Filtering methods to improve the accuracy of indoor positioning data for dairy cows

Pastell, Matti; Frondelius, Lilli; Järvinen, Mikko; Backman, Juha

doi:10.1016/j.biosystemseng.2018.01.008

Cited by 35 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The plausibility check of replacements by controlling if the actor was detected at another location when the receiver left the bin appears to be a promising approach for further improvements. Combining this algorithm with data from other sensors, including accelerometers (Ledgerwood et al, 2010) and location tracking (Pastell et al, 2018), could improve performance. Direct or video observation is commonly used as the gold standard to evaluate behavioral detection methods.…”

Section: Replacement Detection Algorithmmentioning

confidence: 99%

Automatic detection of feeding- and drinking-related agonistic behavior and dominance in dairy cows

Foris

Thompson

Keyserlingk

et al. 2019

Journal of Dairy Science

View full text Add to dashboard Cite

Accurate assessments of social behavior and dominance relationships in cattle can be time consuming. We investigated whether replacements at the feed bunk and water trough-one type of agonistic interaction-can be used to automatically assess dominance relationships. Our study set out to (1) validate a replacement detection algorithm using combined data from electronic feed and water bins, and (2) investigate the applicability of this algorithm to identify individual dominance scores and group-level social hierarchy in freestall-housed dairy cows. We used 4 groups of lactating cows kept in different group sizes (11 to 20 cows) located at 2 research facilities. In both facilities, feed and water were provided via automated feeding systems. A trained observer recorded all agonistic interactions in the pen over multiple days using video. Data from the electronic feed and water bins for the same days were analyzed using an algorithm to detect replacements (i.e., visits where a receiver cow was competitively replaced by an actor cow). Most agonistic interactions at the feed bunk were replacements. These replacements were associated with a brief interval between the time the receiver cow left the bin and the actor cow took her place; the optimal threshold to detect these replacements varied from 22 to 27 s between groups, independent of stocking density. The recall and precision of an algorithm based upon this threshold was high (on average >0.8), comparable to that of trained human observers. We improved data preparation by controlling for detection errors and included filtering to reduce false positives. This resulted in a >20% decrease in false positives and an increase in precision of 0.043. The dominance hierarchy based upon algorithm-detected replacements was similar to that based upon total agonistic interactions observed in the pen; the Spearman rank correlation coefficient between these hierarchies varied among the groups from 0.81 to 0.96. We conclude that data from electronic feed and water bins can accurately estimate agonistic behavior and dominance relationships among dairy cows.

show abstract

Section: Replacement Detection Algorithmmentioning

confidence: 99%

Automatic detection of feeding- and drinking-related agonistic behavior and dominance in dairy cows

Foris

Thompson

Keyserlingk

et al. 2019

Journal of Dairy Science

View full text Add to dashboard Cite

show abstract

“…Therefore, we distinguish between the types of drift phenomena, as shown in Figure 8. If SP.time > timeThreh then 15.…”

Section: Drift Phenomenon In Stay Pointsmentioning

confidence: 99%

“…However, regardless of the type of positioning technology, there will inevitably be errors, and improved positioning accuracy first relies on identifying the factors that affect regional positioning [15][16][17]. The large number of localization algorithms and the complex factors influencing error in positioning data have been discussed by several authors [18][19][20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

A Drift-of-Stay Pattern Extraction Method for Indoor Pedestrian Trajectories for the Error and Accuracy Assessment of Indoor Wi-Fi Positioning

Wang

2019

IJGI

View full text Add to dashboard Cite

The uncertainty of indoor Wi-Fi positioning is susceptible to many factors, such as sensor distribution, the internal environment (e.g., of a shopping mall), differences between receivers, and the flow of people. In this paper, an indoor pedestrian trajectory pattern mining approach for the assessment of the error and accuracy of indoor Wi-Fi positioning is proposed. First, the stay points of the customer were extracted from the pedestrian trajectories based on the spatiotemporal staying patterns of the customers in a shopping mall. Second, the drift points were distinguished from the stay points through analysis of noncustomer behavior patterns. Finally, the drift points were presented to calculate the errors in the pedestrian trajectories for the accuracy assessment of the indoor Wi-Fi positioning system. A one-month indoor pedestrian trajectories dataset from the Xinxiang Baolong shopping mall in Henan Province, China, was used for the assessment of the error and accuracy values with the proposed approach. The experimental results were verified by incorporating the distribution of the AP sensors. The proposed approach using big data pattern mining can explore the error distribution of indoor positioning systems, which can provide strong support for improving indoor positioning accuracy in the future.

show abstract

“…The height measurement (z-axis) was not calibrated and therefore not used in the analysis. The system setup, and validation and the filtering method are described in detail in (Pastell et al, 2018). Cows were housed in two sections of 24 cows in a freestall curtain-wall barn with rubber mattresses and steel separators in stall and, slatted alleys cleaned using manure robots.…”

Section: Indoor Positioning Datamentioning

confidence: 99%

“…Several indoor positioning systems have been introduced for use on commercial dairy farms. Ultra wide-band (UWB) based systems have an accuracy of below 1m in dairy barns after proper filtering (Pastell et al, 2018;Porto et al, 2014). These systems have been used to measure the feeding time of cows based on their proximity to feeding area (Shane et al, 2016;Tullo et al, 2016;Oberschätzl et al, 2015) as compared to behavioral observations.…”

Section: Introductionmentioning

confidence: 99%

A Hidden Markov Model to Estimate the Time Dairy Cows Spend in Feeder Based on Indoor Positioning Data

Pastell

Frondelius

2018

Preprint

Self Cite

View full text Add to dashboard Cite

The feeding time of dairy cows is linked with the health status of the animal and can be used to estimate daily feed intake together with other measurements. The aim of this study was to develop a model to to measure the time a dairy cow spends at a feed bunk using an Ultra wide-band indoor positioning system. We measured the feeding behavior of 50 dairy cows during 7 days using Ubisense indoor positioning system and Insentec roughage feeders. We calculated the feeding (presence at the feeder) probability of the cow using logistic regression model with the distance to feed barrier as input and used the Viterbi algorithm to calculate the most likely state (feeding or not feeding) given state transition probabilities. The model was able to predict whether the cow was at the feeding trough or not with the accuracy of 97.6%, sensitivity 95.3% and specificity 97.9%. The model was also able to estimate the mean bout duration and the number of feeding bouts.

show abstract

Filtering methods to improve the accuracy of indoor positioning data for dairy cows

Cited by 35 publications

References 18 publications

Automatic detection of feeding- and drinking-related agonistic behavior and dominance in dairy cows

Automatic detection of feeding- and drinking-related agonistic behavior and dominance in dairy cows

A Drift-of-Stay Pattern Extraction Method for Indoor Pedestrian Trajectories for the Error and Accuracy Assessment of Indoor Wi-Fi Positioning

A Hidden Markov Model to Estimate the Time Dairy Cows Spend in Feeder Based on Indoor Positioning Data

Contact Info

Product

Resources

About