Affective State Recognition in Livestock-Artificial Intelligence Approaches

Abstract

Farm animals, numbering over 70 billion worldwide, are increasingly managed in large-scale, intensive farms. With both public awareness and scientific evidence growing that farm animals experience suffering, as well as affective states such as fear, frustration and distress, there is an urgent need to develop efficient and accurate methods for monitoring their welfare. At present, there are not scientifically validated 'benchmarks' for quantifying transient emotional (affective) states in farm animals, and no established measures of good welfare, only indicators of poor welfare, such as injury, pain and fear. Conventional approaches to monitoring livestock welfare are time-consuming, interrupt farming processes and involve subjective judgments. Biometric sensor data enabled by artificial intelligence is an emerging smart solution to unobtrusively monitoring livestock, but its potential for quantifying affective states and ground-breaking solutions in their application are yet to be realized. This review provides innovative methods for collecting big data on farm animal emotions, which can be used to train artificial intelligence models to classify, quantify and predict affective states in individual pigs and cows. Extending this to the group level, social network analysis can be applied to model emotional dynamics and contagion among animals. Finally, 'digital twins' of animals capable of simulating and predicting their affective states and behaviour in real time are a near-term possibility.

Keywords: affective states; animal emotions; animal welfare; animal-based measures; emotion modelling; sensors.

Figure 1

Photo of the wearable 3-in-1 sensor patch for measuring heart and respiration rates, and activity simultaneously (Source: TNO Holst Centre, The Netherlands).

Figure 2

Multimodal affective state recognition data analysis workflow framework of the per-animal quantified approach. EEG—electroencephalogram; FNIRS—functional near-infrared spectroscopy; ML—machine learning; CNN—convolutional neural networks.

Figure 3

Pipeline of WUR Wolf (Wageningen University and Research—Wolf Mascot) automatic approach [102] in coding affective states from facial features of cows using machine learning models. SVM—support vector machine; AU—arbitrary units.

Figure 4

Overview of the farm animal affective measurement experimental set-up and block scheme of heart-rate signal processing and data classification chain.

Figure 5

A framework for animal welfare assessment incorporating multimodal robust measures.

Figure 6

(A) Typical experimental paradigm for farm animal cognitive bias tasks. (B) Impact of bias in machine learning algorithm on animal emotion estimates.

Figure 7

Digital Twin system reference architecture for smart animal welfare platform in predicting the behaviour of farm animals.

Figure 8

Sensor-based Digital Twin animal emotion modelling process.