A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors

Abstract

We designed and evaluated an assumption-free, deep learning-based methodology for animal health monitoring, specifically for the early detection of respiratory disease in growing pigs based on environmental sensor data. Two recurrent neural networks (RNNs), each comprising gated recurrent units (GRUs), were used to create an autoencoder (GRU-AE) into which environmental data, collected from a variety of sensors, was processed to detect anomalies. An autoencoder is a type of network trained to reconstruct the patterns it is fed as input. By training the GRU-AE using environmental data that did not lead to an occurrence of respiratory disease, data that did not fit the pattern of “healthy environmental data” had a greater reconstruction error. All reconstruction errors were labelled as either normal or anomalous using threshold-based anomaly detection optimised with particle swarm optimisation (PSO), from which alerts are raised. The results from the GRU-AE method outperformed state-of-the-art techniques, raising alerts when such predictions deviated from the actual observations. The results show that a change in the environment can result in occurrences of pigs showing symptoms of respiratory disease within 1–7 days, meaning that there is a period of time during which their keepers can act to mitigate the negative effect of respiratory diseases, such as porcine reproductive and respiratory syndrome (PRRS), a common and destructive disease endemic in pigs.

The Politics of Digital Agricultural Technologies: A Preliminary Review

“…At the herd scale, sensors and other technologies (including https://www.sciencedirect.com/topics/chemistry/microfluidics, sound https://www.sciencedirect.com/topics/engineering/analyzer, image‐detection techniques, sweat and salivary sensing and serodiagnosis) are now being used to monitor risk factors that could identify anomalous environmental conditions, physiological parameters and animal behaviours that could lead to early intervention to prevent or detect diseases. For example, sound analysis is being used to identify respiratory disease in pigs in Europe (Ferrari et al ) and detect stress in laying hens in South Korea (Lee et al ), and biosensors are being used for early detection of respiratory disease pigs in the UK (Cowton et al ) and in calves in Japan (Nogami et al ). Big data is also being used at the level of veterinary epidemiology, identifying high risk populations so that surveillance and monitoring can be targeted efficiently (Van der Waal et al ).…”

Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks

“…More novel approaches to time series anomaly detection use encoder-decoder neural network models to identify anomalies in multivariate time series data. These algorithms have had success in learning complex features, specifically in highly irregular sensing data [ 25 - 27 ]. Unlike statistical approaches, neural networks do not require assumptions about the underlying distribution of the data and are often ideal compared with classical machine learning techniques because they can provide accurate predictions without the need for complex feature engineering.…”

Combination of Sensor Data and Health Monitoring for Early Detection of Subclinical Ketosis in Dairy Cows

“…In their results, k-Nearest Neighbors showed the best results, outperforming deep learning methods and decision trees. In [30], the authors test deep learning architectures for early detection of respiratory disease in pigs and compare them with classical time series regression approaches. Their results do not show any significant differences in performance measures of the presented methods.…”