International audience

Abstract We aim to facilitate the daily-life activities of frail or elderly people in collaboration with mobile assistive robots through the means of a digital twin-powered smart home. Being able to quickly and efficiently produce a digital twin of the human user’s environment, can help to further develop personalized assistive solutions. As our first investigation toward this goal, we describe our proof-of-concept “digital twin-driven smart home” implementation. It consists of a virtual representation, robot navigation and environment semantics using open-source software. The initial obtained results on the building process of the digital twin are encouraging and suggest the possibility of integration of digital twin for smart spaces.

Abstract With life expectancy growing rapidly over the past century, societies are being increasingly faced with a need to find smart living solutions for elderly care and active ageing. The e-VITA project, which is a joint European (H2020) and Japanese (MIC) funded project, is based on an innovative approach to virtual coaching that addresses the crucial domains of active and healthy ageing. In this paper we describe the role of spoken dialogue technology in the project. Requirements for the virtual coach were elicited through a process of participatory design in workshops, focus groups, and living labs, and a number of use cases were identified for development using the open-source RASA framework. Knowledge Graphs are used as a shared representation within the system, enabling an integration of multimodal data, context, and domain knowledge.

Abstract Building Energy Management (BEM) and monitoring systems should not only consider HVAC systems and building physics but also human behaviors. These systems could provide information and advice to occupants about the significance of their practices with regard to the current state of a dwelling. It is also possible to provide services such as assistance to the elderly, comfort and health monitoring. For this, an intelligent building must know the daily activities of its residents and the algorithms of the smart environment must track and recognize the activities that the occupants normally perform as part of their daily routine. In the literature, deep learning is one of effective supervised learning model and cost-efficient for real-time HAR, but it still struggles with the quality of training data (missing values in time series and non-annotated event), the variability of data, the data segmentation and the ontology of activities. In this work, recent research works, existing algorithms and related challenges in this field are firstly highlighted. Then, new research directions and solutions (performing fault detection and diagnosis for drift detection, multi-label classification modeling for multi-occupant classification, new indicators for training data quality, new metrics weighted by the number of representations in dataset to handle the issue of missing data and finally language processing for complex activity recognition) are suggested to solve them respectively and to improve this field.

In this paper, we propose a method to support seamless mobility for sessions carried by SIPTO connections. Session continuity has been considered an issue to be solved within 3GPP, as none of the solutions proposed for Mobile IP directly apply in the context of LTE. As in some cases, typically when SIPTO relies on using Local Gateways (LGW), it is necessary to change the IP address allocated to a User Equipment (UE), an active session may be interrupted. We propose an MPTCP based solution within the LTE architecture to maintain a single session, initially carried over a given SIPTO connection, and then carried over another SIPTO connection initiated due to the mobility of user equipment (UE). We identify how MPTCP operates over the LTE architecture, and estimate whether the corresponding delay is compatible with session continuity.

A dynamic decision making framework implementing multi criteria routing of multimedia services at private-public network border with access technology convergence while offering multi-homed infrastructure is presented. Multi Criteria Decision Making (MCDM) theory and Ontology are integrated over the platform for addressing the diversity, dimensionality along with multiple objectives over distinct planes and inter/intra-domain semantics variations issues respectively. A simple use-case involving the dynamic decision-based routing at private-public network border over the same framework is presented to validate the proposed solution. The system gives higher throughput and lower call dropping probability with an add-on susceptible delay while offering good QoS and QoE.

We present a UML 1.5 profile named TURTLE (Timed UML and RT-LOTOS Environment) endowed with a formal semantics given in terms of RT-LOTOS. TURTLE relies on UML's extensibility mechanisms to enhance class and activity diagrams. Class diagrams are extended with specialized classes named Tclasses, which communicate and synchronize through gates. Also, associations between Tclasses are attributed by a composition operator (Parallel, Synchro, Invocation, Sequence, or Preemption) which provides them with a formal semantics. TURTLE extends UML activity diagrams with synchronization actions and temporal operators (deterministic delay, nondeterministic delay, time-limited offer, and time-capture). The real-time dimension of TURTLE has been further improved by the addition of two composition operators, periodic and suspend, as well as suspendable delay, latency, and time-limited offer operators at the activity diagram level. Core characteristics of TURLE are supported by TTool - the TURTLE toolkit - which includes a diagram editor, a RT-LOTOS code generator and a result analyzer. The toolkit reuses RTL, a RT-LOTOS validation tool offering debug-oriented simulation and exhaustive analysis. TTool hides RT-LOTOS to the end-user and allows him/her to directly check TURTLE modeling against logical errors and timing inconsistencies. Besides the foundations of the TURTLE profile, this paper also discusses its application in the context of space-based embedded software.

The utilization of Interactive Multimedia Documents (IMDs) has been largely addressed in several fields such as education, medicine, etc. since these documents can be distributed and accessed over the World-Wide-Web. In this context, the W3C standard Synchronized Multimedia Integration Language (SMIL) has been proposed for the presentation of IMD's over the Web. However, the flexibility of the temporal model of SMIL 2.0 allows the author to describe temporal synchronization relationships that potentially can not be resolved during the presentation of the document, known as temporal inconsistencies. For this reason, an approach that enables to detect and correct these inconsistencies is needed.This paper presents a formal approach for the verification, scheduling and presentation of consistent SMIL 2.0 documents based on the RT-LOTOS formal description technique. Thus, the consistency analysis of SMIL 2.0 documents is presented and some solutions are proposed in order to deal with potential state space explosion problems. Further on, some contributions are also presented concerning the scheduling and presentation of SMIL 2.0 documents based on a simple scheduling graph, called a Time Labeled Automata (TLA), derived automatically from the document formal specification. Finally, a global Java-based architecture for the implementation of a player of consistent SMIL 2.0 documents is presented.