April 3, 2025 | 02:20 GMT +7

  • Click to copy
Tuesday- 11:20, 05/09/2023

Researchers test automatic detection of aggressive pig behaviour

(VAN) Researchers from China recently tested a hybrid model that combines a convolutional neural network and a gated recurrent unit to identify aggressive behaviour of group-housed pigs.

They also integrated a spatio-temporal attention mechanism in the model to improve the effect of aggressive behaviour recognition.

Researchers looked at agressive behaviour in group-housed pigs. Photo: Michel Velderman

Researchers looked at agressive behaviour in group-housed pigs. Photo: Michel Velderman

The convolutional neural network acted as a spatial feature extractor to learn appearance representations of behaviour in each individual video frame. The gated recurrent unit network functioned as a temporal feature extractor to learn motion representations of behaviour in a behaviour episode.

Data collection

The researchers defined aggressive behaviour of group-housed pigs as biting, knocking, trampling and chasing. They defined mounting, playing, lying, feeding, and drinking as non-aggressive behaviour. The team observed 541 video recordings of aggressive behaviour with a duration of 3 seconds, and 565 video recordings of non-aggressive behaviour with a duration of 3 seconds.

The researchers integrated the video frames to the model. Spatial feature extractors, integrated with a spatial attention mechanism extracted behavourial representations from each individual frame. The role of the spatial attention model is to improve the feature expression of local areas, thereby enhancing the feature expression of the area where aggressive behaviour occurs and weakening the feature expression of irrelevant areas. The temporal feature extractor integrating with a temporal attention mechanism extracted motion representations of behaviour from spatial features over different frames. The team identified aggressive and non-aggressive behaviour based on these features.

The effectiveness of models

The baseline model had the lowest recognition accuracy. However, adding the spatial attention mechanism improved the recognition accuracy in the test dataset by 2.2% and optimised the spatial feature extraction. Adding temporal attention improved the performance of the model compared to the baseline model, but it did not optimise the spatial feature extractor part. Integrating both spatial and temporal attention mechanisms to the model increased the recognition accuracy to 94.8%, proving that the spatio-temporal attention model is valid.

Hybrid model works best

The authors concluded that the variant model that combines spatial and temporal attention mechanisms in a hybrid model of convolutional neural network and gated recurrent unit has the best recognition performance, which proves the effectiveness of the model in this paper.

However, further research is required to clearly capture information such as the body parts used by pigs with aggressive behaviour with a multi-camera data collection method.

HD

(PP)

Banks see a dire climate future - and ways to profit

Banks see a dire climate future - and ways to profit

(VAN) The nation’s top banks are quietly advising their clients on how to build a financial life raft - or perhaps life yacht - from the wreckage of runaway climate change.

Conflict and rising food prices drive Congolese into one of the world's worst food crises

Conflict and rising food prices drive Congolese into one of the world's worst food crises

(VAN) From FAO Office in the Democratic Republic of the Congo.

Brazil faces inflation risks as surging corn prices eclipse rice plunge

Brazil faces inflation risks as surging corn prices eclipse rice plunge

(VAN) Corn prices in the Campinas region have surged past 90 reais ($15.80) per 60-kg bag, the highest nominal level in nearly three years, marking a more than 23% jump year-to-date, according to the widely followed Cepea index from the University of Sao Paulo.

Breaking cycle of forest land grabs

Breaking cycle of forest land grabs

(VAN) Thailand’s efforts to address landlessness among its population has been a priority for multiple administrations.

Engaging the next generation in the connection between forests and foods

Engaging the next generation in the connection between forests and foods

(VAN) FAO, together with the Government of Italy, and a forest expert and a master ice cream maker from Italy, educate young students on the significance of forest foods at FAO Park.

The glyphosate debate

The glyphosate debate

(VAN) The EU has recently approved the use of glyphosate for another decade. Bárbara Pinho examines the controversial pesticide’s presence in British farming and considers the possibility of a ban in the UK.

The spread of H5N1 highly pathogenic avian influenza calls for stepped up action, FAO says

The spread of H5N1 highly pathogenic avian influenza calls for stepped up action, FAO says

(VAN) Averting losses of hundreds of millions of poultry crucial to mitigate impacts on food security, nutrition and affordability of poultry products.

Read more