A noise robust automatic radiolocation animal tracking system

Agriculture is becoming increasingly reliant upon accurate data from sensor arrays, with localization an emerging application in the livestock industry. Ground‐based time difference of arrival (TDoA) radio location methods have the advantage of being lightweight and exhibit higher energy efficiency than methods reliant upon Global Navigation Satellite Systems (GNSS). Such methods can employ small primary battery cells, rather than rechargeable cells, and still deliver a multi‐year deployment. In this paper, we present a novel deep learning algorithm adapted from a one‐ dimensional U-Net implementing a convolutional neural network (CNN) model, originally developed for the task of semantic segmentation. The presented model (ResUnet-1d) both converts TDoA sequences directly to posi‐ tions and reduces positional errors introduced by sources such as multipathing. We have evaluated the model using simulated animal movements in the form of TDoA position sequences in combination with real‐world distributions of TDoA error. These animal tracks were simulated at various step intervals to mimic potential TDoA transmission inter‐ vals. We compare ResUnet-1d to a Kalman filter to evaluate the performance of our algorithm to a more traditional noise reduction approach. On average, for simulated tracks having added noise with a standard deviation of 50 m, the described approach was able to reduce localization error by between 66.3% and 73.6%. The Kalman filter only achieved a reduction of between 8.0% and 22.5%. For a scenario with larger added noise having a standard deviation of 100 m, the described approach was able to reduce average localization error by between 76.2% and 81.9%. The Kalman filter only achieved a reduction of between 31.0% and 39.1%. Results indicate that this novel 1D CNN U-Net like encoder/decoder for TDoA location error correction outperforms the Kalman filter. It is able to reduce average localization errors to between 16 and 34 m across all simulated experimental treatments while the uncorrected aver‐ age TDoA error ranged from 55 to 188 m.

[1]  Wu Liming,et al.  A Improved Wireless Location Algorithm in Nlos Environment , 2013 .

[2]  Tad Gonsalves,et al.  Effectiveness of U-Net in Denoising RGB Images , 2019 .

[3]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[4]  Hans Peter Amann,et al.  Application of Kalman filtering to noisereduction on microsensor signals , 1998 .

[5]  Lorenzo Quaglietta,et al.  SiMRiv: an R package for mechanistic simulation of individual, spatially-explicit multistate movements in rivers, heterogeneous and homogeneous spaces incorporating landscape bias , 2019, Movement Ecology.

[6]  D. D. Clark.  Overview Of The Argos System , 1989, Proceedings OCEANS.

[7]  Tim Wark,et al.  Using high fix rate GPS data to determine the relationships between fix rate, prediction errors and patch selection , 2008 .

[8]  Xianming Liu,et al.  When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach , 2017, IJCAI.

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  I. Priede.  A BASKING SHARK (CETORHINUS-MAXIMUS) TRACKED BY SATELLITE TOGETHER WITH SIMULTANEOUS REMOTE-SENSING , 1984 .

[11]  R. Schwab,et al.  Early Summer Activities of Porcupines as Determined by Radio-Positioning Techniques , 1962 .

[12]  A. Lossie,et al.  The effect of floor surface on dairy cow immune function and locomotion score. , 2009, Journal of dairy science.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Zheng Zhang,et al.  MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[15]  Yoshua Bengio,et al.  Justifying and Generalizing Contrastive Divergence , 2009, Neural Computation.

[16]  Frank C. Craighead,et al.  Satellite and ground radiotracking of elk , 1972 .

[17]  Zhongliang Deng,et al.  A Pseudorange Measurement Scheme Based on Snapshot for Base Station Positioning Receivers , 2017, Sensors.

[18]  Andy M. Reynolds,et al.  Mussels realize Weierstrassian Lévy walks as composite correlated random walks , 2014, Scientific Reports.

[19]  K. C. Ho,et al.  Joint time-scale and TDOA estimation: analysis and fast approximation , 2005, IEEE Transactions on Signal Processing.

[20]  Maik Stille,et al.  Residual U-Net Convolutional Neural Network Architecture for Low-Dose CT Denoising , 2018, Current Directions in Biomedical Engineering.

[21]  P. Turchin.  Quantitative analysis of movement : measuring and modeling population redistribution in animals and plants , 1998 .

[22]  Yi-Fan Zhang,et al.  SSIM—A Deep Learning Approach for Recovering Missing Time Series Sensor Data , 2018, IEEE Internet of Things Journal.

[23]  H. Weimerskirch,et al.  Satellite tracking of Wandering albatrosses , 1990, Nature.

[24]  M.N. de Sousa,et al.  Enhanced Localization Systems with Multipath Fingerprints and Machine Learning , 2019, 2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

[25]  Feng Jiang,et al.  A novel time difference of arrival localization algorithm using a neural network ensemble model , 2018, Int. J. Distributed Sens. Networks.

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Peter Caccetta,et al.  ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[28]  Itziar G. Alonso-González,et al.  Discrete Indoor Three-Dimensional Localization System Based on Neural Networks Using Visible Light Communication , 2018, Sensors.

[29]  Juan M. Morales,et al.  EXTRACTING MORE OUT OF RELOCATION DATA: BUILDING MOVEMENT MODELS AS MIXTURES OF RANDOM WALKS , 2004 .

[30]  Don Menzies,et al.  A scoping study to assess the precision of an automated radiolocation animal tracking system , 2016, Comput. Electron. Agric..