Sensor nodes fault detection for agricultural wireless sensor networks based on NMF

Abstract Nowadays, Wireless Sensor Networks (WSN) are widely been employed to solve agricultural problems related to the optimization of scarce farming resources, decision making support, and land monitoring. However, the small sensing devices that are part of WSNs – known as sensor nodes – suffer from degradation and so producing erroneous measurements. In this paper, a machine learning method based on Non-Negative Matrix Factorization (NMF) is applied to the spectral representation of data acquired by a WSN to extract features that model the normal behavior of sensor node readings leading to a good representation of data using a low number of features. This procedure is accompanied by a classifier that decides if there is a set of features that deviates from the normal ones. Experiments on soil moisture data show that NMF achieves good results detecting flaws in readings from sensors. Results are compared with other method based on Principal Component Analysis (PCA), the Multi-scale PCA (MSPCA) algorithm.

[1]  Ahmed Zouinkhi,et al.  A machine learning methods: Outlier detection in WSN , 2015, 2015 16th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA).

[2]  Narendra Singh Raghuwanshi,et al.  Wireless sensor networks for agriculture: The state-of-the-art in practice and future challenges , 2015, Comput. Electron. Agric..

[3]  Mohamed N. Nounou.  Multiscale finite impulse response modeling , 2006, Eng. Appl. Artif. Intell..

[4]  B. Bakshi.  Multiscale PCA with application to multivariate statistical process monitoring , 1998 .

[5]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[6]  Bu Sung Lee Francis,et al.  Combining MIC feature selection and feature-based MSPCA for network traffic anomaly detection , 2016, 2016 Third International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC).

[7]  K. Sharmila,et al.  Application of multiscale principal component analysis (MSPCA) for enhancement of ECG signals , 2011, 2011 IEEE International Instrumentation and Measurement Technology Conference.

[8]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[9]  I. Jolliffe.  Principal Component Analysis and Factor Analysis , 1986 .

[10]  Bu-Sung Lee,et al.  Detection of network anomalies using Improved-MSPCA with sketches , 2017, Comput. Secur..

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Jimmy Ludeña-Choez,et al.  Acoustic Event Classification using spectral band selection and Non-Negative Matrix Factorization-based features , 2016, Expert Syst. Appl..

[13]  Jimmy Ludeña-Choez,et al.  NMF-Based Spectral Analysis for Acoustic Event Classification Tasks , 2013, NOLISP.

[14]  Yu-Jin Zhang,et al.  Nonnegative Matrix Factorization: A Comprehensive Review , 2013, IEEE Transactions on Knowledge and Data Engineering.

[15]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[16]  Hazem Nounou,et al.  Improving the prediction and parsimony of ARX models using multiscale estimation , 2007, Appl. Soft Comput..

[17]  Oliver Obst,et al.  Wireless Sensor Network Anomalies: Diagnosis and Detection Strategies , 2011 .

[18]  Salah Zidi,et al.  Fault Detection in Wireless Sensor Networks Through SVM Classifier , 2018, IEEE Sensors Journal.

[19]  Riaz Ahmed Shaikh,et al.  An analysis of fault detection strategies in wireless sensor networks , 2017, J. Netw. Comput. Appl..

[20]  Heiko Hoffmann,et al.  Kernel PCA for novelty detection , 2007, Pattern Recognit..

[21]  Gregory J. Pottie,et al.  Sensor network data fault types , 2007, TOSN.

[22]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[23]  Jimmy Ludeña-Choez,et al.  Speech Denoising Using Non-negative Matrix Factorization with Kullback-Leibler Divergence and Sparseness Constraints , 2012, IberSPEECH.

[24]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[25]  Francesco Masulli,et al.  A survey of kernel and spectral methods for clustering , 2008, Pattern Recognit..

[26]  Bu-Sung Lee,et al.  A MSPCA based intrusion detection algorithm tor detection of DDoS attack , 2015, 2015 IEEE/CIC International Conference on Communications in China (ICCC).

[27]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.