Wearable IMU-based Early Limb Lameness Detection for Horses using Multi-Layer Classifiers

Objective, automated early lameness detection plays an important role for animal well-being. The work in this paper uses horse locomotion data collected by wearable inertial measurement units, extracts gait cycle routines and constructs a multi-layer classifier for horse lameness detection, identification, and evaluation. Multi-layer classifier (MLC) is based on support vector machine and K-Nearest-Neighbors methods. Each layer is independently designed and works as a binary classifier. Horse gait classification and limb lameness detection and evaluation are then handled by each layer successively. Experiment results show that the MLC achieves 94 % detection accuracy and also generates superior performance than a deep convolutional neural network-based multiclass classifier in terms of various assessment criteria.

[1]  L Roepstorff,et al.  Do we have to redefine lameness in the era of quantitative gait analysis? , 2017, Equine veterinary journal.

[2]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[3]  D. Wilson,et al.  Repeatability of subjective evaluation of lameness in horses. , 2010, Equine veterinary journal.

[4]  Thilo Pfau,et al.  Quantitative assessment of gait parameters in horses: Useful for aiding clinical decision making? , 2016 .

[5]  L C Voute,et al.  Use of a wireless, inertial sensor-based system to objectively evaluate flexion tests in the horse. , 2012, Equine veterinary journal. Supplement.

[6]  J. Kaler,et al.  Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep , 2020, Royal Society Open Science.

[7]  Emil Olsen,et al.  Accuracy and Precision of Equine Gait Event Detection during Walking with Limb and Trunk Mounted Inertial Sensors , 2012, Sensors.

[8]  Berend Jan van der Zwaag,et al.  EquiMoves: A Wireless Networked Inertial Measurement System for Objective Examination of Horse Gait , 2018, Sensors.

[9]  T. Pfau,et al.  Head, withers and pelvic movement asymmetry and their relative timing in trot in racing Thoroughbreds in training , 2017, Equine veterinary journal.

[10]  B. Goldner,et al.  Kinematic adaptions to induced short-term pelvic limb lameness in trotting dogs , 2018, BMC Veterinary Research.

[11]  P. R. Weeren,et al.  A survey of the workload and clinical skills in current equine practices in The Netherlands , 2007 .

[12]  Omid Dehzangi,et al.  IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion , 2017, Sensors.

[13]  Kevin G Keegan,et al.  Evidence-based lameness detection and quantification. , 2007, The Veterinary clinics of North America. Equine practice.

[14]  Yoshiharu Yonezawa,et al.  Assessment of repeatability of a wireless, inertial sensor-based lameness evaluation system for horses. , 2011, American journal of veterinary research.

[15]  Diego Torricelli,et al.  IMU-Based Classification of Parkinson's Disease From Gait: A Sensitivity Analysis on Sensor Location and Feature Selection , 2018, IEEE Journal of Biomedical and Health Informatics.

[16]  Yoshiharu Yonezawa,et al.  Associations of force plate and body-mounted inertial sensor measurements for identification of hind limb lameness in horses. , 2016, American journal of veterinary research.

[17]  Francesco Fioranelli,et al.  Animal Lameness Detection With Radar Sensing , 2018, IEEE Geoscience and Remote Sensing Letters.

[18]  Iain Murray,et al.  Gait Phase Detection for Normal and Abnormal Gaits Using IMU , 2019, IEEE Sensors Journal.

[19]  Alper Yilmaz,et al.  A Deep Learning Strategy for Stride Detection , 2018, 2018 IEEE SENSORS.

[20]  Zhaozheng Yin,et al.  Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks , 2015, ACM Multimedia.