A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors
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 (GRU...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/8/2521 |
| _version_ | 1828347014036848640 |
|---|---|
| author | Jake Cowton Ilias Kyriazakis Thomas Plötz Jaume Bacardit |
| author_facet | Jake Cowton Ilias Kyriazakis Thomas Plötz Jaume Bacardit |
| author_sort | Jake Cowton |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-14T00:34:08Z |
| format | Article |
| id | doaj.art-8a9404e793cd411bb9f933a206683016 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T00:34:08Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8a9404e793cd411bb9f933a2066830162022-12-22T02:22:26ZengMDPI AGSensors1424-82202018-08-01188252110.3390/s18082521s18082521A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental SensorsJake Cowton0Ilias Kyriazakis1Thomas Plötz2Jaume Bacardit3Interdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing, Newcastle University, Newcastle upon Tyne NE1 7RU, UKAgriculture, School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, UKOpen Lab, Newcastle University, Newcastle upon Tyne NE1 7RU, UKInterdisciplinary Computing and Complex BioSystems (ICOS) Research Group, School of Computing, Newcastle University, Newcastle upon Tyne NE1 7RU, UKWe 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.http://www.mdpi.com/1424-8220/18/8/2521anomaly detectiondeep learningsensorsGRUpighealthdisease |
| spellingShingle | Jake Cowton Ilias Kyriazakis Thomas Plötz Jaume Bacardit A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors Sensors anomaly detection deep learning sensors GRU pig health disease |
| title | A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors |
| title_full | A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors |
| title_fullStr | A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors |
| title_full_unstemmed | A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors |
| title_short | A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors |
| title_sort | combined deep learning gru autoencoder for the early detection of respiratory disease in pigs using multiple environmental sensors |
| topic | anomaly detection deep learning sensors GRU pig health disease |
| url | http://www.mdpi.com/1424-8220/18/8/2521 |
| work_keys_str_mv | AT jakecowton acombineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT iliaskyriazakis acombineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT thomasplotz acombineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT jaumebacardit acombineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT jakecowton combineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT iliaskyriazakis combineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT thomasplotz combineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors AT jaumebacardit combineddeeplearninggruautoencoderfortheearlydetectionofrespiratorydiseaseinpigsusingmultipleenvironmentalsensors |