In-home Sensor Research Articles

TECHNOLOGY-BASED HOME MONITORING TO ASSESS AND IMPROVE THE HEALTH AND WELL-BEING OF OLDER ADULTS

Technology, including in-home sensors, monitoring systems, and wearables, holds great promise with respect to being able to help manage chronic conditions, improve older adults’ health, support their safety, prolong independence, and collect data for healthcare and research purposes. This symposium will introduce novel ways in which these systems are being deployed, and also important challenges to their implementation that could decrease their potential benefits. This technology will only be successful if it addresses key issues of adherence and privacy, and considers users’ preferences. The first talk in this session will explore the novel use of GPS-based wearable sensors to capture the concept of life-space mobility, a measure critically related to quality of life and independence. The next talk focuses on a mobile health cardiovascular system and smartphone application, and finds that such systems can successfully transmit meaningful mHealth data while maintaining reasonable protocol adherence. Next, issues of user preference are discussed, including the types of data older adults and their children are willing to share, and the tradeoffs between values of privacy and independence. The session will conclude with a talk on older adults’ attitudes toward privacy related to in-home monitoring, and individual difference predictors of privacy concerns. In sum, this session will provide an overview of the potential and pitfalls related to in-home sensors and monitoring systems for older adults, their formal and informal caregivers, and aging researchers.

DO OLDER ADULTS AND THEIR CHILDREN AGREE ABOUT THE USE OF LOCATION TRACKING, IN-HOME SENSORS, AND WEB-CAMERAS?

On the dyad and aggregate level, we compare preferences of older adult women and their adult children for three remote monitoring technologies: location tracking, in-home sensors, and Web-cameras. Their assessments of each technology’s impact on privacy, safety, independence, freedom, relationship with family member, social life, and identity are also compared. Twenty-eight individual, in-depth structured interviews were conducted with 18 women who are Meals on Wheels clients and 10 of their adult children. Adult children preferred each technology more than their mothers did and underestimated both their mothers’ ability to comprehend the functions of the technologies and the importance of engaging them fully in decision making. For both groups, privacy was the most-cited concern, and participants perceived significant overlap between values of privacy, independence, identity, and freedom. Shared decision-making tools are needed to promote remote monitoring use consistent with older adults’ values and to prevent conflict and caregiver overreach.

HARNESSING VOICE-ASSISTED TECHNOLOGY AND IN-HOME SENSORS TO MANAGE OLDER ADULT HEALTH: A USER PREFERENCE STUDY

In recent years voice-assisted technologies, such as the Amazon Echo Show and Google Home, have been harnessed to help older adults manage their health. However, little is known about the use of such technologies in combination with in-home sensor systems to help older adults age in place. Therefore, this research explored user preferences of older adults and a designated family member/friend in using voice-assisted technologies to retrieve in-home sensor-generated health information, such as fall risk and other early indicators of health changes. Seventeen dyad interviews were conducted with known pairs of older adults (Mean age=75; 56% female) and a family member/friend (Mean age=64; 89% female). Participants were given a description of the technology and its capabilities, and then were instructed to interact with each device using a prepared scenario. Participants asked each device health-related questions to elicit pre-programmed information for the respective scenarios and provided user experience feedback for each device. At the end of the interview, participants completed a speech recognition test for each device and a technology acceptance survey. Overall acceptance of the technology was high, and participants believed that using voice-assisted technologies to retrieve sensor-generated health information would be beneficial in managing their health or providing care to a family member/friend. However, advantages and disadvantages exist with each device and the Google Home generally performed better on the speech recognition test for each dyad pair. These findings provide valuable insight about older adults’ preferences (as well as family members’/friends) in using voice-assisted technologies to manage their health.

In-home monitoring evaluation by home-dwelling older adults, caregivers and healthcare providers

Abstract Background In Europe, population ageing is increasing the healthcare needs and costs. Both frailty and chronic diseases affecting older people reduce their ability to live independently. However, most older people prefer to age in their own homes. New development of in-home monitoring can play a role in staying independent, active and healthy. Our objective was to evaluate a new in-home monitoring system among home-dwelling older adults (OA), their family caregivers (FC), and their healthcare providers (HCP) for the support of home care. Methods The system continuously monitored OA’s daily activities (e.g., mobility, sleep habits, fridge visits, door events) at home by ambient sensor system (DomoCare®) and health-related events by wearable sensors (Fitbit®, ECG). In case of deviations in daily activities (e.g., changes in mobility), alerts were transmitted to HCP via email. Using specific questionnaires, the opinion of 13 OA, 13 FC, and 20 HCP were collected at the end of 12-month of follow-up focusing on their user experience and the impact of in-home monitoring on home care services. Results These preliminary results underlined that the majority of OA, FC, and HCP consider that in-home sensors can help staying at home, improving home care, reducing family stress, and preventing domestic accidents. The opinion tended to be more favourable toward ambient sensors (80%) than toward Fitbit® (67%) and ECG (64%). On average, OA (80%) and FC (73%) tended to be more enthusiast than HCP (63%). Some barriers reported by HCP were a fear of weakening of the relationship with OA and an excessive surveillance. Conclusions Overall, the opinion of OA, FC and HCP were positive related to in-home sensors, with HCP being more mixed about their use in clinical practice. Key messages In-home monitoring technologies seem to be generally well accepted. In-home monitoring technologies could be help facilitating home care of older people.

Linguistic summarization of in-home sensor data.

With the increase in the population of older adults around the world, a significant amount of work has been done on in-home sensor technology to aid the elderly age independently. However, due to the large amounts of data generated by the sensors, it takes a lot of effort and time for the clinicians to makes sense of this data. In this work, we develop a system to help make this data more useful by presenting it in the form of natural language. We start by identifying important attributes in the sensor data that are relevant to the health of the elderly. We then develop algorithms to extract these important health related features from the sensor parameters and summarize them in natural language. We focus on making the natural language summaries to be informative, accurate and concise. We designed multiple surveys using real and synthetic data to validate the summaries produced by our algorithms. We show that the algorithms produce meaningful results comparable to human subjects. We also implemented our linguistic summarization system to produce summaries of data leading to health alerts derived from the sensor data. The system is running live in 110 apartments currently. By the means of retrospective case studies, we illustrate that the linguistic summaries are able to make the connection between changes in the sensor data and the health of the elderly. We present a system that extracts important clinically relevant features from in-home sensor data generated in the apartments of the elderly and summarize those features in natural language. The preliminary testing of our summarization system shows that it has the potential to help the clinicians utilize this data effectively.

BESI: BEHAVIORAL AND ENVIRONMENTAL SENSING AND INTERVENTION FOR DEMENTIA CAREGIVER EMPOWERMENT

Introduction Caregiver burden associated with dementia-related agitation is one of the most common reasons community-dwelling persons with dementia (PWD) transition to a care facility. Agitation in dementia can be defined as “inappropriate verbal, vocal, or motor activity that is not explained by needs or confusion per se” and is “consistent with emotional distress”. Agitation can be physically non-aggressive, aggressive, or verbally agitated behavior. Up to 90% of PWDs experience agitation and it is one of the principal factors for institutionalization. Agitation can be unpredictable, remain undetected in the early stages, and quickly escalate. Caregivers of PWD report high levels of emotional, physical, and financial stress and are susceptible to disease and health complications. BESI is an interactive, cybersociophysical system comprising of in-home and body-worn sensors, a caregiver tablet interface, online modeling, and caregiver notifications built to help detect the environmental triggers and early signs of agitation in PWD. Methods This is a mixed method, prospective study using descriptive, qualitative, and quantitative measures of caregiver-PWD dyads. Baseline psychosocial and behavioral status for both members of the dyad were assessed using validated assessment tools. Phase 1 (System Verification) - controlled settings (laboratory and homes of 2 healthy volunteers) and study settings (homes of 2 study dyads) & usability testing Phase 2 (System Effectiveness) - homes of 10 study dyads for 30 days each Home Visits First: provide detailed description of study, obtain informed consent, and document demographic and medical information. Second: complete assessment battery and BESI system installation. Results Phase 1 The tablet application usability was assessed and revised showing it to be a viable tool. We observed and documented caregiver emotional-state evolution over the day in relation to agitation episodes, the correlation between agitation events and accelerometer Teager energy magnitudes, and the variability in environmental parameters across rooms temporally and during agitation episodes. Audio levels did not yield enough information for more complex audio processing such as verbal agitation detection. We concluded that additional model training and evaluation was needed for physical agitation detection and PWD room localization. Phase 2 An upgraded audio data collection system was implemented to provide more complex audio processing. Comparing this with the verbal agitation episode reports on the tablet application, this method produced a 76.7% accuracy in detecting verbal agitation events. Multiple models were explored for physical agitation detection, with long short-term memory (LSTM) cell based recurrent neural network providing the highest performance. Decision rules was used to structure covariance factor retention for each dyad to feed into artificial neural network models. Doorway-based sensors and Markov models with room transition probabilities provided ∼90% room-level tracking accuracy of the PWD. Conclusions Phases 1 & 2 results facilitated targeted changes in BESI, thus improving its overall usability for the final phase of the study. This research was funded by This study is funded by the National Science Foundation Smart and Connected Health Program. [Grant Number 1418622]

Associations Between Self-Reported Symptoms and Gait Parameters Using In-Home Sensors in Persons With Multiple Sclerosis.

Multiple sclerosis (MS) is a progressive neurological disorder, characterized by exacerbations and remissions, often resulting in disability affecting multiple neurological functions. The purpose of this article was (1) to describe the frequencies of self-reported symptoms in a natural environment and (2) to determine characteristics and associations between self-reported symptoms and home gait parameters (speed, stride time, and stride length) at baseline and at 3 months in patients with MS. Participants completed the self-report MS-Related Symptom Scale to measure symptoms. A three-dimensional depth imaging system (Foresite Healthcare) was used to measure gait parameters in the home environment. These data show significant correlations between the following symptoms: knee locking or collapsing, difficulty sleeping, depression, and anxiety with decreased number of average walks per day; however, the symptoms including trouble-making toilet: day and difficulty in starting urine were positively correlated with average walks per day. The symptom numbness was significantly correlated with decreased speed and decreased stride length. Our findings suggest that certain groups of symptoms were more frequently reported with certain gait parameters (stride time/speed) in persons with MS. Rehabilitation nurses can provide optimal care to prevent future decline in symptoms and gait.

Health management and pattern analysis of daily living activities of people with dementia using in-home sensors and machine learning techniques.

The number of people diagnosed with dementia is expected to rise in the coming years. Given that there is currently no definite cure for dementia and the cost of care for this condition soars dramatically, slowing the decline and maintaining independent living are important goals for supporting people with dementia. This paper discusses a study that is called Technology Integrated Health Management (TIHM). TIHM is a technology assisted monitoring system that uses Internet of Things (IoT) enabled solutions for continuous monitoring of people with dementia in their own homes. We have developed machine learning algorithms to analyse the correlation between environmental data collected by IoT technologies in TIHM in order to monitor and facilitate the physical well-being of people with dementia. The algorithms are developed with different temporal granularity to process the data for long-term and short-term analysis. We extract higher-level activity patterns which are then used to detect any change in patients’ routines. We have also developed a hierarchical information fusion approach for detecting agitation, irritability and aggression. We have conducted evaluations using sensory data collected from homes of people with dementia. The proposed techniques are able to recognise agitation and unusual patterns with an accuracy of up to 80%.

Understanding Smart Home Sensor Data for Ageing in Place Through Everyday Household Routines: A Mixed Method Case Study

BackgroundAn ongoing challenge for smart homes research for aging-in-place is how to make sense of the large amounts of data from in-home sensors to facilitate real-time monitoring and develop reliable alerts.ObjectiveThe objective of our study was to explore the usefulness of a routine-based approach for making sense of smart home data for the elderly.MethodsMaximum variation sampling was used to select three cases for an in-depth mixed methods exploration of the daily routines of three elderly participants in a smart home trial using 180 days of power use and motion sensor data and longitudinal interview data.ResultsSensor data accurately matched self-reported routines. By comparing daily movement data with personal routines, it was possible to identify changes in routine that signaled illness, recovery from bereavement, and gradual deterioration of sleep quality and daily movement. Interview and sensor data also identified changes in routine with variations in temperature and daylight hours.ConclusionsThe findings demonstrated that a routine-based approach makes interpreting sensor data easy, intuitive, and transparent. They highlighted the importance of understanding and accounting for individual differences in preferences for routinization and the influence of the cyclical nature of daily routines, social or cultural rhythms, and seasonal changes in temperature and daylight hours when interpreting information based on sensor data. This research has demonstrated the usefulness of a routine-based approach for making sense of smart home data, which has furthered the understanding of the challenges that need to be addressed in order to make real-time monitoring and effective alerts a reality.

Metrics from in-home sensor data to assess gait change due to weighted vest therapy

Abstract A set of metrics and a methodology were developed to characterize a subject's ability to ambulate. These metrics use the movement of the subject's centroid as detected by an inexpensive depth camera system. The centroid is chosen as it is less sensitive to cluttered environments typically found in a person's home. Three classes of metrics focusing on three major categories of motion were developed. The first class measures fundamental characteristics of movement in three directions. The second class focuses on measuring the walk's entropy. The third class uses periodicity in the subject's motion to deduce temporal gait parameters including stride length. Metrics are validated and compared to existing Fall Risk Assessments (FRA's). While results show strong correlation to many FRA's, not every subject has the same relationships between metrics and FRA's suggesting a unique “fingerprint” of metrics associated with a subject and/or their condition. The methodology was tested using a group of subjects undergoing Balance Wear Therapy targeting sensory inputs to improve balance control. The ability of the metrics to detect changes in the subject's ambulation when the vest is either put on, or taken off was also explored. Results show sufficient sensitivity to detect changes when the vest is donned and doffed. Many effects are not seen immediately, but over 2–4 h following donning or doffing the vest. Results also demonstrate the ability, using the size of the analysis window, to focus on the time required for the effects of each metric to change.

Cognitive impairment categorized in community-dwelling older adults with and without dementia using in-home sensors that recognise activities of daily living

Cognitive impairment due to dementia decreases functionality in Activities of Daily Living (ADL). Its assessment is useful to identify care needs, risks and monitor disease progression. This study investigates differences in ADL pattern-performance between dementia patients and healthy controls using unobtrusive sensors. Around 9,600 person-hours of activity data were collected from the home of ten dementia patients and ten healthy controls using a wireless-unobtrusive sensors and analysed to detect ADL. Recognised ADL were visualized using activity maps, the heterogeneity and accuracy to discriminate patients from healthy were analysed. Activity maps of dementia patients reveal unorganised behaviour patterns and heterogeneity differed significantly between the healthy and diseased. The discriminating accuracy increases with observation duration (0.95 for 20 days). Unobtrusive sensors quantify ADL-relevant behaviour, useful to uncover the effect of cognitive impairment, to quantify ADL-relevant changes in the course of dementia and to measure outcomes of anti-dementia treatments.

Promotion of active ageing combining sensor and social network data

The increase of life expectancy in modern society has caused an increase in elderly population. Elderly people want to live independently in their home environment for as long as possible. However, as we age, our physical skills tend to worsen and our social circle tends to become smaller, something that often leads to a considerable decrease of both our physical and social activities. In this paper, we present an AAL framework developed within the SONOPA project, whose objective is to promote active ageing by combining a social network with information inferred using in-home sensors.

Exploring the feasibility and acceptability of sensor monitoring of gait and falls in the homes of persons with multiple sclerosis

Gait parameters variability and falls are problems for persons with MS and have not been adequately captured in the home. Our goal was to explore the feasibility and acceptability of monitoring of gait and falls in the homes of persons with MS over a period of 30 days. To test the feasibility of measuring gait and falls for 30days in the home of persons with MS, spatiotemporal gait parameters stride length, stride time, and gait speed were compared. A 3D infrared depth imaging system has been developed to objectively measure gait and falls in the home environment. Participants also completed a 16-foot GaitRite electronic pathway walk to validate spatiotemporal parameters of gait (gait speed (cm/s), stride length (cm), and gait cycle time(s)) during the timed 25 foot walking test (T25FWT). We also documented barriers to feasibility of installing the in-home sensors for these participants. The results of the study suggest that the Kinect sensor may be used as an alternative device to measure gait for persons with MS, depending on the desired accuracy level. Ultimately, using in-home sensors to analyze gait parameters in real time is feasible and could lead to better analysis of gait in persons with MS.

Could In-Home Sensors Surpass Human Observation of People with Parkinson's at High Risk of Falling? An Ethnographic Study.

Self-report underpins our understanding of falls among people with Parkinson's (PwP) as they largely happen unwitnessed at home. In this qualitative study, we used an ethnographic approach to investigate which in-home sensors, in which locations, could gather useful data about fall risk. Over six weeks, we observed five independently mobile PwP at high risk of falling, at home. We made field notes about falls (prior events and concerns) and recorded movement with video, Kinect, and wearable sensors. The three women and two men (aged 71 to 79 years) having moderate or severe Parkinson's were dependent on others and highly sedentary. We most commonly noted balance protection, loss, and restoration during chair transfers, walks across open spaces and through gaps, turns, steps up and down, and tasks in standing (all evident walking between chair and stairs, e.g.). Our unobtrusive sensors were acceptable to participants: they could detect instability during everyday activity at home and potentially guide intervention. Monitoring the route between chair and stairs is likely to give information without invading the privacy of people at high risk of falling, with very limited mobility, who spend most of the day in their sitting rooms.

Smart home gateway system over Bluetooth low energy with wireless energy transfer capability

As billions of sensors and smart meters connect to the Internet of Things (IoT), current wireless technologies are taking decisive steps to ensure their sustainable operation. One popular IoT scenario features a smart home service gateway, which becomes the central point of user’s home environment facilitating a multitude of tasks. Given that most IoT devices connected to residential gateway are small-scale and battery-powered, the key challenge is to extend their lifetime without recharging/replacing batteries. To this end, a novel radio technology named Bluetooth low energy (BLE) has recently been completed to enable energy-efficient data transfer. Another inspiring innovation is the capability of sensors to harvest wireless energy in their local environment. In this work, we envision a scenario where many in-home sensors are communicating with a smart gateway over the BLE protocol, while at the same time harvesting RF energy transmitted from the gateway wirelessly via a dedicated radio interface. We thoroughly investigate performance limitations of such wireless energy transfer interface (WETI) with dynamic analytical model and with important practical considerations. Our methodology delivers the upper bound on WETI operation coupled with BLE-based communication, which characterizes ultimate system performance over the class of practical radio and energy resource management algorithms.

Automated In-Home Fall Risk Assessment and Detection Sensor System for Elders.

Falls are a major problem for the elderly people leading to injury, disability, and even death. An unobtrusive, in-home sensor system that continuously monitors older adults for fall risk and detects falls could revolutionize fall prevention and care. A fall risk and detection system was developed and installed in the apartments of 19 older adults at a senior living facility. The system includes pulse-Doppler radar, a Microsoft Kinect, and 2 web cameras. To collect data for comparison with sensor data and for algorithm development, stunt actors performed falls in participants' apartments each month for 2 years and participants completed fall risk assessments (FRAs) using clinically valid, standardized instruments. The FRAs were scored by clinicians and recorded by the sensing modalities. Participants' gait parameters were measured as they walked on a GAITRite mat. These data were used as ground truth, objective data to use in algorithm development and to compare with radar and Kinect generated variables. All FRAs are highly correlated (p < .01) with the Kinect gait velocity and Kinect stride length. Radar velocity is correlated (p < .05) to all the FRAs and highly correlated (p < .01) to most. Real-time alerts of actual falls are being sent to clinicians providing faster responses to urgent situations. The in-home FRA and detection system has the potential to help older adults remain independent, maintain functional ability, and live at home longer.

Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data.

Smart homes for the aging population have recently started attracting the attention of the research community. The “health state” of smart homes is comprised of many different levels; starting with the physical health of citizens, it also includes longer-term health norms and outcomes, as well as the arena of positive behavior changes. One of the problems of interest is to monitor the activities of daily living (ADL) of the elderly, aiming at their protection and well-being. For this purpose, we installed passive infrared (PIR) sensors to detect motion in a specific area inside a smart apartment and used them to collect a set of ADL. In a novel approach, we describe a technology that allows the ground truth collected in one smart home to train activity recognition systems for other smart homes. We asked the users to label all instances of all ADL only once and subsequently applied data mining techniques to cluster in-home sensor firings. Each cluster would therefore represent the instances of the same activity. Once the clusters were associated to their corresponding activities, our system was able to recognize future activities. To improve the activity recognition accuracy, our system preprocessed raw sensor data by identifying overlapping activities. To evaluate the recognition performance from a 200-day dataset, we implemented three different active learning classification algorithms and compared their performance: naive Bayesian (NB), support vector machine (SVM) and random forest (RF). Based on our results, the RF classifier recognized activities with an average specificity of 96.53%, a sensitivity of 68.49%, a precision of 74.41% and an F-measure of 71.33%, outperforming both the NB and SVM classifiers. Further clustering markedly improved the results of the RF classifier. An activity recognition system based on PIR sensors in conjunction with a clustering classification approach was able to detect ADL from datasets collected from different homes. Thus, our PIR-based smart home technology could improve care and provide valuable information to better understand the functioning of our societies, as well as to inform both individual and collective action in a smart city scenario.

Automated Health Alerts Using In-Home Sensor Data for Embedded Health Assessment.

We present an example of unobtrusive, continuous monitoring in the home for the purpose of assessing early health changes. Sensors embedded in the environment capture behavior and activity patterns. Changes in patterns are detected as potential signs of changing health. We first present results of a preliminary study investigating 22 features extracted from in-home sensor data. A 1-D alert algorithm was then implemented to generate health alerts to clinicians in a senior housing facility. Clinicians analyze each alert and provide a rating on the clinical relevance. These ratings are then used as ground truth for training and testing classifiers. Here, we present the methodology for four classification approaches that fuse multisensor data. Results are shown using embedded sensor data and health alert ratings collected on 21 seniors over nine months. The best results show similar performance for two techniques, where one approach uses only domain knowledge and the second uses supervised learning for training. Finally, we propose a health change detection model based on these results and clinical expertise. The system of in-home sensors and algorithms for automated health alerts provides a method for detecting health problems very early so that early treatment is possible. This method of passive in-home sensing alleviates compliance issues.

Detecting daily routines of older adults using sensor time series clustering.

The aim of this paper is to develop an algorithm to identify deviations in patterns of day-to-day activities of older adults to generate alerts to the healthcare providers for timely interventions. Daily routines, such as bathroom visits, can be monitored by automated in-home sensor systems. We present a novel approach that finds periodicity in sensor time series data using clustering approach. For this study, we used data set from TigerPlace, a retirement community in Columbia, MO, where apartments are equipped with a network of motion, pressure and depth sensors. A retrospective multiple case study (N=3) design was used to quantify bathroom visits as parts of the older adult's daily routine, over a 10-day period. The distribution of duration, number, and average time between sensor hits was used to define the confidence level for routine visit extraction. Then, a hierarchical clustering was applied to extract periodic patterns. The performance of the proposed method was evaluated through experimental results.

ALTERATION OF CORTICAL NEURONAL ACTIVITY DURING THE ACUTE STAGE OF TRANSIENT GLOBAL AMNESIA

of cognition. Methods: Phone monitors were installed in the homes of 26 independent elderly individuals from the ORCATECH Life Laboratory cohort (age 86 6 4.5, 88% female) and used to monitor the total daily number of incoming phone calls for an average of 174 days. General cognitive status was assessed using a composite score composed of five Z-normalized cognitive domain tests. Because the daily number of incoming calls is a count variable, we used a mixed effects Poisson regression to model the effect of cognition on phone use controlling for age, sex, education, loneliness and pain. Results: Individuals with higher cognitive function receive significantly more phone calls (b 1⁄40.41, p<0.01; 95% CI 0.141, 0.671) (Figure 1). People received fewer calls on the weekend than the weekday (b 1⁄4-0.44, p<0.001; 95% CI -0.50, -0.39), and women received more calls than men (b 1⁄40.60, p<0.001; 95% CI 0.47, 0.74). Individuals reporting higher levels of pain also received more phone calls (b 1⁄40.047, p<0.05; 95% CI 0.0075, 0.086) while lonelier individuals received fewer calls, although this result was not significant (b 1⁄4-0.0061, p1⁄40.155; 95% CI -0.0144, 0.0023). Conclusions: Among independent elders, higher cognitive function positively influences phone activity as assessed by the number of phone calls received. Telephone activity may be used to assess subtle cognitive change in a continuous, unobtrusive manner. Incorporating such measures into in-home sensor platforms could enable earlier detection and treatment of cognitive decline. Future studies will explore these and related metrics across a wider range o f cognitive function.