13 December 2017

Publications

Below a list of papers published by different partners of OPLON Consortium, strictly connected to the results of the project.

    1. Gandino, Filippo; Ferrero, Renato; Rebaudengo, Maurizio (2017)
      A Key Distribution Scheme for Mobile Wireless Sensor Networks: Q-s-Composite.

      Published in: IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, vol. 12 n. 1, pp. 34-47. – ISSN 1556-6013

      Brief abstract: This work proposes a management scheme of secret cryptographic keys in sensor networks and can be applied to all systems compatible with smart home approach to perform a remote monitoring of the patients. Security mechanisms are always needed in these situations, due to:
      – the high sensitivity of the data managed by these systems;
      – the risks associated to possible manipulations of the same data by undesired organizations and
      – the risks associated to the use of the data for undesired purposes, e.g. the monitoring of patients’ movements.

    2. Gandino, Filippo; Celozzi, Cesare; Rebaudengo, Maurizio (2017)
      A key management scheme for mobile wireless sensor networks.

      Published in: APPLIED SCIENCES, vol. 7 n. 5. – ISSN 2076-3417

      Brief abstract: This work focuses on a management approach of secret cryptographic keys. The proposed method is compatible with mobile devices and consequentially suitable for those hybrid systems made up by sensors both within a body sensor area network and within a smart environment in which the patient is able to move.

    3. Gandino, Filippo; Ferrero, Renato; Montrucchio, Bartolomeo; Rebaudengo, Maurizio (2016)
      Fast Hierarchical Key Management Scheme with Transitory Master Key for Wireless Sensor Networks.

      Published in: IEEE INTERNET OF THINGS JOURNAL, vol. 3 n. 6, pp. 1334-1345. – ISSN 2327-4662

      Brief abstract: This work proposes a new solution for the management of secret cryptografic keys for static routing networks. In particular, the proposed solution takes advantage of a new identification procedure between the different nodes of the network in order to reduce the time required to generate the keys.

    4. Hemmatpour, Masoud; Ferrero, Renato; Montrucchio, Bartolomeo; Rebaudengo, Maurizio (2016)
      Baseline walking dataset exploiting accelerometer and gyroscope for fall prediction and prevention systems.

      Published in: 11th International Conference on Body Area Networks, Torino, December 15–16, 2016.

      Brief abstract: Within this paper a dataset is used to enable the analysis and comparison of different fall prediction and/or prevention systems. The purpose of this dataset is not only to support the project itself, but, more in general, to support the activity of scientific community in this field.

    5. Hemmatpour, Masoud; Ferrero, Renato; Montrucchio, Bartolomeo; Rebaudengo, Maurizio (2016)
      Eigenwalk: a Novel Feature for Walk Classification and Fall Prediction

      Published in: 11th International Conference on Body Area Networks, Torino, December 15–16, 2016

      Brief abstract: The activities associated to the classification of walking typologies and the ones associated to fall prediction have resulted in a new technique called “eigenwalk”, based on data coming from accelerometers and gyroscopes. This technique is used in combination with a classificator, called “random forest”: within this framework several decision threes are generated in order to apply at the end the majority rule. The computation complexity of the proposed approach has been reduced applying methods based on “co-occurrence” matrixes to the used training set.

    6. Ferrero, Renato; Gandino, Filippo; Hemmatpour, Masoud; Montrucchio, Bartolomeo; Rebaudengo, Maurizio (2016)
      Exploiting accelerometers to estimate displacement.

      Published in: 5th Mediterranean Conference on Embedded Computing (MECO-2016), Bar (Montenegro), 12-16 giugno 2016.

      Brief abstract: This paper presents an experimental study for evaluating the reliability of simple techniques for indentifying the position of an object through datas collected by triaxial accelerometers. Even if the acceleration is phisically dependent on the object motion, every time the object changes its position the double integration of the acceleration in the time field does not provide precise information about the performed movement, due to noise and measurement errors. Among the basic techniques in order to improve these results, there is the usage of a correction method based on a Kalman filter in order improve the precision of the object movement estimation. The experiments have been performed recording the acceleration values with a commercial accelerometer: while the percentual error coming out from the simple integration of acceleration data can go up to 68% in a generic case of spatial movement, it can be drastically reduced down to 9% with the proposed technique. A even lower percentual error can be obtained when the movement is bound to be performed along a plane or an axis.

    7. Masoud, Hemmatpour; Ferrero, Renato; Montrucchio, Bartolomeo; Rebaudengo, Maurizio (2016)
      A neural network model based on co-occurrence matrix for fall prediction.

      Published in: International Conference on Wireless Mobile Communication and Healthcare, MILANO, NOVEMBER 14–16, 2016. pp. 241-248

      Brief abstract: This papaer proposes to use a new technique for “fall prediction”, developed using a set of 6 features, 5 of which based on co-occurrency matrixes and the sixth of which based on relative frequencies.

    8. Ferrero R.; Gandino F.; Montrucchio B.; Rebaudengo M.; Velasco A.; Benkhelifa I. (2015)
      On gait recognition with smartphone accelerometer.

      Published in: 4th Mediterranean Conference on Embedded Computing (MECO-2015), Budva (Montenegro), 14-18 Giugno 2015. pp. 368-373

      Brief abstract: This paper focuses on the goal of gait recognition. Under a technlogical profile, we chose to use the acceletometers built-in in the modern smartphones. Beside the capability to reveal useful information, such as sex, age, possible disabilities, the gait of each person is so peculiar that can enable to identify a single person. It’s obvious that the peculiarities enabling the recognition of an individual by his/her gait can be of great usefulness in the recognition of the mobility of the same individual. Even if the first gait analyses were carried on in specific laboratories with dedicated equipment, portable sensors have been adopted as soon as they were available thanks to the technology minuaturization. Aiming to an even less invasive analysis of the observed individual, recent proposals have been based on the data collected thanks to the use of the triaxial accelerometer present in most of commercially available smartphone on the market. In spite of this, in these cases the recognition techniques must be shaped considering the low quality of these accelorometers and considering the limited computational capabilities of the smartphone in use. This stat of the art research activity identifies the guidelines for the gait recognition by the use of smartphone built-in sensors.

    9. Samanta Rosati, Maddalena Zema, Cristina Castagneri, Fulvio Marchetti, and Gabriella Balestra, Member, IEEE 
      Modelling and Analysis of Four Telemedicine Italian Experiences*

      Published in: 39th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC’17) – International Convention Center, JeJu Island, S. Korea, 11-15 July 2017 

      Brief abstract: In the last 10 years the European population aged 65 years and over grew of 2.3%, with Italy having the highest share of elderly persons in the total population. OPLON (OPportunities for active and healthy LONgevity) is a project supported by the Italian Ministry of Education, Universities, and Research aiming to identify and prevent frailty and to improve the life quality of elderly subjects. The main goal of OPLON is to develop a “Care&Cure” model for the management of subjects with different morbidities and comorbidities, adaptable to the subject’s risk level and to the regional contexts. In this study we analyzed four Italian telemedicine experiences addressed to chronic, geriatric or partially self-sufficient subjects. Each of them was exhaustively described by means of three process modelling tools (synopsis, workflow and swimlane activity diagrams). Starting from this analysis, we defined a general model of tele-monitoring and tele-assistance of frail and pre-frail people with different needs and pathologies. The proposed model was characterized by three macro processes (enrollment, assessment and assistance) and four groups of actors (patient, general practitioner/specialist physician, multidisciplinary team, and healthcare professionals). Combining this model with a detailed analysis of regulations and legislations in force both at local and national level, it will be possible to design the complete and efficient “Care&Cure” model.