Table 2.
Details of the 79 studies included in scoping review analysis.
| Reference | Objective | Environment | Population | Sensor | Feature Categories |
|---|---|---|---|---|---|
| Health Status Monitoring | |||||
| Judah 2017 [22] | To develop and test a reliable RTLS system that can recognize various bathroom activities and behaviours of multiple individuals | Bathroom | Not Given | Combo (Elpas) | Trajectory, Proximity |
| Kaye 2012 [23] | To examine the relation between measures of walking activity and function | Private Home | Adults | IR | Activity Levels |
| Hayes 2008 [24] | To find distinguishable differences in the motor activity of healthy and cognitively impaired elders | Private Home | Older Adults | IR | Activity Levels |
| Lymberopoulos 2011 [25] | To develop a model that describes and determines a person’s routine based on their spatiotemporal activity | Private Home | Older Adults | IR | Dwell, Trajectory |
| Petersen 2014 [26] | To describe and validate a method for detecting time spent out-of-home using a logistic regression-based classifier with inputs derived from passive sensor data. | Private Home | Older Adults | IR | Activity Levels |
| Fiorini 2017 [27] | To describe and define groups of behavioural patterns starting from unannotated data analysis and a “blind” approach for activity recognition | Private Home | Older Adults | IR | Activity Levels |
| Enshaeifar 2018 [28] | To develop an algorithm that identifies daily routines, detects unusual patterns and possible agitation events | Private Home | Older Adults | Pressure | Activity, Trajectory |
| Akl 2015 a [6] | To explore the feasibility of autonomously detecting mild cognitive impairment (MCI) using various features of location-tracked data | Private Home | Older Adults | IR | Activity Levels |
| Akl 2015 b [29] | To detect mild cognitive impairment using differences in walking speed distributions | Private Home | Older Adults | Not Given | Activity levels |
| Akl 2016 [30] | To automatically detect MCI in older adults using the distribution of activity in different rooms of the home | Private Home | Older Adults | IR | Activity levels |
| Akl 2017 [31] | To develop models of home activity that can support early detection of dementia | Private Home | Older Adults | IR | Dwell, Trajectory |
| Dodge 2012 [32] | To test if the assessment of walking speed and its variability can distinguish those with mild cognitive impairment (MCI) from those with intact cognition | Private Home | Older Adults | IR | Activity, Dwell |
| Yahaya 2019 [33] | To develop a method of finding thresholds for abnormalities in Activities of Daily Living (ADL) correlated to changes in sleeping behaviour | Private Home | Adults | IR; CASAS | Activity Levels |
| Tan 2018 [34] | To develop a novel DCNN classifier to recognize different activities in a smart home | Private Home | Adults | CASAS | DCNN Classifier |
| Gochoo 2019 [35] | To develop an unobtrusive activity recognition classifier using deep convolutional neural network (DCNN) | Private Home | Adults | CASAS | DCNN Classifier |
| Xu 2020 [36] | To compare different classification algorithms in their ability to recognize the at-home activity of elderly people | Private home | Older Adults | CASAS | Activity Levels |
| Eisa 2017 [37] | To detect unusual changes in regular mobility behaviour by monitoring daily room-to-room transitions and permanence habits | Private Home | Older Adults | CASAS | Activity, Dwell, Trajectory |
| Gochoo 2017 b [38] | To classify walking/travel patterns of elderly people living alone using a Deep Convolutional Neural Network classifier (DCNN) | Private Home | Older Adults | CASAS | Activity, Dwell, Trajectory |
| Gochoo 2017 c [39] | To develop a Deep Convolutional Neural Network (DCNN) classifier for elderly activity recognition | Private Home | Older Adults | CASAS | Activity Levels |
| Zhang 2017 [40] | To propose an unsupervised learning approach that can determine movement patterns and daily activities without event annotations | Private Home | Older Adults | CASAS | Trajectory |
| Fang 2020 [41] | To locate and predict the position of the elderly, helping to detect the abnormal behaviours or irregular life routines | Private Home | Adults | State-change Sensors | Trajectory |
| Fahad 2013 [42] | To monitor the change in the repeated group of activities that make up the daily routine of a person living in a smart home | Private Home | Adults | State-change Sensors | Activity, Trajectory |
| Su 2018 [43] | To build an activity recognition system for elder persons with dementia via the classification of hand movements and indoor position data | Smart Home | Not Given | Bluetooth | Random Forest Model |
| Li 2017 [44] | To test a system for screening elders who are likely to have dementia from performing eight activities from IADL | Smart Home | Older Adults | CASAS | Activity, Trajectory |
| Aramendi 2018 [45] | To evaluate the correlation of different behavioural features derived from daily activities to IADL-C scores and their effectiveness in detecting change in functional health decline | Smart Home | Older Adults | CASAS | Activity Levels |
| Rantz 2011 [46] | To investigate the use of passive monitoring of residents to detect early signs of illness, functional decline, and/or urinary tract infection | Retirement Community | Older Adults | IR | Activity Levels |
| Skubic 2015 [47] | To exploring behavioural features that are more or less useful in detecting early changes in health status across different chronic health conditions and home layouts | Retirement Community | Older Adults | IR | Activity, Dwell, Proximity |
| Galambos 2013 [7] | To investigate whether visual features from motion density maps are sensitive enough to detect changes in mental health over time | Retirement Community | Older Adults | IR | Activity, Dwell |
| Alberdi 2018 [48] | To evaluate use activity behaviour data to detect the multimodal symptoms that are often found to be impaired in Alzheimer’s Disease (AD) and predict related clinical scores | Retirement Community | Older Adults | CASAS | Activity Levels |
| Dawadi 2016 [49] | To evaluate the effectiveness of an algorithm that can model daily activity routines and detect changes in behavioural routines | Retirement Community | Older Adults | CASAS | Activity, Trajectory |
| Gochoo 2017 a [50] | To develop an algorithm that determines what activity is occurring at the front door and detect memory lapses (forget events from brief-return-and-exit at door) | Retirement Community | Older Adults | CASAS | Activity, Dwell, Trajectory |
| Tan 2017 [51] | To classify front-door events (exit, enter, visitor, other, and brief-return-and-exit) of a resident in the smart house | Retirement Community | Older Adults | CASAS | Activity, Dwell, Trajectory |
| Cheng 2019 [52] | To estimate dementia conditions based on graph representations of daily locomotion | Assisted Living | Older Adults | UWB | Trajectory |
| Bellini 2020 [53] | To assesses both the degree of relations among residents and the popularity of the facility spaces as an indicator of accessibility | Assisted Living | Older Adults | Bluetooth | Proximity |
| Kearns 2010 [54] | To explore whether elders with greater path tortuosity (irregular movement) was associated with greater cognitive impairment | Assisted Living | Older Adults | UWB | Trajectory |
| Kearns 2012 [55] | To investigate whether variability in voluntary movement paths would be greater in the week preceding a fall compared with non-fallers | Assisted Living | Older Adults | UWB | Activity, Trajectory |
| Bowen 2016 [9] | To examine how intraindividual changes in ambulation characteristics may be used to predict falls. | Assisted Living | Older Adults | UWB | Activity Levels |
| Bowen 2018 [8] | To determine the influence of cognitive impairment (CI), gait quality, and balance ability on walking distance and speed | Nursing Home | Older Adults | UWB | Activity Levels |
| Bowen 2019 [56] | To examine the characteristics of wandering associated with preserved versus worsened ADL function. | Nursing Home | Older Adults | UWB | Activity Levels |
| Grunerbl 2011 [57] | To develop and evaluate a system for coarse assessment of the health status of dementia patients in a nursing home | Nursing Home | Older Adults | UWB | Activity, Dwell |
| Jansen 2017 [5] | To provide descriptive analysis of life-space movement patterns in nursing home residents and to identify associated factors of different patterns | Nursing Home | Older Adults | Not Given | Activity, Dwell |
| Yang 2020 [58] | To classify probable social interaction patterns and identify mobility patterns and associated levels of privacy with both social and movement patterns | Nursing Home | Older Adults | Bluetooth | Activity, Dwell, Trajectory |
| Okada 2019 [59] | To predict scores on the dementia scale using behavioural features as observed through human–robot interactions and indoor daily activity | Nursing Home | Older Adults | Bluetooth | Dwell Time |
| Ramezani 2019 [60] | To examine the ability of combination of physical activity and indoor location features to discriminate subacute care patients who are re-admitted to the hospital | Inpatient Unit | Older Adults | Bluetooth | Activity, Dwell |
| Vuong 2014 [61] | To determine an automated system for detecting and classifying travel patterns in people with dementia using movement data | Inpatient Unit | Older Adults | RFID | Trajectory |
| Jeong 2017 [4] | To assess the feasibility of using an infrared-based RTLS for measuring patient ambulation in a 2-min walk test (2MWT) | Inpatient Unit | Adults | IR | Activity Levels |
| Kearns 2016 [62] | To determine if improvements in cognitive function during traumatic brain injury treatment can be measured using movement path tortuosity in everyday ambulation | Inpatient Unit | Adults | UWB | Trajectory |
| Jeong 2020 [63] | To evaluate novel ambulation metrics in predicting 30-day readmission rates, discharge location, and length of stay of postoperative cardiac surgery patients | Inpatient Unit | Cardiac Patients | IR | Activity, Dwell |
| Consumer Behaviour | |||||
| Dogan 2019 [64] | To show the potential of process mining techniques to understand customer needs and behavioural trends based on gender differences | Shopping Mall | Shoppers | Bluetooth | Trajectory |
| Liu 2020 [65] | To produce a method to infer customer profiles, mainly gender and age, using indoor location data | Shopping Mall | Shoppers | WiFi | Activity, Dwell, Trajectory |
| Dogan 2020 [66] | To use process mining to determine customer visit time and describe different customer flows between customers who purchase and those who do not | Supermarket | Shoppers | Bluetooth | Dwell, Trajectory |
| Kholod 2011 [67] | To examine grocery shoppers’ moving direction within the store and its influence on their buying behaviour | Supermarket | Shoppers | RFID | Trajectory |
| Popa 2013 [68] | To develop a framework for automatic assessment of customers’ behaviours to categorize them into different shoppers’ types by goal | Supermarket | Shoppers | Camera | Trajectory |
| Paolanti 2017 [69] | To model and predict shopper’s behaviour in retail environments to predict the shopper’s trajectory | Supermarket | Shoppers | UWB | Activity, Dwell, Trajectory |
| Yang 2019 [70] | To define the relationship between the layout of the shelves, and shopping behaviour and product sales | Supermarket | Students | UWB | Activity, Dwell |
| Takai 2010 [71] | To describe the relation between the time customers spend in a store section and the probability they will make a purchase | Supermarket | Shoppers | RFID | Dwell Time |
| Takai 2011 [72] | To correlate the number of purchased items by stationary time and find a two-category model that groups shopper behaviours using this correlation | Supermarket | Shoppers | RFID | Dwell Time |
| Takai 2012 [73] | To capture dependencies among variables that describe purchasing behaviour based on section of stores | Supermarket | Shoppers | RFID | Dwell Time |
| Takai 2013 [74] | To find homogeneous groups of customers based on the number of purchased items and determine whether time period that the customer shops influences this group classification | Supermarket | Shoppers | RFID | Dwell Time |
| Kaneko 2018 [75] | To build a purchase behaviour model of customers and predict whether the customer will make a purchase or not | Supermarket | Shoppers | RFID | Dwell Time |
| Nakahara 2012 [76] | To propose models that clarify the relationship between product zone visit sequences and shopping behaviour and use them to characterize high-value purchasing customers and low-value purchasing customers | Supermarket | Shoppers | RFID | Activity, Dwell, Trajectory |
| Zuo 2015 [77] | To improve methods of predicting whether a customer will make a purchase or not | Supermarket | Shoppers | RFID | Dwell Time |
| Li 2016 [78] | To study relationships between different variables derived from the amount of time spent in different areas of the store, how much was purchased from each area, and the area type | Supermarket | Shoppers | RFID | Activity, Dwell |
| Gu 2019 [79] | To measure differences in product search behaviour and search benefits depending on the customer and their varying levels of self-control | Supermarket | Shoppers | RFID | Dwell Time |
| Yoshimura 2014 [80] | To identify aspects of visitor behaviour that could explain museum overcrowding | Museum | Museum Visitors | Bluetooth | Activity, Dwell, Trajectory |
| Yoshimura 2019 [81] | To compare museum visitor movements when more or fewer choices are offered | Museum | Museum Visitors | Bluetooth | Dwell, Trajectory |
| Kanda 2007 [82] | To estimate visitor trajectories to analyse space, visiting patterns, and relationships | Museum | Museum Visitors | RFID | Activity, Dwell, Trajectory, Proximity |
| Lanir 2013 [83] | To compare the movement of museum visitors who used a mobile multimedia location-aware guide to those who did not | Museum | Museum Visitors | RFID | Activity, Dwell, Proximity |
| Martella 2017 [84] | To understand the behaviour of museum visitors and the attraction power of different displays | Museum | Museum Visitors | RFID | Dwell, Trajectory, Proximity |
| Safety and Operational Efficiency | |||||
| Booth 2019 [85] | To develop a technique for clustering room purpose based on patterns in human movement data and to predict mental wellness levels of hospital staff | Hospital | Primary Care Staff | Bluetooth | Dwell, Trajectory |
| Feng 2020 a [86] | To detect and discover location-driven routines and physiological data to understand the movement intensity of nurses at different times in a work shift | Hospital | Nurses | Bluetooth | Dwell, Trajectory |
| Feng 2020 b [87] | To develop a method to quantify the relations between physiological signals and indoor locations at a real-world workplace. The method is validated on individuals’ workplace performance in a large hospital setting. | Hospital | Nurses | Bluetooth | Dwell Time |
| Lopez-de-Teruel 2017 [88] | To provide a method to differentiate location data of employees from non-employees and generate clusters related to the different working teams | Office | Workers | Custom wireless network + cell phones | Activity Levels |
| Cheng 2013 [89] | To design and validate a new method to analyse the spatio-temporal conflicts between workers and automatically defined hazard, and define an indicator that can measure the safety performance of workers | Construction | Workers | UWB | Activity, Dwell |
| Arslan 2018 [90] | To develop a model that uses worker mobility patterns to identify unsafe worker behaviours | Construction | Workers | Bluetooth | Activity, Trajectory |
| Arslan 2019 [91] | To test if semantic trajectories can visualize site-zone density to avoid congestion and provide proximity analysis to prevent collisions, accidents, and unauthorized access | Construction | Workers | Bluetooth | Activity, Dwell, Trajectory |
| Hwang 2019 [92] | To monitor pedestrian flow in a subway station and use sensor-based insights to improve pedestrian flow | Subway Station | Subway Commuters | Bluetooth/ Wi-Fi | Activity Levels |
| Developmental Behaviour | |||||
| Jorge 2019 [93] | To develop and validate an algorithm that detects unusual social behaviour and finds significant subgroups within the population | School Playground | Children | Set 1—IMU GNSS, Set 2—UWB | Proximity |
| Messinger 2019 [94] | To investigate differences in social interaction and movement within a classroom based on gender and describe the classroom social network | Classroom | Children | UWB | Activity, Trajectory, Proximity |