Model ensemble for an effective on-line reconstruction of missing data in sensor networks

The literature has shown that model ensemble techniques are particularly effective to solve regression/classification applications by providing, given a suitable aggregation mechanism, a better generalization ability than the generic model of the ensemble. However, only few recent results consider the use of ensembles for a time-dependent framework, with focus on time-series forecasting. Here, we propose the use of ensemble of models to an on-line reconstruction of missing data coming from a sensor network. Reconstructing missing data is of paramount importance for any further data processing and must be carried out on-line not to introduce unnecessary latency when data lead to a decision or control action. The ensemble is designed by both exploiting temporal and spatial dependencies existing among the sensors composing the network. An effective aggregation mechanism is proposed for the considered models to improve the generalization ability of the ensemble. Results demonstrate the effectiveness of the proposed approach in reconstructing missing data.

[1]  Baoming Hong,et al.  Radial basis function neural network-based nonparametric estimation approach for missing data reconstruction of non-stationary series , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[2]  Vicenç Puig,et al.  Validation and reconstruction of flow meter data in the Barcelona water distribution network , 2010 .

[3]  Lennart Ljung,et al.  System identification (2nd ed.): theory for the user , 1999 .

[4]  Gyula Simon,et al.  The flooding time synchronization protocol , 2004, SenSys '04.

[5]  Krzysztof Siwek,et al.  Neural predictor ensemble for accurate forecasting of PM10 pollution , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[6]  Marcus Chang,et al.  Mote-Based Online Anomaly Detection Using Echo State Networks , 2009, DCOSS.

[7]  Saad Bennis,et al.  Improving single-variable and multivariable techniques for estimating missing hydrological data , 1997 .

[8]  Cesare Alippi,et al.  A high-frequency sampling monitoring system for environmental and structural applications , 2013, TOSN.

[9]  Alf Isaksson,et al.  Identification of ARX-models subject to missing data , 1993, IEEE Trans. Autom. Control..

[10]  Jean-Pierre Martens,et al.  Connected Digit Recognition by Means of Reservoir Computing , 2011, INTERSPEECH.

[11]  Chidchanok Lursinsap,et al.  Time-series data prediction based on reconstruction of missing samples and selective ensembling of FIR neural networks , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[12]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[13]  Sina Mirsaidi,et al.  LMS-like AR modeling in the case of missing observations , 1997, IEEE Trans. Signal Process..

[14]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[15]  Cesare Alippi,et al.  A Cognitive Fault Diagnosis System for Distributed Sensor Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Ekaterina Mangalova,et al.  Time series forecasting using ensemble of AR models with time-varying structure , 2012, 2012 IEEE Conference on Evolving and Adaptive Intelligent Systems.

[17]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[18]  F. Ding,et al.  Least‐squares parameter estimation for systems with irregularly missing data , 2009 .

[19]  C. S. Cox,et al.  COMPARISON OF AUTOASSOCIATIVE NEURAL NETWORKS AND KOHONEN MAPS FOR SIGNAL FAILURE DETECTION AND RECONSTRUCTION , 1999 .

[20]  M. Ogorzalek,et al.  Time series prediction with ensemble models , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  H. Talebi,et al.  A Recurrent Neural-Network-Based Sensor and Actuator Fault Detection and Isolation for Nonlinear Systems With Application to the Satellite's Attitude Control Subsystem , 2009, IEEE Transactions on Neural Networks.

[22]  A. Krogh,et al.  Statistical mechanics of ensemble learning , 1997 .

[23]  M. Milelli,et al.  Multimodel SuperEnsemble technique for quantitative precipitation forecasts in Piemonte region , 2010 .

[24]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[25]  Yun Zhang,et al.  Design of ensemble neural network using the Akaike information criterion , 2008, Eng. Appl. Artif. Intell..

[26]  Cesare Alippi,et al.  On-line reconstruction of missing data in sensor/actuator networks by exploiting temporal and spatial redundancy , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).