Skip to main content

Über dieses Buch

This volume contains the proceedings of the 6th International Symposium on Ambient Intelligence (ISAmI 2015), held in Salamanca, Spain on June 3th-5th at the University of Salamanca. After a careful review, 27 papers from 10 different countries were selected to be presented in ISAmI 2015 at the conference and published in the proceedings.

ISAmI has been running annually and aiming to bring together researchers from various disciplines that constitute the scientific field of Ambient Intelligence to present and discuss the latest results, new ideas, projects and lessons learned, namely in terms of software and applications and aims to bring together researchers from various disciplines that are interested in all aspects of this area.

Ambient Intelligence is a recent paradigm emerging from Artificial Intelligence, where computers are used as proactive tools assisting people with their day-to-day activities, making everyone’s life more comfortable. Another main concern of AmI originates from the human computer interaction domain and focuses on offering ways to interact with systems in a more natural way by means user friendly interfaces. This field is evolving quickly as can be witnessed by the emerging natural language and gesture based types of interaction.



Using Evolutionary Algorithms to Personalize Controllers in Ambient Intelligence

As users can have greatly different preferences, the personalization of ambient devices is of utmost importance. Several approaches have been proposed to establish such a personalization in the form of machine learning or more dedicated knowledge-driven learning approaches. Despite its huge successes in optimization, evolutionary algorithms (EAs) have not been studied a lot in this context, mostly because it is known to be a slow learner. Currently however, quite fast EA based optimizers exist. In this paper, we investigate the suitability of EAs for ambient intelligence.
Shu Gao, Mark Hoogendoorn

Automatic Early Risk Detection of Possible Medical Conditions for Usage Within an AMI-System

Using hyperglycemia as an example, we present how Bayesian networks can be utilized for automatic early detection of a person’s possible medical risks based on information provided by unobtrusive sensors in their living environments. The network’s outcome can be used as a basis on which an automated AMI-system decides whether to interact with the person, their caregiver, or any other appropriate party. The networks’ design is established through expert elicitation and validated using a half-automated validation process that allows the medical expert to specify validation rules. To interpret the networks’ results we use an output dictionary which is automatically generated for each individual network and translates the output probability into the different risk classes (e.g., no risk, risk).
H. Joe Steinhauer, Jonas Mellin

Reducing Stress and Fuel Consumption Providing Road Information

In this paper, we propose a solution to reduce the stress level of the driver, minimize fuel consumption and improve safety. The system analyzes the driving and driver workload during the trip. If it discovers an area where the stress increases and the driving style is worse from the point of view of energy efficiency, a photo is taken and is saved along with its location in a shared database. On the other hand, the solution warns the user when is approaching a region where the driving is difficult (high fuel consumption and stress) using the shared database. In this case, the proposal shows on the screen of the mobile device the image captured previously of the area. The aim is that driver knows in advance the driving environment. Therefore, he or she may adjust the vehicle speed and the driver workload decreases. Data Envelopment Analysis is used to estimate the efficiency of driving and driver workload in each area. We employ this method because there is no preconceived form on the data in order to calculate the efficiency and stress level. A validation experiment has been conducted with 6 participants who made 96 driving tests in Spain. The system reduces the slowdowns (38 %), heart rate (4.70 %), and fuel consumption (12.41 %). The proposed solution is implemented on Android mobile devices and does not require the installation of infrastructure on the road. It can be installed on any model of vehicle.
Víctor Corcoba Magaña, Mario Muñoz Organero

Policy-Based Adaptation of Context Provisioning in AmI

With the increasing openness and complexity introduced by recent Ambient Intelligence application domains (e.g. Web-of-Things, Sensing-as-a-Service), adaptation of Context Provisioning becomes a key issue. However, methods to easily specify and engineer such mechanisms remain insufficiently explored. In this work we present and evaluate our approach of using semantic-web and multi-agent technologies to define and execute context provisioning policies within our Context Management Middleware called CONSERT.
Alexandru Sorici, Gauthier Picard, Olivier Boissier, Adina Florea

An Adaptive Particle Filter for Indoor Robot Localization

This paper develops an adaptive particle filter for indoor mobile robot localization, in which two different resampling operations are implemented to adjust the number of particles for fast and reliable computation. Since the weight updating is usually much more computationally intensive than the prediction, the first resampling-procedure so-called partial resampling is adopted before the prediction step, which duplicates the large weighted particles while reserves the rest obtaining better estimation accuracy and robustness. The second resampling, adopted before the updating step, decreases the number of particles through particle merging to save updating computation. In addition to speeding up the filter, sample degeneracy and sample impoverishment are counteracted. Simulations on a typical 1D model and for mobile robot localization are presented to demonstrate the validity of our approach.
Hao Lang, Tiancheng Li, Gabriel Villarrubia, Shudong Sun, Javier Bajo

A Discomfort-Sensitive Chair for Pointing Out Mental Fatigue

In our busy daily life, we often have the feeling of being exhausted, accompanied with a sense of performance degradation and increase of discomfort in the execution of even simple tasks. This often takes place in the workplace and in a silent way, influencing our productivity, our performance the number of errors or the quality of our production. This paper details a chair to be used in workplace environments that is sensitive to the onset of fatigue. Based on built-in accelerometers it recognizes signs of discomfort, which may be related to mental fatigue, to point out moments when an individual should consider taking a pause or a rest. This chair complements a previously developed software for the assessment of mental fatigue from the analysis of the individual’s interaction with the computer.
André Pimenta, Davide Carneiro, Paulo Novais, José Neves

Development of a High Mobility Assistant Personal Robot for Home Operation

This paper presents the development of an Assistant Personal Robotic (APR) designed with the objective of creating a high reliable robot that can be used in several home applications such as: home safety, elder people supervision and remote assistance, remote presence, etc. In this proposal the APR is remotely controlled by a smartphone or portable tablet with Wi-Fi connectivity. The APR design has taken into consideration safety factors, mobility and physical restrictions of an average home; including opened doors, tight turns, and narrow corridors. The APR design includes several onboard sensors in order to protect the robot and avoid collisions with fixed or moving surrounding objects.
Eduard Clotet, Dani Martínez, Javier Moreno, Marcel Tresanchez, Jordi Palacín

Using ICT for Tacit Knowledge Preservation in Old Age

As the world population is aging, numerous challenges were raised. How to maintain a sustainable aging? How to increase the active role of older adults in society? How to promote healthy aging along with the improvement of social and technological inclusion and enhance emotional well-being? How to preserve the vast tacit knowledge existent in seniors? Pervasive computing can giving an enormous contribution to overcome this issues. In the present paper we introduce eService platform as a novel service ecosystem mainly developed for senior population, including life experiences and knowledge record service. We have researched and selected the most relevant accessibility guidelines concerning senior population and made a low fidelity prototype, followed by both fidelity prototypes, one with and one without guideline application. Finally we conducted usability tests and semi structured interviews with 6 individuals to validate our work. The experimental results demonstrated that the proposed guideline checklist was validated, well accepted and easy to use by seniors. They also validate the extreme importance of knowledge preservation.
Isabel Marcelino, José Góis, Rosalía Laza, António Pereira

Step Count and Classification Using Sensor Information Fusion

In order to suppress the GNSS (Global Navigation Satellite System) limitation to track persons in indoor or in dense environments, a pedestrian inertial navigation system can be used. However, this type of systems have huge location estimation errors due to the Pedestrian Dead Reckoning (PDR) characteristics and the use of low-cost inertial sensors. To suppress some of these errors we propose a system that uses several sensors spread in person’s body combined with information fusion techniques. Information fusion techniques provide lighter algorithms implementations, to count and classify the type of step, to run in mobile devices. Thus, improving pedestrian inertial navigation systems accuracy.
Ricardo Anacleto, Lino Figueiredo, Ana Almeida, Paulo Novais, António Meireles

ECG Signal Prediction for Destructive Motion Artefacts

This paper addresses the ability of Burg algorithm to predict the ECG signal when it was completely destroyed by motion artefacts. The application focus of this study is portable devices used in telemedicine and healthcare, where the daily activity of patients produces several contact losses and movements of electrodes on the skin. The paper starts with a short analysis of noise sources that affects the ECG signal, followed by the algorithm implementation and the results. The obtained results show that Burg algorithm is a very promising technique to predict the ECG signal for at least three sequential heart beats.
António Meireles, Lino Figueiredo, Luís Seabra Lopes, Ricardo Anacleto

A Sentiment Analysis Classification Approach to Assess the Emotional Content of Photographs

The integration of Ambient Intelligence and Sentiment Analysis provides mutual benefits. On the one hand, Sentiment Analysis may enable developing interfaces providing a more natural interaction with human-computer interfaces. On the other, AmI enables using context-awareness information to enhance the performance of the system, achieving a more efficient and proactive human-machine communication that can be dynamically adapted to the user’s state and the status of the environment. In this paper, we describe a novel Sentiment Analysis approach combining a lexicon-based model for specifying the set of emotions and a statistical methodology to identify the most relevant topics in the document that are the targets of the sentiments. Our proposal also includes an heuristic learning method that allows improving the initial knowledge considering the users’ feedback. We have integrated the proposed Sentiment Analysis approach into an Android-based mobile App that automatically assigns sentiments to pictures taking into account the description provided by the users.
David Griol, José Manuel Molina

Opportunistic Sensoring Using Mobiles for Tracking Users in Ambient Intelligence

The necessity of using new technologies to monitoring elderly people in open-air environments by their caregivers has become a priority in the last years. In this direction, Ambient Intelligence (AmI) provides useful mechanisms and the geo-localization technologies embedded in smartphones allows tracking elderly people through opportunistic sensoring. The aim of this paper is to show a practical example to how to combine some technologies for monitoring elderly people through the system SafeRoute. We describe the two components of this system: the Android application CareofMe and the web system SafeRoute. The proposed system uses GPS, Wifi and accelerometer sensoring, GoogleMaps functionalities in Android and web environments and an alert system for caregivers.
Javier Jiménez Alemán, Nayat Sanchez-Pi, Ana Cristina Bicharra Garcia

Mobile Crowd Sensing for Solidarity Campaigns

We present an ongoing project (This work is partially supported by the InfoCrowds project-PTDC/ECM-TRA/1898/2012 This work is supported by CISUC, via national funding by the FCT - Fundação para a Ciência e Tecnologia.) which has two separate strands, one refers to the technological study about the applicability of high performance and high availability technologies in Web Services and the other is directed to a practical application of these technologies to solidarity campaigns in collecting goods. The focus of this paper is in the first one, a technological study where several frameworks for building Web Services, databases of different types and libraries to assist in obtaining product codes (barcodes) and data are analyzed, this includes a study of performance, availability and reliability, as well as appraisals for each one. Besides this, we introduce an experimental setup and results obtained so far in a third sector institution, Caritas Diocesana of Coimbra (http://​www.​caritas.​pt/​site/​nacional/​ Portuguese Website (last visited in March 2015)), a non-profit organization part of Caritas (http://​www.​caritas.​eu/​ (last visited in March 2015)). As main contribution, we propose a distributed architecture for Mobile Crowd Sensing able not only to allow real time inventory through simultaneous campaigns but also it gives feedback to volunteers in order to instantly acquire information about which categories of goods are more needed.
Ana Alves, David Silva

3D Reconstruction of Bone Structures Based on Planar Radiography

The 3D reconstruction of bone structures has many advantages in orthopedic applications. 3D bone models could be used in computer assisted surgery systems or in the pre-operative planning of an orthopedic surgery. The visualization of these models will lead to higher surgery accuracy. Usually the 3D reconstruction is done with CT or MRI scans. However these modalities have some disadvantages like the high costs, high acquisition time and high radiation. So, the planar radiography emerges as a more advantageous modality, because it avoids exposure to high radiation, reduces the acquisition time and costs and also is the most usually acquired study in the pre-operative planning of an orthopedic surgery. The principal challenge in reconstructing bone models from planar radiography is that a lot of information is missing when only one or two orthogonal images are used. So it’s hard to obtain a precise geometry of the bone structure with only this information. In this work, we present a solution for the problem of reconstructing bone structures from planar radiography. With this solution, it’s possible to obtain a 3D model of the bone that is suitable for orthopedic surgery planning.
Ana Coelho, João Pedro Ribeiro, Jaime Campos, Sara Silva, Victor Alves

Context-Aware Well-Being Assessment in Intelligent Environments

The implementation of concepts such as smart cities, ambient intelligence and internet of things enables the construction of complex systems that may follow users across environments through many devices. One potential application is the assessment and assurance of well-being of users within different environment with different configurations. This is a complex task that requires the capture of the state and context of both users and environments through sensors dispersed across environments and users. It’s the opportunities created by the emergence of technology that provide enough information to intelligent autonomous systems. Adapting expectations of a well-being assessment system to task and context is possible using the new techniques imported from different fields such as sensor networks, sensor fusion and machine learning. This article encompasses the design and implementation of a platform to evaluate well-being according to each context and translate it to sustainable indicators.
Fábio Silva, Celestino Gonçalves, Cesar Analide

An Overview of the Quality of Service in Bluetooth Communications in Healthcare

Currently, the general public requires devices getting faster and great performance, that is, devices ensuring a better quality of service. One way to achieve these goals is through the use of devices supported by the mobile computing with tools to help the search for information. Bluetooth technology is an open standard for wireless communication allowing the transmission of data and information between electronic devices within walking distance, with minimum resource expenditures, safe and rapid transition of data. So, the Bluetooth technology was initially designed to support simple network devices and personal devices such as mobile phones, PDAs and computers, but quickly it were discovered other applications in several areas. In this article, it will be performed a literature review on the topic, with the goal to understand how the Bluetooth technology can benefit increases in the Quality of Service and the presentation of some actual and potential biomedical applications.
Ana Pereira, Eliana Pereira, Eva Silva, Tiago Guimarães, Filipe Portela, Manuel Filipe Santos, António Abelha, José Machado

Computer Vision Based Indoor Navigation: A Visual Markers Evaluation

The massive diffusion of smartphones and the exponential rise of location based services (LBS) have made the problem of localization and navigation inside buildings one of the most important technological challenges of the last years. Indoor positioning systems have a huge market in the retail sector and contextual advertising; moreover, they can be fundamental to increase the quality of life for the citizens. Various approaches have been proposed in scientific literature. Recently, thanks to the high performances of the smartphones’ cameras, marker-less and marked-based computer vision approaches have been investigated. In a previous paper, we proposed a technique for indoor navigation using both Bluetooth Low Energy (BLE) and a 2D visual markers system deployed into the floor. In this paper, we present a qualitative performance evaluation of three 2D visual markers suitable for real-time applications.
Gaetano C. La Delfa, V. Catania, S. Monteleone, Juan F. De Paz, J. Bajo

A Framework for the Secure Storage of Data Generated in the IoT

The Internet of Things can be seen has a growing number of things that inter-operate using an Internet-based infrastructure and that has evolved during the last years with little concern for the privacy of its users, especially regarding how the collected data is stored. Technological measures ensuring users privacy must be established. In this paper we will present a technological framework for the secure storage of data. Things can then interact with the framework’s API much in the same way they now interact with its current servers, after which, the framework will perform the required operations in order to secure the data before storing it. The methods adopted for the secure storage will maintain the sharing ability, conveniently allowing authorized access to other users, the initial user’s terms (e.g. data anonymity) and the ability to revoke assigned privileges at all times.
Ricardo Costa, António Pinto

Multi-agent Systems for Classification of E-Nose Data

Metal Oxide Semiconductor Gas Sensors are used to measure and classify odors. This kind of system requires both advanced sensor design and classification techniques. In this paper we present a MOGS (Metal Oxide Gas Sensor) specifically designed to classify the breath of humans. We propose an architecture that incorporates new sensing technology and a classification technique based on multi-agent systems. The proposal is evaluated using samples from Asian and European participants. The results obtained are promising.
Yoshinori Ikeda, Sigeru Omatu, Pablo Chamoso, Alberto Pérez, Javier Bajo

Using Machine Learning Techniques for the Automatic Detection of Arterial Wall Layers in Carotid Ultrasounds

A fully automatic segmentation method for ultrasound images of the common carotid artery is proposed in this paper. The goal of this procedure is the detection of the arterial wall layers to assist in the evaluation of the Intima-Media Thickness (IMT), which is an early indicator of atherosclerosis and, therefore, of the cardiovascular risk. By measuring and monitoring the IMT, specialists are able to detect the incipient thickening of the arteries when the patient is still asymptomatic and to prescribe the appropriate preventive care. The proposed methodology is completely based on Machine Learning and it applies Auto-Encoders and Deep Learning to obtain abstract and efficient data representations. A set of 45 ultrasound images have been used in the validation of the suggested system. In particular, the resulting automatic contours for each image have been compared with four manual segmentations performed by two different observers. This study demonstrates the accuracy of our segmentation method, which achieves the correct recognition of the arterial layers in all the tested images in a totally user-independent and repeatable manner.
Rosa-María Menchón-Lara, José-Luis Sancho-Gómez, Adrián Sánchez-Morales, Álvar Legaz-Aparicio, Juan Morales-Sánchez, Rafael Verdú-Monedero, Jorge Larrey-Ruiz

eServices - Service Platform for Pervasive Elderly Care

In this paper, we present a solution to improve elderly’s quality of life. eServices – Service platform for pervasive elderly care was designed to aggregate several services developed to meet senior population’s needs. It monitors basic life signs, environment variables and uses personal location technology. Besides sensor services, eServices solution contains digital services align with emotional and social care needs. Due to target population specifications, eServices was designed to be as simple and accessible as possible in order to remove technological barriers. One of eServices major features is to detect imminent danger situations, act accordingly. It also collects the data from the sensors, location routines and from the interactions between the elderlies and the provided services to detect behavior deviations in order to act preventively. The platform was tested by seniors in real scenario. The experimental results demonstrated that the proposed platform was well accepted and easy to use by seniors, which demonstrated enthusiasm and interest in daily bases use.
Isabel Marcelino, Rosalía Laza, Patrício Domingues, Silvana Gómez-Meire, António Pereira

A Sensor-Based Framework to Support Clinicians in Dementia Assessment: The Results of a Pilot Study

This paper presents the main mechanisms of a sensor-based framework to support clinical diagnosis of people suffering from Alzheimer disease and dementia. The framework monitors patients at a lab environment while trying to accomplish specific tasks. Different types of sensors are used for monitoring the patients, while a graphical user interface enables the clinicians to access and visualize the results. Sensor data is semantically integrated and analyzed using knowledge-driven interpretation techniques based on Semantic Web technologies. Moreover, this paper presents encouraging preliminary results of a pilot study in which 59 patients (29 Alzheimer disease –AD– and 30 mild cognitive impairment –MCI) participated in a clinical protocol. Their analysis indicated that MCI patients outperformed AD patients in specific tasks of the protocol, verifying the initial clinical assessment.
Anastasios Karakostas, Georgios Meditskos, Thanos G. Stavropoulos, Ioannis Kompatsiaris, Magda Tsolaki

Unified Fingerprinting/Ranging Localization for e-Healthcare Systems

Indoor localization constitutes one of the main pillars for the provision of context-aware services in e-Healthcare systems. Fingerprinting and ranging have traditionally been placed facing each other to meet the localization requirements. However, accurate fingerprinting may worth the exhaustive calibration effort in some critical areas while easy-to-deploy ranging can provide adequate accuracy for certain non-critical spaces. In this paper, we propose a framework and algorithm for seamless integration of both systems from the Bayesian perspective. We assessed the proposed framework with conventional WiFi devices in comparison to conventional implementations. The presented techniques exhibit a remarkable accuracy improvement while they avoid computationally exhaustive algorithms that impede real-time operation.
Javier Prieto, Juan F. De Paz, Gabriel Villarrubia, Javier Bajo, Juan M. Corchado

My Kinect Is Looking at Me - Application to Rehabilitation

This paper studies the feasibility of using two Kinect sensors, compared to only one, as part of a system of computer-aided rehabilitation. The use of multiple sensors to collect and further process the movements of users, is initially an advantage over the use of a single sensor, but the interference due to the co-existence of two sensors in the same scene must be considered. The purpose of this paper is to determine how overlapping of several beams of infrared light affect the capture of users, in function of the angle of incidence and the distance to the targets. The paper also examines whether the use of two Kinect sensors increases the accuracy of the data collected and the range of action of the sensors.
Miguel Oliver, Antonio Fernández-Caballero, Pascual González, José Pascual Molina, Francisco Montero

Flying Depth Camera for Indoor Mapping and Localization

This paper introduces a flying robot mapping and localization proposal from an onboard depth camera. The miniature flying robot is part of an ongoing project related to ambient assisted living and home health. The flying depth camera is used with a double function; firstly, as a range sensor for mapping from scratch during navigation, and secondly, as a gray-scale camera for localization. The Harris corner detection algorithm is implemented as key point detector for the creation and/or identification of indoor spatial relations. During the localization phase, the spatial relations created from detected corners in the mapping phase are compared to the corners identified in the map. The flying robot position is estimated by matching these spatial relations.
Lidia María Belmonte, José Carlos Castillo, Antonio Fernández-Caballero, Sergio Almansa-Valverde, R. Morales

Emotion Detection in Ageing Adults from Physiological Sensors

The increasing life expectancy is causing a fast ageing population around the globe, which is raising the demand on assistive systems based on ambient intelligence. While numerous papers have focused on the physical aspects in elderly, only a few works have attempted to regulate their emotional state. In this work, a new approach for monitoring and detecting the emotional state in elderly is presented. First, different physiological signals are acquired by means of wearable sensors, and data are transmitted to the embedded system. Next, noise and artifacts are removed by applying different signal processing techniques, depending on the signal behavior. Finally, several temporal and statistical markers are extracted and used to feed the classification model. In this very first version, a logistic regression model is used to detect two possible emotional states. In order to calibrate the model and adjust the boundary decision, twenty volunteers have agreed to be monitored and recorded to train the model. Finally, a decision maker regulates the environment, acting directly upon the elderly’s emotional state.
Arturo Martínez-Rodrigo, Roberto Zangróniz, José Manuel Pastor, José Miguel Latorre, Antonio Fernández-Caballero

Augmented Tangible Surfaces to Support Cognitive Games for Ageing People

The continuous and rapidly increasing elderly population requires a revision of technology design in order to devise systems usable and meaningful for this social group. Most applications for ageing people are built to provide supporting services, taking into account the physical and cognitive abilities that decrease over time. However, this paper focuses on building technology to improve such capacities, or at least slow down their decline, through cognitive games. This is achieved by means of a digitally-augmented table-like surface that combines touch with tangible input for a more natural, intuitive, and appealing means of interaction. Its construction materials make it an affordable device likely to be used in retirement homes in the context of therapeutic activities, and its form factor enables a versatile, quick, and scalable configuration, as well as a socializing experience.
Fernando Garcia-Sanjuan, Javier Jaen, Alejandro Catala


Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!