Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Nordahl, Christian; Persson, Marie; Grahn, Håkan

doi:10.1109/icdmw.2017.101

Cited by 13 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…37 The increasing trend in the elderly population is another factor that has clear implications for residential energy intensity. 38 The percentages of elderly individuals in the populations of almost all countries have been expanding. 39 About 9.1% of the global population in 2019 (or 701 million people) was 65 years of age or older, and that percentage is projected to increase to 15.9% or more by 2050.…”

Section: Literature Reviewmentioning

confidence: 99%

Impact of the rise of solo living and an ageing population on residential energy consumption in South Korea

Cho

Soh

Park

et al. 2021

Energy & Environment

View full text Add to dashboard Cite

Demographic changes have a profound impact on residential energy consumption. The number of single-person households is rapidly increasing around the world and the percentages of elderly individuals in the populations of almost all countries are expanding. The objective of our research was to analyze how single-person households and elderly households impact residential energy intensity, defined as annual residential energy consumption per capita per unit of finished area of the household’s house, and how those impacts interact with each other using South Korea as a case study. Our findings suggest that the rise of solo living and an ageing population have overlapping effects on energy consumption and threaten future improvements in residential energy intensity. Specifically, an increase of single-person households results in a decline in energy intensity regardless of whether the household is elderly or non-elderly and the effect of an increase in elderly households on energy intensity depends on whether the household is single- or multiple-person. Given the similar average size of finished area for single-person households, the difference in per unit energy consumption between elderly versus non-elderly households likely comes from behavioral differences such as a greater use of energy-intensive appliances by non-elderly households than elderly households. However, for multiple-person households, the effect of such behavioral differences seems to be dominated by the effect of a house’s shared amenities. The common space and energy-consuming amenities of a house are shared by more individuals in non-elderly households, leading to more intensive energy consumption by non-elderly multiple-person households than by elderly multiple-person households.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Impact of the rise of solo living and an ageing population on residential energy consumption in South Korea

Cho

Soh

Park

et al. 2021

Energy & Environment

View full text Add to dashboard Cite

show abstract

“…IoT Device Utility or Communication Data Activity detection [1,2,4,[11][12][13][14], [6][7][8][9] * [16][17][18][19][20][21] Anomaly detection [3,5,10], [6][7][8][9] * [22][23][24][25][26][27][28][29] * Studies that used both analysis methods.…”

Section: Methodsmentioning

confidence: 99%

“…Communication usage data processed from call detail records (CDRs) are used to find call patterns and location movements [ 20 , 21 ]; Anomaly detection-based: It checks whether an abnormality exceeding a specific threshold has occurred. Various techniques such as Bayesian networks, support vector machines, nearest neighbors, clustering, hidden Markov models (HMMs), and neural networks have been applied to detect such anomalies [ 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ]. …”

Section: Related Workmentioning

confidence: 99%

“…For this reason, the use of utility data, such as electricity, water, and gas, has been gaining significant attention [ 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ]. This method provides an advantage in that the required data can be easily collected without causing discomfort to single-person households.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Activity Detection from Electricity Consumption and Communication Usage Data for Monitoring Lonely Deaths

Kim

Park

2021

Sensors

View full text Add to dashboard Cite

As the number of single-person households grows worldwide, the need to monitor their safety is gradually increasing. Among several approaches developed previously, analyzing the daily lifelog data generated unwittingly, such as electricity consumption or communication usage, has been discussed. However, data analysis methods in the domain are currently based on anomaly detection. This presents accuracy issues and the challenge of securing service reliability. We propose a new analysis method that finds activities such as operation or movement from electricity consumption and communication usage data. This is evidence of safety. As a result, we demonstrate better performance through comparative verification. Ultimately, this study aims to contribute to a more reliable implementation of a service that enables monitoring of lonely deaths.

show abstract

“…They then linked individual appliance usage with ADLs for e-health. [10] investigated the abnormal behaviours through power consumption data, and the remote nursing of the elderly living alone has been studied. The experimental results showed that this method has the advantages of easy deployment, low cost and non-intrusion.…”

Section: Related Workmentioning

confidence: 99%

A telehealth framework for dementia care: an ADLs patterns recognition model for patients based on NILM

Dai

Wang

Meng

2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The ageing of the population and the increasing number of patients with dementia in modern society undoubtedly put tremendous pressure on the medical system. Providing telehealth care for potential patients and patients with dementia can reduce the burden on both the health system and caregivers. This paper describes a telehealth framework for dementia early detection and dementia care. Specifically, we propose an improved deep neural network model for Non-Intrusive Load Monitoring (NILM), which disaggregates the household's overall energy usage into those of individual appliances based on the sequence-to-point model and transfer learning. The daily behaviour regularities of patients are then inferred by combining principal component analysis and K-means clustering based on the disaggregated appliance-level consumptions. Experiments show that the proposed model can significantly improve training efficiency and maintain load disaggregation accuracy, and the inferred behaviour regularities have great potential to be used as useful inputs and prior knowledge to the dementia condition detection platform for early detection and real-time monitoring of patient's conditions.

show abstract

Detection of Residents’ Abnormal Behaviour by Analysing Energy Consumption of Individual Households

Cited by 13 publications

References 18 publications

Impact of the rise of solo living and an ageing population on residential energy consumption in South Korea

Impact of the rise of solo living and an ageing population on residential energy consumption in South Korea

Activity Detection from Electricity Consumption and Communication Usage Data for Monitoring Lonely Deaths

A telehealth framework for dementia care: an ADLs patterns recognition model for patients based on NILM

Contact Info

Product

Resources

About