Emna Mezghani

A Semantic Big Data Platform for Integrating Heterogeneous Wearable Data in Healthcare

Advances supported by emerging wearable technologies in healthcare promise patients a provision of high quality of care. Wearable computing systems represent one of the most thrust areas used to transform traditional healthcare systems into active systems able to continuously monitor and control the patients’ health in order to manage their care at an early stage. However, their proliferation creates challenges related to data management and integration. The diversity and variety of wearable data related to healthcare, their huge volume and their distribution make data processing and analytics more difficult. In this paper, we propose a generic semantic big data architecture based on the “Knowledge as a Service” approach to cope with heterogeneity and scalability challenges. Our main contribution focuses on enriching the NIST Big Data model with semantics in order to smartly understand the collected data, and generate more accurate and valuable information by correlating scattered medical data stemming from multiple wearable devices or/and from other distributed data sources. We have implemented and evaluated a Wearable KaaS platform to smartly manage heterogeneous data coming from wearable devices in order to assist the physicians in supervising the patient health evolution and keep the patient up-to-date about his/her status.

Knowledge as a Service Framework for Disaster Data Management

Each year, a number of natural disasters strike across the globe, killing hundreds and causing billions of dollars in property and infrastructure damage. Minimizing the impact of disasters is imperative in todays society. As the capabilities of software and hardware evolve, so does the role of information and communication technology in disaster mitigation, preparation, response, and recovery. A large quantity of disaster-related data is available, including response plans, records of previous incidents, simulation data, social media data, and Web sites. However, current data management solutions offer few or no integration capabilities. Moreover, recent advances in cloud computing, big data, and NoSQL open the door for new solutions in disaster data management. In this paper, a Knowledge as a Service (KaaS) framework is proposed for disaster cloud data management (Disaster-CDM), with the objectives of 1) storing large amounts of disaster-related data from diverse sources, 2) facilitating search, and 3) supporting their interoperability and integration. Data are stored in a cloud environment using a combination of relational and NoSQL databases. The case study presented in this paper illustrates the use of Disaster-CDM on an example of simulation models.

A Model-Driven Methodology for the Design of Autonomic and Cognitive IoT-Based Systems: Application to Healthcare

Due to its abilities to capture real-time data concerning the physical world, the Internet of Things (IoT) phenomenon is fast gaining momentum in different applicative domains. Its benefits are not limited to connecting things, but lean on how the collected data are transformed into insights and interact with domain experts for better decisions. Nonetheless, a set of challenges including the complexity of IoT-based systems and the management of the ensuing big and heterogeneous data and as well as the system scalability need to be addressed for the development of flexible smart IoT-based systems that drive the business decision-making. Consequently, inspired from the human nervous system and cognitive abilities, we have proposed a set of autonomic cognitive design patterns that alleviate the design complexity of smart IoT-based systems, while taking into consideration big data and scalability management. The ultimate goal of these patterns is providing generic and reusable solutions for elaborating flexible smart IoT-based systems able to perceive the collected data and provide decisions. These patterns are articulated within a model-driven methodology that we have proposed to incrementally refine the system functional and nonfunctional requirements. Following the proposed methodology, we have combined and instantiated a set of patterns for developing a flexible cognitive monitoring system to manage patients’ health based on heterogeneous wearable devices. We have highlighted the gained flexibility and demonstrated the ability of our system to integrate and process heterogeneous large-scale data streams. Finally, we have evaluated the system performance in terms of response time and scalability management.

Collaborative knowledge as a service applied to the disaster management domain

Cloud computing offers services which promise to meet continuously increasing computing demands by using a large number of networked resources. However, data heterogeneity remains a major hurdle for data interoperability and data integration. In this context, a knowledge as a service (KaaS) approach has been proposed with the aim of generating knowledge from heterogeneous data and making it available as a service. In this paper, a collaborative knowledge as a service (CKaaS) architecture is proposed, with the objective of satisfying consumer knowledge needs by integrating disparate cloud knowledge through collaboration among distributed KaaS entities. The NIST cloud computing reference architecture is extended by adding a KaaS layer that integrates diverse sources of data stored in a cloud environment. CKaaS implementation is domain-specific; therefore, this paper presents its application to the disaster management domain. A use case demonstrates collaboration of knowledge providers and shows how CKaaS operates with simulation models.

Towards an approach for modeling and formalizing SOA design patterns with Event-B

This paper introduces a formal architecture-centric approach, which allows first to model message-oriented SOA design patterns with the SoaML standard language, and second to formally specify these patterns at a high level of abstraction using the Event-B method. These two steps are performed before undertaking the effective coding of a design pattern providing correct by construction pattern-based software architectures. We implement our approach under the Rodin platform which we use to prove model consistency.

DRF4SOA: A Dynamic Reconfigurable Framework for Designing Autonomic Application Based on SOA

Service Oriented Architecture (SOA) allows modeling dynamic interaction between heterogeneous providers. Coupling with Service Component Architecture (SCA) enables governing the development of complex applications. The dynamic reconfiguration of such applications is a key feature, since it gives measures to ensure runtime adaptation in order to guarantee Quality of Service (QoS) and manage the performance. For instance, recovering a QoS degradation requires the identification of its sources and the capacity of reconfiguration planning and execution. This paper presents DRF4SOA, a Dynamic Reconfigurable Framework to design autonomic application based on SOA, that implements the autonomic control loop phases (Monitoring, Analysis, Planning, Execution) with SCA in order to provide flexibility to support evolving of itself and to include new non-functional requirements at runtime.

A Web-Based Knowledge Management System for Scientific Research Team

Scientific research teams have immense valuable knowledge that need to be managed. Organizing scientific contributions of team members constitutes a major challenge for the monitoring of knowledge evolution, team member’s competences discovery, and facilitating information retrieval processes. However, performing manual annotations is often time consuming and labor-intensive task, especially in case of complex annotation schemas. Currently, existing knowledge management systems focus on ensuring the scientific knowledge creation, sharing, organization and evaluation but don’t provide a way for helping researchers in the classification task. In this paper, we introduce a knowledge management system that offers an annotation service for researchers’ contributions by including some natural language processing techniques. The provided service process comprises four phases: (1) the semantic enrichment of domain ontology based on the extraction of background data from Babelnet knowledge base, (2) the automatic generation of candidate categories using the enriched domain ontology, (3) the forwarding of the pre-annotated papers to our web-based system to interact with researchers, and finally (4) the human revision of the generated annotations. Evaluation results show its advantage not only in reducing human effort and time consumption during the annotation task but also in improving annotations quality.

An Ontology-driven Adaptive System for the Patient Treatment Management.

Advances in the Web and healthcare data capture technologies have far-reaching benefits for the development of new clinical decision support systems that accelerate decision- making and generate personalized treatments. However, the diversity of healthcare data formats, the lack of computer interpretable representation of medical interventions, and the distribution of reliable medical knowledge sources constitute important barriers to better support the medical decision process. To deal with these issues, we propose the Treatment Plan Ontology (TPO) that formalizes medical interventions, and allows medical systems sharing and reasoning over them. This knowledge together with the acquired patient data are then reused by the autonomic processes that we have developed in order to timely detect anomalie s and support the physicians in personalizing the patient treatment at the right time. We demonstrate the system efficiency through a use case for managing hyperglycemia in type 2 diabetes.

QoS-driven Autonomic Abilities through a Multi-homed Transport Protocol

With the development of Internet technologies, distributed and multimedia applications are more and more used. Because these applications have Quality of Service (QoS) expectations (bounded delay, guaranteed bandwidth, etc.), a set of QoS oriented protocols aimed at aiding end-to-end communications are proposed. Each one of these protocols offers one or several mechanisms. Selecting the best protocol with the best mechanism(s) according to the application requirements and network contexts is a challenge if we want to provide enough QoS to the final users. Also because contexts can evolve, for example when network characteristics change, the previous selected protocol can become obsolete. In this context, an adaptation is mandatory. In this paper, we show how the OSI transport layer can become autonomic in order to perform dynamically reconfiguration actions when it is needed. Our approach consists in including at the transport layer the MAPE loop of the autonomic computing proposal to monitor and analyze the communication in order to predict or to detect a QoS degradation induced by changes of network context, and to plan and execute dynamically new reconfiguration actions in order to keep the communication at the expected QoS level. To implement and evaluate our approach, we extend the new Multipath-TCP (MPTCP) protocol, which offers an extensible application oriented layer. This layer gives opportunity to deploy QoS-aware mechanisms. The test results show that the consumption time of autonomic selection and composition of these mechanisms at run time does not prevent enhancing the QoS, and encourage us to continue working in this approach.