An activity monitoring system for elderly care using generative and discriminative models

In this paper, we present a close reading of work in ubicomp of applications for older people. Starting from three lines of enquiry defined in the inaugural issue of this journal, we discuss how ubicomp research has presented the relationship between technologies and older users. We base our reasoning on a review of papers published in Personal and Ubiquitous Computing (1997Computing ( -2014. The lines of enquiry refer to paradigms (functional vs. sociotechnical), users (stereotype and involvement), and contexts (indoor and/or outdoor). These themes address the presentation of SUITCASE project (SUstainable Integrated & Territorial CAre SErvices). This is a two-year research on care services for older citizens within the smart home construct. We develop an initial framework that not only provides a cohesive view of technologies for older people, but also serves as a salient guideline for reflective design which extends beyond the target population. This framework may also address future design projects, funding schemes, and editorial policies.

show abstract

“…Some of them referred to supportive technology (e.g. [20,65]), other focused on responsive systems [27,69] or preventive AT [39,48].…”

Section: The Functional Paradigmmentioning

confidence: 99%

Ubiquitous technologies for older people

Cozza

Angeli

Tonolli

2017

Pers Ubiquit Comput

View full text Add to dashboard Cite

show abstract

“…Recognition with Activity-LocationCorrelation There are many studies which estimate a user's activity by utilizing the correlation between the activity and location of the user [15], [16]. That is, if the user exists in the kitchen, the system estimates that the user cooks.…”

Section: Activitymentioning

confidence: 99%

“…Kasteren et al [15] design a system for recognizing living activities such as eating, watching TV, going out, using the toilet, taking showers, doing the laundry, and changing clothes in a smart home embedded with door sensors, pressure-sensitive mats, float sensors, and temperature sensors. The recognition accuracy of their system ranges from 49% to 98%.…”

Section: Activitymentioning

confidence: 99%

Implementation and Evaluation of Analog-PIR-Sensor-Based Activity Recognition

Fujiwara

Kashimoto

Fujimoto

et al. 2017

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

: These days, smart home applications such as concierge service for residents, home appliance control, and so on are attracting attention. To realize these applications, we need a system which recognizes various human activities accurately with a low cost device. There are many studies on the activity recognition in a smart home. We also have proposed an activity recognition technique in a smart home by utilizing digital-output-PIR (passive infrared) sensors, door sensors, and power meters. However, the study has an unsolved issue: we cannot distinguish similar activities happening at the same place, for example, "eating" and "reading" while sitting on a sofa. In order to cope with this challenge, we introduce ALPAS: analog-output-PIR-sensor-based activity recognition technique which recognizes the different activities in the same place. Our technique recognizes user's activity by utilizing machine learning with frequency components of the sensor's output as features. However, because the number of features used in ALPAS is 1000 for each analog PIR-sensor, a large capacity memory is required. To reduce the number of features, we select a part of the sensing data. We call the starting point of the selected data as starting frequency (SF) and ending part as ending frequency (EF). We searched SF and EF using a grid search, and evaluated the recognition accuracy. We evaluated the proposed technique in a smarthome testbed. In the evaluation, five participants performed four different activities while sitting on a sofa. As a result, we achieved F-Measure: 63.9% when the EF is 1.4 Hz, and F-Measure: 50% or lower when the SF is 9.9 Hz or higher.

show abstract

“…[12], [13]; for the collection of data from gestures and postures [14]- [18]; and moving to some other activities like sleeping, eating and cooking, it acquires location based sensors which are used to determine activity in indoor environments [19], [20]. So, from the subject of smart city applications, we can also create intelligent application for environment such as smart environment which has been adopted widely for health monitoring [21] and with strong power source these can be affective for collection of data for a long time [22]. And to recognize these activities we are required with some models that can detect the class of an activity and understand the differences between the activities i.e.…”

Section: Smart Home/healthcare Facilitating Toolsmentioning

confidence: 99%

Artificial Intelligence in Bio-Medical Domain

Salman¹,

Ahmed²,

Khan³

et al. 2017

ijacsa

View full text Add to dashboard Cite

Abstract-In this era and in the future, artificially intelligent machines are replacing and playing a key role to enhance human capabilities in many areas. It is also making life style better by providing convenience to all including normal human beings and professionals as well. That is why AI is gaining huge attention and popularity in the field of computer science by which it has revolutionized the rapidly growing technology known as expert system. The applications of AI are working in many areas with huge impact and being used widely as well. AI provides quality and efficiency in almost every area, we are evolving it in. The main purpose of this paper is to explore the area of medical and health-care with respect to AI along with 'Machine Learning', and 'Neural Networks'. This work explores the current use of AI in innovations, in the particular field of Bio-Medical and evaluated that how it has improved hospital inpatient care and other sectors related to it i.e. smart medical home, virtual presence of doctors and patients, automation in diagnostic, etc. that has changed the infrastructure of medical domain. Finally, an investigation of some expert systems and applications is made. These systems and applications are widely used throughout the world and a ranking mechanism of their performance has proposed accordingly in an organized manner. We hope, this work will be helpful for the researchers coming to this particular area and to provide a syntactic information that how computer science (i.e. AI, ANN, ML) is revolutionizing the field of biomedical and healthcare.

show abstract

An activity monitoring system for elderly care using generative and discriminative models

Cited by 209 publications

References 29 publications

Ubiquitous technologies for older people

Ubiquitous technologies for older people

Implementation and Evaluation of Analog-PIR-Sensor-Based Activity Recognition

Artificial Intelligence in Bio-Medical Domain

Contact Info

Product

Resources

About