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 (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.

[1]  Jun Miao,et al.  One-Class Classification with Extreme Learning Machine , 2015 .

[2]  D. Berckmans,et al.  Precision livestock farming technologies for welfare management in intensive livestock systems. , 2014, Revue scientifique et technique.

[3]  Witold Pedrycz,et al.  Multivariate time series anomaly detection: A framework of Hidden Markov Models , 2017, Appl. Soft Comput..

[4]  Xiangjian He,et al.  Intrusion detection method based on nonlinear correlation measure , 2014, Int. J. Internet Protoc. Technol..

[5]  S. Mortensen,et al.  Risk factors for infection of sow herds with porcine reproductive and respiratory syndrome (PRRS) virus. , 2002, Preventive veterinary medicine.

[6]  Li Wei,et al.  Experiencing SAX: a novel symbolic representation of time series , 2007, Data Mining and Knowledge Discovery.

[7]  Yongwha Chung,et al.  Automatic Detection and Recognition of Pig Wasting Diseases Using Sound Data in Audio Surveillance Systems , 2013, Sensors.

[8]  W. Cleveland.  Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .

[9]  Kimberly VanderWaal,et al.  Using Machine Learning to Predict Swine Movements within a Regional Program to Improve Control of Infectious Diseases in the US , 2017, Front. Vet. Sci..

[10]  Fei-Fei Li,et al.  Visualizing and Understanding Recurrent Networks , 2015, ArXiv.

[11]  Rama K. Singh,et al.  Ensemble Approach for Zoonotic Disease Prediction Using Machine Learning Techniques , 2015 .

[12]  K. Stärk.  Epidemiological investigation of the influence of environmental risk factors on respiratory diseases in swine--a literature review. , 2000, Veterinary journal.

[13]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[16]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[17]  Lovekesh Vig,et al.  Anomaly detection in ECG time signals via deep long short-term memory networks , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[18]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[19]  Georg Carle,et al.  Traffic Anomaly Detection Using K-Means Clustering , 2007 .

[20]  R. Huhn.  Swine enzootic pneumonia: incidence and effect on rate of body weight gain. , 1970, American journal of veterinary research.

[21]  Syed Mahfuzul Aziz,et al.  Sensor Anomaly Detection in Wireless Sensor Networks for Healthcare , 2015, Sensors.

[22]  Adriano Lorena Inácio de Oliveira,et al.  One-class Classification for heart disease diagnosis , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[23]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[24]  Li Wei,et al.  Assumption-Free Anomaly Detection in Time Series , 2005, SSDBM.

[25]  Ilias Kyriazakis,et al.  Porcine lie detectors: Automatic quantification of posture state and transitions in sows using inertial sensors , 2016, Comput. Electron. Agric..

[26]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[27]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[28]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[29]  Michael E. Fitzpatrick,et al.  Anomaly detection in time series data using a combination of wavelets, neural networks and Hilbert transform , 2015, 2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA).

[30]  Daniel V. Smith,et al.  A comparison of autoencoder and statistical features for cattle behaviour classification , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[31]  Finale Doshi-Velez,et al.  Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models , 2016, ArXiv.

[32]  Mooi Choo Chuah,et al.  ECG Anomaly Detection via Time Series Analysis , 2007, ISPA Workshops.

[33]  Bharadwaj Veeravalli,et al.  Real-Time, Personalized Anomaly Detection in Streaming Data for Wearable Healthcare Devices , 2017, Handbook of Large-Scale Distributed Computing in Smart Healthcare.

[34]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[35]  Ilias Kyriazakis,et al.  Whittemore's Science and Practice of Pig Production , 2006 .

[36]  Yoshua Bengio,et al.  Gated Feedback Recurrent Neural Networks , 2015, ICML.

[37]  Ilias Kyriazakis,et al.  Early detection of health and welfare compromises through automated detection of behavioural changes in pigs , 2016, Veterinary journal.

[38]  Xue-wen Chen,et al.  Big Data Deep Learning: Challenges and Perspectives , 2014, IEEE Access.

[39]  Ying Wah Teh,et al.  Time-series clustering - A decade review , 2015, Inf. Syst..

[40]  Toby P. Breckon,et al.  SMS Spam Filtering Using Probabilistic Topic Modelling and Stacked Denoising Autoencoder , 2016, ICANN.

[41]  Andrew W. Moore,et al.  Bayesian Network Anomaly Pattern Detection for Disease Outbreaks , 2003, ICML.

[42]  Lovekesh Vig,et al.  LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection , 2016, ArXiv.

[43]  Stephen R Hughes.  Application Areas , 2013, Journal of laboratory automation.

[44]  Enrique Fernández-Blanco,et al.  Early warning in egg production curves from commercial hens: A SVM approach , 2016, Comput. Electron. Agric..

[45]  Andrew W. Moore,et al.  What's Strange About Recent Events (WSARE): An Algorithm for the Early Detection of Disease Outbreaks , 2005, J. Mach. Learn. Res..