Periodicity intensity for indicating behaviour shifts from lifelog data

Hu, Feiyan; Smeaton, Alan F.

doi:10.1109/bibm.2016.7822655

Cited by 5 publications

(7 citation statements)

References 10 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Determining the intensity of 24 h periodicity over a time series of up to 8 weeks would result in a single periodicity intensity for weeks of data, which would not provide any insights into the behaviour during those weeks. Therefore, we used a sliding window of 7 days duration and determined the 24 h periodicity intensity for those 7 days, and then shifted it by 15 min before repeating the process across the next 7 days of data [ 16 ]. This time-lagged overlapping window across the entire data set for each calf provides intensity scores as schematically shown in Figure 2 .…”

Section: Methodsmentioning

confidence: 99%

Periodicity Intensity of the 24 h Circadian Rhythm in Newborn Calves Show Indicators of Herd Welfare

Rhodes

Maguire

Shetty

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Circadian rhythms are a process of the sleep–wake cycle that regulates the physical, mental and behavioural changes in all living beings with a period of roughly 24 h. Wearable accelerometers are typically used in livestock applications to record animal movement from which we can estimate the activity type. Here, we use the overall movement recorded by accelerometers worn on the necks of newborn calves for a period of 8 weeks. From the movement data, we calculate 24 h periodicity intensities corresponding to circadian rhythms, from a 7-day window that slides through up to 8-weeks of data logging. The strength or intensity of the 24 h periodicity is computed at intervals as the calves become older, which is an indicator of individual calf welfare. We observe that the intensities of these 24 h periodicities for individual calves, derived from movement data, increase and decrease synchronously in a herd of 19 calves. Our results show that external factors affecting the welfare of the herd can be observed by processing and visualising movement data in this way and our method reveals insights that are not observable from movement data alone.

show abstract

Section: Methodsmentioning

confidence: 99%

Periodicity Intensity of the 24 h Circadian Rhythm in Newborn Calves Show Indicators of Herd Welfare

Rhodes

Maguire

Shetty

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Periodicity has been successfully applied in a number of fields including engineering, astronomy, biology, and physics [17]. In this paper we focus on the application of periodicity detection to time-series sensor data and we draw on our previous work in [8], [3] and [9]. In this previous work we applied periodicity analysis to accelerometer data captured from wrist-worn smart watches.…”

Section: Periodicity Analysis Of Sensor Datamentioning

confidence: 99%

“…In this previous work we applied periodicity analysis to accelerometer data captured from wrist-worn smart watches. In particular, [8] demonstrated that relevant periodicities can be detected from wrist-worn sensors, and we introduced the idea of measuring the intensity of periodicities over time. We contrasted six different methods for measuring the intensity of a periodicity, giving special consideration to irregularly-sampled data, and data that is missing large numbers of values.…”

Section: Periodicity Analysis Of Sensor Datamentioning

confidence: 99%

Tracking Human Behavioural Consistency by Analysing Periodicity of Household Water Consumption

Quinn

Murphy

Smeaton

2019

Proceedings of the 2019 2nd International Conference on Sensors, Signal and Image Processing

Self Cite

View full text Add to dashboard Cite

People are living longer than ever due to advances in healthcare, and this has prompted many healthcare providers to look towards remote patient care as a means to meet the needs of the future. It is now a priority to enable people to reside in their own homes rather than in overburdened facilities whenever possible. The increasing maturity of IoT technologies and the falling costs of connected sensors has made the deployment of remote healthcare at scale an increasingly attractive prospect. In this work we demonstrate that we can measure the consistency and regularity of the behaviour of a household using sensor readings generated from interaction with the home environment. We show that we can track changes in this behaviour regularity longitudinally and detect changes that may be related to significant life events or trends that may be medically significant. We achieve this using periodicity analysis on water usage readings sampled from the main household water meter every 15 minutes for over 8 months. We utilise an IoT Application Enablement Platform in conjunction with low cost LoRaenabled sensors and a Low Power Wide Area Network in order to validate a data collection methodology that could be deployed at large scale in future. We envision the statistical methods described here being applied to data streams from the homes of elderly and at-risk groups, both as a means of early illness detection and for monitoring the well-being of those with known illnesses.

show abstract

“…That work also found that high levels of periodicity indicating regular sleep and movement patterns were associated with lower measures of LDL-cholesterol, triglycerides and hs-CRP as well as improved health-related quality of life measures [9]. The same technique for visualising periodicity strength over time was used in an analysis of lifelog data defined as the automatic digital recording of everyday activities, and it provided insights into shifts in underlying behaviour of the subjects [10].…”

Section: Introductionmentioning

confidence: 98%