Lmg Loe Feijs

A relational approach to support software architecture analysis

This paper reports on our experience with a relational approach to support the analysis of existing software architectures. The analysis options provide for visualization and view calculation. The approach has been applied for reverse engineering. It is also possible to check concrete designs against architecture‐related rules. The paper surveys the theory, the tools and some of the applications developed so far.

Smart Jacket Design for Neonatal Monitoring with Wearable Sensors

Critically ill new born babies admitted at the Neonatal Intensive Care Unit (NICU) are extremely tiny and vulnerable to external disturbance. Smart Jacket proposed in this paper is the vision of a wearable unobtrusive continuous monitoring system realized by body sensor networks (BSN) and wireless communication. The smart jacket aims for providing reliable health monitoring as well as a comfortable clinical environment for neonatal care and parent-child interaction. We present the first version of the neonatal jacket that enables ECG measurement by textile electrodes. We also explore a new solution for skin-contact challenges that textile electrodes pose. The jacket is expandable with new wearable technologies and has aesthetics that appeal to parents and medical staff. An iterative design process in close contact with the users and experts lead to a balanced integration of technology, user focus and aesthetics. We demonstrate the prototype and the experimental results obtained in clinical setting.

Monitoring body temperature of newborn infants at neonatal intensive care units using wearable sensors

Body temperature is one of the key parameters for health monitoring of premature infants at the neonatal intensive care unit (NICU). In this paper, we propose and demonstrate a design of non-invasive neonatal temperature monitoring with wearable sensors. A negative temperature coefficient (NTC) resistor is applied as the temperature sensor due to its accuracy and small size. Conductive textile wires are used to make the sensor integration compatible for a wearable non-invasive monitoring platform, such as a neonatal smart jacket. Location of the sensor, materials and appearance are designed to optimize the functionality, patient comfort and the possibilities for aesthetic features. A prototype belt is built of soft bamboo fabrics with NTC sensor integrated to demonstrate the temperature monitoring. Experimental results from the testing on neonates at NICU of Máxima Medical Center (MMC), Veldhoven, the Netherlands, show the accurate temperature monitoring by the prototype belt comparing with the standard patient monitor.

A design of power supply for neonatal monitoring with wearable sensors

Continuous monitoring of health parameters is crucial for preterm new born babies admitted at the neonatal intensive care unit (NICU) in hospitals. The critically ill neonates are extremely tiny and vulnerable to external disturbance. In the context of ambient intelligence and smart environments, non-invasive health monitoring with wearable sensors is promising for the survival of these neonates and the quality of their life later on. A key question for health monitoring with wearable sensors is how to obtain reliable electrical power for the sensors, signal amplifiers, filters and transmitters. In this paper, we propose a design of wireless power supply based on the principle of inductive contactless energy transfer for use in NICU. The design process consists of scientific and user research, idea generation and selection, proof of technology, prototype implementation, and experimental validation. The proposed power supply satisfies the requirements of neonatal monitoring and provides continuous power when the neonate is inside the incubator or during Kangaroo mother care. A prototype is designed and implemented to demonstrate the performance of the power supply and the possibilities for aesthetic features. Experimental results show that the prototype transfers approximately 840 mW of power.

Exploring the potentials of combining photo annotating tasks with instant messaging fun

The combination of photo annotation tasks and with instant messaging fun offers great potentials to both end-users and researchers. In this paper, we first describe our prototype system that allows users to share and annotate digital photos over the Internet while they are chatting online. In addition to manual annotation, our system can extract information from conversations to generate extra annotations. The advantage of using our system is that the boring and tedious task of annotating photos is turned into an essential part of an attractive fun activity, viz. online chatting. Extracting meaningful information from instant messages is challenged by abbreviations, pronouns, jargon, ellipsis, grammatical errors, ambiguities and asynchrony, all of which frequently appear in message conversations. In the paper we provide a roadmap, i.e. a systematic analysis of linguistic aspects of automated interpretation of message conversations.

Non-invasive blood oxygen saturation monitoring for neonates using reflectance pulse oximeter

Blood oxygen saturation is one of the key parameters for health monitoring of premature infants at the neonatal intensive care unit (NICU). In this paper, we propose and demonstrate a design of a wearable wireless blood saturation monitoring system. Reflectance pulse oxymeter based on Near Infrared Spectroscopy (NIRS) techniques are applied for enhancing the flexibility of measurements at different locations on the body of the neonates and the compatibility to be integrated into a non-invasive monitoring platform, such as a neonatal smart jacket. Prototypes with the reflectance sensors embedded in soft fabrics are built. The thickness of device is minimized to optimize comfort. To evaluate the performance of the prototype, experiments on the premature babies were carried out at NICU of Máxima Medical Centre (MMC) in Veldhoven, the Netherlands. The results show that the heart rate and SpO2 measured by the proposed design are corresponding to the readings of the standard monitor.

From events to goals: Supporting semantic interaction in smart environments

When we connect smart devices to one another we open up many new possibilities. One interesting possibility is to support high-level semantic interaction without requiring multiple steps on multiple devices. In this paper we investigate how ontologies, runtime task models, Belief-Desire-Intention (BDI) models, and the blackboard architectural pattern may be used to enable semantic interaction for pervasive computing. An initial demonstrator was developed to visualize and manipulate semantic connections between devices in a smart home environment. The demonstrator provides a way for users to physically interact with devices on a high level of semantic abstraction without being bothered with the low-level details.

Semantic connections: Exploring and manipulating connections in smart spaces

In envisioned smart environments, enabled by ubiquitous computing technologies, electronic objects will be able to interconnect and interoperate. How will users of such smart environments make sense of the connections that are made and the information that is exchanged? This Internet of Things could have a life of its own, exchanging digital concepts and values between its members, having an understanding of each other and communicating in their own language. In this paper we report on an ongoing research project in the context of smart home environments. We discuss possibilities to represent this digital world in the physical reality we live in, by providing handles to control and clues to understand, build conceptual models of connections that exist or can be made. This is achieved by making semantic abstractions of low-level events and presenting them to users at a higher level, in a simplified fashion. Furthermore, we used an ontology to describe the low-level events, and used reasoning to infer high-level meaningful information. Although we are in the preliminary stages of our research, we consider it worthwhile to share and illustrate our findings by presenting a demonstrator, that implements our ideas in a home entertainment scenario.

EXPLORING EXPRESSION OF FORM, ACTION AND INTERACTION

The central theme in Ambient Intelligence is that powerful computation, communication and storage facilities are available, but are invisible. We believe that objects will play an important role as mediators. In order to make models of mediation and to study the mediation of behaviour, traditional modelling techniques, such as foam models, rendering etc. fall short. Although it is easy to make two-dimensional models of screens and front-panels and connect actions to the corresponding buttons, this approach is inadequate for new types of interfaces and behaviours which are not screen-based. Therefore we have experimented with an approach which we call 4D Sketching. The term 4D refers to the fact that it includes sketching in 3D space with the active behaviour adding a fourth, temporal dimension. We use foam, cardboard, a glue-gun, and other easy-to-use materials for the spatial sketching. We use a microprocessor, servo-motors and sensors to sketch active behaviour. The article describes the underlying philosophy, the technical aspects and a number of experiences gathered so-far, including student work from a project called Semotion.

Using semantic technologies to describe robotic embodiments

This paper presents our approach to using semantic technologies to describe robot embodiments. We introduce a prototype implementation of RoboDB, a robot database based on semantic web technologies with the functionality necessary to store meaningful information about the robots body structure. We present a heuristic evaluation of the user interface to the system, and discuss the possibilities of using the semantic information gathered in the database for applications like building a robot ontology, and the development of robot middleware systems.