Data Fusion Applications Research Articles

An Improved Belief Entropy and Its Application in Decision-Making

Uncertainty measure in data fusion applications is a hot topic; quite a few methods have been proposed to measure the degree of uncertainty in Dempster-Shafer framework. However, the existing methods pay little attention to the scale of the frame of discernment (FOD), which means a loss of information. Due to this reason, the existing methods cannot measure the difference of uncertain degree among different FODs. In this paper, an improved belief entropy is proposed in Dempster-Shafer framework. The proposed belief entropy takes into consideration more available information in the body of evidence (BOE), including the uncertain information modeled by the mass function, the cardinality of the proposition, and the scale of the FOD. The improved belief entropy is a new method for uncertainty measure in Dempster-Shafer framework. Based on the new belief entropy, a decision-making approach is designed. The validity of the new belief entropy is verified according to some numerical examples and the proposed decision-making approach.

Applications of Multi-height Sensors Data Fusion and Fault-tolerant Kalman Filter in Integrated Navigation System of UAV

This paper presents a scheme for integrated navigation systems with applications of multi-height sensors data fusion and fault-tolerant Kalman filter(FTKF). It can complete data fusion for multi-height sensors, detect faulty sensors online and conduct fault tolerance in real time. First, implement optimal data fusion of multi-height sensors by weighted method based on output error variance of every height sensor. Then, a fault-tolerant Kalman filter scheme is designed, including three sub-filters(GPS/barometric altimeter /radar altimeter) and a main Kalman filter. The FTKF can detect and isolate the faulty sensors by using fault detection based on method of residuals Chi-Square test and state Chi-Square test with two state vectors propagators. The comparative analysis of simulation results in case of radar altimeter fault shows that the proposed scheme may achieve the expected fault-tolerant performance in integrated navigation system of UAV.

Application of Multiple Sensor Data Fusion for the Analysis of Human Dynamic Behavior in Space: Assessment and Evaluation of Mobility-Related Functional Impairments

The authors have applied a systems analysis approach to describe the musculoskeletal system as consisting of a stack of superimposed kinematic hier-archical segments in which each lower segment tends to transfer its motion to the other superimposed segments. This segmental chain enables the derivation of both conscious perception and sensory control of action in space. This applied systems analysis approach involves the measurements of the complex motor behavior in order to elucidate the fusion of multiple sensor data for the reliable and efficient acquisition of the kinetic, kinematics and electromyographic data of the human spatial behavior. The acquired kinematic and related kinetic signals represent attributive features of the internal recon-struction of the physical links between the superimposed body segments. In-deed, this reconstruction of the physical links was established as a result of the fusion of the multiple sensor data. Furthermore, this acquired kinematics, kinetics and electromyographic data provided detailed means to record, annotate, process, transmit, and display pertinent information derived from the musculoskeletal system to quantify and differentiate between subjects with mobility-related disabilities and able-bodied subjects, and enabled an inference into the active neural processes underlying balance reactions. To gain insight into the basis for this long-term dependence, the authors have applied the fusion of multiple sensor data to investigate the effects of Cerebral Palsy, Multiple Sclerosis and Diabetic Neuropathy conditions, on biomechanical/neurophysiological changes that may alter the ability of the human loco-motor system to generate ambulation, balance and posture.

A method to determine basic probability assignment in the open world and its application in data fusion and classification

Under the circumstance of the complete frame of discernment, There are quantities sufficient researches applying the Dempster-Shafer evidence theory (D-S theory) to process uncertain information. However, in most real cases, the frame of discernment is not complete, and the classic evidence theory is not applicable in some degree, including the basic probability assignment (BPA) generation method. In this paper, under the assumption of the open world, the BPA determination issue is focused originally, and a new method based on triangular fuzzy member is proposed to determine BPA. First, the mean value, standard deviation, extreme values as well as the triangular membership function of each attribute can be determined. Then, a nested structure BPA function with an assignment for the null set can be constructed, using the intersection point of one test sample and the models above. Experiments are conducted with the proposed method to determine BPA, through which the classification accuracy rates are computed, analyzed and compared with those generated by other BPA determination methods, which demonstrates the efficiency of the proposed method both in the open world and in the closed world.

Application of Data Fusion and Sensor Head Algorithm for Data Extraction from Wireless Sensor Networks

Objectives: The primary objective of the paper is to propose an optimized data extraction technique to obtain data from the Wireless Sensor Networks (WSNs)using ‘Sensor Head Algorithm’ and Data Fusion. Methods/Statistical Analysis: The proposed idea works in a three-layered architecture which includes the deployed sensors, the selected Sensor Head and the Static Data Sink. The Sensor Head Algorithm is used to select a sensor head that collects data from all sensors. The Data Fusion algorithm results in generation of unified data which is used to derive the output. Finally, the fused data is transmitted from the Sensor Head to the Static Data sink. Findings: A sample data was used to verify the working of the model using simulations. On the application of Sensor Head Algorithm, the sensors are assigned priorities on the basis of their residual energies. The sensor with highest residual energy becomes the Sensor Head. All the sensors transmit their data to the Sensor Head where the Data Fusion takes place later. Data Fusion initially removes redundancy in from the collected data making the processing simpler and saving the energy. The resultant data is then used to generate fused inference using Fuzzy Logic Controller (FLC). These inferences are recorded and later used to generate final output. The proposed idea ensures reduction of load on the system, simplifies the previously proposed methods, reduces latency in data collection and improves network lifetime. This data, finally transmitted to the static data sink, can be used for finding inferences or reaching a conclusion about the target area in the desired way. Application/Improvements: In the current paper, we have proposed an idea which we shall use to develop a fully functional model. Since, the proposed technique is concerned with data extraction, it can be applied to every situation where the Wireless Sensor Network is deployed.

Mobile agent itinerary planning for WSN data fusion: considering multiple sinks and heterogeneous networks

SummaryMobile agent (MA)‐based middleware has been thoroughly investigated in the past few years as a means to address the efficiency, scalability, and reliability issues of data fusion applications on wireless sensor networks. Deriving an efficient itinerary for each MA to follow is of high importance, because itineraries determine to a large extent the overall performance of data fusion tasks. In this article, we present a novel algorithmic approach for efficient itinerary planning of MA objects undertaking data fusion tasks. We adopt a method based on iterated local search to construct the itineraries (ie, visiting sequences of source nodes) assigned to multiple traveling MAs. We apply alternative optimization criteria which aim either at minimizing the overall energy expenditure over all derived MA itineraries or prolonging the network lifetime. Furthermore, we propose algorithmic solutions for 2 realistic settings which have not been investigated in the past: firstly, the employment of multiple sinks that share the responsibility of MA‐based data fusion tasks across the sensor field, and secondly, the consideration of heterogeneous sensor networks comprising nodes powerful enough to host the runtime environment required to execute MA code as well as “ordinary” nodes which lack these resources. Simulation tests verify the performance gain attained by our algorithmic methods against alternative itinerary planning approaches which involve multiple MAs. Copyright © 2016 John Wiley & Sons, Ltd.

A Novel Two-way Time Synchronization Protocol for Fusion Application

Data fusion application is one of the most popular applications in Wireless sensor networks (WSNs). Time synchronization is an important technology for data fusion applications due to its necessary for data fusion in the networks. Aimed at reliable time synchronization performance, this paper proposes a novel two-way time synchronization protocol (NTSP). Combing node’s clock model and two-way packet exchange mechanism, NTSP makes time synchronization protocol more precise and much steadier. NTSP adopts simulated annealing (SA) algorithm to defend random noise and malicious delay attacks. Network simulations are carried out to analyze performances of NTSP on time synchronization accuracy, convergent rate and defensive degree for malicious delay attacks. Comparing to traditional time synchronization protocols, NTSP is an effective time synchronization protocol in WSNs.

Vertical grid of retrieved atmospheric profiles

The choice of the vertical grid of atmospheric profiles retrieved from remote sensing observations is discussed considering the two cases of profiles used to represent the results of individual measurements and of profiles used for subsequent data fusion applications. An ozone measurement of the MIPAS instrument is used to assess, for different vertical grids, the quality of the retrieved profiles in terms of profile values, retrieval errors, vertical resolutions and number of degrees of freedom. In the case of individual retrievals no evident advantage is obtained with the use of a grid finer than the one with a reduced number of grid points, which are optimized according to the information content of the observations. Nevertheless, this instrument dependent vertical grid, which seems to extract all the available information, provides very poor results when used for data fusion applications. A loss of about a quarter of the degrees of freedom is observed when the data fusion is made using the instrument dependent vertical grid relative to the data fusion made using a vertical grid optimized for the data fusion product. This result is explained by the analysis of the eigenvalues of the Fisher information matrix and leads to the conclusion that different vertical grids must be adopted when data fusion is the expected application.

A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring

The wealth of complementary data available from remote sensing missions can hugely aid efforts towards accurately determining land use and quantifying subtle changes in land use management or intensity. This study reviewed 112 studies on fusing optical and radar data, which offer unique spectral and structural information, for land cover and use assessments. Contrary to our expectations, only 50 studies specifically addressed land use, and five assessed land use changes, while the majority addressed land cover. The advantages of fusion for land use analysis were assessed in 32 studies, and a large majority (28 studies) concluded that fusion improved results compared to using single data sources. Study sites were small, frequently 300–3000 km 2 or individual plots, with a lack of comparison of results and accuracies across sites. Although a variety of fusion techniques were used, pre-classification fusion followed by pixel-level inputs in traditional classification algorithms (e.g., Gaussian maximum likelihood classification) was common, but often without a concrete rationale on the applicability of the method to the land use theme being studied. Progress in this field of research requires the development of robust techniques of fusion to map the intricacies of land uses and changes therein and systematic procedures to assess the benefits of fusion over larger spatial scales.

Application of Fuzzy Data Fusion in Storage Environment Security Monitoring

In this paper, fuzzy set theory and multi-sensor data fusion technology are combined and applied in the safety monitoring of the storage environment, this paper establishes the sensor information fusion model and colligate incomplete information collected by multiple sensors, and eliminating the possible redundant and contradictory information among the multi sensor. After the analysis and process of the two level fusion model, the accurate estimation of the safe condition of the storage environment can be obtained. Finally, the method, which can effectively improve the reliability of the safe condition of the storage environment, is verified by an example.

RB Particle Filter Time Synchronization Algorithm Based on the DPM Model.

Time synchronization is essential for node localization, target tracking, data fusion, and various other Wireless Sensor Network (WSN) applications. To improve the estimation accuracy of continuous clock offset and skew of mobile nodes in WSNs, we propose a novel time synchronization algorithm, the Rao-Blackwellised (RB) particle filter time synchronization algorithm based on the Dirichlet process mixture (DPM) model. In a state-space equation with a linear substructure, state variables are divided into linear and non-linear variables by the RB particle filter algorithm. These two variables can be estimated using Kalman filter and particle filter, respectively, which improves the computational efficiency more so than if only the particle filter was used. In addition, the DPM model is used to describe the distribution of non-deterministic delays and to automatically adjust the number of Gaussian mixture model components based on the observational data. This improves the estimation accuracy of clock offset and skew, which allows achieving the time synchronization. The time synchronization performance of this algorithm is also validated by computer simulations and experimental measurements. The results show that the proposed algorithm has a higher time synchronization precision than traditional time synchronization algorithms.

Data Fusion in Metabolomics Using Coupled Matrix and Tensor Factorizations

With a goal of identifying biomarkers/patterns related to certain conditions or diseases, metabolomics focuses on the detection of chemical substances in biological samples such as urine and blood using a number of analytical techniques, including nuclear magnetic resonance (NMR) spectroscopy, liquid chromatography-mass spectrometry (LC–MS), and fluorescence spectroscopy. Data sets measured using these methods provide partly complementary information, and their joint analysis has the potential to reveal underlying structures, which are, otherwise, difficult to extract. While we can collect vast amounts of data using different analytical methods, data fusion remains a challenging task, in particular, when the goal is to capture the underlying factors and use them for interpretation, e.g., for biomarker identification. Furthermore, many data fusion applications require joint analysis of heterogeneous (i.e., in the form of higher order tensors and matrices) data sets with shared/unshared factors. In order to jointly analyze such heterogeneous data sets, we formulate data fusion as a coupled matrix and tensor factorization (CMTF) problem, which has already proved useful in many data mining applications, and discuss its extension to a structure-revealing data fusion model, i.e., a data fusion model that can identify shared and unshared factors. The traditional methods commonly used for data fusion in the presence of shared/unshared factors are matrix factorization-based methods. Using both simulations and prototypical experimental coupled data sets, we assess the performance of various state-of-the-art data fusion methods and demonstrate that while matrix factorization-based approaches have limitations when used for joint analysis of heterogeneous data sets, the structure-revealing CMTF model can successfully capture the underlying factors by exploiting the low-rank structure of higher order data sets.

Determining Basic Probability Assignment Based on the Improved Similarity Measures of Generalized Fuzzy Numbers

Dempster-Shafer theory of evidence has been widely used in many data fusion application systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, is still an open issue. In this paper, an improved method to determine the similarity measure between generalized fuzzy numbers is presented. The proposed method can overcome the drawbacks of the existing similarity measures. Then, we propose a new method for obtaining basic probability assignment (BPA) based on the proposed similarity measure method between generalized fuzzy numbers. Finally, the efficiency of the proposed method is illustrated by the classification of Iris data.

Chemometric classification of Chinese lager beers according to manufacturer based on data fusion of fluorescence, UV and visible spectroscopies

We report an application of data fusion for chemometric classification of 135 canned samples of Chinese lager beers by manufacturer based on the combination of fluorescence, UV and visible spectroscopies. Right-angle synchronous fluorescence spectra (SFS) at three wavelength difference Δλ=30, 60 and 80nm and visible spectra in the range 380–700nm of undiluted beers were recorded. UV spectra in the range 240–400nm of diluted beers were measured. A classification model was built using principal component analysis (PCA) and linear discriminant analysis (LDA). LDA with cross-validation showed that the data fusion could achieve 78.5–86.7% correct classification (sensitivity), while those rates using individual spectroscopies ranged from 42.2% to 70.4%. The results demonstrated that the fluorescence, UV and visible spectroscopies complemented each other, yielding higher synergic effect.

The Study of Prognostic and Health Management System for Smart Grid Based on Wireless Sensor Networks

This paper studies prognostic and health management (PHM) system for smart grid based on wireless sensor networks. The system function is analyzed firstly. Then, problems like networking hardware selection and data processing method have been discussed. The application of data fusion is discussed specially. In the end, the system platform based on a data-centric hierarchical technology architecture is designed with four layers: network configuration layer, network communication layer, platform basis layer and application layer. The research work of this paper is theoretical support for the realization of PHM for smart grid and the application of WSNs in smart grid.

An Integrated Model for Robust Multisensor Data Fusion

This paper presents an integrated model aimed at obtaining robust and reliable results in decision level multisensor data fusion applications. The proposed model is based on the connection of Dempster-Shafer evidence theory and an extreme learning machine. It includes three main improvement aspects: a mass constructing algorithm to build reasonable basic belief assignments (BBAs); an evidence synthesis method to get a comprehensive BBA for an information source from several mass functions or experts; and a new way to make high-precision decisions based on an extreme learning machine (ELM). Compared to some universal classification methods, the proposed one can be directly applied in multisensor data fusion applications, but not only for conventional classifications. Experimental results demonstrate that the proposed model is able to yield robust and reliable results in multisensor data fusion problems. In addition, this paper also draws some meaningful conclusions, which have significant implications for future studies.

A comparison of STARFM and an unmixing-based algorithm for Landsat and MODIS data fusion

The focus of the current study is to compare data fusion methods applied to sensors with medium- and high-spatial resolutions. Two documented methods are applied, the spatial and temporal adaptive reflectance fusion model (STARFM) and an unmixing-based method which proposes a Bayesian formulation to incorporate prior spectral information. Furthermore, the strengths of both algorithms are combined in a novel data fusion method: the Spatial and Temporal Reflectance Unmixing Model (STRUM). The potential of each method is demonstrated using simulation imagery and Landsat and MODIS imagery. The theoretical basis of the algorithms causes STARFM and STRUM to produce Landsat-like reflectances while preserving the spatial patterns found in Landsat images, and the unmixing-based method to produce MODIS-like reflectances. The ability of fused images to capture phenological variations is also assessed using temporal NDVI profiles. Temporal profiles of STARFM NDVI closely resembled Landsat NDVI profiles. However, the unmixing-based method and STRUM produced a more accurate reconstruction of the NDVI trajectory in experiments simulating situations where few input high-resolution images are available. STRUM had the best performance as it produced surface reflectances which had the highest correlations to reference Landsat images. The results of this study indicate that STRUM is more suitable for data fusion applications requiring Landsat-like surface reflectances, such as gap-filling and cloud masking, especially in situations where few high-resolution images are available. Unmixing-based data fusion is recommended in situations which downscale the spectral characteristics of the medium-resolution input imagery and the STARFM method is recommended for constructing temporal profiles in applications containing many input high-resolution images.

Research on Technology and Application of Multi-Sensor Data Fusion for Indoor Service Robots

The autonomous navigation process of a mobile service robot is usually in uncertain environment. The information only given by sensors has been unable to meet the demand of the modern mobile robots, so multi-sensor data fusion has been widely used in the field of robots. The platform of this project is the achievement of the important 863 Program national research project-a prototype nursing robot. The aim is to study a mobile service robot’s multi-sensor information fusion, path planning and movement control method. It can provide a basis and practical use’s reference for the study of an indoor robot’s localization.

Research of Multi-Source Data Fusion in Power Grid Planning

To meet the growing requirement of multi-source data handling, this paper carries out the application and research of data fusion technique in network planning. The fundamental theory hierarchy of data fusion working for power system planning is established, basing on it this paper analyses the fusion model in power system planning, and then designs an application case to explain the concrete fusion process. It is proved that the application of multi-source data fusion helps to make a fuller and more effective use of the massive information resource of data systems, so that the planning decision is more reasonable.

Error and Noise Analysis in an IMU using Kalman Filter

Kalman filtering is a well-established methodology used in various multi-sensor data fusion applications. In our experiment, we first obtain measurements from the accelerometer and gyroscope and fuse them using Kalman filter in an inertial measurement unit (IMU). We estimate Kalman filter output and estimation error. The affect of process noise and measurement noise on estimation error is tested. It is explored that the measurement noise has significant role to increase estimation error in the data fusion process.