Detection of anomalies in cow activity using wavelet transform based features

2025-02-28

AI Summary

To address the challenge of early detection of physiological anomalies (e.g., disease, estrus) in precision livestock farming, this paper proposes an interpretable anomaly detection method tailored for high-noise, 24-hour bovine activity time-series data. The method innovatively integrates continuous wavelet transform (CWT) with individualized temporal baseline modeling to extract wavelet-mean features and periodic waveform statistics, effectively distinguishing true physiological anomalies from biological noise. Anomaly detection is performed using a lightweight Isolation Forest, where wavelet-domain features exhibit the highest contribution. Experimental results demonstrate that the average time-to-detection precedes veterinarian clinical annotations by 1.3 days, with some cases detected 1–2 days earlier—significantly outperforming manual observation. The approach achieves strong early detection capability, model interpretability, and individual adaptability, thereby providing reliable, actionable early-warning support for precision livestock management.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

In Precision Livestock Farming, detecting deviations from optimal or baseline values - i.e. anomalies in time series - is essential to allow undertaking corrective actions rapidly. Here we aim at detecting anomalies in 24h time series of cow activity, with a view to detect cases of disease or oestrus. Deviations must be distinguished from noise which can be very high in case of biological data. It is also important to detect the anomaly early, e.g. before a farmer would notice it visually. Here, we investigate the benefit of using wavelet transforms to denoise data and we assess the performance of an anomaly detection algorithm considering the timing of the detection. We developed features based on the comparisons between the wavelet transforms of the mean of the time series and the wavelet transforms of individual time series instances. We hypothesized that these features contribute to the detection of anomalies in periodic time series using a feature-based algorithm. We tested this hypothesis with two datasets representing cow activity, which typically follows a daily pattern but can deviate due to specific physiological or pathological conditions. We applied features derived from wavelet transform as well as statistical features in an Isolation Forest algorithm. We measured the distance of detection between the days annotated abnormal by animal caretakers days and the days predicted abnormal by the algorithm. The results show that wavelet-based features are among the features most contributing to anomaly detection. They also show that detections are close to the annotated days, and often precede it. In conclusion, using wavelet transforms on time series of cow activity data helps to detect anomalies related to specific cow states. The detection is often obtained on days that precede the day annotated by caretakers, which offer possibility to take corrective actions at an early stage.

Problem

• Detect anomalies in cow activity time series
• Distinguish anomalies from noise in biological data
• Early detection of disease or oestrus in cows

Innovation

• Wavelet transforms denoise cow activity data.
• Isolation Forest algorithm detects anomalies early.
• Wavelet-based features enhance anomaly detection accuracy.