Search

Purpose: For prevention of sarcopenia and functional decline in community dwelling older adults, a higher daily protein intake is needed in addition to increased exercise. A new e-health strategy for dietary counseling was usedwith the aim to increase total daily protein intake to optimal levels (minimal 1.2 g/kg/day, optimal 1.5 g/kg/day) through use of regular food products.Methods: The VITAMIN (VITal AMsterdam older adults IN the city) RCT included 245 community dwelling older adults (age ≥ 55y): control, exercise, and exercise plus dietary counseling (protein) group. The dietary counselingintervention was based on behavior change and personalization was offered by a dietitian coach, by use of face-to-face contacts and videoconferencing during a 6-month intervention. Dietary intake was measured by a 3d dietaryrecord at baseline, after 6-month intervention and 12-month follow-up. The primary outcome was average daily protein intake (g/kg/day). Sub-group analysis and secondary outcomes included daily protein distribution, sources,product groups. A Linear Mixed Models (LMM) of repeated measures was performed with STATA v13.Results: Mean age of the 224 subjects was 72.0(6.5) years, a BMI of 26.0(4.2) and 71% were female. The LMM showed a significant effect of time and time*group (p

De auteurs gaan in dit artikel in op de mogelijkheden van innovatieve technologie in het stimuleren van sport en bewegen en het op maat aanpassen van beweegvriendelijke omgevingen in een stedelijke context. Ze concluderen dat laagdrempelige technologie zoals smartphone applicaties (apps) en wearables veelvuldig worden gebruikt door minder actieve lopers en door vrouwelijke lopers en dat app-gebruikers vaak jonger zijn. De auteurs zien deze mogelijkheden als veelbelovend, maar concluderen ook dat toekomstig onderzoek nodig is om korte- en langetermijneffecten van deze technologie te bevestigen.

Purpose: The early detection of a decline in daily functioning of independently living older people can aid health care professionals in providing preventive interventions. To monitor daily activity patterns and, thereby detect a decline in daily functioning, new technologies, such as sensors can be placed in the home environment. The purpose of this qualitative study was to determine the perspectives of older people regarding the use of sensor monitoring in their daily lives. Design and Methods: We conducted indepth, semistructured interviews with 11 persons between 68 and 93 years who had a sensor monitoring system installed in their home. The data were analyzed using Interpretative Phenomenological Analysis. Results: The interviewed older persons positively valued sensor monitoring and indicated that the technology served as a strategy to enable independent living. The participants perceived that the system contributed to their sense of safety as an important premise for independent living. Some of the participants stated that it helped them to remain active. The potential privacy violation was not an issue for the participants. The participants considered that health care professionals’ continuous access to their sensor data and use of the data for their safety outweighed the privacy concerns. Implications: These results provide new evidence that older persons experience sensor monitoring as an opportunity or strategy that contributes to independent living and that does not disturb their natural way of living. Based on this study, the development of new strategies to provide older people with access to their sensor data must be further explored.

Human activity recognition is an essential task for robots to effectively and efficiently interact with the end users. Many machine learning approaches for activity recognition systems have been proposed recently. Most of these methods are built upon a strong assumption that the labels in the training data are noise-free, which is often not realistic. In this paper, we incorporate the uncertainty of labels into a max-margin learning algorithm, and the algorithm allows the labels to deviate over iterations in order to find a better solution. This is incorporated with a hierarchical approach where we jointly estimate activities at two different levels of granularity. The model is tested on two datasets, i.e., the CAD-120 dataset and the Accompany dataset, and the proposed model shows outperforming results over the state-of-the-art methods.

This chapter focuses on the analysis of data that is collected from sensors in the home environment. First we discuss the need for a good model that relates sensor data (or features derived from the data) to indicators of health and well-being. Then we present several methods for model building. We distinguish between supervised methods that need data annotated with the desired health indicators, unsupervised methods that find characteristic patterns by just analyzing large amounts of data, and knowledge-driven methods that use expert knowledge. We discuss the advantages and disadvantages of the different methods.

An activity recognition system is a very important component for assistant robots, but training such a system usually requires a large and correctly labeled dataset. Most of the previous works only allow training data to have a single activity label per segment, which is overly restrictive because the labels are not always certain. It is, therefore, desirable to allow multiple labels for ambiguous segments. In this paper, we introduce the method of soft labeling, which allows annotators to assign multiple, weighted, labels to data segments. This is useful in many situations, e.g. when the labels are uncertain, when part of the labels are missing, or when multiple annotators assign inconsistent labels. We treat the activity recognition task as a sequential labeling problem. Latent variables are embedded to exploit sub-level semantics for better estimation. We propose a novel method for learning model parameters from soft-labeled data in a max-margin framework. The model is evaluated on a challenging dataset (CAD-120), which is captured by a RGBD sensor mounted on the robot. To simulate the uncertainty in data annotation, we randomly change the labels for transition segments. The results show significant improvement over the state-of-the-art approach.

In this paper we present a digital coach for runners that provides feedback in an intuitive way, without interrupting the athletes running flow. This is done by giving vibration pulses in combination with visual led feedback. The digital coach is built into a wristband with GPS module, vibration motor and several LEDs. The digital coach is given a personality model according to the DISC coaching model. From the GPS data collected the digital coach should identify which style gives the best results for the athlete.

The availability of cheap imaging sensors makes it possible to increase the robustness of vision-based alarm systems. This paper explores the benefit of data fusion in the application of fall detection. Falls are a common source of injury for elderly people and automatic fall detection is, therefore, an important development in automated home care. We first evaluate a skeleton-based classification method that uses the Microsoft Kinect as a sensor. Next, we evaluate an overhead camera-based method that looks at bounding ellipse features. Then, we fuse the data from these two methods by validating the skeleton tracked by the Kinect. Data fusion proves beneficial, since the data fusion approach outperforms the other methods.

Email Print Request Permissions Save to Project With changes in life expectancy across the world, technologies enhancing well-being of individuals, specifically for older people, are subject to a new stream of research and development. In this paper we present the ACCOMPANY project, a pan-European project which focuses on home companion technologies. The projects aims to progress beyond the state of the art in multiple areas such as empathic and social human-robot interaction, robot learning and memory visualisation, monitoring persons and chores at home, and technological integration of these multiple approaches on an existing robotic platform, Care-O-Bot®3 and in the context of a smart-home environment utilising a multitude of sensor arrays. The resulting prototype from integrating these developments undergoes multiple formative cycles and a summative evaluation cycle towards identifying acceptable behaviours and roles for the robot for example role as a butler or a trainer. Furthermore, the evaluation activities will use an evaluation grid in order to assess achievement of the identified user requirements, formulated in form of distinct scenarios. Finally, the project considers ethical concerns and by highlighting principles such as autonomy, independence, enablement, safety and privacy, it embarks on providing a discussion medium where user views on these principles and the existing tension between some of these principles for example tension between privacy and autonomy over safety, can be captured and considered in design cycles and throughout project developments.

In this paper we present the concept and initial design stages of the TaSST (Tactile Sleeve for Social Touch). The TaSST consists of a soft pressure-sensitive input layer, and an output layer containing vibration motors. A touch to ones own sleeve is felt as a vibration on the sleeve of another person. The idea behind the TaSST is to enable two people to communicate different types of touch at a distance. We will outline the design process of the TaSST, describe some initial results from a user study, and discuss possible applications of the TaSST.

We describe a system that recognizes human postures with heavy self-occlusion. In particular, we address posture recognition in a robot assisted-living scenario, where the environment is equipped with a top-view camera for monitoring human activities. This setup is very useful because top-view cameras lead to accurate localization and limited inter-occlusion between persons, but conversely they suffer from body parts being frequently self-occluded. The conventional way of posture recognition relies on good estimation of body part positions, which turns out to be unstable in the top-view due to occlusion and foreshortening. In our approach, we learn a posture descriptor for each specific posture category. The posture descriptor encodes how well the person in the image can be `explained' by the model. The postures are subsequently recognized from the matching scores returned by the posture descriptors. We select the state-of-the-art approach of pose estimation as our posture descriptor. The results show that our method is able to correctly classify 79.7% of the test sample, which outperforms the conventional approach by over 23%.

As interactive systems become increasingly complex and entwined with the environment, technology is becoming more and more invisible. This means that much of the technology that people come across every day goes unnoticed and that the (potential) workings of ambient systems are not always clearly communicated to the user. The projects discussed in this paper are aimed at increasing public understanding of the existence, workings and potential of screens and ambient technology by visualizing its potential. To address issues and implications of visibility and system transparency, this paper presents work in progress as example cases for engaging people in ambient monitoring and public screening. This includes exploring desired scenarios for ambient monitoring with users as diverse as elderly people or tourists and an interactive tool for mapping public screens.

Ambient activity monitoring systems produce large amounts of data, which can be used for health monitoring. The problem is that patterns in this data reflecting health status are not identified yet. In this paper the possibility is explored of predicting the functional health status (the motor score of AMPS = Assessment of Motor and Process Skills) of a person from data of binary ambient sensors. Data is collected of five independently living elderly people. Based on expert knowledge, features are extracted from the sensor data and several subsets are selected. We use standard linear regression and Gaussian processes for mapping the features to the functional status and predict the status of a test person using a leave-oneperson-out cross validation. The results show that Gaussian processes perform better than the linear regression model, and that both models perform better with the basic feature set than with location or transition based features. Some suggestions are provided for better feature extraction and selection for the purpose of health monitoring. These results indicate that automated functional health assessment is possible, but some challenges lie ahead. The most important challenge is eliciting expert knowledge and translating that into quantifiable features.

The project discussed in this paper is aimed at increasing people’s understanding of the existence and desired workings of ambient technology in the home by demonstrating its potential. For this purpose, an interactive dollhouse is presented. The dollhouse, a miniature model of a sensor-equipped home, was developed and used to engage elderly users in the design of an ambient monitoring system. This paper explains the design of the interactive dollhouse and the ways it was used as an elderly-centered design method for increasing understanding of the desired workings of ambient monitoring in the home.

People suffering from dementia often have problems with way finding and feel restless. In this paper we present an interactive wall developed for decreasing the amount of wandering behaviour of people suffering from dementia. The installation aims at making these people feel more at home in the nursing homes by guiding them with a motion triggered audio path. This leads them to a wall with large windows displaying images and short movie tracks from their hometown. The results of an observation study show that the interactive wall succeeds in attracting people and thus reducing the wandering behaviour. Remarks of the elderly as well as their family and caretakers support this conclusion.

People counting is a challenging task with many applications. We propose a method with a fixed stereo camera that is based on projecting a template onto the depth image. The method was tested on a challenging outdoor dataset with good results and runs in real time.

Interview met Ben Kröse, bijzonder hoogleraar ambient robotics aan de Universiteit van Amsterdam over de toepassing van intelligente systemen zoals robots, observatiesystemen en interactieve apparaten in de gezondheidszorg.

We will demonstrate a prototype exergame aimed at the serious domain of elderly fitness. The exergame incorporates straightforward means to gesture recognition, and utilises a Kinect camera to obtain 2.5D sensory data of the human user.

De laatste jaren zijn tal van sensoren goedkoper geworden en worden ze op diverse plekken toegepast, zoals in de auto-industrie, publieke ruimten en games. Sensoren verrijken de traditionele toetsenbord en beeldscherm interfaces en deze rijkere vorm van interactie biedt kansen om aantrekkelijk informaticaonderwijs te verzorgen. De focus verschuift namelijk van puur administratieve systemen naar interactie gedreven systemen, waarmee studenten zelf kunnen experimenteren. In het lectoraat Digital Life van de Hogeschool van Amsterdam lopen verschillende projecten waarbij ambient sensoren worden bestudeerd om dagelijkse activiteiten van ouderen te herkennen. Voor het herkennen van deze activiteiten worden probabilistische modellen zoals de Hidden Markov Modellen gebruikt. In dit artikel beschrijven we hoe deze Hidden Markov Modellen ook toegepast kunnen worden voor het herkennen van gebaren van studenten.

This chapter focuses on activity monitoring in a home setting for health care purposes. First the most current sensing systems are described, which consist of wearable and ambient sensors. Then several approaches for the monitoring of simple actions are discussed, like falls or therapies. After that, the recognition of more complex activities is discussed. A number of applications for the care givers is presented. The chapter concludes with a section on acceptance and privacy.

In this paper we propose a head detection method using range data from a stereo camera. The method is based on a technique that has been introduced in the domain of voxel data. For application in stereo cameras, the technique is extended (1) to be applicable to stereo data, and (2) to be robust with regard to noise and variation in environmental settings. The method consists of foreground selection, head detection, and blob separation, and, to improve results in case of misdetections, incorporates a means for people tracking. It is tested in experiments with actual stereo data, gathered from three distinct real-life scenarios. Experimental results show that the proposed method performs well in terms of both precision and recall. In addition, the method was shown to perform well in highly crowded situations. From our results, we may conclude that the proposed method provides a strong basis for head detection in applications that utilise stereo cameras.

Valongevallen zijn de meest voorkomende oorzaak van letsel door een ongeval bij ouderen. Omdat veel ouderen alleen wonen is het van belang dat de val tijdig wordt opgemerkt met een alarmsysteem. Er zijn veel systemen op de markt waarbij de gebruiker een alarmknop op een polsband of hanger moet indrukken. Uit onderzoek blijkt dat ouderen het alarmsysteem vaak niet gebruiken omdat de hanger niet meegedragen wordt of omdat de werking van het systeem niet duidelijk is. Een ‘ambient’ systeem heeft daarom de voorkeur. In het lectoraat Digital Life van de Hogeschool van Amsterdam bestuderen we ambient sensoren (schakelaars, stroommeters, drukmatten, bewegingsmelders etc.) en imaging sensors (camera’s, range camera’s, stereocamera’s) om activiteiten van mensen te meten. In onze presentatie beschrijven we het gebruik van ‘slimme’ camera’s voor valdetectie en laten enkele resultaten zien. Ook beschrijven we ons ‘ValLab’, waar onderzoekers en studenten HBO en WO data kunnen opnemen in realistische omgevingen.

In dit artikel wordt het belang aangegeven van onderzoeksvaardigheden in het HBO. Met de komst van de lectoraten en de nieuwe positionering van het HBO is het belangrijk om een antwoord te vinden hoe het onderzoek binnen het HBO vormgegeven moet worden. Hierbij wordt gekeken naar de bruikbaarheid van verschillende onderzoeksmethoden en naar rollen die een student binnen een curriculum in het onderzoek kan hebben.

Motivation--This paper describes our work in progress to develop a personal monitoring system that can monitor the physical and emotional condition of a patient by using contextual information from a sensor network, provide the patient with feedback concerning their health status and motivate the patient to adopt behavior with a positive health impact (such as exercising or taking medication at the right moment).Research approach -- We will extend the capabilities of an existing robotic health buddy with a (DBN based) sensor network. Then we will carry out a series of controlled, long-term field experiments where we identify and evaluate the effects of various agent social communicative behaviours on the user's adoption of health improving lifestyle patterns.Findings/Design -- The findings of the experiments will inform the final design of the health buddy and it's behaviours. We will also realise system adaptivity of the data processing and data fusion methods as well as the health buddy adaptivity to the user's emotional state.Research limitations/Implications -- The project will limit itself to monitoring and motivating people who suffer from cardiovascular chronic conditions and to the home environment.Originality/Value -- The research makes a contribution to the needs of health monitoring for a specific user group. The health buddy will use social behaviours to motivate users over a long-term time period.Take away message -- Home health monitoring and self care can be more enjoyable and easier through motivating smart health buddies.

Cliënten associëren beeldcommunicatie met ziekte en onvermogen. Door de techniek ook te gebruiken voor amusement en sociale contacten en cliënten meer controle te geven over de toepassing ervan, kan de acceptatie van beeldcommunicatie verbeterd worden.

This paper compares different methods for detecting the speaking person when multiple persons are interacting with a robot. We evaluate the state-of-the-art speaker detection methods on the iCat robot. These methods use the synchrony between audio and video to locate the most probable speaker. We compare them to simple motion-based speaker detection and present a simple heuristic with low computational requirements, which performs equally well to the audiovisual methods in a set of multiperson recordings with a fraction of the computational cost, thus making real-time interaction possible.

In this paper we explore the concept of enjoyment as a possible factor influencing acceptance of robotic technology by elderly people. We describe an experiment with a conversational robot and elderly users (n=30) that incorporates both a test session and a long term user observation. The experiment did confirm the hypothesis that perceived enjoyment has an effect on the intention to use a robotic system. Furthermore, findings show that the general assumption in technology acceptance models that intention to use predicts actual use is also applicable to this specific technology used by elderly people.

Based on observations in previous experiments with a robotic companion in eldercare and on findings in related literature, we developed the concept of Perceived Adaptiveness. We integrated this in our technology acceptance methodology for robotic eldercare companions and found in a small experiment that adaptiveness of the system as perceived by elderly users is indeed a relevant item, being a direct influence on Perceived Usefulness.