Nuova ricerca

VALERIA VILLANI

Ricercatore t.d. art. 24 c. 3 lett. A presso: Dipartimento di Scienze e Metodi dell'Ingegneria


Home | Curriculum(pdf) | Didattica |


Pubblicazioni

2021 - Worker satisfaction with adaptive automation and working conditions: theoretical model and questionnaire as assessment tool [Articolo su rivista]
Villani, Valeria; Sabattini, Lorenzo; Żołnierczyk-Zreda, Dorota; Mockałło, Zofia; Barańska, Paulina; Fantuzzi, Cesare
abstract


2020 - Human-Friendly Robotics 2019. HFR 2019. [Monografia/Trattato scientifico]
Ferraguti, F.; Villani, V.; Sabattini, L.; Bonfè, M.
abstract


2020 - Humans interacting with multi-robot systems: a natural affect-based approach [Articolo su rivista]
Villani, V.; Capelli, B.; Secchi, C.; Fantuzzi, C.; Sabattini, L.
abstract

This paper proposes a novel human–multi-robot-system interaction approach that enjoys two main features: natural interaction and affect-based adaptation of robots behavior. Specifically, the proposed system enables interaction by means of a wrist-worn device, such as a commercial smartwatch, which allows to track user’s movements and heart activity. Thus, on the one side, the proposed system allows the user to intuitively drive the robots by establishing a natural mapping between wrist movements and robots velocity. On the other side, the system estimates user’s mental fatigue during interaction by means of the analysis of heart rate variability. The proposed interaction system adapts then the behavior of the multi-robot system when the interacting user gets overwhelmed with the interaction and control task, which is then simplified. Experimental validation is provided, to show the effectiveness of the proposed system. First, the natural and affect-based interaction are considered separately. Then, the approach is tested considering a complex realistic scenario, which is simulated in virtual reality in order to get an immersive and realistic interaction experience. The results of the experimental validation clearly show that the proposed affect-based adaptive system leads to relieving the user’s fatigue and mental workload.


2020 - Mutualistic and adaptive human-machine collaboration based on machine learning in an injection moulding manufacturing line [Relazione in Atti di Convegno]
Bettoni, A.; Montini, E.; Righi, M.; Villani, V.; Tsvetanov, R.; Borgia, S.; Secchi, C.; Carpanzano, E.
abstract

This paper proposes an adaptive human-machine collaboration paradigm based on machine learning. Human-machine collaboration requires more than letting humans and machines interact according to fixed rules. A decision-maker is needed to assess production status and to activate adaptations that improve productivity and workers' well-being. The proposed solution has been tested in an injection moulding manufacturing line. By introducing a physiological monitoring system and a smart decision-maker, relief from fatigue and mental stress is pursued by adjusting the level of support offered through a cobot. Results reported a reduction of operators' physical and mental workload as well as productivity increase.


2020 - The INCLUSIVE System: A General Framework for Adaptive Industrial Automation [Articolo su rivista]
Villani, Valeria; Sabattini, Lorenzo; Baranska, Paulina; Callegati, Enrico; Czerniak, Julia N.; Debbache, Adel; Fahimipirehgalin, Mina; Gallasch, Andreas; Loch, Frieder; Maida, Rosario; Mertens, Alexander; Mockallo, Zofia; Monica, Francesco; Nitsch, Verena; Talas, Engin; Toschi, Elisabetta; Vogel-Heuser, Birgit; Willems, JeanMarc; Zolnierczyk-Zreda, DorotaDorota; Fantuzzi, Cesare
abstract


2020 - The index of cognitive activity - eligibility for task-evoked informational strain and robustness towards visual influences [Articolo su rivista]
Czerniak, Julia N.; Schierhorst, Nikolas; Villani, Valeria; Sabattini, Lorenzo; Brandl, Christopher; Mertens, Alexander; Schwalm, Maximilian; Nitsch, Verena
abstract


2020 - Wearable devices for the assessment of cognitive effort for human-robot interaction [Articolo su rivista]
Villani, Valeria; Righi, Massimiliano; Sabattini, Lorenzo; Secchi, Cristian
abstract

This paper is motivated by the need of assessing cognitive effort in affective robotics. In this context, the ultimate goal is that of assessing the mental state while the subject is interacting with a robotic system, by gathering implicit and objective information unobtrusively. To this end, we focus on wearable devices that do not affect the interaction of a human with a robot. In particular, we consider some commercial multi-purpose wearable devices, such as an armband, a smartwatch and a chest strap, and compare them in terms of accuracy in detecting cognitive effort. In an experiment setting, thirty participants were exposed to an increase in their cognitive effort by means of standard cognitive tests. Mental fatigue was estimated by measuring cardiac activity, in terms of heart rate and heart rate variability. The results have shown that the analysis of heart rate variability measured by the chest strap provides the most accurate detection of cognitive effort. Nevertheless, also measurements by the armband are sensitive to cognitive effort.


2019 - A General Approach to Natural Human-Robot Interaction [Relazione in Atti di Convegno]
Sabattini, Lorenzo; Villani, Valeria; Secchi, Cristian; Fantuzzi, Cesare
abstract

This paper proposes a scheme for letting a human interact with a generic robot in a natural manner. Based on the concept of natural user interfaces, the proposed methods exploit recognition of the users’ forearm motion to produce commands for the robotic system. High-level commands are provided based on gesture recognition, and velocity commands are computed for the robot by mapping, in a natural manner, the motion of the user’s forearm. The method is proposed in a general manner, and is then instantiated considering two different robotic systems, namely a quadrotor and a wheeled mobile robot. Usability of the system is evaluated with experiments involving users.


2019 - A General Methodology for Adapting Industrial HMIs to Human Operators [Articolo su rivista]
Villani, Valeria; Sabattini, Lorenzo; Loch, Frieder; Vogel-Heuser, Birgit; Fantuzzi, Cesare
abstract

Modern production systems are becoming more and more complex to comply with diversified market needs, flexible production, and competitiveness. Despite technological progress, the presence of human operators is still fundamental in production plants, since they have the important role of supervising and monitoring processes, by interacting with such complex machines. The complexity of machines implies an increased complexity of human-machine interfaces (HMIs), which are the main point of contact between the operator and the machine. Thus, HMIs cannot be considered anymore an accessory to the machine and their improvement has become an important part of the design of the whole machines, to enable a nonstressful interaction and make them easy to also use less skilled operators. In this article, we present a general framework for the design of HMIs that adapt to the skills and capabilities of the operator, with the ultimate aim of enabling a smooth and efficient interaction and improving user's situation awareness. Adaptation is achieved by considering three different levels: Perception (i.e., how information is presented), cognition (i.e., what information is presented), and interaction (i.e., how interaction is enabled). For each level, general guidelines for adaptation are provided, thus defining a meta-HMI independent of the application. Finally, some examples of how the proposed adaptation patterns can be applied to the case of procedural and extraordinary maintenance tasks are presented. Note to Practitioners-This article was motivated by the problem of facilitating the interaction of human operators with human-machine interfaces (HMIs) of complex industrial systems. Standard industrial HMIs are static and do not consider the user's characteristics. As a consequence, least-skilled operators are prevented from their use and/or have poor performance. In this article, we suggest a novel methodology to the design of adaptive industrial HMIs that adapt to the skills and capabilities of operators and compensate their limitations (e.g., due to age or inexperience). In particular, we propose a methodological framework that consists of general rules to accommodate the user's characteristics. Adaptation is achieved at three different levels: Perception (i.e., how information is presented), cognition (i.e., what information is presented), and interaction (i.e., how interaction is enabled). The presented rules are independent of the target application. Nevertheless, we establish a relationship between such design rules and user's impairments and capabilities and kind of working tasks. Hence, designers of HMIs are called to instantiate them considering the specific requirements and characteristics of the users and the working tasks of the application at hand.


2019 - An Adaptive Virtual Training System Based on Universal Design [Relazione in Atti di Convegno]
Loch, Frieder; Fahimipirehgalin, Mina; Czerniak, Julia N.; Mertens, Alexander; Villani, Valeria; Sabattini, Lorenzo; Fantuzzi, Cesare; Vogel-Heuser, Birgit
abstract

The increasing complexity of manufacturing environments requires effective training systems to prepare the operation personnel for their tasks. Several training systems have been proposed. A common approach is the application of virtual environments to train interactions with an industrial machine in a safe, attractive, and efficient way. However, these training systems cannot adapt to the requirements of an increasingly diversified workforce. This paper introduces an approach for the design of an adaptive virtual training system based on the idea of universal design. The system is based on a two-step approach that consists of an initial adaptation to the user capabilities and real-time adaptations during training based on measurements of the user. The adaptations concern the use of different representations of lessons with different complexity and interaction modalities. The proposed approach provides a flexible training system that can adapt to the needs of a broad group of users.


2019 - Guest editorial note: Special issue on human-robot collaboration in industrial applications [Breve Introduzione]
Leali, Francesco; Pini, Fabio; Villani, Valeria
abstract

Focusing on these challenges, this Special Issue in Mechatronics aims at providing an up-to-date overview of recent advanced solutions that can significantly promote HRC in industrial scenarios, with an emphasis on the mechatronic aspects related to the design of integrated systems, knowledge sharing between human and robots, modelling and simulation of interaction and safety countermeasures. The central theme of the Special Issue is the development of systems, methodologies, and new concepts for crossing the gap between laboratories and reality that will help foster the adoption of human-robot collaborative solutions to real-world industrial applications.


2019 - Measurement and classification of human characteristics and capabilities during interaction tasks [Articolo su rivista]
Villani, V.; Czerniak, J. N.; Sabattini, L.; Mertens, A.; Fantuzzi, C.
abstract

In this paperwe address the need to design adaptive interacting systems for advanced industrial production machines. Modern production systems have become highly complex and include many subsidiary functionalities, thus making it difficult for least skilled human operators interact with them. In this regard, adapting the behavior of the machine and of the operator interface to the characteristics of the user allows a more effective interaction process, with a positive impact on manufacturing efficiency and user's satisfaction. To this end, it is crucial to understandwhich are the user's capabilities that influence the interaction and, hence, should be measured to provide the correct amount of adaptation.Moving along these lines, in this paper we identify groups of users that, despite having different individual capabilities and features, have common needs and response to the interaction with complex production systems. As a consequence,we define clusters of users that have the same need for adaptation. Then, adaptation rules can be defined by considering such users' clusters, rather than addressing specific individual user's needs.


2019 - New trends in the design of human-machine interaction for CNC machines [Relazione in Atti di Convegno]
Lotti, Giulia; Villani, Valeria; Battilani, Nicola; Fantuzzi, Cesare
abstract


2019 - Survey on usability assessment for industrial user interfaces [Relazione in Atti di Convegno]
Villani, Valeria; Lotti, Giulia; Battilani, Nicola; Fantuzzi, Cesare
abstract


2019 - Systematic Approach to Develop a Flexible Adaptive Human-Machine Interface in Socio-Technological Systems [Relazione in Atti di Convegno]
Czerniak, J. N.; Villani, V.; Sabattini, L.; Loch, F.; Vogel-Heuser, B.; Fantuzzi, C.; Brandl, C.; Mertens, A.
abstract

Modern automatic machines in production have been becoming more and more complex within the recent years. Thus, human-machine interfaces (HMI) reflect multiple different functions. An approach to improve human-machine interaction can be realised by adjusting the HMI to the operators’ requirements and complementing their individual skills and capabilities, supporting them in self-reliant machine operation. Based on ergonomic concepts of information processing, we present a systematic approach for developing an adaptive HMI after the MATE concept (Measure, Adapt & Teach). In a first step, we develop a taxonomy of human capabilities that have an impact on individual performance during informational work tasks with machine HMI. We further evaluate three representative use cases by pairwise comparison regarding the classified attributes. Results show that cognitive information processes, such as different forms of attention and factual knowledge (crystalline intelligence) are most relevant on average. Moreover, perceptive capabilities that are restricted by task environment, e.g. several auditory attributes; as well as problem solving demand further support, according to the experts’ estimation.


2019 - Understanding Multi-Robot Systems: on the Concept of Legibility [Relazione in Atti di Convegno]
Capelli, Beatrice; Villani, Valeria; Secchi, Cristian; Sabattini, Lorenzo
abstract


2018 - A Framework for Affect-Based Natural Human-Robot Interaction [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Secchi, Cristian; Fantuzzi, Cesare
abstract

In this paper we present a general framework for affective human-robot interaction that allows users to intuitively interact with a robot and takes into account their mental fatigue, thus simplifying the task or providing assistance when the user feels stressed. Interaction with the robot is achieved by naturally mapping user's forearm motion, detected with a smartwatch, into robot's motion. High-level commands can be provided by means of gestures. An approach based on affective robotics is used to adapt the level of robot's autonomy to the cognitive workload of the user. User's mental fatigue is detected from the analysis of heart rate, also measured by the smartwatch. The framework is general and can be applied to different robotic systems. In this paper, we consider its experimental validation on a wheeled mobile robot.


2018 - An Adaptive Speech Interface for Assistance in Maintenance and Changeover Procedure [Relazione in Atti di Convegno]
Loch, Frieder; Czerniak, Julia; Villani, Valeria; Sabattini, Lorenzo; Fantuzzi, Cesare; Mertens, Alexander; Vogel-Heuser, Birgit
abstract

Machine operators remain important in future production environments and need intuitive and powerful interaction techniques. Many assistance and support applications for machine operators use speech-based interfaces since they are suitable during manual tasks and when visual attention cannot be occupied. Due to developments like the demographic change or the need for skilled personnel, the skills and capabilities of the workers will become increasingly diverse. Speech-based interfaces therefore need to be adaptable to the capabilities, limitations and preferences of individual operators. This paper addresses this requirement and proposes an adaptive speech interface that supports machine operators during maintenance and changeover procedures. All aspects of the proposed application can be adapted to the requirements of the user. The system uses a process model, instruction templates, a user model, and a model of the input vocabulary to describe the components of the application. This allows a flexible adaptation of the speech interface and the provided instructions to the requirements of individual users and to further use cases.


2018 - An Industrial Social Network for Sharing Knowledge Among Operators [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Levratti, Alessio; Fantuzzi, Cesare
abstract

Due to the increasing complexity of modern automatic machines typically used in several industrial applications, the need for assistive technologies is becoming very relevant. Typical approaches consist in designing advanced and adaptive human-machine interfaces (HMIs) that can be effectively used by any operator and that provide guided procedures for the most common situations. However, when dealing with complex systems, infrequent and unforeseen situations may happen, whose solution require the experience owned by a limited number of skilled operators. To this end, in this paper we propose an industrial social network concept to allow an effective exchange of information among the operators and to facilitate the solution of unforeseen events, such as unscheduled maintenance activities or troubleshooting.


2018 - MATE Robots Simplifying My Work: The Benefits and Socioethical Implications [Articolo su rivista]
Villani, Valeria; Sabattini, Lorenzo; Czerniak, Julia N.; Mertens, Alexander; Fantuzzi, Cesare
abstract

With the increasing complexity of modern industrial automatic and robotic systems, an increasing burden is put on the operators, who are requested to supervise and interact with very complex systems, typically under challenging and stressful conditions. To overcome this issue, it is necessary to adopt a responsible approach based on the anthropocentric design methodology, such that machines adapt to the humans capabilities, and not vice versa. Moving along these lines, in this paper we consider an integrated methodological design approach, which we call MATE, consisting in devising complex automatic or robotic solutions that measure current operator's status, adapting the interaction accordingly, and providing her/him with proper training to improve the interaction and learn lacking skills and expertise. Accordingly, a MATE system is intended to be easily usable for all users, thus meeting the principles of inclusive design. Using such a MATE system gives rise to several ethical and social implications, which are discussed in this paper. Additionally, a discussion about which factors in the organization of companies are critical with respect to the introduction of a MATE system is presented.


2018 - Methodological Approach for the Evaluation of an Adaptive and Assistive Human-Machine System [Relazione in Atti di Convegno]
Sabattini, Lorenzo; Villani, Valeria; Fantuzzi, Cesare; Czerniak, Julia N.; Mertens, Alexander; Loch, Frieder; Vogel-Heuser, Birgit
abstract

With the increasing complexity of modern industrial automatic and robotic systems, an increasing burden is put on the operators, who are requested to supervise and interact with such complex systems, typically under challenging and stressful conditions. To overcome this issue, it is necessary to adopt a responsible approach based on the anthropocentric design methodology, such that machines adapt to the humans capabilities. Moving along these lines, a methodological approach called MATE was introduced in [1], which consists in devising complex automatic or robotic solutions that measure current operator's status, adapting the interaction accordingly, and providing her/him with proper training to improve the interaction and learn lacking skills and expertise. In this paper we propose an evaluation and validation procedure to guarantee the achievement of the requirements of a MATE system.


2018 - Relieving operators’ workload: Towards affective robotics in industrial scenarios [Articolo su rivista]
Talignani Landi, Chiara; Villani, Valeria; Ferraguti, Federica; Sabattini, Lorenzo; Secchi, Cristian; Fantuzzi, Cesare
abstract

This paper proposes a novel approach based on affective robotics that can be applied to industrial applications. Considering a human-robot interaction task, we propose to analyze the mental workload of the operator, and subsequently adapt the behavior of the robotic system, introducing assistive technologies. These technologies would prevent the performances deterioration caused by the human stress, helping him/her only when needed and decreasing the user's mental workload. This represents a general methodology, which can be applied to several industrial applications, leading to increase the overall performances of human-robot interaction exploiting principles of human-centered design. As a case study, we consider a teleoperation task, where virtual fixtures are utilized as an assistive technology. The stress of the operator is monitored in terms of heart rate variability, measured by means of a wearable sensor tied at the operator's wrist. Experimental validation of the proposed architecture is performed on a group of 15 users that teleoperate an industrial robot for performing a pick and place task.


2018 - Survey on human-robot collaboration in industrial settings: Safety, intuitive interfaces and applications [Articolo su rivista]
Villani, Valeria; Pini, Fabio; Leali, Francesco; Secchi, Cristian
abstract

Easy-to-use collaborative robotics solutions, where human workers and robots share their skills, are entering the market, thus becoming the new frontier in industrial robotics. They allow to combine the advantages of robots, which enjoy high levels of accuracy, speed and repeatability, with the flexibility and cognitive skills of human workers. However, to achieve an efficient human-robot collaboration, several challenges need to be tackled. First, a safe interaction must be guaranteed to prevent harming humans having a direct contact with the moving robot. Additionally, to take full advantage of human skills, it is important that intuitive user interfaces are properly designed, so that human operators can easily program and interact with the robot. In this survey paper, an extensive review on human-robot collaboration in industrial environment is provided, with specific focus on issues related to physical and cognitive interaction. The commercially available solutions are also presented and the main industrial applications where collaborative robotic is advantageous are discussed, highlighting how collaborative solutions are intended to improve the efficiency of the system and which the open issue are.


2018 - Survey on Human-Robot Interaction for Robot Programming in Industrial Applications [Capitolo/Saggio]
Villani, Valeria; Pini, Fabio; Leali, Francesco; Secchi, Cristian; Fantuzzi, Cesare
abstract

The recent trends in modern industry highlight an increasing use of robots for a wide range of applications, which span from established manufacturing operations to novel tasks characterized by a close collaboration with the operators. Although human-robot collaboration allows to relieve operators of exhausting works, an effective collaboration requires a straightforward interaction to foster the use of robot assistants. This paper provides a comprehensive survey on human-robot interaction approaches and related interfaces addressed to robot programming. An overview of on-line and off-line robot programming techniques is first presented. Then, novel intuitive interaction means, such as those based on multi-modal interaction, virtual and augmented reality, are considered. The paper aims at pointing out that collaborative robotics can effectively reduce operator's physical workload if easy to use interfaces for robot programming are provided.


2018 - Towards an integrated approach for supporting the workers in Industry 4.0 [Relazione in Atti di Convegno]
Lotti, Giulia; Villani, Valeria; Battilani, Nicola; Fantuzzi, Cesare
abstract

Assisting and supporting human operators in modern industry is becoming crucial to increase the efficiency. Available tools, like use and maintenance manual, have a complex organization due to variety of information treated and purposes. Confusion and disorientation bring a series of disadvantages that increase the cognitive effort of the users. Tasks such as set-up, maintenance, and troubleshooting, strongly depend on the skills of human operators. To tackle this problem, in this paper we present an integrated approach with the aim of developing a thorough system that starts from a structured management of technical documen- tation and provides useful support to the users during their work. The approach is composed by three phases i) Data organization and management, obtaining with a standard that allows to edit and manage the information in a structured way; ii) Content extraction and filtering, for collecting the technical labelled information; iii) Support to the user during use and maintenance of the machine, consisting in a set of on-line tools. At the end of this paper, we present an application of the proposed approach to the specific case of troubleshooting support, by considering MyAID, a tool designed to assist operators to solve machine failures.


2018 - Use of Virtual Reality for the Evaluation of Human-Robot Interaction Systems in Complex Scenarios [Relazione in Atti di Convegno]
Villani, Valeria; Capelli, Beatrice; Sabattini, Lorenzo
abstract

Human-robot interaction has gained a lot of attention in recent years, since the use of robots can complement and improve human capabilities. To make such interaction smooth, proper interaction approaches are needed. Customarily these are tested in simplified scenarios and tame laboratory environment, since reproducing complex real use cases is often difficult. Achieved results are then not representative of actual interaction in reality and do not scale to complex scenarios. To overcome this issue, in this paper we consider the use of virtual reality as an alternative tool to assess HRI in those scenarios that are difficult to reproduce in reality. To this end, we compare the interaction experience for the same task, which is carried out in both virtual reality and real environment. To assess user's interaction in the two scenarios, we consider quantitative task related metrics, mental workload sustained, and subjective reporting. Results show that virtual reality allows to reproduce a faithful interaction experience and, thus, can be used to reliably validate human-robot interaction approaches in complex scenarios.


2017 - A Natural Infrastructure-Less Human–Robot Interaction System [Articolo su rivista]
Villani, Valeria; Sabattini, Lorenzo; Riggio, Giuseppe; Secchi, Cristian; Minelli, Marco; Fantuzzi, Cesare
abstract

This letter introduces a novel methodology for letting a user interact with a robotic system in a natural manner. The main idea is that of defining an interaction system that does not require any specific infrastructure or device but relies on commonly utilized objects while leaving the user’s hands free. Specifically, we propose to utilize a smartwatch (or any commercial sensorized wristband) for recognizing the motion of the user’s forearm. This is achieved by measuring accelerations and angular velocities, which are then elaborated for recognizing gestures and for defining velocity commands for the robot. The proposed interaction system is evaluated experimentally with different users controlling a semiautonomous quadrotor. Results show that the usability and effective- ness of the proposed natural interaction system provide significant improvement in the human–robot interaction experience.


2017 - Interacting With a Mobile Robot with a Natural Infrastructure-Less Interface [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Riggio, Giuseppe; Levratti, Alessio; Secchi, Cristian; Fantuzzi, Cesare
abstract

In this paper we introduce a novel approach that enables users to interact with a mobile robot in a natural manner. The proposed interaction system does not require any specific infrastructure or device, but relies on commonly utilized objects while leaving the user’s hands free. Specifically, we propose to utilize a smartwatch (or a sensorized wristband) for recognizing the motion of the user’s forearm. Measurements of accelerations and angular velocities are exploited to recognize user’s gestures and define velocity commands for the robot. The proposed interaction system is evaluated experimentally with different users controlling a mobile robot and compared to the use of a remote control device for the teleoperation of robots. Results show that the usability and effectiveness of the proposed natural interaction system based on the use of a smartwatch provide significant improvement in the human-robot interaction experience.


2017 - Methodological approach for the design of a complex inclusive human-machine system [Relazione in Atti di Convegno]
Sabattini, Lorenzo; Villani, Valeria; Czerniak, Julia N.; Mertens, Alexander; Fantuzzi, Cesare
abstract

Modern industrial automatic machines and robotic cells are equipped with highly complex human-machine interfaces (HMIs) that often prevent human operators from an effective use of the automatic systems. In particular, this applies to vulnerable users, such as those with low experience or education level, the elderly and the disabled. To tackle this issue, it becomes necessary to design user-oriented HMIs, which adapt to the capabilities and skills of users, thus compensating their limitations and taking full advantage of their knowledge. In this paper, we propose a methodological approach to the design of complex adaptive human-machine systems that might be inclusive of all users, in particular the vulnerable ones. The proposed approach takes into account both the technical requirements and the requirements for ethical, legal and social implications (ELSI) for the design of automatic systems. The technical requirements derive from a thorough analysis of three use cases taken from the European project INCLUSIVE. To achieve the ELSI requirements, the MEESTAR approach is combined with the specific legal issues for occupational systems and requirements of the target users.


2017 - Natural interaction based on affective robotics for multi-robot systems [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Secchi, Cristian; Fantuzzi, Cesare
abstract

In this paper we introduce a novel approach that enables users to interact with a multi-robot system in a natural manner. Additionally, interaction adapts to the user’s affect and stamina. To this end, we consider the use of a smartwatch for recognizing the motion of the user’s forearm, which is then translated in velocity commands for the robots. A natural mapping between user’s movements and robots commands is implemented, so that the user can intuitively drive the robots by mimicking real-world behavior. Additionally, the operator’s heart rate is measured, since it is a measure of mental stress. Thus, when an increase in mental stress is detected, the behavior of the multi-robot system is changed in order to simplify the interaction task and relieve the user. The proposed interaction system is tested with different users. Specifically, the effectiveness of the natural interaction is evaluated and compared to the use of a joypad and a haptic device. Moreover, we preliminarily test the affective interaction approach.


2017 - Towards modern inclusive factories: A methodology for the development of smart adaptive human-machine interfaces [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Czerniaki, Julia N.; Mertens, Alexander; Vogel-Heuser, Birgit; Fantuzzi, Cesare
abstract

Modern manufacturing systems typically require high degrees of flexibility, in terms of ability to customize the production lines to the constantly changing market requests. For this purpose, manufacturing systems are required to be able to cope with changes in the types of products, and in the size of the production batches. As a consequence, the human-machine interfaces (HMIs) are typically very complex, and include a wide range of possible operational modes and commands. This generally implies an unsustainable cognitive workload for the human operators, in addition to a non-negligible training effort. To overcome this issue, in this paper we present a methodology for the design of adaptive human-centred HMIs for industrial machines and robots. The proposed approach relies on three pillars: measurement of user's capabilities, adaptation of the information presented in the HMI, and training of the user. The results expected from the application of the proposed methodology are investigated in terms of increased customization and productivity of manufacturing processes, and wider acceptance of automation technologies. The proposed approach has been devised in the framework of the European project INCLUSIVE.


2016 - A detection-estimation approach with refinement to filtering for Gaussian systems with intermittent observations [Relazione in Atti di Convegno]
Fasano, Antonio; Longhi, Sauro; Monteriù, Andrea; Villani, Valeria
abstract

In this paper we consider the problem of state estimation for linear discrete-time Gaussian systems with intermittent observations resulting from packet dropouts. We assume that the receiver does not know the sequence of packet dropouts. This is a typical situation, e.g., in wireless sensor networks. Under this hypothesis, the problem of state estimation has been previously solved by the authors using a detection-estimation approach consisting of two stages: the first is a nonlinear optimal detector, which decides if a packet dropout has occurred, and the second is a time-varying Kalman filter, which is fed with both the observations and the decisions from the first stage. This work extends that solution, introducing a refinement stage whose purpose is to significantly improve the decision on packet dropouts and, in turn, on state estimation. The overall estimator has finite memory and the tradeoff between performance and computational complexity can be easily controlled. Numerical results highlight the effectiveness of the approach based on detection-estimation with refinement, which outperforms both the estimator without refinement and the optimal linear filter of Nahi.


2016 - MyAID: a Troubleshooting Application for Supporting Human Operators in Industrial Environment [Relazione in Atti di Convegno]
Villani, Valeria; Battilani, Nicola; Lotti, Giulia; Lotti, Giulia; Fantuzzi, Cesare
abstract

Nowadays manufacturing systems are increasing in sophistication and complexity. In this scenario, human operators experience many diffculties to interact effciently with the machine. To tackle this problem, in this paper we present a novel interactive troubleshooting tool to be used in industrial environment. The application, called MyAID, relies on a hypermedia information system and aims at assisting shopoor workers in a factory to perform preventive and corrective machine maintenance. The main advantages of MyAID are the following. First, it overcomes limitations of conventional printed documentation. Second, it can be easily updated and adapted to other machines or uses, other than troubleshooting, since it enjoys a modular structure. Third, it can be connected directly to the control unit of the machine to read active alarms or verify whether the user is following correctly the troubleshooting procedure. Finally, the plan for usability assessment of the proposed application, which is organized in a preliminary heuristic evaluation according to Nielsen's heuristics and field tests with users, is introduced.


2016 - Smartwatch-Enhanced Interaction with an Advanced Troubleshooting System for Industrial Machines [Relazione in Atti di Convegno]
Villani, Valeria; Sabattini, Lorenzo; Battilani, Nicola; Fantuzzi, Cesare
abstract

Smartwatches are unobtrusive everyday devices which can be also exploited for effective gesture-based human-machine interaction. In this paper, we propose the use of a smartwatch to interact with an advanced troubleshooting application to be used in industrial environment. The application is a hypermedia information system aiming at assisting workers in performing preventive and corrective machine maintenance. The smartwatch allows a handsfree interaction, thus facilitating the use of the whole system when wearing personal protective equipment such as gloves or having fingers greased with oil or dust, which prevent operating touch screens. The algorithm for gesture recognition we have devised, which is based on template matching, is described in the paper, together with its experimental validation. Finally, we present a preliminary usability assessment of the overall system, meant as integration of the smartwatch with the hypermedia system.


2015 - A detection-estimation approach to filtering with intermittent observations with generally correlated packet dropouts [Relazione in Atti di Convegno]
Fasano, Antonio; Monteriu, Andrea; Villani, Valeria
abstract

This paper is concerned with the problem of state estimation for the class of linear discrete-time Gaussian systems with intermittent observations due to packet losses. This is a common case in networked control systems, where the state of a remote plant is estimated from measurements carried through a lossy network. We assume that the receiver does not know the sequence of packet dropouts. This is typical, e.g., in wireless sensor networks or in networks that cannot rely on protocols that provide information on packet loss. Moreover, we assume that the sequence of packet dropouts is correlated, thus subsuming both the cases of independent dropouts and dropouts modeled as a Markov chain. We propose a detection-estimation approach to the problem of state estimation. The estimator consists of two stages: the first is a nonlinear optimal detector, which decides if a packet dropout has occurred, and the second is a time-varying Kalman filter, which is fed with both the observations and the decisions from the first stage. The overall estimator has finite memory and the tradeoff between performance and computational complexity can be easily controlled. As a case study, we derive the decision rule in closed form in the case of dropout sequence modeled as a Markov chain. Simulation results highlight the effectiveness of the proposed approach, which outperforms the linear recursive estimator of Hadidi and Schwartz.


2015 - ECG baseline wander removal with recovery of the isoelectric level [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria
abstract

Baseline wander removal is an unavoidable step in ECG signal processing. The in-band nature of this noise makes its removal difficult without affecting the ECG. Many approaches have been proposed in the literature. Among them, cubic spline interpolation is the only one able to recover the isoelectric level in the detrended signal. However, it exhibits poor detrending performance. In this paper we extend our recent approach based on the notion of quadratic variation reduction, to address the problem of recovery of the isoelectric level. This is achieved by constraining the amplitude of few fiducial points to lie on isoelectric segments. Conversely to cubic spline interpolation, which requires a fiducial point for each beat, the proposed approach requires very few points: as few as one single point is sufficient. Simulation results show that the proposed approach largely outperforms cubic spline interpolation, being very effective in removing baseline wander and recovering the isoelectric level, while preserving ECG morphology.


2015 - Fast and effective estimation of narrowband components for bioelectrical signals [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria
abstract

In this paper we propose a novel approach for estimating narrowband components from bioelectrical signals. The approach is based on the notion of modulated quadratic variation, introduced as a measure of variability for narrowband signals. The algorithm is the closed-form solution to a constrained convex optimization problem, where narrowband components are estimated tracking the slow variations around a central frequency in the measured signal. The approach is general and can be applied to any bioelectrical signal, either for diagnostic or denoising purposes. In this paper we assess its performance on ECG and EMG signals. Numerical results show its effectiveness in removing narrowband artifacts, such as power-line interference, while preserving signal morphology. It greatly outperforms conventional notch filtering. Moreover, it is also very fast, as its computational complexity is linear in the size of the vector to process.


2015 - Statistical assessment of performance of algorithms for detrending RR series [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria
abstract

Detrending RR series is a common processing step prior to HRV analysis. Customarily, RR series, which are inherently unevenly sampled, are interpolated and uniformly resampled, thus introducing errors in subsequent HRV analysis. We have recently proposed a novel approach to detrending unevenly sampled series, which is based on the notion of weighted quadratic variation reduction. In this paper, we extensively assess its performance on RR series through a statistical analysis. Numerical results confirm the effectiveness of the approach, which outperforms state-of-the-art methods. Furthermore, it is statistically uniformly better than competing algorithms. A sensitivity analysis shows that it is robust to variations of its controlling parameter. The algorithm is simple and favorable in terms of computational complexity, thus being suitable for long-term HRV analysis. To the best of the authors' knowledge, it is the fastest algorithm for detrending RR series.


2014 - A Framework for ECG Signal Preprocessing based on Quadratic Variation Reduction [Relazione in Atti di Convegno]
Villani, Valeria
abstract

ECG signals are corrupted by several kinds of noise and artifacts, which negatively affect any subsequent analysis. In the literature, the only approach that can handle any noise and artifacts corrupting the ECG is linear time-invariant filtering. However, it suffers from some important limitations regarding effectiveness and computational complexity. In this paper we propose a novel frame- work for ECG signal preprocessing based on the notion of quadratic variation reduction. The framework is very general, since it can cope with all the different kinds of noise and artifacts that corrupt ECG records. It relies on a single algorithmic structure, thus enjoying an easy and robust implementation. Results show that the framework is effective in improving the quality of ECG, while preserving signal morphology. Moreover, it is very fast, even on long recordings, thus being perfectly suited for real-time applications and implementation on devices with reduced computational power, such as handheld devices.


2014 - Baseline Wander Removal for Bioelectrical Signals by Quadratic Variation Reduction [Articolo su rivista]
Fasano, Antonio; Villani, Valeria
abstract

Baseline wander is a low-frequency additive noise affecting almost all bioelectrical signals, in particular the ECG. In this paper, we propose a novel approach to baseline wander estimation and removal for bioelectrical signals, based on the notion of quadratic variation reduction. The quadratic variation is meant as a measure of variability for vectors or sampled functions, and is a consistent measure in this regard. Baseline wander is estimated solving a constrained convex optimization problem where quadratic variation enters as a constraint. The solution depends on a single parameter whose value is not critical, as proven by a sensitivity analysis. Numerical results confirm the effectiveness of the approach, which outperforms state-of-the-art algorithms. The algorithm compares favorably also in terms of computational complexity, which is linear in the size of the vector to detrend. This makes it suitable for real-time applications as well as for applications on devices with reduced computing power, such as handheld devices.


2014 - ECG Baseline Wander Removal by QVR Preserving the ST Segment [Relazione in Atti di Convegno]
Fasano, A; Villani, Valeria
abstract

Baseline wander removal is an unavoidable step in ECG signal processing. The in-band nature of this noise makes its removal difficult without affecting the ECG, in particular the ST segment. This portion of the ECG has high clinical relevance, as it is related to the diagnosis of acute coronary syndromes. We have recently proposed a novel approach to baseline wander removal based on the notion of quadratic variation reduction. In this paper, we assess its performance in terms of both effectiveness in removing baseline wander and distortion introduced in the ST segment. Numerical results highlight the effectiveness of the approach, which outperforms state-of-the-art algorithms both in removing baseline drift and preserving the ST segment. The algorithm is also very fast, as its computational complexity is linear in the size of the vector to detrend.


2014 - Fast Detrending of RR Series for HRV Analysis [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Detrending RR series is a common processing step prior to HRV analysis. Classical approaches to detrending apply to uniformly sampled data. Thus, RR series, which are inherently unevenly sampled, are interpolated and uniformly resampled prior to detrending. However, this interpolation-resampling process introduces significant errors in the spectral analysis of HRV. We have recently proposed a novel approach to detrending unevenly sampled RR series, which is based on the notion of weighted quadratic variation reduction. In this paper, we assess its performance through statistical analysis. Numerical results confirm the effectiveness of the approach, which outperforms competing algorithms. Moreover, it allows easy implementation and is favorable in terms of computational complexity, which is linear in the size of the series to detrend. This makes it suitable for long-term HRV analysis. To the best of the authors’ knowledge, it is the fastest algorithm for detrending RR series.


2014 - Fast Estimation of Narrowband Components for ECG Signals [Relazione in Atti di Convegno]
Villani, Valeria
abstract

In this paper we propose a novel approach for estimating narrowband components from ECG records. The approach is based on the notion of modulated quadratic variation, meant as a measure of variability for narrowband signals. The algorithm is the closed-form solution to a constrained convex optimization problem, where narrowband components are estimated tracking the slow variations around a central frequency in the measured signal. The proposed approach is applied to power-line interference suppression. Numerical results confirm its effectiveness. Moreover, the approach is general and can be applied to any bioelectrical signal, either for denoising or diagnostic purposes. It is also very fast, as its computational complexity is linear in the size of the vector to process.


2014 - Implementation of a Model Database for a Novel Ultrasonic Approach to Bone Evaluation [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Osteoporosis is considered as a major public health problem, second only to cardiovascular diseases. The gold standard for its diagnosis is currently represented by dual energy X-ray absorptiometry (DXA), which, however, suffers from some important drawbacks. In order to overcome such limitations, the use of ultrasound (US) techniques has been proposed. In this paper, a novel approach to the diagnosis of osteoporosis through US scans on lumbar spine and proximal femur is described. The approach relies on the estimation of diagnostic parameters by measuring the degree of similarity between the spectra of the raw radiofrequency (RF) echo signals and reference spectral models of osteoporotic or healthy bones. Reference models are representative of the features of either osteoporotic or healthy bone structures and are matched with subject age, sex, ethnic group and body mass index to take into account variations in bone physiological condition and subject anatomy. In this paper, the methods implemented to build the database of reference models and to estimate diagnostic parameters are presented. The performance of the approach was assessed on a total of 145 Caucasian underweight and normal-weighted women with age in the range from 46 to 55. Performance was assessed through direct comparison with DXA results. The obtained median relative error in the estimation of bone mineral density was as low as 9.1% on women aged 51 to 55 years and 12.0% on women with age in the range from 46 to 50 years. Moreover, for the two groups, the estimation error was lower than 20% for 81% and 78.6% of subjects, respectively. Therefore, the proposed method combines the advantages of the use of US techniques with a remarkable diagnostic accuracy, thus lending itself to the possibility of being used for population mass screenings.


2014 - Osteoporotic Fractures: Risk Estimation, Possible Therapies and Related Costs [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Osteoporosis affects about 200 million subjects in the world and is responsible for 8.9 million fractures each year. The combined annual cost of all osteoporotic fractures in Europe has been estimated to be 30 billion Euros. The frequency of osteoporotic fractures is rising in many countries, in particular because of the increased longevity of the population. In Italy, around 4 million of women and more than 800,000 men are exposed to a high fracture risk. The National Healthcare System spends about 500 million Euros for hospitalization and chirurgical treatment of hip fractures and costs related to rehabilitation are even greater. The situation is more critical in southern Italy, where the incidence of elderly people is higher than in the other regions. Therefore, there is a strong need for the assessment of the best practices in prevention and treatment of osteoporosis. In this paper, after an overview of the socioeconomic impact of osteoporosis in Italy, with particular focus on Apulia region, the most important techniques used to assess the fracture risk are briefly described. In general, they fall into two major categories: physical measurement of skeletal mass and assessment of clinical risk factors. Moreover, the most commonly used pharmacological agents for the treatment of osteoporosis are reported. In conclusion, for a correct management of the disease, it would be necessary to encourage the widespread use of cheap and non-invasive screening techniques for early diagnosis of osteoporosis.


2014 - Social Impact of Osteoporotic Fractures: Early diagnosis and possible therapies [Articolo su rivista]
Villani, Valeria
abstract

Osteoporosis affects about 200 million subjects in the world and is responsible for 8.9 million fractures each year. The frequency of osteoporotic fractures is rising in many countries, due to the increased longevity of the population. In Europe, the annual cost of all osteoporotic fractures has been estimated to be 30 billion of Euros. In this paper, after an overview of the socioeconomic impact of osteoporosis in the world and in Italy, with particular focus on Apulia region, the most important techniques used to assess the fracture risk are briefly described. Moreover, the most commonly used pharmacological agents for the treatment of osteoporosis are reported. The aim of this review is to analyze the main factors causing the huge impact of osteoporosis on healthcare system, in terms of diagnosis and therapies, and to illustrate recent advances for treatment and prevention of this “silent disease”.


2013 - Baseline Wander Removal in ECG and AHA Recommendations [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Baseline wander is a kind of noise that affects all ECG signals. We have recently proposed a novel approach to its removal which is based on Quadratic Variation Reduction (QVR). The approach has very favorable properties and has shown to be effective in removing baseline wander, while preserving the ST segment level. It requires the determination of a detrending parameter. In this pa- per, we derive a linear time-invariant filter approximating QVR. The filter retains (approximately) the same optimality properties as QVR. Moreover, it provides a criterion for choosing the proper value of the parameter governing QVR, as a function of the spectral characteristics of base- line wander noise. Simulation results show that the filter is effective in removing baseline wander, while introducing minor distortion in the ST segment.


2013 - ECG Baseline Wander Removal and Impact on Beats Morphology: A Comparative Analysis [Relazione in Atti di Convegno]
Villani, Valeria
abstract

The aim of this study is to assess the impact of different baseline wander removal techniques on ECG signal morphology. We consider high-pass filtering, median filtering, adaptive filtering and wavelet adaptive filtering, which are common methods to baseline wander removal, and our recent approach based on quadratic variation reduction. The algorithms are compared both in terms of effectiveness in removing baseline wander and distortion introduced in beat morphology. Numerical results show that the approach based on quadratic variation reduction out- performs state-of-the-art algorithms in estimating baseline wander, while preserving the morphology of all waveforms in ECG, both in normal and ectopic beats.


2013 - Fast Detrending of Unevenly Sampled Series with Application to {HRV} [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Detrending RR series is a common processing step prior to HRV analysis. In the classical approaches RR series, which are inherently unevenly sampled, are interpolated and uniformly resampled, thus introducing errors in sub- sequent HRV analysis. In this paper, we propose a novel approach to detrending unevenly sampled series and apply it to RR series. The approach is based on the notion of weighted quadratic variation, which is a suitable mea- sure of variability for unevenly sampled series. Detrending is performed by solving a constrained convex optimization problem that exploits the weighted quadratic variation. Numerical results confirm the effectiveness of the approach. The algorithm is simple and favorable in terms of computational complexity, which is linear in the size of the series to detrend. This makes it suitable for long-term HRV analysis. To the best of the authors’ knowledge, it is the fastest algorithm for detrending RR series.


2012 - ECG Denoising and Power-line Interference Rejection by Local Quadratic Variation Reduction [Relazione in Atti di Convegno]
Villani, Valeria
abstract

The ECG is the standard noninvasive test used to measure the electrical activity of heart. Unfortunately ECG signals are corrupted by several kinds of noise and artifacts, such as power-line interference, that may negatively affect any subsequent analysis. We have recently proposed a novel algorithm for denoising ECG signals, based on the notion of quadratic variation reduction. The algorithm proved to be quite good in denoising ECG records affected by noise, but its effectiveness reduces when it is used in filtering out power-line interference. In this paper, we propose an algorithm that overcomes this limitation and extends our approach allowing it to both denoise and reject power-line interference. Simulation results confirm the effectiveness of the approach and highlight a notable ability to remove both noise and power-line interference in ECG signals.


2012 - Fast and Effective Baseline Wander Estimation and Removal [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Baseline wander removal is an unavoidable prepro- cessing step in ECG signal processing. The in-band nature of baseline wander makes its removal difficult without affecting ECG, in particular the ST segment. This is a portion of the ECG with high clinical relevance, as it is related to the diagnosis of acute coronary syndromes. We have recently proposed a novel baseline removal algorithm based on the notion of quadratic variation reduction. In this paper, we shortly recall the rationale behind our approach and report main results of performance analysis of our algorithm versus state-of-the-art approaches. Simulation results confirm the effectiveness of the approach and highlight its ability to remove baseline wander while preserving the ST segment. The algorithm compares favorably also in terms of computational complexity, which is linear in the size of the vector to detrend. Eventually, it is worthwhile noting that its application is not limited to ECG, but can be effectively applied to a broader class of signals, such as EEG or EMG.


2012 - Joint Denoising and Narrowband Artifact Rejection for ECG Signals [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria
abstract

ECG signals are corrupted by various kinds of noise and artifacts that may negatively affect any subsequent analysis. In particular, narrowband artifacts include power-line interference and harmonic artifacts. Customarily, noise reduction and artifact rejection are tackled as two distinct problems. In this paper, we propose a joint approach to de- noising and narrowband artifact rejection that exploits the local structure of a noisy ECG. Simulation results confirm the effectiveness of the approach and highlight a notable ability to remove both noise and narrowband artifacts in ECG signals.


2011 - Baseline wander estimation and removal by quadratic variation reduction [Relazione in Atti di Convegno]
Fasano, A; Villani, Valeria; Vollero, L.
abstract

The baseline wander is a low frequency additive noise partially overlapping the band of ECG signal. This makes its removal difficult without affecting the ECG. In this work we propose a novel approach to baseline wander estimation and removal based on the notion of quadratic variation. The quadratic variation is a suitable index of variability for vectors and sampled functions. We derive an algorithm for baseline estimation solving a constrained convex optimization problem. The computational complexity of the algorithm is linear in the size of the ECG record to detrend, making it suitable for realtime applications. Simulation results confirm the effectiveness of the approach and highlight its ability to remove baseline wander. Eventually, the proposed algorithm is not limited to ECG signals, but can be effectively applied whenever baseline estimation and removal are needed, such as EEG records. © 2011 IEEE.


2011 - Denoising and harmonic artifacts rejection for ECG P-waves by quadratic variation reduction [Relazione in Atti di Convegno]
Fasano, A; Villani, Valeria; Vollero, L.
abstract

Atrial fibrillation (AF) is a common cardiac arrhythmia related to irregular atrial contractions. Several studies have shown that the analysis of P-waves extracted from ECG signals is helpful in understanding the predisposing factors to AF. However, P-waves are usually highly corrupted by noise and harmonic artifacts and this makes quite difficult their analysis. Recently we proposed a novel algorithm for denoising P-waves based on the notion of quadratic variation reduction. It is quite good in denoising P-waves affected by noise, but its effectiveness reduces when it is used in filtering out harmonic artifacts, like power-line interference. In this paper we propose an algorithm that overcomes this limitation and extends our previous method allowing it to both denoise and reject harmonic artifacts. Simulation results confirm the effectiveness of the approach and highlight its ability to remove both noise and artifacts. The algorithm has reduced computational complexity and this makes it suitable for real-time applications. © 2011 IEEE.


2011 - ECG P-Wave Smoothing and Denoising by Quadratic Variation Reduction [Relazione in Atti di Convegno]
Villani, Valeria
abstract

Atrial fibrillation is the most common persistent cardiac arrhythmia and it is characterized by a disorganized atrial electrical activity. Its occurrence can be detected, and even predicted, through P-waves time-domain and morphological analysis in ECG tracings. Given the low signal-to-noise ratio associated to P-waves, such anal- ysis are possible if noise and artifacts are effectively filtered out from P-waves. In this paper a novel smoothing and denoising algorithm for P-waves is proposed. The algorithm is solution to a convex optimization problem. Smoothing and denoising are achieved reducing the quadratic variation of the measured P-waves. Simulation results confirm the effectiveness of the approach and show that the proposed algorithm is remarkably good at smoothing and denoising P-waves. The achieved SNR gain exceeds 15 dB for input SNR below 6 dB. Moreover the proposed algorithm has a computational complexity that is linear in the size of the vector to be processed. This property makes it suitable also for real-time applications.


2011 - ECG smoothing and denoising by local quadratic variation reduction [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria; Vollero, Luca
abstract

The ECG is the standard noninvasive test used to measure the electrical activity of the heart. Unfortunately, ECG signal is corrupted by several kinds of noise and artifacts that may negatively affect any subsequent analysis. In this work, we present a fast and effective algorithm for smoothing and denoising ECG records. The algorithm is the closed-form solution to a constrained convex optimization problem, where smoothing and denoising are achieved by locally reducing the quadratic variation of different portions of the ECG. Such a reduction is inversely related to the local SNR. The computational complexity of the algorithm is linear in the size of the vector under analysis, thus making it suitable for real-time applications. Simulation results confirm the effectiveness of the approach and highlight a notable ability to smooth and denoise ECG signals. © 2011 ACM.


2011 - Fast ECG baseline wander removal preserving the ST segment [Relazione in Atti di Convegno]
Fasano, Antonio; Villani, Valeria; Vollero, Luca
abstract

Baseline wander removal is an unavoidable preprocessing step in ECG signal analysis. Unfortunately, the in-band nature of this kind of noise makes its removal difficult without affecting ECG waveform, in particular the ST segment. This is a portion of the ECG with high clinical relevance, as it is related to the diagnosis of acute coronary syndromes. The ST segment is highly susceptible to distortion when baseline removal is performed affecting the low-frequency region of ECG spectrum, where are concentrated the harmonic components that mainly contribute to the shape of the ST segment. In this paper, we propose to tackle the problem of baseline removal from a different perspective, considering the quadratic variation as an alternative measure of variability not directly related to the frequency domain. In this regard, we recently proposed a novel baseline removal algorithm based on quadratic variation reduction. In this paper, we assess its performance with respect to the distortion of the ST segment comparing it to state-of-the-art algorithms. Simulation results confirm the effectiveness of the approach based on quadratic variation reduction. Our algorithm outperforms state-of-the-art algorithms tailored to minimize distortion of the ST segment. Moreover, it compares favorably also in terms of computational complexity, which is linear in the size of the vector to detrend. This makes it suitable also for real-time applications. © 2011 ACM.


2011 - Measuring P-wave morphological variability for AF-prone patients identification [Relazione in Atti di Convegno]
Villani, Valeria; Fasano, Antonio; Vollero, Luca; Censi, Federica; Boriani, Giuseppe
abstract

Atrial fibrillation is the most common arrhythmia encountered in clinical practice. Abnormal P-waves have been observed in patients prone to AF and the analysis of P-waves from surface electrocardiogram has been extensively used to identify patients prone to atrial arrhythmias. Measuring the temporal variability of P- waves, i.e., the variation over time of morphological characteristics of single P-waves, may represent a useful method for characterizing and predicting AF cases. In this paper, we propose a method for the statistical analysis of P-waves variability. It is based on the evaluation of the empirical distribution function of differences energy among normalized P-waves. The proposed method seems promising for capturing atrial anomalies and identifying patients prone to AF.