Floriano Zini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Floriano Zini has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Francesco Ricci
Free University of Bozen-Bolzano, Bolzano, Italy
8 shared publications K. Stockinger
Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
5 shared publications- Mauro Gaspari
University of Bologna
5 shared publications R. Carvajal-Schiaffino
Universidad de Santiago de Chile, Av. Bernardo O'Higgins 3363, Santiago de Chile, Chile
4 shared publicationsA.P. Millar
University of Glasgow, Glasgow, G12 8QQ, Scotland
3 shared publicationsC. Nicholson
University of Glasgow, Glasgow, G12 8QQ, Scotland
3 shared publications
Latest Publications
- Open Access
- 10 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 108583-108603
Sensor-Based Activity Recognition and Performance Assessment in Climbing: A Review
In the past decades, a number of technological developments made it possible to continuously collect various types of sport activity data in an unobtrusive way. Machine learning and analytical methods have been applied to flows of sensor data to predict the conducted sport activity as well as to calculate key performance indicators. In that scenario, researchers started to be interested in leveraging pervasive information technologies for sport climbing, thus allowing, in day-to-day climbing practice, the realization of systems for automatic assessment of a climber’s performance, detection of injury risk factors, and virtual coaching. This article surveys recent research works on the recognition of climbing activities and the evaluation of climbing performance indicators, where data have been acquired with accelerometers, cameras, force sensors, and other types of sensors. We describe the main types of sensors and equipment adopted for data acquisition, the techniques used to extract relevant features from sensor data, and the methods that have been proposed to identify the activities performed by a climber and to calculate key performance indicators. We also present a classification taxonomy of climbing activities and of climbing performance indicators, with the aim to unify the existing work and facilitate the comparison of methods. Moreover, open problems that call for new approaches and solutions are here discussed. We conclude that there is considerable scope for further work, particularly in the application of recognition techniques to problems involving various climbing activities. We hope that this survey will assist in the translation of research effort into intelligent environments that climbers will benefit from.
- 10 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 108583-108603
Open AccessSensor-Based Activity Recognition and Performance Assessment in Climbing: A Review
In the past decades, a number of technological developments made it possible to continuously collect various types of sport activity data in an unobtrusive way. Machine learning and analytical methods have been applied to flows of sensor data to predict the conducted sport activity as well as to calculate key performance indicators. In that scenario, researchers started to be interested in leveraging pervasive information technologies for sport climbing, thus allowing, in day-to-day climbing practice, the realization of systems for automatic assessment of a climber’s performance, detection of injury risk factors, and virtual coaching. This article surveys recent research works on the recognition of climbing activities and the evaluation of climbing performance indicators, where data have been acquired with accelerometers, cameras, force sensors, and other types of sensors. We describe the main types of sensors and equipment adopted for data acquisition, the techniques used to extract relevant features from sensor data, and the methods that have been proposed to identify the activities performed by a climber and to calculate key performance indicators. We also present a classification taxonomy of climbing activities and of climbing performance indicators, with the aim to unify the existing work and facilitate the comparison of methods. Moreover, open problems that call for new approaches and solutions are here discussed. We conclude that there is considerable scope for further work, particularly in the application of recognition techniques to problems involving various climbing activities. We hope that this survey will assist in the translation of research effort into intelligent environments that climbers will benefit from.
- Open Access
- 4 March 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 12 (1) , 1-29
Adaptive Cognitive Training with Reinforcement Learning
Computer-assisted cognitive training can help patients affected by several illnesses alleviate their cognitive deficits or healthy people improve their mental performance. In most computer-based systems, training sessions consist of graded exercises, which should ideally be able to gradually improve the trainee’s cognitive functions. Indeed, adapting the difficulty of the exercises to how individuals perform in their execution is crucial to improve the effectiveness of cognitive training activities. In this article, we propose the use of reinforcement learning (RL) to learn how to automatically adapt the difficulty of computerized exercises for cognitive training. In our approach, trainees’ performance in performed exercises is used as a reward to learn a policy that changes over time the values of the parameters that determine exercise difficulty. We illustrate a method to be initially used to learn difficulty-variation policies tailored for specific categories of trainees, and then to refine these policies for single individuals. We present the results of two user studies that provide evidence for the effectiveness of our method: a first study, in which a student category policy obtained via RL was found to have better effects on the cognitive function than a standard baseline training that adopts a mechanism to vary the difficulty proposed by neuropsychologists, and a second study, demonstrating that adding an RL-based individual customization further improves the training process.
- 4 March 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 12 (1) , 1-29
Open AccessAdaptive Cognitive Training with Reinforcement Learning
Computer-assisted cognitive training can help patients affected by several illnesses alleviate their cognitive deficits or healthy people improve their mental performance. In most computer-based systems, training sessions consist of graded exercises, which should ideally be able to gradually improve the trainee’s cognitive functions. Indeed, adapting the difficulty of the exercises to how individuals perform in their execution is crucial to improve the effectiveness of cognitive training activities. In this article, we propose the use of reinforcement learning (RL) to learn how to automatically adapt the difficulty of computerized exercises for cognitive training. In our approach, trainees’ performance in performed exercises is used as a reward to learn a policy that changes over time the values of the parameters that determine exercise difficulty. We illustrate a method to be initially used to learn difficulty-variation policies tailored for specific categories of trainees, and then to refine these policies for single individuals. We present the results of two user studies that provide evidence for the effectiveness of our method: a first study, in which a student category policy obtained via RL was found to have better effects on the cognitive function than a standard baseline training that adopts a mechanism to vary the difficulty proposed by neuropsychologists, and a second study, demonstrating that adding an RL-based individual customization further improves the training process.
- 1 December 2020
- Published by Taylor & Francis in Disability and Rehabilitation: Assistive Technology
- Vol. 18 (3) , 313-326
Enhancing cognitive rehabilitation in multiple sclerosis with a disease-specific tool
Purpose: Computerised rehabilitation programs can be used to address cognitive deficits typically caused by multiple sclerosis (MS). However, there are still doubts on their effectiveness, due to mixed results obtained in clinical trials. The objective of this paper is to improve cognitive rehabilitation (CR) practices in MS, by presenting and assessing a MS-specific cognitive rehabilitation software. Methods: We conducted a detailed analysis of how CR is carried out in practice in MS rehabilitation centres. From the analysis, we elicited a reference CR process, and identified the essential features a software supporting the process should have. We designed and implemented MS-rehab, a novel MS-specific computerised rehabilitation system having the identified features. We experimented MS-rehab in a pilot study involving eight MS patients. To highlight the improvement with respect to the state of the art, we compared MS-rehab with available professional tools selected using well defined criteria. Results: This paper has three main contributions: (1) the identification of a set of essential features a computerised tool for CR in MS should provide; (2) MS-rehab, a novel CR system designed for MS therapists and patients, which embodies innovative MS specific features; (3) the assessment of MS-rehab efficacy in a pilot study with MS patients. Conclusions: The availability of a MS-specific CR system like MS-rehab fosters the design of more rigorous clinical studies on the effectiveness of computerised rehabilitation in MS. MS-rehab demonstrated its potential and innovativeness as a tool for cognitive rehabilitation in MS.
- 1 December 2020
- Published by Taylor & Francis in Disability and Rehabilitation: Assistive Technology
- Vol. 18 (3) , 313-326
Enhancing cognitive rehabilitation in multiple sclerosis with a disease-specific tool
Purpose: Computerised rehabilitation programs can be used to address cognitive deficits typically caused by multiple sclerosis (MS). However, there are still doubts on their effectiveness, due to mixed results obtained in clinical trials. The objective of this paper is to improve cognitive rehabilitation (CR) practices in MS, by presenting and assessing a MS-specific cognitive rehabilitation software. Methods: We conducted a detailed analysis of how CR is carried out in practice in MS rehabilitation centres. From the analysis, we elicited a reference CR process, and identified the essential features a software supporting the process should have. We designed and implemented MS-rehab, a novel MS-specific computerised rehabilitation system having the identified features. We experimented MS-rehab in a pilot study involving eight MS patients. To highlight the improvement with respect to the state of the art, we compared MS-rehab with available professional tools selected using well defined criteria. Results: This paper has three main contributions: (1) the identification of a set of essential features a computerised tool for CR in MS should provide; (2) MS-rehab, a novel CR system designed for MS therapists and patients, which embodies innovative MS specific features; (3) the assessment of MS-rehab efficacy in a pilot study with MS patients. Conclusions: The availability of a MS-specific CR system like MS-rehab fosters the design of more rigorous clinical studies on the effectiveness of computerised rehabilitation in MS. MS-rehab demonstrated its potential and innovativeness as a tool for cognitive rehabilitation in MS.
- Open Access
- 28 November 2018
- Published by Association for Computing Machinery (ACM)
- p. 214-219
A Planning-Based Serious Game for Cognitive Rehabilitation in Multiple Sclerosis
- 28 November 2018
- Published by Association for Computing Machinery (ACM)
- p. 214-219
Open AccessA Planning-Based Serious Game for Cognitive Rehabilitation in Multiple Sclerosis
- Open Access
- 18 September 2017
- Published by Association for Computing Machinery (ACM)
- p. 1-10
A formative user-based usability study for an advanced cognitive rehabilitation system
We present a formative usability study we conducted in order to evaluate the interface of MS-rehab, an advanced tablet-based web application for cognitive rehabilitation in multiple sclerosis. In our study, we adopted eGLU, a user-centered protocol including simplified usability tests, which is specific for finding critical issues in websites and web applications. Although the user interface had been carefully internally tested prior to our study, by involving just few users we were able to individuate a significant number of critical usability issues we had not previously identified. This indicates that formative user--based usability studies are an essential prerequisite for the realization of cognitive rehabilitation tools and, more in general, of interactive software medical devices, where it is fundamental that the clinical effectiveness of the system is not hampered by hidden usability issues.
- 18 September 2017
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessA formative user-based usability study for an advanced cognitive rehabilitation system
We present a formative usability study we conducted in order to evaluate the interface of MS-rehab, an advanced tablet-based web application for cognitive rehabilitation in multiple sclerosis. In our study, we adopted eGLU, a user-centered protocol including simplified usability tests, which is specific for finding critical issues in websites and web applications. Although the user interface had been carefully internally tested prior to our study, by involving just few users we were able to individuate a significant number of critical usability issues we had not previously identified. This indicates that formative user--based usability studies are an essential prerequisite for the realization of cognitive rehabilitation tools and, more in general, of interactive software medical devices, where it is fundamental that the clinical effectiveness of the system is not hampered by hidden usability issues.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
An advanced system to support cognitive rehabilitation in multiple sclerosis
Recent studies demonstrate the benefits of cognitive rehabilitation (CR) showing that it reduces cognitive impairment in Multiple Sclerosis (MS) improving performance of patients in memory and attention. However, CR procedures are still in a germinal stage and have not been accepted worldwide as a standard therapy yet. In this scenario, the use of computerized training systems has several advantages with respect to pen- and-paper based exercises (such as flexibility and immediate feedback), but the use of information technology is currently limited to provide general purpose tools (i.e., not tailored for specific diseases) that support rehabilitation exercises for single patients only. On the contrary, CR for MS patients must be considered as a part of a comprehensive and complex care process that involves many aspects that must be deeply analyzed to build an effective therapy program. In this paper, we argue that a computerized system, able to integrate the various phases of cognitive rehabilitation processes, may have an essential role in improving CR procedures, optimizing them for routine clinical use in MS. To illustrate our claim, we present MS-rehab, an advanced system specific for MS, highlighting its main features and comparing it with other computerized tools for CR.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
An advanced system to support cognitive rehabilitation in multiple sclerosis
Recent studies demonstrate the benefits of cognitive rehabilitation (CR) showing that it reduces cognitive impairment in Multiple Sclerosis (MS) improving performance of patients in memory and attention. However, CR procedures are still in a germinal stage and have not been accepted worldwide as a standard therapy yet. In this scenario, the use of computerized training systems has several advantages with respect to pen- and-paper based exercises (such as flexibility and immediate feedback), but the use of information technology is currently limited to provide general purpose tools (i.e., not tailored for specific diseases) that support rehabilitation exercises for single patients only. On the contrary, CR for MS patients must be considered as a part of a comprehensive and complex care process that involves many aspects that must be deeply analyzed to build an effective therapy program. In this paper, we argue that a computerized system, able to integrate the various phases of cognitive rehabilitation processes, may have an essential role in improving CR procedures, optimizing them for routine clinical use in MS. To illustrate our claim, we present MS-rehab, an advanced system specific for MS, highlighting its main features and comparing it with other computerized tools for CR.
- 1 December 2016
- Published by Springer Nature
- p. 282-293
Increasing Quality of Life Awareness with Life-Logging
- 1 December 2016
- Published by Springer Nature
- p. 282-293
Increasing Quality of Life Awareness with Life-Logging
- Open Access
- 18 May 2015
- Published by Association for Computing Machinery (ACM)
- p. 131-132
Life-logs Aggregation for Quality of Life Monitoring
We investigate how life-logs from commercial wearable trackers and smartphone sensors can be leveraged to automatically provide patients with knowledge for self-reflection on their disease. We present here: (1) An architecture for the acquisition of life-logs, their fusion, and their storage; and (2) A prototype GUI for the visualization of quality of life indicators.
- 18 May 2015
- Published by Association for Computing Machinery (ACM)
- p. 131-132
Open AccessLife-logs Aggregation for Quality of Life Monitoring
We investigate how life-logs from commercial wearable trackers and smartphone sensors can be leveraged to automatically provide patients with knowledge for self-reflection on their disease. We present here: (1) An architecture for the acquisition of life-logs, their fusion, and their storage; and (2) A prototype GUI for the visualization of quality of life indicators.
- Open Access
- 19 October 2014
- Published by Association for Computing Machinery (ACM)
- p. 409-410
Gamified children universities
Children universities see universities hosting activities for exposing children to research findings. However, universities are not per-se designed for children. This paper advances the idea of gamifying university contexts for children in order to provide them with a positive engaging experience. The reported qualitative study serves as proof-of-concept. Engagement results, albeit preliminary, are positive.
- 19 October 2014
- Published by Association for Computing Machinery (ACM)
- p. 409-410
Open AccessGamified children universities
Children universities see universities hosting activities for exposing children to research findings. However, universities are not per-se designed for children. This paper advances the idea of gamifying university contexts for children in order to provide them with a positive engaging experience. The reported qualitative study serves as proof-of-concept. Engagement results, albeit preliminary, are positive.
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 365-368
A multi-functional mobile information system for hospital assistance
Ospedale Amico (Friendly Hospital) is a mobile and personalized information system, aimed at improving the quality of the communication between medical staff and patients. The system provides the patients with up-to-date and context dependent day hospital activity guidance, and let them enter personal data and browse user-adapted descriptions of their disease. In this paper we describe the system functionality an discuss how we have addressed the limitations identified in the field study of an earlier prototype.
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 365-368
A multi-functional mobile information system for hospital assistance
Ospedale Amico (Friendly Hospital) is a mobile and personalized information system, aimed at improving the quality of the communication between medical staff and patients. The system provides the patients with up-to-date and context dependent day hospital activity guidance, and let them enter personal data and browse user-adapted descriptions of their disease. In this paper we describe the system functionality an discuss how we have addressed the limitations identified in the field study of an earlier prototype.