bluemix. We evaluate the two approaches in terms of performance, the quality of NLP result, OWL completeness and richness.

The development of a complex software system involves many actors, whose skills and knowledge are very heterogeneous. The requirements representation made using the Business Process notations is far more understandable than the classic UML representation, at least for Business experts, as it allows to investigate the system from other points of view which are not merely connected the development of the software itself. However, it is not possible to completely disregard UML representations, as they catch software design information which would be lost otherwise. In order to use both representations as basic tools through the whole software development life cycle, a key point is to ensure that they can be easily combined together to facilitate the development of the system software assets. In this paper we address this interoperability scope and provide a unified semantic representation, capable of covering every aspect of software development life cycle and of bonding the different Business and Software development points of view, from the requirements definition to the actual implementation of the source code, including the migration of applications to the Cloud.

In the present work, we describe a procedure and a prototype implementation for the automatic recognition of design patterns from documentation of software artefacts design and implementation, provided in a machine readable form, namely, the XML Metadata Interchange (XMI) coded representation of UML class diagrams. The procedure exploits a semantic representation of the patterns to be recognized, based on an existing Web Ontology Language (OWL), known as object design ontology layer (ODOL), defined by the University of Massey (New Zealand), which has been augmented with an OWL-S based representation of the patterns' dynamic behaviour. Both the UML set of diagrams related to the analysed software artefacts and the ODOL+OWL-S patterns representation are automatically scanned and translated into a first-order logic representation (namely Prolog). A set of first-order logic rules, independent from the specific pattern to be recognized, has been defined to describe the heuristics and features which trigger the recognition, exploiting the Prolog description of the patterns to be recognized and the base of Prolog facts, which represents the UML documentation. Copyright © 2015 John Wiley & Sons, Ltd.

Cloud computing is driving formidable change in the technology industry and transforming how to do business in Europe and around the world. Despite the obvious advantages of cloud computing there are a number of issues that require solutions for Cloud computing to develop further. In particular challenges include (but are not limited to) lack of support for heterogeneous Cloud providers, lack of meaningful cross-platform Cloud resource descriptions, lack of lifecycle management of Cloud applications. In this paper we propose an overview of two solutions for cloud services description and orchestration, TOSCA (Topology and Orchestration Specification for Cloud Applications) and HOT (Heat Orchestration Template), a comparison among these two solution and examples of how these two solutions correlate with cloud patterns.

The Cloud Computing paradigm has been adopted in countless areas of application and forms the basis of a growing number of business cases. Similar to the situation with service providers in the 1980th, it becomes apparent that different Cloud providers build walled gardens around their offerings. While multiple projects and organizations are working on standards for federating Cloud domains, the scalable exchange of descriptions about heterogeneous resources are often not well considered. Our approach is to adopt both, ideas initially developed for the Internet to define a scalable architecture and concepts from the Semantic Web to define a canonical Intercloud ontology. An initial implementation of the architecture has been developed to form a basis for further refinement of the proposed concepts. As a result, we have defined an initial ontology for Intercloud resources and implemented a catalog for the IEEE Intercloud architecture.

Business Process management has attracted the attention of companies and organizations, which have heavily invested in the research and development of tools and standards for process representation and business requirement formalization. Several tools have been produced for the representation and management of Business processes, and many companies have designed their enterprise models using business process standards. In this paper we analyse different approaches to enrich the existing standards, in particular the Business Process Model Notation (BPMN), with the semantic information provided by OWL ontologies. We also discuss the motivations behind the need of a semantic annotation for Business Processes and provide an overview of existing research efforts and results.

Virtualization technologies represent the basis of many software architectures and frameworks existing today, Cloud Computing being probably the most influenced paradigm in the current scenery. With the steady growth of new Cloud and Virtualization platforms, which have caused the proliferation of many Cloud Services and Virtual appliances, it seems necessary to put order in the chaos of overlapping functionalities such services and appliances provide. A common representation of both Cloud Services and Virtual Appliances can be the perfect starting point to define a functional classification that could help customers choose the resources which best adhere to their objectives. A semantic based representation, implemented through an OWL [1] ontology, is probably the best candidate for this purpose, thanks to the flexibility of the OWL language and the possibility to navigate the ontology using both visual tools and query languages.

This paper focuses on two aspects related to the widespread of cloud computing: first, the definition of a common formalism, based on a unique and shared model, which could be used to completely describe Cloud patterns, second, the investigation of a methodology to automatize the recognition of similar elements in Design and Cloud patterns, thus defining an automatic mapping among representations of application that follow these patterns. These aspects are handled on one hand by extending an existing semantic based Design pattern language in order to properly represent both Design and Cloud patterns together with its possible related architectural implementations and on the other hand by using these agnostic representations to define a mapping between Design patterns (a single design pattern or a composition of pattern) and Cloud patterns, in order to obtain a clear model of the cloud applications which could satisfy its original requirements and exploit all the benefits of cloud computing at the same time.

Here we describe a procedure and a prototype implementation for the automatic recognition of Design Patterns from documentation of Software Artefacts' design and implementation, provided in a machine readable form, namely the XMI coded representation of UML diagrams. The procedure exploits a semantic representation of the patterns to be recognized, based on the ODOL ontology defined by the University of Massey (New Zealand) [12], which we have augmented with an OWL-S based representation of the patterns' dynamic behaviour. Both the UML set of diagrams related to the analysed Software Artefacts and the ODOL+OWL-S patterns' representation are automatically scanned and translated into a first order logic representation (namely Prolog). A set of first order logic rules, independent from the specific pattern to be recognized, have been defined to describe the heuristics and features which trigger the recognition, exploiting the Prolog description of the patterns to be recognized and the base of Prolog facts which represents the UML documentation.

This paper describes a semantic based representation for Design Patterns, defined on the base of the formal pattern language known as ODOL, which has been corrected and extended to better represent both structural and behavioural aspects of pattern descriptions. In particular, new concepts have been added to the underlying OWL ontology to enrich the structural description of patterns, while OWL-S has been adopted to describe patterns' behaviour by representing participants' methods as services. Our goal is to define a new, flexible and easily extendible pattern representation, which could be used to describe all aspects of Design Patterns and could be also applied to cloud computing, in particular to the description of Cloud Patterns. We provide details on the defined language and considerations on its ability to describe both Design and Cloud Patterns.