Expert Knowledge for Modeling Functional Health from Sensor Data

Summary Background: ICT based solutions are increasingly introduced for active and healthy ageing. In this context continuous monitoring of older adults with domestic sensor systems has been suggested to provide important information about their functional health. However, there is not yet a solid model for the interpretation of the sensor data. Objectives: The aim of our study is to define a set of predictors of functional health that can be measured with domestic sensors and to determine thresholds that identify relevant changes in these predictors. Methods: On the basis of literature we develop a model that relates functional health predictors to features derived from sensor data. The parameters of this model are determined on the basis of a study among health experts (n = 38). The use of the full model is illustrated with three cases. Results: We identified 25 predictors and their attributes. For 12 of them that can be measured with passive infrared motion sensors we determined their parameters: the attribute thresholds and the urgency thresholds. Conclusions: With the parametrized predictors in the model, domestic sensors can be deployed to assess functional health in a standardized way. Three case examples showed how the model can be used as a screening instrument for functional decline.

Download Full-text

System Architecture of Unobtrusive Sensors for Supporting Home Care and Independet Living

International Journal of Mathematics and Computers in Simulation ◽

10.46300/9102.2021.15.26 ◽

2021 ◽

Vol 15 ◽

pp. 141-146

Author(s):

Cvetko Pirš ◽

Boris Cigale ◽

Damjan Zazula ◽

Dejan Usar

Keyword(s):

Home Care ◽

Home Environment ◽

Data Structures ◽

System Architecture ◽

Data Transmission ◽

Continuous Monitoring ◽

Short Description ◽

Sensor Data ◽

Functional Health ◽

Event Driven

The paper deals with an implementation of unobtrusive sensors installed in home environment for continuous monitoring of functional-health parameters of the observed persons. A multi-tier architecture links sensory devices through sensor-data concentrators to a home server. Automated sensory measurements are supported by a concept of sensoractivated events, event-driven data transmission and processing by a dedicated application interface. Its logic and data structures are revealed. Examples of three typical execution scenarios are given and a short description depicts clinical installation of proposed system for testing purposes.

Download Full-text

Long-term trajectories of decline in cognition and daily functioning before and after stroke

Journal of Neurology Neurosurgery & Psychiatry ◽

10.1136/jnnp-2021-326043 ◽

2021 ◽

pp. jnnp-2021-326043

Author(s):

Alis Heshmatollah ◽

Lisanne J. Dommershuijsen ◽

Lana Fani ◽

Peter J. Koudstaal ◽

M. Arfan Ikram ◽

...

Keyword(s):

Continuous Monitoring ◽

Mini Mental State Examination ◽

Functional Decline ◽

Population Based ◽

Daily Functioning ◽

Linear Mixed Effects ◽

Before And After ◽

State Examination

ObjectiveAlthough knowledge on poststroke cognitive and functional decline is increasing, little is known about the possible decline of these functions before stroke. We determined the long-term trajectories of cognition and daily functioning before and after stroke.MethodsBetween 1990 and 2016, we repeatedly assessed cognition (Mini-Mental State Examination (MMSE), 15-Word Learning, Letter–Digit Substitution, Stroop, Verbal Fluency, Purdue Pegboard) and basic and instrumental activities of daily living (BADL and IADL) in 14 712 participants within the population-based Rotterdam Study. Incident stroke was assessed through continuous monitoring of medical records until 2018. We matched participants with incident stroke to stroke-free participants (1:3) based on sex and birth year. Trajectories of cognition and daily functioning of patients who had a stroke 10 years before and 10 years after stroke and the corresponding trajectories of stroke-free individuals were constructed using adjusted linear mixed effects models.ResultsDuring a mean follow-up of 12.5±6.8 years, a total of 1662 participants suffered a first-ever stroke. Patients who had a stroke deviated from stroke-free controls up to 10 years before stroke diagnosis in cognition and daily functioning. Significant deviations before stroke were seen in scores of MMSE (6.4 years), Stroop (5.7 years), Purdue Pegboard (3.8 years) and BADL and IADL (2.2 and 3.0 years, respectively).ConclusionPatients who had a stroke have steeper declines in cognition and daily functioning up to 10 years before their first-ever stroke compared with stroke-free individuals. Our findings suggest that accumulating intracerebral pathology already has a clinical impact before stroke.

Download Full-text

Empowering Advanced Driver-Assistance Systems from Topological Data Analysis

Mathematics ◽

10.3390/math9060634 ◽

2021 ◽

Vol 9 (6) ◽

pp. 634

Author(s):

Tarek Frahi ◽

Francisco Chinesta ◽

Antonio Falcó ◽

Alberto Badias ◽

Elias Cueto ◽

...

Keyword(s):

Data Analysis ◽

The State ◽

Sensor Data ◽

Topological Data Analysis ◽

Motion Sensors ◽

Driver Assistance Systems ◽

The Road ◽

Topological Features ◽

Recent Developments ◽

Topological Data

We are interested in evaluating the state of drivers to determine whether they are attentive to the road or not by using motion sensor data collected from car driving experiments. That is, our goal is to design a predictive model that can estimate the state of drivers given the data collected from motion sensors. For that purpose, we leverage recent developments in topological data analysis (TDA) to analyze and transform the data coming from sensor time series and build a machine learning model based on the topological features extracted with the TDA. We provide some experiments showing that our model proves to be accurate in the identification of the state of the user, predicting whether they are relaxed or tense.

Download Full-text

Assessing the Mobility of Elderly People in Domestic Smart Home Environments

10.5121/csit.2020.101911 ◽

2020 ◽

Author(s):

Björn Friedrich ◽

Enno-Edzard Steen ◽

Sebastian Fudickar ◽

Andreas Hein

Keyword(s):

Elderly People ◽

Smart Home ◽

Continuous Monitoring ◽

Early Stage ◽

Motion Sensor ◽

Motion Sensors ◽

Physical Strength ◽

Assessment Scores ◽

Mobility Assessment ◽

Smart Home Environments

A continuous monitoring of the physical strength and mobility of elderly people is important for maintaining their health and treating diseases at an early stage. However, frequent screenings by physicians are exceeding the logistic capacities. An alternate approach is the automatic and unobtrusive collection of functional measures by ambient sensors. In the current publication, we show the correlation among data of ambient motion sensors and the wellestablished mobility assessment Short-Physical-Performance-Battery and Tinetti. We use the average number of motion sensor events for correlation with the assessment scores. The evaluation on a real-world dataset shows a moderate to strong correlation with the scores of standardised geriatrics physical assessments.

Download Full-text

Push-Up Detector Applications Using Quality Function Development and Anthropometry for Movement Error Detection

Scientific Journal of Informatics ◽

10.15294/sji.v5i2.16332 ◽

2018 ◽

Vol 5 (2) ◽

pp. 248-257 ◽

Cited By ~ 1

Author(s):

Ari Muzakir ◽

Christofora Desi Kusmindari

Keyword(s):

Error Detection ◽

Injury Risk ◽

Sensor Data ◽

Motion Sensors ◽

Quality Function ◽

Risk Of Injury ◽

Movement Error ◽

Sample Data ◽

Quality Function Development ◽

Push Up

Push-up is the simplest and most widely performed sport. Although simple, it also has a high risk of injury risk if done not in accordance with the rules. Push-up detector is a good push-up motion monitoring solution. In this way, nonstandard movements can be detected and corrected immediately. It has two motion sensors integrated with Arduino-based microcontroller. From this detector tool got the data of push-up result from sensor mounted. Sensor data will be displayed in the application in real-time. Quality function development is used to determine the criteria of the user. The sample data involved 200 participants who followed the testing of this tool and got 90% who can do the push-up correctly. Factors that affect the height, age, and weight. Tests conducted on adolescent boys aged 18-23 years. The results of this study is an application capable of monitoring each push-up movement to position in accordance with the provisions to minimize injuries resulting from movement errors.

Download Full-text

Automated monitoring and assessment of productivity in earthmoving projects

Canadian Journal of Civil Engineering ◽

10.1139/cjce-2018-0183 ◽

2018 ◽

Vol 45 (11) ◽

pp. 958-972 ◽

Cited By ~ 1

Author(s):

Ashraf Salem ◽

Osama Moselhi

Keyword(s):

Data Fusion ◽

Continuous Monitoring ◽

Research Work ◽

Sensor Data ◽

Fusion Algorithm ◽

Cost Overruns ◽

Knowledge Based ◽

Monitoring Model ◽

Multi Sensor Data Fusion ◽

Proposed Model

Continuous monitoring of productivity and assessment of its variations are crucial processes that significantly contribute to success of earthmoving projects. Numerous factors may lead to productivity variations. However, these factors are subjectively identified using manual knowledge-based expert judgment. Such manual recognition process is not only subject to errors but also time-consuming. There is a lack of research work that focuses on near real-time assessment of productivity variation and its effect on cost, schedule and effective utilization of resources in earthmoving projects. This paper presents a customized multi-source automated data acquisition model that acquires data from a variety of wireless sensing technologies. The acquired multi-sensor data are transmitted to a central MySQL database. Then a newly developed data fusion algorithm is applied for truck state recognition, and hence the duration of each earthmoving state. Multi-sensor data fusion facilitates measurement of actual productivity, and consequently the assessment of productivity ratios that support continuous monitoring of productivity variation in earthmoving operations. The developed tracking and monitoring model generates an early warning that supports proactive decisions to avoid schedule delays, cost overruns, and inefficient depletion of resources. A case study is used to reveal the applicability of the proposed model in monitoring and assessing actual productivity and its deviations from planned productivity. Finally, results are discussed and conclusions are drawn highlighting the features of the proposed model.

Download Full-text

A Hierarchical Deep Fusion Framework for Egocentric Activity Recognition Using a Wearable Hybrid Sensor System

Sensors ◽

10.3390/s19030546 ◽

2019 ◽

Vol 19 (3) ◽

pp. 546 ◽

Cited By ~ 5

Author(s):

Haibin Yu ◽

Guoxiong Pan ◽

Mian Pan ◽

Chong Li ◽

Wenyan Jia ◽

...

Keyword(s):

Activity Recognition ◽

Short Term Memory ◽

Specific Activity ◽

Negative Influence ◽

Sensor System ◽

Sensor Data ◽

Motion Sensor ◽

Motion Sensors ◽

Motion State ◽

Fusion Framework

Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its wide applicability in medical care, smart homes, and security monitoring. In this study, we developed and implemented a deep-learning-based hierarchical fusion framework for the recognition of egocentric activities of daily living (ADLs) in a wearable hybrid sensor system comprising motion sensors and cameras. Long short-term memory (LSTM) and a convolutional neural network are used to perform egocentric ADL recognition based on motion sensor data and photo streaming in different layers, respectively. The motion sensor data are used solely for activity classification according to motion state, while the photo stream is used for further specific activity recognition in the motion state groups. Thus, both motion sensor data and photo stream work in their most suitable classification mode to significantly reduce the negative influence of sensor differences on the fusion results. Experimental results show that the proposed method not only is more accurate than the existing direct fusion method (by up to 6%) but also avoids the time-consuming computation of optical flow in the existing method, which makes the proposed algorithm less complex and more suitable for practical application.

Download Full-text

AGING IN COMMUNITY: A LEGAL MAPPING ANALYSIS OF MASSACHUSETTS MUNICIPAL ACCESSORY DWELLING UNIT ZONING BYLAWS

Innovation in Aging ◽

10.1093/geroni/igz038.939 ◽

2019 ◽

Vol 3 (Supplement_1) ◽

pp. S250-S251

Author(s):

Travis M Gagen

Keyword(s):

Older Adults ◽

Functional Decline ◽

Institutional Care ◽

Well Being ◽

Functional Health ◽

Dwelling Unit ◽

Older Americans ◽

Alternative Housing ◽

Accessory Dwelling Units ◽

Health Promoting

Abstract Accessory-dwelling units (ADUs) are one alternative housing arrangement that enable older adults to remain in the home despite functional decline. Functional decline increases with age making older adults more susceptible to loosing independent housing. Involuntary relocation to institutional care can result in a decline of functional health, reduced life satisfaction, impairment of psychological well-being and increased mortality rate. The majority of older Americans (93%) wish to remain in their home for as long as possible. ADUs function to maintain, stimulate and support an older adult as a means to prevent relocation to an institution. The modified environment coupled with adaptable features maintains and supports activities of daily living (ADL) within a familiar place. Under Massachusetts law MGL c. 40A, the state gives authority to cities and towns to adopt ordinances and bylaws to regulate the use of land, buildings and structures. Restrictive zoning laws limit the ability to construct health-promoting built-environments to age-in-community. All 351 Massachusetts municipalities Accessory Dwelling Unit (ADU) zoning bylaws were coded using the ADU Friendliness Score. Once scored, the 351 municipalities were placed into four categories based off their ADU score; the four categories are poor (0-24), fair (25-49), good (50-74), and excellent (75-100). Eighty-nine municipalities (25%) are in the poor category; thirty municipalities (8.5%) are in the fair category; one hundred and eighty-five municipalities (53%) are in the good category; forty-seven municipalities (13.5%) are in the excellent category. These findings contributed to a model ADU bylaw specific for aging Americans for municipalities to adopt.

Download Full-text

FLAGS: A methodology for adaptive anomaly detection and root cause analysis on sensor data streams by fusing expert knowledge with machine learning

Future Generation Computer Systems ◽

10.1016/j.future.2020.10.015 ◽

2021 ◽

Vol 116 ◽

pp. 30-48

Author(s):

Bram Steenwinckel ◽

Dieter De Paepe ◽

Sander Vanden Hautte ◽

Pieter Heyvaert ◽

Mohamed Bentefrit ◽

...

Keyword(s):

Machine Learning ◽

Anomaly Detection ◽

Data Streams ◽

Expert Knowledge ◽

Root Cause Analysis ◽

Sensor Data ◽

Cause Analysis ◽

Root Cause

Download Full-text

Noninvasive Continuous Monitoring of Vital Signs With Wearables: Fit for Medical Use?

Journal of Diabetes Science and Technology ◽

10.1177/1932296820904947 ◽

2020 ◽

Vol 15 (1) ◽

pp. 34-43 ◽

Cited By ~ 3

Author(s):

Malte Jacobsen ◽

Till A. Dembek ◽

Guido Kobbe ◽

Peter W. Gaidzik ◽

Lutz Heinemann

Keyword(s):

Continuous Monitoring ◽

Literature Search ◽

Vital Signs ◽

Cost Effective ◽

Motion Sensors ◽

Wearable Computer ◽

Randomized Controlled ◽

Medical Context ◽

General Physical ◽

Digital Biomarkers

Background: Wearables (= wearable computer) enable continuous and noninvasive monitoring of a range of vital signs. Mobile and cost-effective devices, combined with powerful data analysis tools, open new dimensions in assessing body functions (“digital biomarkers”). Methods: To answer the question whether wearables are ready for use in the medical context, a PubMed literature search and analysis for their clinical-scientific use using publications from the years 2008 to 2018 was performed. Results: A total of 79 out of 314 search hits were publications on clinical trials with wearables, of which 16 were randomized controlled trials. Motion sensors were most frequently used to measure defined movements, movement disorders, or general physical activity. Approximately 20% of the studies used sensors to detect cardiovascular parameters. As for the sensor location, the wrist was chosen in most studies (22.8%). Conclusion: Wearables can be used in a precisely defined medical context, when taking into account complex influencing factors.

Download Full-text