Search

The current travel demand in railways requires the adoption of novel approaches and technologies in order to increase network capacity. Virtual Coupling is considered one of the most innovative solutions to increase railway capacity by drastically reducing train headway. The aim of this paper is to provide an approach to investigate the potential of Virtual Coupling in railways by composing stochastic activity networks model templates. The paper starts describing the Virtual Coupling paradigm with a focus on standard European railway traffic controllers. Based on stochastic activity network model templates, we provide an approach to perform quantitative evaluation of capacity increase in reference Virtual Coupling scenarios. The approach can be used to estimate system capacity over a modelled track portion, accounting for the scheduled service as well as possible failures. Due to its modularity, the approach can be extended towards the inclusion of safety model components. The contribution of this paper is a preliminary result of the PERFORMINGRAIL (PERformance-based Formal modelling and Optimal tRaffic Management for movING-block RAILway signalling) project funded by the European Shift2Rail Joint Undertaking.

Convolutional Neural Networks (CNNs) are opening for unprecedented scenarios in fields where designing effective features is tedious even for domain experts. This is the case of medical imaging, i.e. procedures acquiring images of a human body interior for clinical proposes. Despite promising, we argue that CNNs naive use may not be effective since “medical images are more than pictures”. A notable example is breast Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI), in which the kinetic of the injected Contrast Agent (CA) is crucial for lesion classification purposes. Therefore, in this work we introduce a new GAN like approach designed to simultaneously learn how to disentangle the CA effects from all the other image components while performing the lesion classification: the generator is an intrinsic Deforming Autoencoder (DAE), while the discriminator is a CNN. We compared the performance of the proposed approach against some literature proposals (both classical and CNN based) using patient-wise cross-validation. Finally, for the sake of completeness, we also analyzed the impact of variations in some key aspect of the proposed solution. Results not only show the effectiveness of our approach ( + 8 % AUC w.r.t. the runner-up) but also confirm that all the approach’s components effectively contribute to the solution.

Some applications have the property of being resilient, meaning that they are robust to noise (e.g. due to error) in the data. This characteristic is very useful in situations where an approximate computation allows to perform the task in less time or to deploy the algorithm on embedded hardware. Deep learning is one of the fields that can benefit from approximate computing to reduce the high number of involved parameters thanks to its impressive generalization ability. A common approach is to prune some neurons and perform an iterative re-training with the aim of both reducing the required memory and to speed-up the inference stage. In this work we propose to face CNN size reduction from a different perspective: instead of reducing the network weights or look for an approximated network very close to the Pareto frontier, we investigate whether it is possible to remove some neurons only from the fully connected layers before the network training without substantially affecting the network performance. As a case study, we will focus on “fine-tuning”, a branch of transfer learning that has shown its effectiveness especially in domains lacking effective expert-designed features. To further compact the network, we apply weight quantization to the convolutional kernels. Results show that it is possible to tailor some layers to reduce the network size, both in terms of the number of parameters to learn and required memory, without statistically affecting the performance and without the need for any additional training. Finally, we investigate to what extent the sizing operation affects the network robustness against adversarial perturbations, a set of approaches aimed at misleading deep neural networks.

In this paper we present a modeling approach suitable for practical evaluation of the delays that may affect security monitoring systems in (multitenant) cloud based architecture, and in general to support professionals in planning and evaluating relevant parameters in dealing with new designs or migration projects. The approach is based on modularity and multiformalism techniques to manage complexity and guide designers in an incremental process, to help transferring technical knowledge into modeling practice and to help easing the use of simulation. We present a case study based on a real experience, triggered by a new legal requirement that Italian Public Administration should comply about their datacenters.

The article revises the different views and conceptualizations for cyber resilience and proposes a novel holistic definition able to accommodate in a unique coherent vision the existing multiple facets. The resulting integrated concept has been formalisied defining a new comprehensive domain-based ontology for Cyber Resilience to be used as a knowledge base for an effective data driven multi-criteria decision making for resilience.

Recent times have demonstrated how much the modern critical infrastructures (e.g., energy, essential services, people and goods transportation) depend from the global communication networks. However, in the current Cyber-Physical World convergence, sophisticated attacks to the cyber layer can provoke severe damages to both physical structures and the operations of infrastructure affecting not only its functionality and safety, but also triggering cascade effects in other systems because of the tight interdependence of the systems that characterises the modern society. Hence, critical infrastructure must integrate the current cyber-security approach based on risk avoidance with a broader perspective provided by the emerging cyber-resilience paradigm. Cyber resilience is aimed as a way absorb the consequences of these attacks and to recover the functionality quickly and safely through adaptation. Several high-level frameworks and conceptualisations have been proposed but a formal definition capable of translating cyber resilience into an operational tool for decision makers considering all aspects of such a multifaceted concept is still missing. To this end, the present paper aims at providing an operational formalisation for cyber resilience starting from the Cyber Resilience Ontology presented in a previous work using model-driven principles. A domain model is defined to cope with the different aspects and “resilience-assurance” processes that it can be valid in various application domains. In this respect, an application case based on critical transportation communications systems, namely the railway communication system, is provided to prove the feasibility of the proposed approach and to identify future improvements.

The modelling and verification of systems security is an open research topic whose complexity and importance needs, in our view, the use of formal and non-formal methods. This paper addresses the modelling of security using misuse cases and the automatic verification of survivability properties using model checking. The survivability of a system characterises its capacity to fulfil its mission (promptly) in the presence of attacks, failures, or accidents, as defined by Ellison. The original contributions of this paper are a methodology and its tool support, through a framework called surreal . The methodology starts from a misuse case specification enriched with UML profile annotations and obtains, as a by-product, a survivability assessment model (SAM). Using predefined queries the survivability properties are proved in the SAM. A total of fourteen properties have been formulated and also implemented in surreal , which encompasses tools to model the security specification, to create the SAM and to prove the properties. Finally, the paper validates the methodology and the framework using a cyber–physical system (CPS) case study, in the automotive field.

With the growing number of digital medical imaging records, the need for an automatic procedure to retrieve only data of interest is of increasing importance. A Picture Archiving and Communication System (PACS) provides effective storage and retrieval based on TAGs but does not allow us for query by example. A possible solution is to use a Content-Based Image Retrieval (CBIR) system, namely a system able to retrieve images from a database based on the similarity to a given reference image. The features used to describe the images strongly affect both the performance and the applicability of CBIR to medical images, motivating for the finding of a suitable set of feature for realizing an effective CBIR based PACS. In recent years, Deep Learning (DL) approaches outperformed classical machine learning methods in many computer vision applications, thanks to their ability to learn compact hierarchical features of input data that well fit the specific task to solve. In this paper we introduce a simple yet effective modular architecture to implement a “Smart PACS”, namely a PACS exploiting a deep-based CBIR compatible with the classical Hospital Information System (HIS) infrastructure. The feature extraction relies on Convolutional Neural Networks, a DL approach commonly applied in image processing, while the image indexing and look-up are based on Apache Solr. As application case-study, we analysed the need for a physician to obtain all the images of past studies having similar traits with the patient under analysis.

Modern predictive maintenance is the convergence of several technological trends: developing new techniques and algorithms can be very costly due to the need for a physical prototype. This research has the final aim to build a simulation-based software framework for modeling and analysing complex systems and for defining predictive maintenance algorithms. By the usage of simulation, quantitative evaluation of the dependability of such systems will be possible. The ERTMS/ETCS dependability case study is presented to prove the applicability of the software.

Federate architectures are able to provide a scalable and shared environment for the distributed training and testing of machine learning applications. However, federated learning architectures shows potential security vulnerabilities in particular to the data poisoning attacks, incoming from participants to the federation. In such a scenario, a malicious participant may inject bad data in order to sabotage the result of the training. Such attacks may provide both a downgrade of the general performance of the learned model and may compromise the fairness of the machine learning application. As such applications are growing in criticality, such learning models must face with security and privacy as well as with scalability issues. The aim of the paper is to improve federated models by providing an architecture base on cloud computing which grants these additional features. The paper also discusses technical details, in particular, the usage of blockchain schemes to provide integrity and homomorphic cryptography for guaranteeing privacy.

Traditional safety-critical systems are engineered in a way to be predictable in all operating conditions. They are common in industrial automation and transport applications where uncertainties (e.g., fault occurrence rates) can be modeled and precisely evaluated. Furthermore, they use high-cost hardware components to increase system reliability. On the contrary, future systems are increasingly required to be “smart” (or “intelligent”) that is to adapt to new scenarios, learn and react to unknown situations, possibly using low-cost hardware components. In order to move a step forward to fulfilling those new expectations, in this paper we address run-time stochastic evaluation of quantitative safety targets, like hazard rate, in self-adaptive event detection systems by using Bayesian Networks and their extensions. Self-adaptation allows changing correlation schemes on diverse detectors based on their reputation, which is continuously updated to account for performance degradation as well as modifications in environmental conditions. To that aim, we introduce a specific methodology and show its application to a case-study of vehicle detection with multiple sensors for which a real-world data-set is available from a previous study. Besides providing a proof-of-concept of our approach, the results of this paper pave the way to the introduction of new paradigms in the dynamic safety assessment of smart systems.

Product and application life-cycle management (PLM/ALM) are the processes that govern a product and a software system, respectively, encompassing the creation, deployment and operation of a system from the beginning to the end of its life. As both PLM and ALM require cross-discipline collaboration and cooperation, tools integration and inter-operation are necessary to enable the efficient and effective usage of tool suites supporting the management of the entire system life-cycle and overcome the limitations of all-in-one solutions from one tool vendor. In this context, the Open Services for Life-cycle Collaboration (OSLC) initiative proposes a set of specifications to allow a seamless integration based on linked data. This paper describes the work performed within the ARTEMIS JU project CRYSTAL to develop an environment for the functional system-level testing of railway controllers, relying on OSLC to enable inter-operation with existing PLM/ALM tools. A concrete realization of the proposed architecture is described also discussing some design and implementation choices. A real industrial case study is used to exemplify the features and the usage of the environment in testing one of the functionalities of the Radio Block Centre, the vital core of the European Rail Traffic Management System/European Train Control System (ERTMS/ETCS) Control System.

The availability of a huge amount of data has enabled the massive application of machine learning and deep learning techniques across different domains involving computer-based critical systems. A huge set of automatic learning frameworks tackle different kinds of systems, enabling the diffusion of Big Data analysis, cloud computing systems and (Industrial) Internet of Things. As such applications become more and more widespread, data analysis techniques have shown their capability to identify operational patterns and to predict future behaviours for anticipating possible problems. Knowledge outcoming from these approaches are still hard to manipulate with high-level reasoning mechanisms (formal reasoning, model checking, model-based approaches): this special issue aims at exploring the synergy of model-based and data-driven approaches to boost critical applications and systems analysis and monitoring.

Artificial Intelligence systems have enabled significant benefits for users and society, but whilst the data for their feeding are always increasing, a side to privacy and security leaks is offered. The severe vulnerabilities to the right to privacy obliged governments to enact specific regulations to ensure privacy preservation in any kind of transaction involving sensitive information. In the case of digital and/or physical documents comprising sensitive information, the right to privacy can be preserved by data obfuscation procedures. The capability of recognizing sensitive information for obfuscation is typically entrusted to the experience of human experts, who are over-whelmed by the ever increasing amount of documents to process. Artificial intelligence could proficiently mitigate the effort of the human officers and speed up processes. Anyway, until enough knowledge won’t be available in a machine readable format, automatic and effectively working systems can’t be developed. In this work we propose a methodology for transferring and leveraging general knowledge across specific-domain tasks. We built, from scratch, specific-domain knowledge data sets, for training artificial intelligence models supporting human experts in privacy preserving tasks. We exploited a mixture of natural language processing techniques applied to unlabeled domain-specific documents corpora for automatically obtain labeled documents, where sensitive information are recognized and tagged. We performed preliminary tests just over 10.000 documents from the healthcare and justice domains. Human experts supported us during the validation. Results we obtained, estimated in terms of precision, recall and F1-score metrics across these two domains, were promising and encouraged us to further investigations.

With the increasing spread of easy and effective frameworks, in recent years Deep Learning approaches are becoming more and more used in several application fields, including computer vision (such as natural and biomedical image processing), automatic speech recognition (ASR) and time-series analysis. If, on one hand, the availability of such frameworks allows developers to use the one they feel more comfortable with, on the other, it raises questions related to the reproducibility of the designed model across different hardware and software configurations, both at training and at inference times. The reproducibility assessment is important to determine if the resulting model produces good or bad outcomes just because of luckier or blunter environmental training conditions. This is a non-trivial problem for Deep Learning based applications, not only because their training and optimization phases strongly rely on stochastic procedures, but also because of the use of some heuristic considerations (mainly speculative procedures) at training time that, although they help in reducing the required computational effort, tend to introduce non-deterministic behavior, with a direct impact on the results and on the model’s reproducibility. Usually, to face this problem, designers make use of probabilistic considerations about the distribution of data or focus their attention on very huge datasets. However, this kind of approach does not really fit some application field standards (such as medical imaging analysis with Computer-Aided Detection and Diagnosis systems – CAD) that require strong demonstrable proofs of effectiveness and repeatability of results across the population. It is our opinion that in those cases it is of crucial importance to clarify if and to what extent a Deep Learning based application is stable and repeatable as well as effective, across different environmental (hardware and software) configurations. Therefore, the aim of this work is to quantitatively analyze the reproducibility problem of Convolutional Neural Networks (CNN) based approaches for the biomedical image processing, in order to highlight the impact that a given software framework and hardware configurations might have when facing the same problem by the same means. In particular, we analyzed the problem of breast tissue segmentation in DCE-MRI by using a modified version of a 2D U-Net CNN, a very effective deep architecture for semantic segmentation, using two Deep Learning frameworks (MATLAB and TensorFlow) across different hardware configurations.

The use of biometric-based authentication systems spread over daily life consumer electronics. Over the years, researchers’ interest shifted from hard (such as fingerprints, voice and keystroke dynamics) to soft biometrics (such as age, ethnicity and gender), mainly by using the latter to improve the authentication systems effectiveness. While newer approaches are constantly being proposed by domain experts, in the last years Deep Learning has raised in many computer vision tasks, also becoming the current state-of-art for several biometric approaches. However, since the automatic processing of data rich in sensitive information could expose users to privacy threats associated to their unfair use (i.e. gender or ethnicity), in the last years researchers started to focus on the development of defensive strategies in the view of a more secure and private AI. The aim of this work is to exploit Adversarial Perturbation, namely approaches able to mislead state-of-the-art CNNs by injecting a suitable small perturbation over the input image, to protect subjects against unwanted soft biometrics-based identification by automatic means. In particular, since ethnicity is one of the most critical soft biometrics, as a case of study we will focus on the generation of adversarial stickers that, once printed, can hide subjects ethnicity in a real-world scenario.

Nowadays, Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is increasingly succeeding as a complementary methodology for breast cancer, with Computer Aided Detection/Diagnosis (CAD) systems becoming essential technological tools to provide early detection and diagnosis of tumours. Several CADs make use of machine learning, resulting in a constant design of hand-crafted features aimed at better assisting the physician. In recent years, Deep learning (DL) approaches raised in popularity in many pattern recognition tasks thanks to their ability to learn compact hierarchical features that well fit the specific task to solve. If, on one and, this characteristic suggests to explore DL suitability for biomedical image processing, on the other, it is important to take into account the physiological inheritance of the images under analysis. With this goal in mind, in this work we propose "3TP U-Net", an U-Shaped Deep Convolutional Neural Network that exploits the well-known Three Time Points approach for the lesion segmentation task. Results show that our proposal is able to outperform not only the classical (non-deep) approaches but also some very recent deep proposal, achieving a median Dice Similarity Coefficient of 61.24%.

Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is a diagnostic method for the detection and diagnosis of breast cancer. Requiring the acquisition of images before and after the injection of a paramagnetic contrast agent, it provides a large amount of data that can hardly be analyzed without the use of a Computer Aided Diagnosis (CAD) system, whose aim is to support radiologists in the interpretation of medical images. Among the major issues in developing a CAD for the breast DCE-MRI there is the lesion diagnosis, namely the classification of lesioned tissues according to the tumour aggressiveness. Several studies have been conducted so far to explore the applicability of Deep Learning (DL) approaches to the automatic breast lesions classification. However, we argue that solutions only relying on DL are not so effective since past learned experience in the radiomics field should also be kept in mind to better exploit the dynamics of contrast agent and its effect on the acquired images. To this aim, we propose an approach that exploits the well-known Three Time Points (3TP) idea to select the specific time points that best highlight the tissues under analysis. Our findings show that promising results can then be obtained by using transfer learning, resulting in an approach that is able to outperform both the classical (non-deep) and some very recent deep proposals.

Modern physical protection systems integrate a number of security systems (including procedures, equipments, and personnel) into a single interface to ensure an adequate level of protection of people and critical assets against malevolent human actions. Due to the critical functions of a protection system, the quantitative evaluation of its effectiveness is an important issue that still raises several challenges. In this paper we propose a model-driven approach to support the design and the evaluation of physical protection systems based on (a) UML models representing threats, protection facilities, assets, and relationships among them, and (b) the automatic construction of a Bayesian Network model to estimate the vulnerability of different system configurations. Hence, the proposed approach is useful both in the context of vulnerability assessment and in designing new security systems as it enables what-if and cost–benefit analyses. A real-world case study is further illustrated in order to validate and demonstrate the potentiality of the approach. Specifically, two attack scenarios are considered against the depot of a mass transit transportation system in Milan, Italy. © 2016, Springer-Verlag Berlin Heidelberg.

Model-driven techniques can be used to automatically produce formal models from different views of a system realised by using several modelling languages and notations. Specifications are transformed into formal models so facilitating the analysis of complex system for design, validation or verification purposes. However, no single formalism suits for representing all system’s views. In particular, the assessment of non-functional properties often requires integrated modelling approaches. The ultimate goal of the research work described in this paper is to develop a comprehensive, theoretical and practical framework able to support the development and the integration of new or existing model-driven approaches for the automatic generation of multi-formalism models. This paper defines the core theoretical ideas on which the framework is based and demonstrates their concrete applicability to the development of a multi-formalism approach for performability assessment.

Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is a diagnostic method suited for the early detection and diagnosis of cancer, involving the serial acquisition of images before and after the injection of a paramagnetic contrast agent. Dealing with long acquisition times, DCE-MRI inevitably shows noise (artefacts) in acquired images due to the patient (often involuntary) movements. As a consequence, over the years, machine learning approaches showed that some sort of motion correction technique (MCT) have to be applied in order to improve performance in tumours segmentation and classification. However, in recent times classic machine learning approaches have been outperformed by deep learning based ones, thanks to their ability to autonomously learn the best set of features for the task under analysis. This paper proposes a first investigation to understand if deep learning based approaches are more robust to the misalignment of images over time, making the registration no longer needed in this context. To this aim, we evaluated the effectiveness of a MCT both for the classification and for the segmentation of breast lesions in DCE-MRI by means of some literature proposal. Our results show that while MCTs seems to be still quite useful for the lesion segmentation task, they seem to be no longer strictly required for lesion classification one.

Evolutionary computing has demonstrated its effectiveness in supporting the development of robust and intelligent systems: when used in combination with formal and quantitative models, it becomes a primary tool in critical systems. Among the modern critical infrastructures, smart energy grids are getting a growing interest from many communities (academic, industrial and political) fostering the development of a robust energy distribution infrastructure. Energy grids are also an example of critical cyber physical social systems since their equilibrium can be perturbed not only by cyber and physical attacks but also by economical and social crises as well as changes in the consumption profiles. The paper illustrates a practical framework supporting the run-time evolution of the control logic inside the Smart Meter: the centre of modern Smart Homes. By combining the modeling and analysis capabilities of Fluid Stochastic Petri Nets and the flexibility of Genetic Programming, this approach can be used to adapt the control logic of the Smart Meters to the changes of the structure and functionalities of the Smart Home as well as of the operational environment. While the main objective of the evolution is to guarantee the energetic sustainability of the Smart Home, the fulfilment of the user's requirements about the energetic need of the home allows to preserve the identity of the Smart Meter during its evolution.

The cloud era is accelerating the long term growth of Data-Centric Systems in critical applications. In this chapter, we focus on the risk assessment methods of traditional large-scale, computer-based systems and on the necessity to extend such approaches to Data-Centric Systems. Hence, after a presentation of the main risk factors in traditional and future systems, an assessment methodology is presented showing how to use advanced formal modeling techniques as the multiformalism approach to evaluate security risk, based on two widespread formalisms: Bayesian Networks and Attack Trees.

Virtual Coupling adds to Automatic Train Control (ATC) systems the further functionality of being able to virtually connect two or more trains, so drastically reducing their headways and increasing line capacity. For this reason it is considered among the most relevant innovations to be researched within the European Horizon 2020 Shift2Rail Joint Undertaking. Indeed, Virtual Coupling also introduces some critical issues related to potential hazards as well as strict requirements on tolerated latency associated to the channels used for train-to-trackside and train-to-train communications. In this paper, we introduce Virtual Coupling in the context of a standard ATC, that is ERTMS/ETCS. Considering a reference ATC simplifies the discussion about implementation and performance issues. We will provide some preliminary hints, models and results and draw conclusions about required safety analyses and future developments.

While the term "vulnerability" is widespread in the protection of the critical infrastructures, there is still a gap between its meanings according to the different perspectives from which the security problem is viewed. Cyber and physical notions of vulnerability are different notwithstanding the scientific community has underlined the importance to deal with these two aspects in a unified way. This paper introduces a mathematical foundation of physical vulnerability by means of which it is possible to quantify such variables: the paper also gives a first application to cyber-security in order to show that this way towards a unified approach is reasonable.

Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is gaining popularity as a complementary diagnostic method for early detection and diagnosis of breast cancer. However, due to the large amount of data, DCE-MRI can hardly be inspected without the use of a Computer Aided Diagnosis (CAD) system. Among the major issues in developing CAD for breast DCE-MRI there is the classification of regions of interest according to their aggressiveness. For this task newer hand-crafted features are continuously proposed by domain experts. On the other hand, deep learning approaches have gained popularity in many pattern recognition tasks, being able to outperform classical machine learning techniques in different fields, by learning compact hierarchical representations of an image which well fit the specific task to solve. The aim of this work is to explore the applicability of Convolutional Neural Networks (CNN) in automatic lesion malignancy assessment for breast DCE-MRI data. Our findings show that while promising results in treating DCE-MRI can be obtained by using transfer learning, CNNs have to be carefully designed and tuned in order to outperform approaches specifically designed to exploit all the available data information.

ETCS is an European system for high speed trains control and protection within ERTMS, the European standard for rail traffic management system. ERTMS/ETCS implementations use GSM-R for communications. As GSM-R is becoming obsolete, the adoption of more advanced technologies is investigated for next generation trains. New communication systems for railway infrastructures are expected to overcome the limitations of GSM-R, providing enhanced performance and reliability, as well as safety and security functionality to meet the requirements of the future signalling systems, control and users’ applications. While 4G technologies (LTE and LTE-A) are currently tested in a few field trials, railway operators should consider that fifth generation (5G) mobile communications technologies will soon be available. One of the foundational aspects of the 5G architecture is control-plane programmability, achieved through the SDN paradigm. Being aware that in a railway scenario this opportunity can be exploited to dynamically reconfigure the network behavior to better match the communication flows produced by moving trains, we aim at defining a framework, integrating formal modeling and analysis tools and techniques into a network emulator, to evaluate the impact on ERTMS/ETCS safety and security deriving from the adoption of an SDN model in the communication infrastructure. In this paper we describe a first step towards this objective, by presenting a first proof-of-concept implementation of the framework and its use to reproduce a simple railway infrastructure. In our current implementation, Finite State Machines are used to model communication protocols between ERTMS/ETCS entities and to automatically produce code and Promela models. Generated code is directly used to control the network behavior while the Promela model allows to generate and verify a network configuration by model checking.

Critical infrastructures as water treatment, power distribution, or telecommunications, provide daily services essential to our lifestyle. Any service discontinuity can have a high impact into our society and even into our safety. Thus, security of these systems against intentional threats must be guaranteed. However, many of these systems are based on protocols initially designed to operate on closed, unroutable networks, making them an easy target for cybercriminals. In this regard, Modbus is a widely adopted protocol in control systems. Modbus protocol, however, lacks for security properties and is vulnerable to plenty of attacks (as spoofing, flooding, or replay, to name a few). In this paper, we propose a formal modeling of Modbus protocol using an extension of hierarchical state-machines that is automatically transformed to a Promela model. This model allows us to find counterexamples of security properties by model-checking. In particular, the original contribution of this paper is the formal demonstration of the existence of man-in-the-middle attacks in Modbus-based systems. Our approach also allows to formally evaluate security properties in future extensions of Modbus protocols.

Verification and Validation of railway controllers is the most critical and time-consuming phase in a system development life-cycle. It is regulated by international standards, which explicitly recommend the usage of state machines to model the specification of the system under test. Despite the great deal of works addressing the usage of state machines and their extensions, model-based verification and validation processes still lack concise and expressive-enough notations able to easily capture peculiar features of the specific domain of multi-process control systems, on which proper tool chains can be implemented in order to realize effective and automated environments. This paper introduces a novel class of hierarchical state machines, called Dynamic STate Machines (DSTMs), and proposes an approach for modelling and validating railway control systems, based on the new specification language. Key features of DSTM are recursive execution, parallelism, parameter passing, abortion transition, and communication through global variables and channels, but its main peculiarity resides in the semantics of fork and join operators which allows for dynamic instantiation of machines (processes). The formal semantics of DSTM allows for the definition of verification and validation methodologies supported by automated tools. The paper also describes how DSTM specifications may be mapped to Promela models in order to achieve automated generation of test cases by model checking and Spin. The work presented in this paper was carried out in the context of an European project and is strongly driven by the industrial necessity of tackling issues concerning the automation of functional system-level testing of modern railway signalling systems. Hence, the language and the proposed approach are illustrated and motivated by applying them to a specific functionality of the Radio Block Centre, the vital core of the ERTMS/ETCS Control System.

Now, data collection and analysis are becoming more and more important in a variety of application domains, as long as novel technologies advance. At the same time, we are experiencing a growing need for human&ndash, machine interaction with expert systems, pushing research toward new knowledge representation models and interaction paradigms. In particular, in the last few years, eHealth&mdash, which usually indicates all the healthcare practices supported by electronic elaboration and remote communications&mdash, calls for the availability of a smart environment and big computational resources able to offer more and more advanced analytics and new human&ndash, computer interaction paradigms. The aim of this paper is to introduce the HOLMeS (health online medical suggestions) system: A particular big data platform aiming at supporting several eHealth applications. As its main novelty/functionality, HOLMeS exploits a machine learning algorithm, deployed on a cluster-computing environment, in order to provide medical suggestions via both chat-bot and web-app modules, especially for prevention aims. The chat-bot, opportunely trained by leveraging a deep learning approach, helps to overcome the limitations of a cold interaction between users and software, exhibiting a more human-like behavior. The obtained results demonstrate the effectiveness of the machine learning algorithms, showing an area under ROC (receiver operating characteristic) curve (AUC) of 74.65% when some first-level features are used to assess the occurrence of different chronic diseases within specific prevention pathways. When disease-specific features are added, HOLMeS shows an AUC of 86.78%, achieving a greater effectiveness in supporting clinical decisions.

The construction of a usable, formal, and extensible modeller and simulator for Smart Energy Grids is of a paramount importance in the industrial settings. Final users are interested in deploying effective smart-home configurations able to satisfy energy requests in the most economical way. Hence, a tool able to forecast both energy consumption and related costs of a smarthome configuration is needed. In this paper, the µGRIMOIRE (micro GRId MOdelling envIRonmEnt) toolset is presented. This tool is based on the well-known model-driven paradigm and its successful applications in the generation of formal/quantitative models for complex systems. By using a Domain Specific Modelling Language, a final user can define a smart-home system configuration and energy saving logics. Then, the tool offers the possibility of evaluating the desired user metrics by translating the model into a Fluid Stochastic Petri Net model representing both discrete and continuous variables. © Gentile et al.

Dynamic Contrast Enhanced - Magnetic Resonance Imaging (DCE-MRI) is gaining popularity as complementary diagnostic tool for breast cancer. In a typical Computer Aided Detection (CAD) processing, the identification and segmentation of the breast parenchyma is a crucial stage aimed to reduce computational effort and increase reliability, by reducing the number of voxels to analyse and removing foreign tissues and air. The aim of this work is to propose a fully-automated geometrical-based breast-mask extraction method in DCE-MRI, that combines three 2D Fuzzy C-Means clustering and geometrical breast anatomy characterization. In particular, seven well defined key-points have been considered in order to accurately segment breast parenchyma from air and chest-wall. The proposed approach has been validated on 30 DCE-MRI studies. The median segmentation accuracy and Dice similarity index were 97.86 (±0.49) and 92.66 (±1.48) respectively with p < 0.05, and 100% of neoplastic lesion coverage.

The growing academic and industrial interest in Smart Grids raises the need for methods and techniques supporting the choice of best-saving strategies in intelligent home devices. This paper presents a model-based approach for the integrated evaluation of the energy billing profiles by using the formalism of fluid stochastic Petri nets, able to capture both continuous and discrete system aspects. The prime feature of the modelling approach is the compositionality by which a modeller can easy customise the overall configuration as well as the inner behaviour of a system. This paper also proves the feasibility of the approach by analysing three different saving policies in a Domestic Smart Grid environment and comparing the simulation results. Copyright © 2016 Inderscience Enterprises Ltd.

Critical infrastructures are complex networked systems. They must be able to provide essential services, even when they are compromised by intentional or accidental threats. Guaranteeing essential services means to ensure survivability with an adequate Quality of Service (QoS). This paper proposes a model-driven approach for the assessment of survivability requirements. In particular, we propose a graphical Survivability Assessment Model (SAM), based on UML. It is automatically derived from a UML specification that encompasses essential services, service modes, threats and survivability strategies. Furthermore, model-driven techniques are used to assess the SAM. Then, we propose some preliminary property verifications to discover aws in the specification. The model driven paradigm is used to ensure high level of usability and abstraction of the artifacts that are key issues in communication among stakeholders. The approach has been applied to a scaled-down model of a smart grid, an evolution of traditional power grids based on high performance and dependable computer network