A warning sign of frailty is imbalance. Psycho-motor therapists run tests to evaluate the balance deterioration but not often enough to track the rapidly changing condition of the elderly. The proposed system collects fine-grained data from a smart cane and processes them with Machine Learning (ML) techniques. The originality of our proposition lies in its personalization by the elderly biomarkers in ML algorithms. Our experiments indicate that we can observe the orientation of locomotion through the cane as well as recognize characteristics of specific participants ambulation in the uncontrolled scenario.

We discuss our experience with the design, implementation, deployment and evaluation of a Human Activity Detection application. This application relies on a software architecture for IoT-based monitoring in Ambient Assisted Living (AAL), based on a Semantic Message Oriented Middleware (SeMoM). Going beyond traditional sensor management systems, our architecture addresses the heterogeneity challenge in IoT healthcare systems and ensures semantic and technical interoperability. SeMoM is able to handle the data acquisition process for a variety of heterogeneous devices, and to provide a reasoning mechanism based on expert knowledge and logic through cognitive sensors. Sensor data and observations are annotated using an extended version of the Cognitive Semantic Sensor Network (CoSSN) ontology built on top of the Semantic Sensor Network (SSN) ontology. CoSSN provides a formal representation that supports a semantic detection of activities.

In order to measure the medical activity, hospitals are required to manually encode information concerning an inpatient episode using International Classification of Disease (ICD-10). This task is time consuming and requires substantial training for the staff. We propose to help by speeding up and facilitating the tedious task of coding patient information, specially while coding some secondary diagnoses that are not well described in the medical resources such as discharge letter and medical records. Our approach leverages data mining techniques in order to explore medical databases of previously encoded secondary diagnoses and use the stored structured information (age, gender, diagnoses count, medical procedures…) to build a decision tree that assigns the proper secondary diagnosis code into the corresponding inpatient episode or indicates the impatient episodes that contains implausible secondary diagnoses. The results suggest that better performance could be achieved by using low level of diagnoses granularity along with adding some filters to balance the repartition of the negative and positive examples in the training set. The obtained results show that there is big variation in the evaluation scores of the studied diagnoses, the highest score is 75% using F1 measurement and the lowest 25% using F1 measurement which indicates further enhancements are needed to achieve better performance regardless of the encoded diagnosis. However, the average accuracy of all the studied secondary diagnoses is around 80% which indicates better negative predictions therefore it could be useful in the prevention or the detection of wrong coding assignments of secondary diagnoses in the inpatient stay.

This paper is an extended version of the final version of a paper accepted at EHCI-DSVIS 2004, Lecture Notes in Computer Science n°3425

This paper presents the use of a model-based approach for the formal description of real-time embedded multimodal systems. This modeling technique has been used in the field of military fighter aircrafts. The paper presents the formal description techniques, its application on the case study of a multimodal command and control interface for the Rafale aircraft as well as its relationship with architectural model for interactive systems.

This paper presents a design framework for safety critical interactive systems, based on a formal description technique called the ICO (Interactive Cooperative Object) formalism. ICO allows for describing, in a formal way, all the components of highly interactive (also called post-WIMP) applications. The framework is supported by a case tool called PetShop allowing for editing, verifying and executing the formal models. The first section describes why such user interfaces are challenging for most description techniques, as well as the state of the art in this field. Section 3 presents a development process dedicated to the framework. Then, we use a case study in order to recall the basic concepts of the ICO formalism and the recent extensions added in order to take into account post-WIMP interfaces' specificities. Section 5 presents the case tool PetShop and how the case study presented in the previous section has been dealt with. Lastly, we show how PetShop can be used for interactive prototyping.

CORBA is now established as one of the main contenders in object-oriented middleware.Beyond the definition of this standard for distributed object systems, the Object Management Group (OMG) has specified several object services (Common Object Services, COS) that should foster the interoperability of distributed applications.Based on experiment, the goal of this paper is to show that the OMG's style of specification of the CORBA services is not suited to guarantee that implementers will produce interoperable and substitutable implementations.To illustrate our point, we give an account of an experiment based upon the formal specification of one COS, namely the CORBA Event Service.This formal specification highlights several ambiguities and under-specifications in the OMG document.We then test several commercial and public domain implementations of the CORBA Event Service, in order to assess how the implementers have dealt with these underspecifications.We show that the choices made by the implementers lead to incompatible implementations.We finally suggest a solution to overcome the problem of specification of object services, which satisfies the views of both implementers and users.Specifically, we suggest that the specification of such services be made using a formal description technique, and that implementers be provided with test cases derived from the formal specification.

CORBA is a standard proposed by the Object Management Group (OMG) in order to promote interoperability between distributed object systems. CORBA provides a programming-language neutral Interface Definition Language (IDL) that describes the syntactic aspects of services supported by remote objects. However, CORBA IDL does not provide any means to specify the behavior of objects in an abstract and formal way. In the current practice, behavioral specification is provided either in plain English, or directly in the programming language chosen for the implementation. We propose to extend the CORBA interface definition of distributed objects by a behavioral specification based on high level Petri nets. We detail at the syntactic and semantic level how this formalism supports the features of the CORBA object model. We present a realistic case study to demonstrate our approach. Our technique allows specifying in an abstract, concise and precise way the behavior of CORBA servers, including internal concurrency and synchronization. As the behavioral specification is fully executable, this approach also enables to prototype and test a distributed object system as soon as the behaviors of individual objects have been defined. The paper discusses several implementation issues of the tool that supports the edition of models and their interactive excution. The high level of formality of the chosen formalism allows for mathematical analysis of behavioral specifications. Copyright © 2000 John Wiley & Sons, Ltd.

This paper aims at clarifying the articulation between the task models and system models encountered in CHI design practices. We demonstrate how the use of a formal task model may enhance the design of interactive systems, by providing quantitative results on which designers may base their decisions. We also demonstrate that it is possible to describe both task and system models within the same formal framework. This enables us firstly to formally prove that task and system models comply with each other, and secondly to perform quantitative analysis on the combination of task and system models. The approach is illustrated by a toy example which, despite its small size, allows us to develop both task and device models, and to perform several iterations of the design process. The device and tasks are modelled using the Interactive Cooperative Objects (ICO) formalism, which is based on Petri nets and on the object-oriented approach. The formality of Petri nets allows for axiomatic validation of isolated and interacting subsystems.