Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data

Arablouei, Reza; Wang, Ziwei; Bishop-Hurley, Greg; Liu, Jiajun

doi:10.1016/j.atech.2022.100163

Cited by 8 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to realize the navigation function in the hospital client and achieve humanized service, the navigation module will automatically accept the POIs that HIS pushes to the points of interest that patients may want to go to, such as: payment windows, departments, public facilities, pharmacies, etc. After patients finish registering, they only need to click on the POI list that pops up in mobile applications such as Pocket Hospital APP and WeChat Public, and the program can automatically guide patients to them, and at the same time, they can also You can also set your own destination [9,10].…”

Section: Positioning Navigation and His System Interfacingmentioning

confidence: 99%

Research on Bluetooth AOA-based Indoor Navigation System for Hospitals

Yang¹,

Zhu²,

Gao³

et al. 2023

HSET

View full text Add to dashboard Cite

Bluetooth 5.1 introduces the direction-finding function which can detect the direction of Bluetooth signal, on this basis, this project combines the actual hospital scenario and uses Bluetooth AOA method and IoT technology to design the implementation of intelligent navigation system in hospital. The project uses WebGL technology to provide real-time cross-floor hybrid spatial guidance navigation for patients by interfacing with the hospital's HIS and realizing in-hospital intelligent navigation with the help of WeChat applets to help patients quickly and accurately locate their consultation locations. The application of the hospital indoor navigation system can shorten patients' in-hospital wayfinding time, reduce the work pressure of front desk staff, improve patients' medical experience, and effectively improve the digital management level of the hospital.

show abstract

Section: Positioning Navigation and His System Interfacingmentioning

confidence: 99%

Research on Bluetooth AOA-based Indoor Navigation System for Hospitals

Yang¹,

Zhu²,

Gao³

et al. 2023

HSET

View full text Add to dashboard Cite

show abstract

“…PLF approaches provide the opportunity for continuous and objective monitoring of individual animals and may be used for the assessment of animal health and welfare, productivity, sustainability, and overall farm management [ 5 , 6 , 7 , 8 ]. Data collected by accelerometers have been used to classify livestock behaviours such as grazing, ruminating, and walking [ 9 , 10 , 11 , 12 , 13 ], as well as predict biting and chewing rates [ 14 , 15 ]. Accelerometer data can also be used to quantify activity levels, representing the cumulative forces measured over a specific time window.…”

Section: Introductionmentioning

confidence: 99%

“…According to Lyons et al [ 29 ], the SD of the acceleration is a valuable feature for distinguishing between static and dynamic activities/behaviours. The median is regarded as a more robust statistical feature compared to the mean as it is less sensitive to outliers and erroneous readings [ 13 ]. Support vector machine algorithms have selected the median of the acceleration magnitude as the optimal feature when classifying human behaviours such as walking, ascending stairs, and descending stairs using triaxial accelerometer data [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

Analyzing Cattle Activity Patterns with Ear Tag Accelerometer Data

Hu,

Reverter,

Arablouei

et al. 2024

Animals

Self Cite

View full text Add to dashboard Cite

In this study, we equip two breeds of cattle located in tropical and temperate climates with smart ear tags containing triaxial accelerometers to measure their activity levels across different time periods. We produce activity profiles when measured by each of four statistical features, the mean, median, standard deviation, and median absolute deviation of the Euclidean norm of either unfiltered or high-pass-filtered accelerometer readings over five-minute windows. We then aggregate the values from the 5 min windows into hourly or daily (24 h) totals to produce activity profiles for animals kept in each of the test environments. To gain a better understanding of the variation between the peak and nadir activity levels within a 24 h period, we divide each day into multiple equal-length intervals, which can range from 2 to 96 intervals. We then calculate a statistical measure, called daily differential activity (DDA), by computing the differences in feature values for each interval pair. Our findings demonstrate that patterns within the activity profile are more clearly visualised from readings that have been subject to high-pass filtering and that the median of the acceleration vector norm is the most reliable feature for characterising activity and calculating the DDA measure. The underlying causes for these differences remain elusive and is likely attributable to environmental factors, cattle breeds, or management practices. Activity profiles produced from the standard deviation (a feature routinely applied to the quantification of activity level) showed less uniformity between animals and larger variation in values overall. Assessing activity using ear tag accelerometers holds promise for monitoring animal health and welfare. However, optimal results may only be attainable when true diurnal patterns are detected and accounted for.

show abstract