Multi-level information fusion for environment aware robotic navigation

This thesis develops the hardware and software framework for an integrated navigation system. Dynamic data fusion algorithms are used to develop a system with a high level of resistance to the typical problems that affect standard navigation systems.

Design of coreless PCB transformers for power and signal isolation in a modular ADC system for power quality data acquisition

Available industrial energy meters offer high accuracy and reliability, but are typically expensive and low-bandwidth, making them poorly suited to multi-sensor data acquisition schemes and power quality analysis. An alternative measurement system is proposed in this paper that is highly modular, extensible and compact. To minimise cost, the device makes use of planar coreless PCB transformers to provide galvanic isolation for both power and data. Samples from multiple acquisition devices may be concentrated by a central processor before integration with existing host control systems. This paper focusses on the practical design and implementation of planar coreless PCB transformers to facilitate the module's isolated power, clock and data signal transfer. Calculations necessary to design coreless PCB transformers, and circuits designed for the transformer's practical application in the measurement module are presented. The designed transformer and each application circuit have been experimentally verified, with test data and conclusions made applicable to coreless PCB transformers in general.

Energy Harvesting WSNs for Accurately Estimating the Maximum Sensor Reading: Trade-Offs and Optimal Design

Computing the maximum of sensor readings arises in several environmental, health, and industrial monitoring applications of wireless sensor networks (WSNs). We characterize the several novel design trade-offs that arise when green energy harvesting (EH) WSNs, which promise perpetual lifetimes, are deployed for this purpose. The nodes harvest renewable energy from the environment for communicating their readings to a fusion node, which then periodically estimates the maximum. For a randomized transmission schedule in which a pre-specified number of randomly selected nodes transmit in a sensor data collection round, we analyze the mean absolute error (MAE), which is defined as the mean of the absolute difference between the maximum and that estimated by the fusion node in each round. We optimize the transmit power and the number of scheduled nodes to minimize the MAE, both when the nodes have channel state information (CSI) and when they do not. Our results highlight how the optimal system operation depends on the EH rate, availability and cost of acquiring CSI, quantization, and size of the scheduled subset. Our analysis applies to a general class of sensor reading and EH random processes.

Adaptive modelling, estimation and fusion from data: a neurofuzzy approach

In a world of almost permanent and rapidly increasing electronic data availability, techniques of filtering, compressing, and interpreting this data to transform it into valuable and easily comprehensible information is of utmost importance. One key topic in this area is the capability to deduce future system behavior from a given data input. This book brings together for the first time the complete theory of data-based neurofuzzy modelling and the linguistic attributes of fuzzy logic in a single cohesive mathematical framework. After introducing the basic theory of data-based modelling, new concepts including extended additive and multiplicative submodels are developed and their extensions to state estimation and data fusion are derived. All these algorithms are illustrated with benchmark and real-life examples to demonstrate their efficiency. Chris Harris and his group have carried out pioneering work which has tied together the fields of neural networks and linguistic rule-based algortihms. This book is aimed at researchers and scientists in time series modeling, empirical data modeling, knowledge discovery, data mining, and data fusion.

Multi-target out-of-sequence data association: tracking using graphical models

When performing data fusion, one often measures where targets were and then wishes to deduce where targets currently are. There has been recent research on the processing of such out-of-sequence data. This research has culminated in the development of a number of algorithms for solving the associated tracking problem. This paper reviews these different approaches in a common Bayesian framework and proposes an architecture that orthogonalises the data association and out-of-sequence problems such that any combination of solutions to these two problems can be used together. The emphasis is not on advocating one approach over another on the basis of computational expense, but rather on understanding the relationships among the algorithms so that any approximations made are explicit. Results for a multi-sensor scenario involving out-of-sequence data association are used to illustrate the utility of this approach in a specific context.

A cross layer protocol for energy aware and critical data delivered applications using Wireless Sensor Networks

Environment monitoring applications using Wireless Sensor Networks (WSNs) have had a lot of attention in recent years. In much of this research tasks like sensor data processing, environment states and events decision making and emergency message sending are done by a remote server. A proposed cross layer protocol for two different applications where, reliability for delivered data, delay and life time of the network need to be considered, has been simulated and the results are presented in this paper. A WSN designed for the proposed applications needs efficient MAC and routing protocols to provide a guarantee for the reliability of the data delivered from source nodes to the sink. A cross layer based on the design given in [1] has been extended and simulated for the proposed applications, with new features, such as routes discovery algorithms added. Simulation results show that the proposed cross layer based protocol can conserve energy for nodes and provide the required performance such as life time of the network, delay and reliability.

Reverse Engineering tools: development and experimentation of innovative methods for physical and geometrical data integration and post-processing

In recent years, the use of Reverse Engineering systems has got a considerable interest for a wide number of applications. Therefore, many research activities are focused on accuracy and precision of the acquired data and post processing phase improvements. In this context, this PhD Thesis deals with the definition of two novel methods for data post processing and data fusion between physical and geometrical information. In particular a technique has been defined for error definition in 3D points’ coordinates acquired by an optical triangulation laser scanner, with the aim to identify adequate correction arrays to apply under different acquisition parameters and operative conditions. Systematic error in data acquired is thus compensated, in order to increase accuracy value. Moreover, the definition of a 3D thermogram is examined. Object geometrical information and its thermal properties, coming from a thermographic inspection, are combined in order to have a temperature value for each recognizable point. Data acquired by an optical triangulation laser scanner are also used to normalize temperature values and make thermal data independent from thermal-camera point of view.

Optimización de la Exactitud Geométrica al Integrar Diversas Fuentes de Datos en Proyectos de Inventario Forestal Basados en Escaneo Laser Aerotransportado=Optimizing Geometric Accuracy in Data Source Integration for Airborne Laser Scanning-based Forest Inventory Projects

La mayoría de las aplicaciones forestales del escaneo laser aerotransportado (ALS, del inglés airborne laser scanning) requieren la integración y uso simultaneo de diversas fuentes de datos, con el propósito de conseguir diversos objetivos. Los proyectos basados en sensores remotos normalmente consisten en aumentar la escala de estudio progresivamente a lo largo de varias fases de fusión de datos: desde la información más detallada obtenida sobre un área limitada (la parcela de campo), hasta una respuesta general de la cubierta forestal detectada a distancia de forma más incierta pero cubriendo un área mucho más amplia (la extensión cubierta por el vuelo o el satélite). Todas las fuentes de datos necesitan en ultimo termino basarse en las tecnologías de sistemas de navegación global por satélite (GNSS, del inglés global navigation satellite systems), las cuales son especialmente erróneas al operar por debajo del dosel forestal. Otras etapas adicionales de procesamiento, como la ortorectificación, también pueden verse afectadas por la presencia de vegetación, deteriorando la exactitud de las coordenadas de referencia de las imágenes ópticas. Todos estos errores introducen ruido en los modelos, ya que los predictores se desplazan de la posición real donde se sitúa su variable respuesta. El grado por el que las estimaciones forestales se ven afectadas depende de la dispersión espacial de las variables involucradas, y también de la escala utilizada en cada caso. Esta tesis revisa las fuentes de error posicional que pueden afectar a los diversos datos de entrada involucrados en un proyecto de inventario forestal basado en teledetección ALS, y como las propiedades del dosel forestal en sí afecta a su magnitud, aconsejando en consecuencia métodos para su reducción. También se incluye una discusión sobre las formas más apropiadas de medir exactitud y precisión en cada caso, y como los errores de posicionamiento de hecho afectan a la calidad de las estimaciones, con vistas a una planificación eficiente de la adquisición de los datos. La optimización final en el posicionamiento GNSS y de la radiometría del sensor óptico permitió detectar la importancia de este ultimo en la predicción de la desidad relativa de un bosque monoespecífico de Pinus sylvestris L. ABSTRACT Most forestry applications of airborne laser scanning (ALS) require the integration and simultaneous use of various data sources, pursuing a variety of different objectives. Projects based on remotely-sensed data generally consist in upscaling data fusion stages: from the most detailed information obtained for a limited area (field plot) to a more uncertain forest response sensed over a larger extent (airborne and satellite swath). All data sources ultimately rely on global navigation satellite systems (GNSS), which are especially error-prone when operating under forest canopies. Other additional processing stages, such as orthorectification, may as well be affected by vegetation, hence deteriorating the accuracy of optical imagery’s reference coordinates. These errors introduce noise to the models, as predictors displace from their corresponding response. The degree to which forest estimations are affected depends on the spatial dispersion of the variables involved and the scale used. This thesis reviews the sources of positioning errors which may affect the different inputs involved in an ALS-assisted forest inventory project, and how the properties of the forest canopy itself affects their magnitude, advising on methods for diminishing them. It is also discussed how accuracy should be assessed, and how positioning errors actually affect forest estimation, toward a cost-efficient planning for data acquisition. The final optimization in positioning the GNSS and optical image allowed to detect the importance of the latter in predicting relative density in a monospecific Pinus sylvestris L. forest.

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks

Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

Projected sequential Gaussian processes: flexible interpolation for large data sets

Recently within the machine learning and spatial statistics communities many papers have explored the potential of reduced rank representations of the covariance matrix, often referred to as projected or fixed rank approaches. In such methods the covariance function of the posterior process is represented by a reduced rank approximation which is chosen such that there is minimal information loss. In this paper a sequential framework for inference in such projected processes is presented, where the observations are considered one at a time. We introduce a C++ library for carrying out such projected, sequential estimation which adds several novel features. In particular we have incorporated the ability to use a generic observation operator, or sensor model, to permit data fusion. We can also cope with a range of observation error characteristics, including non-Gaussian observation errors. Inference for the variogram parameters is based on maximum likelihood estimation. We illustrate the projected sequential method in application to synthetic and real data sets. We discuss the software implementation and suggest possible future extensions.

Novel online data cleaning protocols for data streams in trajectory, Wireless Sensor Networks

The promise of Wireless Sensor Networks (WSNs) is the autonomous collaboration of a collection of sensors to accomplish some specific goals which a single sensor cannot offer. Basically, sensor networking serves a range of applications by providing the raw data as fundamentals for further analyses and actions. The imprecision of the collected data could tremendously mislead the decision-making process of sensor-based applications, resulting in an ineffectiveness or failure of the application objectives. Due to inherent WSN characteristics normally spoiling the raw sensor readings, many research efforts attempt to improve the accuracy of the corrupted or "dirty" sensor data. The dirty data need to be cleaned or corrected. However, the developed data cleaning solutions restrict themselves to the scope of static WSNs where deployed sensors would rarely move during the operation. Nowadays, many emerging applications relying on WSNs need the sensor mobility to enhance the application efficiency and usage flexibility. The location of deployed sensors needs to be dynamic. Also, each sensor would independently function and contribute its resources. Sensors equipped with vehicles for monitoring the traffic condition could be depicted as one of the prospective examples. The sensor mobility causes a transient in network topology and correlation among sensor streams. Based on static relationships among sensors, the existing methods for cleaning sensor data in static WSNs are invalid in such mobile scenarios. Therefore, a solution of data cleaning that considers the sensor movements is actively needed. This dissertation aims to improve the quality of sensor data by considering the consequences of various trajectory relationships of autonomous mobile sensors in the system. First of all, we address the dynamic network topology due to sensor mobility. The concept of virtual sensor is presented and used for spatio-temporal selection of neighboring sensors to help in cleaning sensor data streams. This method is one of the first methods to clean data in mobile sensor environments. We also study the mobility pattern of moving sensors relative to boundaries of sub-areas of interest. We developed a belief-based analysis to determine the reliable sets of neighboring sensors to improve the cleaning performance, especially when node density is relatively low. Finally, we design a novel sketch-based technique to clean data from internal sensors where spatio-temporal relationships among sensors cannot lead to the data correlations among sensor streams.

Adaptive Sampling with Mobile Sensor Networks

Mobile sensor networks have unique advantages compared with wireless sensor networks. The mobility enables mobile sensors to flexibly reconfigure themselves to meet sensing requirements. In this dissertation, an adaptive sampling method for mobile sensor networks is presented. Based on the consideration of sensing resource constraints, computing abilities, and onboard energy limitations, the adaptive sampling method follows a down sampling scheme, which could reduce the total number of measurements, and lower sampling cost. Compressive sensing is a recently developed down sampling method, using a small number of randomly distributed measurements for signal reconstruction. However, original signals cannot be reconstructed using condensed measurements, as addressed by Shannon Sampling Theory. Measurements have to be processed under a sparse domain, and convex optimization methods should be applied to reconstruct original signals. Restricted isometry property would guarantee signals can be recovered with little information loss. While compressive sensing could effectively lower sampling cost, signal reconstruction is still a great research challenge. Compressive sensing always collects random measurements, whose information amount cannot be determined in prior. If each measurement is optimized as the most informative measurement, the reconstruction performance can perform much better. Based on the above consideration, this dissertation is focusing on an adaptive sampling approach, which could find the most informative measurements in unknown environments and reconstruct original signals. With mobile sensors, measurements are collect sequentially, giving the chance to uniquely optimize each of them. When mobile sensors are about to collect a new measurement from the surrounding environments, existing information is shared among networked sensors so that each sensor would have a global view of the entire environment. Shared information is analyzed under Haar Wavelet domain, under which most nature signals appear sparse, to infer a model of the environments. The most informative measurements can be determined by optimizing model parameters. As a result, all the measurements collected by the mobile sensor network are the most informative measurements given existing information, and a perfect reconstruction would be expected. To present the adaptive sampling method, a series of research issues will be addressed, including measurement evaluation and collection, mobile network establishment, data fusion, sensor motion, signal reconstruction, etc. Two dimensional scalar field will be reconstructed using the method proposed. Both single mobile sensors and mobile sensor networks will be deployed in the environment, and reconstruction performance of both will be compared.In addition, a particular mobile sensor, a quadrotor UAV is developed, so that the adaptive sampling method can be used in three dimensional scenarios.

Intelligent prognostics of machinery health utilising suspended condition monitoring data

The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models for forecasting machinery health based on condition data. Although these models have aided the advancement of the discipline, they have made only a limited contribution to developing an effective machinery health prognostic system. The literature review indicates that there is not yet a prognostic model that directly models and fully utilises suspended condition histories (which are very common in practice since organisations rarely allow their assets to run to failure); that effectively integrates population characteristics into prognostics for longer-range prediction in a probabilistic sense; which deduces the non-linear relationship between measured condition data and actual asset health; and which involves minimal assumptions and requirements. This work presents a novel approach to addressing the above-mentioned challenges. The proposed model consists of a feed-forward neural network, the training targets of which are asset survival probabilities estimated using a variation of the Kaplan-Meier estimator and a degradation-based failure probability density estimator. The adapted Kaplan-Meier estimator is able to model the actual survival status of individual failed units and estimate the survival probability of individual suspended units. The degradation-based failure probability density estimator, on the other hand, extracts population characteristics and computes conditional reliability from available condition histories instead of from reliability data. The estimated survival probability and the relevant condition histories are respectively presented as “training target” and “training input” to the neural network. The trained network is capable of estimating the future survival curve of a unit when a series of condition indices are inputted. Although the concept proposed may be applied to the prognosis of various machine components, rolling element bearings were chosen as the research object because rolling element bearing failure is one of the foremost causes of machinery breakdowns. Computer simulated and industry case study data were used to compare the prognostic performance of the proposed model and four control models, namely: two feed-forward neural networks with the same training function and structure as the proposed model, but neglected suspended histories; a time series prediction recurrent neural network; and a traditional Weibull distribution model. The results support the assertion that the proposed model performs better than the other four models and that it produces adaptive prediction outputs with useful representation of survival probabilities. This work presents a compelling concept for non-parametric data-driven prognosis, and for utilising available asset condition information more fully and accurately. It demonstrates that machinery health can indeed be forecasted. The proposed prognostic technique, together with ongoing advances in sensors and data-fusion techniques, and increasingly comprehensive databases of asset condition data, holds the promise for increased asset availability, maintenance cost effectiveness, operational safety and – ultimately – organisation competitiveness.

A stochastic model for natural feature representation

This paper presents a robust stochastic model for the incorporation of natural features within data fusion algorithms. The representation combines Isomap, a non-linear manifold learning algorithm, with Expectation Maximization, a statistical learning scheme. The representation is computed offline and results in a non-linear, non-Gaussian likelihood model relating visual observations such as color and texture to the underlying visual states. The likelihood model can be used online to instantiate likelihoods corresponding to observed visual features in real-time. The likelihoods are expressed as a Gaussian Mixture Model so as to permit convenient integration within existing nonlinear filtering algorithms. The resulting compactness of the representation is especially suitable to decentralized sensor networks. Real visual data consisting of natural imagery acquired from an Unmanned Aerial Vehicle is used to demonstrate the versatility of the feature representation.