Josué Iglesias

Towards integrating fuzzy logic capabilities into an ontology-based Inductive Logic Programming framework

Ontologies based on Description Logics (DLs) have proved to be useful in formally sharing knowledge across applications. Recently, several tools have extended ontologies with fuzzy logic capabilities in order to apply ontology-based reasoning to vague and imprecise domains. This paper first analyses the state of the art in tools for fuzzy ontologies management and then describes how some of the most significant ones have been integrated in order to extend an ontology-based Inductive Logic Programming (ILP) system with fuzzy logic capabilities. A fuzzy version of a well-known ILP test case has been developed in order to validate the approach. This research represents a first step towards fuzzy inductive reasoning for OWL ontologies.

Design and validation of a light inference system to support embedded context reasoning

Embedded context management in resource-constrained devices (e.g. mobile phones, autonomous sensors or smart objects) imposes special requirements in terms of lightness for data modelling and reasoning. In this paper, we explore the state-of-the-art on data representation and reasoning tools for embedded mobile reasoning and propose a light inference system (LIS) aiming at simplifying embedded inference processes offering a set of functionalities to avoid redundancy in context management operations. The system is part of a service-oriented mobile software framework, conceived to facilitate the creation of context-aware applications—it decouples sensor data acquisition and context processing from the application logic. LIS, composed of several modules, encapsulates existing lightweight tools for ontology data management and rule-based reasoning, and it is ready to run on Java-enabled handheld devices. Data management and reasoning processes are designed to handle a general ontology that enables communication among framework components. Both the applications running on top of the framework and the framework components themselves can configure the rule and query sets in order to retrieve the information they need from LIS. In order to test LIS features in a real application scenario, an ‘Activity Monitor’ has been designed and implemented: a personal health-persuasive application that provides feedback on the user’s lifestyle, combining data from physical and virtual sensors. In this case of use, LIS is used to timely evaluate the user’s activity level, to decide on the convenience of triggering notifications and to determine the best interface or channel to deliver these context-aware alerts.

A ubiquitous activity-monitor to prevent sedentariness

The Activity Monitor described in this paper is an easy-to-configure context-aware mobile application, capable of estimating and evaluating the users activity all day long. It relies on fusion strategies for movement and location estimation, which combine acceleration and radio data from in-device and external sensors. The final objective of the Activity Monitor is to deliver adequate context-aware notifications in order to make the user aware of his level of activity. The reasoning process to decide when and how to deliver notifications is fully done in the mobile device by using an embedded reasoner, avoiding privacy issues related to personal sensitive data sharing.

A Light Reasoning Infrastructure to Enable Context-aware Mobile Applications

This paper presents a light inference system for context management, ready to perform reasoning tasks in resource-constrained devices. The inference system is part of a service-oriented mobile software framework which runs on Javaenabled handheld devices. This framework serves to facilitate the creation of context-aware applications, as it decouples sensor’s data acquisition and context processing from the application logic itself. The inference architecture is composed by different modules, some of them encapsulate existing tools (ìJena and Bossam) that have been adapted to the mobile working environment. The (rule-based) reasoning is prepared to use a general ontology. Both applications and the frameworks components may configure the query set in order to retrieve the information they need from the inference system. In the paper, a validation example shows how this process is done.

Model-Driven Methodology for Rapid Deployment of Smart Spaces Based on Resource-Oriented Architectures

Advances in electronics nowadays facilitate the design of smart spaces based on physical mash-ups of sensor and actuator devices. At the same time, software paradigms such as Internet of Things (IoT) and Web of Things (WoT) are motivating the creation of technology to support the development and deployment of web-enabled embedded sensor and actuator devices with two major objectives: (i) to integrate sensing and actuating functionalities into everyday objects, and (ii) to easily allow a diversity of devices to plug into the Internet. Currently, developers who are applying this Internet-oriented approach need to have solid understanding about specific platforms and web technologies. In order to alleviate this development process, this research proposes a Resource-Oriented and Ontology-Driven Development (ROOD) methodology based on the Model Driven Architecture (MDA). This methodology aims at enabling the development of smart spaces through a set of modeling tools and semantic technologies that support the definition of the smart space and the automatic generation of code at hardware level. ROOD feasibility is demonstrated by building an adaptive health monitoring service for a Smart Gym.

An Evidential and Context-Aware Recommendation Strategy to Enhance Interactions with Smart Spaces

This work describes a novel strategy implementing a context-aware recommendation system. It has been conceived to offer an intelligent selection of micro-services used to orchestrate networks of smart objects taking into account users’ needs and preferences. The recommendation offering dynamically evolves depending on users’ micro-service management patterns and users’ context. The complete system has been designed within Dempster-Shafer evidential theory framework, ensuring uncertainty support both at context acquisition and at recommendation configuration level.

An Attitude-Based Reasoning Strategy to Enhance Interaction with Augmented Objects

This paper describes a mobile-based system to interact with objects in smart spaces, where the offer of resources may be extensive. The underlying idea is to use the augmentation capabilities of the mobile device to enable it as user-object mediator. In particular, the paper details how to build an attitude-based reasoning strategy that facilitates user-object interaction and resource filtering. The strategy prioritizes the available resources depending on the spatial history of the user, his real-time location and orientation and, finally, his active touch and focus interactions with the virtual overlay. The proposed reasoning method has been partially validated through a prototype that handles 2D and 3D visualization interfaces. This framework makes possible to develop in practice the IoT paradigm, augmenting the objects without physically modifying them.

A Bayesian Strategy to Enhance the Performance of Indoor Localization Systems

This work describes the probabilistic modelling of a Bayesian-based mechanism to improve location estimates of an already deployed location system by fusing its outputs with low-cost binary sensors. This mechanism takes advantage of the localization capabilities of different technologies usually present in smart environments deployments. The performance of the proposed algorithm over a real sensor deployment is evaluated using simulated and real experimental data.

Towards a fuzzy-based multi-classifier selection module for activity recognition applications

Performing activity recognition using the information provided by the different sensors embedded in a smartphone face limitations due to the capabilities of those devices when the computations are carried out in the terminal. In this work a fuzzy inference module is implemented in order to decide which classifier is the most appropriate to be used at a specific moment regarding the application requirements and the device context characterized by its battery level, available memory and CPU load. The set of classifiers that is considered is composed of Decision Tables and Trees that have been trained using different number of sensors and features. In addition, some classifiers perform activity recognition regardless of the on-body device position and others rely on the previous recognition of that position to use a classifier that is trained with measurements gathered with the mobile placed on that specific position. The modules implemented show that an evaluation of the classifiers allows sorting them so the fuzzy inference module can choose periodically the one that best suits the device context and application requirements.

A development methodology to facilitate the integration of Smart Spaces into the Web of Things

How to create or integrate large Smart Spaces (considered as mash-ups of sensors and actuators) into the paradigm of “Web of Things” has been the motivation of many recent works. A cutting-edge approach deals with developing and deploying web-enabled embedded devices with two major objectives: 1) to integrate sensor and actuator technologies into everyday objects, and 2) to allow a diversity of devices to plug to Internet. Currently, developers who want to use this Internet-oriented approach need have solid understanding about sensorial platforms and semantic technologies. In this paper we propose a Resource-Oriented and Ontology-Driven Development (ROOD) methodology, based on Model Driven Architecture (MDA), to facilitate to any developer the development and deployment of Smart Spaces. Early evaluations of the ROOD methodology have been successfully accomplished through a partial deployment of a Smart Hotel.