Concept Of Data Fusion Research Articles

Construction of an Intelligent Processing Platform for Equestrian Event Information Based on Data Fusion and Data Mining

In the past two years, equestrian sports have become more and more popular with the public. Due to the comprehensive development of equestrian preparations for the 2020 Olympic Games in China, the equestrian sports industry presents an unprecedented favorable development environment in China. This article is aimed at studying the construction of an equestrian event information intelligent processing platform based on data fusion and data mining. This article introduces the relevant theoretical knowledge of data mining and data fusion, including the description of the concept of data mining, the common analysis methods and algorithms of data mining, the basic concepts of data fusion, and the functional structure of data fusion. It discusses various algorithms in cluster analysis and focuses on the analysis of distance measurement and similarity coefficient in cluster analysis. In the experimental part, in order to intelligently process and acquire information, an information intelligent processing platform is constructed based on data fusion and data mining technology. The experimental results of this paper show that the precision rate, recall rate, and F‐score of the platform under closed test are much higher than those under open test, and the precision rate is increased by about 7.26%.

Modelling of smart intelligent materials with PZT & PVDF sensors/actuators to control the active vibrations of flexible aluminum mechanical cantilever beams using proportional integral derivative (PID) techniques

Modelling of smart intelligent materials with PZT & PVDF sensors / actuators to control the active vibrations of flexible aluminum mechanical cantilever beams using PID techniques is presented in this research article. A multi input multi output beam (flexible cantilever beam) is considered as the single point of attraction and this is the plant, which is to be subjected to the vibrations, this could be treated as the wing of an aircraft attached to the hub. The flexible mechanical aluminium cantilever beam is subjected to vibrations, say an external force being acted upon by the wind pressure or an exciter. Smart materials have got some special properties that react to the changes in their environmental conditions. The beam is subjected to vibrations. These vibrations should be suppressed in no time, else, the plant may get damaged. Hence, we put piezoelectric (PZT) and poly vinyl derylene fluoride (PVDF) sensor and actuators at 2 different positions to sense the vibrations and act upon immediately to neutralize it. The PZT sensors sense the vibrations & the actuators give an actuating signal to the controller, which in turn generates anti signals to neutralize the effect of the primary source of vibration. We have used the multi-sensor data fusion concept as if we use the same sensor and actuator, we may not get good results. Mathematical modelling of sensor and actuators of the 2 types is done, this is used to design the PID controller to suppress the vibrations in no time. The paper shows the effect of the multi sensor actuator pair of smart intelligent materials used in the vibration suppression. The work done can also compared with others to show the authenticity or the profoundness of the methodology proposed with the help of materials used in the theory of material science.

Use of smart intelligent sensor & actuator mechanical materials (PVDF / PZT) in developing MIMO mathematical model of the smart structure and its use to control the active vibrations using discrete sliding mode control theory with output samples

A multi-input, multi-output based modelling of intelligent flexible mechanical aluminium structures using smart materials with Euler-Bernoulli beam theory & state space techniques is being presented with multi-sensor data fusion concepts. An aluminium cantilever beam of rectangular cross section with known specifications is considered for the modelling purposes. To start with, from the fundamental principles of E-B theory, a Lagrange equation of motion is obtained both for the regular beam element as well as for the PZT & PVDF sensor actuator pair. Following which, a dynamic equation of motion of the smart intelligent structure developed using the smart materials consisting of PZT& PVDF is obtained. The dynamic equation is transformed into a state space model with 2 i/o’s using the concepts of state space theory in control engineering. The model is developed considering the first 2 modes of vibration, which are the most dominant modes in the vibration theory. The developed state space model is used for active vibration control. An external force of 1 N is applied at the end of the smart flexible multivariable multimodel cantilever beam after which the beam is subjected to vibrations. A Discrete Sliding Mode Control (DSMC) based controller on the o/p samples is designed and put in loop with the plant, after which the plant vibrations decays to zero in no time. The mathematical model of the DSMC controller is used to control the vibrations of the plant using the concept of destructive interference. The mathematical model of the DSMC controller can be used to control the vibrations of the plant using the concept of destructive interference.

Improving Data Quality of Low-cost IoT Sensors in Environmental Monitoring Networks Using Data Fusion and Machine Learning Approach

Abstract Environmental monitoring has become an active research area due to the current rise in the global climate change crises. Current environmental monitoring solutions, however, are characterized by high cost of acquisition and complexity of installation; often requiring extensive resources, infrastructure and expertise. It is infeasible to achieve with these solutions, high density in-situ networks such as are required to build refined scale models to facilitate robust monitoring, thus, leaving large gaps within the collected dataset. Low-Cost Sensors (LCS) can offer high-resolution spatiotemporal measurements which could be used to supplement existing dataset from current environmental monitoring solutions. LCS however, require frequent calibration in order to provide accurate and reliable data as they are often affected by environmental conditions when deployed on the field. Calibrating LCS can help to improve their data quality and ensure they are collecting accurate data. Achieving effective calibration, however, requires identifying factors that affect sensor’s data quality for a given measurement. This study evaluates the performance of three Feature Selection (FS) algorithms including Forward Feature Selection (FFS), Backward Elimination (BE) and Exhaustive Feature Selection (EFS) in identifying factors that affect data quality of low-cost IoT sensors in environmental monitoring networks. Applying the concept of data fusion, sensors data were merged with environmental factors and integrated into a single calibration equation to calibrate cairclipO3/NO2 and cairclipNO2 sensors using Linear Regression (LR) and Artificial Neural Networks (ANN). The study showed the effectiveness of calibration in improving low-cost IoT sensor data quality and also demonstrated the convenience of feature selection and the ability of data fusion to provide more consistent, accurate and reliable information for calibration models. The analysis showed that the cairclipO3/NO2 sensor provided measurements that have good correlation with reference measurements whereas the cairclipNO2 sensor showed no reasonable correlation with the reference data. Calibrating the cairclipO3/NO2 yielded good improvement in its measurement outputs when compared to reference measurements (R2=0.83). However, calibrating the cairclipNO2 sensor data yielded no significant improvement in its data quality.

Development of mathematical model for smart intelligent flexible structures using smart intelligent sensor & actuator materials using Timoshenko beam theory & its control using POF

In this research paper, the multivariable modelling of intelligent flexible aerospace structures using smart materials with Timoshenko beam theory & state space techniques with multi-sensor data fusion concept & its control using POF strategy is presented in n this research article. Finite Element Method is used in the analysis also. An aerospace aluminum cantilever beam of rectangular cross section with known specifications is considered for the modelling purposes. To start with from the fundamental principles of Timoshenko beam theory, a Lagrange equation of motion is obtained both for the regular beam element as well as for the PZT & PVDF sensor actuator pair. Following which, a dynamic equation of motion of the smart intelligent structure developed using the smart materials consisting of PZT & PVDF is obtained. Smart materials have got some special properties that react to the changes in their environmental conditions. This means that some of their special properties can be changed by using an external condition, such as temperature, light, pressure, electricity, voltage, pH, or chemical compounds, which could be considered as the special characteristics and this change is reversible, which can be repeated many times. The dynamic equation is transformed into a state space model with 2 inputs and 2 outputs using the concepts of state space theory in the advanced control engineering. The model is developed considering the first 2 modes of vibration, which are the most dominant modes in the vibration theory. The developed state space model is used for active vibration control. The effect of shear is considered in modelling here, which is neglected in case of Euler – Beam theory, thus giving an accurate beam model. An external force of 1 N is applied at the end of the smart flexible multivariable multimodel cantilever beam after which the beam is subjected to vibrations. A POF controller can be designed and put in loop with the plant, after which the plant vibrations decays to zero in no time. The mathematical model of the POF controller can be used to control the vibrations of the plant using the concept of destructive interference. The work done can also be compared with others to show the authenticity or the profoundness of the methodology that is being developed by us.

Multivariable modelling of intelligent flexible mechanical structures using smart materials with FEM, Euler-Bernoulli beam theory, state space & multi-sensor data fusion techniques

In this research paper, the multivariable modelling of intelligent flexible mechanical structures using smart materials with Euler-Bernoulli beam theory & state space techniques is being presented with multi-sensor data fusion concept. To start with from the fundamental principles of E-B theory, a Lagrange equation of motion is obtained both for the regular beam element as well as for the PZT & PVDF sensor actuator pair. Following which, a dynamic equation of motion of the smart intelligent structure developed using the smart materials consisting of PZT& PVDF is obtained. Smart materials have got some special properties that react to the changes in their environmental conditions. This means that some of their special properties can be changed by using an external condition, such as temperature, light, pressure, electricity, voltage, pH, or chemical compounds, which could be considered as the special characteristics and this change is reversible, which can be repeated many times. The dynamic equation is transformed into a state space model with 2 inputs and 2 outputs using the concepts of state space theory in the advanced control engineering. The model is developed considering the first 2 modes of vibration, which are the most dominant modes in the vibration theory. The developed state space model is used for active vibration control. An external force of 1 N is applied at the end of the smart flexible multivariable multimodel cantilever beam after which the beam is subjected to vibrations. A Periodic Output Feedback controller can be designed and put in loop with the plant, after which the plant vibrations decays to zero in no time. The work done can also compared with others to show the authenticity or the profoundness of the methodology that is being developed by us.

Universal hardware and software system of signal converting for integrated sensor devices implementation

The problem of developing a universal signal converter for the construction of integrated sensors in data fusion concept is solved. Considering the requirements of modern microcircuit technique, in particular for sensory devices of the Internet of Things, the signal path of the synthesized sensors is implemented based on PSoC of 5LP Family Cypress. The testing of the developed system was carried out in the process of realization the integrated sensors of thermal analysis, optoelectronics, magnetic tracking and impedance spectroscopy.

A mixture of views network with applications to multi-view medical imaging

This paper examines data fusion methods for multi-view data classification. We present a decision concept that explicitly takes into account the input multi-view structure, where for each case there is a different subset of relevant views. This data fusion concept, which we dub Mixture of Views, is implemented by a special purpose neural network architecture. The single view decisions are combined by a data-driven decision, into a global decision according to the relevance of each view in a given case. The method was applied to two challenging computer-aided diagnosis (CADx) tasks: the task of classifying breast microcalcifications as benign or malignant based on craniocaudal (CC) and mediolateral oblique (MLO) mammography views and segmenting Multiple Sclerosis (MS) white matter lesions. The experimental results show that our method outperforms previously suggested fusion methods.

A heterogeneous benchmark dataset for data analytics: Multiphase flow facility case study

Improvements in sensing, connectivity and computing technologies mean that industrial processes now generate data from a variety of disparate sources. Data may take a number of forms, from time-domain signals, sampled at various rates using a variety of sensors, to alarm and event logs. Novel techniques need to be developed to tackle the challenges of heterogeneous data. Testing such algorithms requires benchmark datasets that allow direct comparison of the performance of the methods. This work presents the PRONTO heterogeneous benchmark dataset. Experiments were conducted on a multiphase flow facility under various operational conditions with and without induced faults. Data were collected from heterogeneous sources, including process measurements, alarm records, high frequency ultrasonic flow and pressure measurements. The presented dataset is suitable for developing and validating algorithms for fault detection and diagnosis and data fusion concepts. Three algorithms are tested using the dataset, illustrating the applicability of the dataset.

A New Correlation Coefficient Based on Generalized Information Quality

How to manage conflict is still an open issue in Dempster-Shafer (D-S) evidence theory. The conflict coefficient k in D-S evidence theory cannot represent conflict reasonably, especially sometimes two Basic Probability Assignments (BPAs) are identical but k is not zero. Generalized information quality, as a concept of data fusion, can effectively measure the uncertainty of BPA. However, how to use the generalized information quality to manage conflicts is still an open question. Therefore, this paper proposed a new correlation coefficient based on generalized information quality to manage conflict. This method can better reflect the correlation coefficient between BPA. Numerical examples are used to demonstrate the effectiveness of the correlation coefficient based on generalized information quality. In addition, a weighted average combination rule based on the new correlation coefficient is presented. A numerical example in target recognition is illustrated to show its validity in combining conflicting evidence.

Non-uniform Quantized Data Fusion Rule for Data Rate Saving and Reducing Control Channel Overhead for Cooperative Spectrum Sensing in Cognitive Radio Networks

In this paper a pretty new concept of non-uniform quantized data fusion (N-QDF) rule reducing control channel data overhead has been proposed for energy detection based cooperative spectrum sensing scheme in cognitive radio networks. To strike a balance between efficient detection performance and less complexity, the network has to allow soften hard or quantized data fusion (QDF) technique though this technique incurs few bit overhead on the control channel from each user. Again lower bit QDF causes loss of more information, where as higher bit QDF increases detection probability at the cost of some extra bits per user. Here lies the beauty of NQDF scheme which uses variable number of bits: more number of bits for lower energy region—thus increases detection probability for a given false alarm, and less number of bits for higher energy region—thus data rate gets saved which in turn alleviates control channel overhead. A holistic simulation study has been done in this very paper where the performance of variable bit NQDF scheme is compared with different uniform bit i.e. 2, 3, 4, 5 QDF with respect to different parameters to validate our proposed scheme.

An experimental framework for future smart cities using data fusion and software defined systems: The case of environmental monitoring for smart healthcare

With the evolution of the concept of Internet into the Internet-of-Things (IoT), in which sensors, devices, and everyday objects (things), are interconnected through the Internet, a large number of interconnected things are expected to produce massive amounts of data, which needs efficient processing in order to provide various services. IoT is of little worth without the ability to process, manage, and control a large amount of heterogeneous data in a timely and efficient manner. The concept of Data Fusion (DF) is based on combining heterogeneous multi-source data in order to produce high quality information, and reduce network traffic. On the other hand, the highly dynamic and heterogeneous nature of IoT requires very flexible and efficient management. The recent software defined systems paradigm is an appealing solution to reduce complexity and overhead in managing complex systems such as IoT by separating the control plane from the data plane. In this work, we present a novel experimental framework for IoT based environmental monitoring applications using concepts from DF and software defined systems (SDS). It is built on top of the software defined networking platform where the core components (the host, switch and the controller) are expanded to support other software defined systems components (such as software defined storage and security) and enable the applications of different DF techniques in IoT environments. We conduct several experiments to highlight features of the presented framework.

A context-aware data fusion approach for health-IoT

The technological advances in low-cost sensor devices and communication technologies bring rapid increase in development of smart homes and smart environments. The developments in wireless sensor networks (WSN), body area networks (BAN), cloud computing and big data technologies trigger the use of Internet of Things (IoT) in healthcare industry. This poses many challenges such as heterogeneous data fusion, context-awareness, complex query processing, reliability and accuracy etc. Data fusion techniques are used to extract meaningful information from heterogeneous IoT data. It combines individual data from sensor sources to collectively obtain a result, which is more reliable, accurate and complete. Apart from wearable sensors, additional context sensors need to be added to build a context. Health IoT applications has potential benefits of using context-aware data fusion. By using context information, the behavior of the application can be customized according to the specific situation. This paper provides a brief concept of context-aware data fusion and includes data management approach for context-aware systems for healthcare applications. Finally, a context-aware data fusion approach for health IoT is proposed. It includes context acquisition, situation building and reasoning and inference.

RETRACTED ARTICLE: Multimedia and multi-feature cluster fusion model based on saliency for mobile network applications

This paper introduces the concept, advantages, structure, method and application of multisensor integration and data fusion, and lists four different integration characteristics of sensors. Data fusion technology combines data from different sensors or other information sources in order to improve the accuracy of location and feature estimation. In the process of data fusion, modeling includes signal model, noise model, converter model, data transformation model and fusion model. The data fusion model includes the fusion method and the structure. This paper introduces the integrated, distributed and hybrid fusion structures, and compares them. The visual saliency map to image processing technology depends on the quality of the obtained good results, the existing visual saliency detection method is usually only detected by visual saliency map attribute rough, seriously affected the image processing results. Therefore, a visual saliency detection method based on Bayesian theory and statistical learning is proposed to detect the visual saliency of the image. The method is based on Bayesian theory of the significance of static images. According to the bottom-up visual saliency model, the ROC curve was used for quantitative evaluation in the two standard data sets. The results show that the nonlinear combination effect is better than the linear combination.

Evaluation of Goddard’s LiDAR, hyperspectral, and thermal data products for mapping urban land-cover types

Goddard’s LiDAR (Light Detection And Ranging), hyperspectral and thermal (G-LiHT) airborne imager is a new system to advance concepts of data fusion for worldwide applications. A recent G-LiHT mission conducted in June 2016 over an urban area opens a new opportunity to assess the G-LiHT products for urban land-cover mapping. In this study, the G-LiHT hyperspectral and LiDAR-canopy height model (LiDAR-CHM) products were evaluated to map five broad land-cover types. A feature/decision-level fusion strategy was developed to integrate two products. Contemporary data processing techniques were applied, including object-based image analysis, machine-learning algorithms, and ensemble analysis. Evaluation focused on the capability of G-LiHT hyperspectral products compared with multispectral data with similar spatial resolution, the contribution of LiDAR-CHM, and the potential of ensemble analysis in land-cover mapping. The results showed that there was no significant difference between the application of the G-LiHT hyperspectral product and simulated Quickbird data in the classification. A synthesis of G-LiHT hyperspectral and LiDAR-CHM products achieved the best result with an overall accuracy of 96.3% and a Kappa value of 0.95 when ensemble analysis was applied. Ensemble analysis of the three classifiers not only increased the classification accuracy but also generated an uncertainty map to show regions with a robust classification as well as areas where classification errors were most likely to occur. Ensemble analysis is a promising tool for land-cover classification.

Constraining a complex biogeochemical model for CO<sub>2</sub> and N<sub>2</sub>O emission simulations from various land uses by model–data fusion

Abstract. This study presents the results of a combined measurement and modelling strategy to analyse N2O and CO2 emissions from adjacent arable land, forest and grassland sites in Hesse, Germany. The measured emissions reveal seasonal patterns and management effects, including fertilizer application, tillage, harvest and grazing. The measured annual N2O fluxes are 4.5, 0.4 and 0.1 kg N ha−1 a−1, and the CO2 fluxes are 20.0, 12.2 and 3.0 t C ha−1 a−1 for the arable land, grassland and forest sites, respectively. An innovative model–data fusion concept based on a multicriteria evaluation (soil moisture at different depths, yield, CO2 and N2O emissions) is used to rigorously test the LandscapeDNDC biogeochemical model. The model is run in a Latin-hypercube-based uncertainty analysis framework to constrain model parameter uncertainty and derive behavioural model runs. The results indicate that the model is generally capable of predicting trace gas emissions, as evaluated with RMSE as the objective function. The model shows a reasonable performance in simulating the ecosystem C and N balances. The model–data fusion concept helps to detect remaining model errors, such as missing (e.g. freeze–thaw cycling) or incomplete model processes (e.g. respiration rates after harvest). This concept further elucidates the identification of missing model input sources (e.g. the uptake of N through shallow groundwater on grassland during the vegetation period) and uncertainty in the measured validation data (e.g. forest N2O emissions in winter months). Guidance is provided to improve the model structure and field measurements to further advance landscape-scale model predictions.

Sum-of-exponentials modeling and common dynamics estimation using Tensorlab

Fitting a signal to a sum-of-exponentials model is a basic problem in signal processing. It can be posed and solved as a Hankel structured low-rank matrix approximation problem. Subsequently, local optimization, subspace, and convex relaxation methods can be used for the numerical solution. In this paper, we show another approach, based on the recently developed concept of structured data fusion. Structured data fusion problems are solved in the Tensorlab toolbox by local optimization methods. The approach allows fitting of signals with missing samples and adding constraints on the model, such as fixed exponents and common dynamics in multi-channel estimation problems. These problems are non-trivial to solve by other existing methods. Tensorlab is publicly available and the results presented are reproducible.

The Research of Multi-sensor Data Fusion Technology

Multi-source information from multi-sensors is very important to command information system. Processed multi-source information can offer useful decision information to commander. On the basis of explaining concept, function and advantage of multi-sensor data fusion, the common model of the data fusion was introduced. Multi-sensor data fusion technologies and system structure of multi-sensor data fusion were analyzed.

Multi-sensor data fusion in the nondestructive measurement of kiwifruit texture

Abstract Three mechanical-based techniques, including falling impact (FAI), forced impact (FOI), and acoustic impulse-response (AIR), were implemented for the nondestructive prediction of the apparent modulus of elasticity (E a ) and Magness-Taylor firmness (MTf) of kiwifruit, cv. Hayward . Considering the merits and limitations of each method in estimating the texture parameters, this study tried to improve the performance of the predictive models by using the concept of multi-sensor data fusion. Two different fusion strategies, including low-level and mid-level fusions, were accordingly applied using partial least square regression (PLSR) and principal component analysis combined with artificial neural network (PCA-ANN), respectively. Better predictions of E a were obtained, as compared to those of MTf, in using each method, as well as their combinations in both fusion strategies, thereby demonstrating the better fitness of E a with the nondestructive data. Moreover, both fusion strategies enhanced the performance of E a and, in most cases, MTf predictive models, as compared with using each technique individually. Comparing two fused systems showed that the mid-level fusion was more effective than the low-level one, where in the best fused systems (integration of all three sensors), the standard deviation ratio (SDR) values for E a and MTf were improved by 11.2% and 9.1%, respectively, and the satisfactory results for both E a ( R 2 p = 0.926, SDR = 3.07) and MTf ( R 2 p = 0.841, SDR = 2.51) were obtained. This study revealed that compared to the implementation of mechanical-based methods individually, and also the low-level fusion of them, their mid-level fusion using PCA-ANN algorithm could be an effective approach for providing more detailed and complementary information about kiwifruit texture.

Data Fusion and Remote Sensing: An ever-growing relationship

Characterized by a certain focus on the heavily discussed topic of image fusion in its beginnings, sensor data fusion has played a significant role in the remote sensing research community for a long time. With this article, we aim to provide a short overview of established definitions, targeting a generalized understanding of the topic. In addition, a review of the state of the art of remote sensing data fusion research is given. By bringing together the conventional view expressed in the classical data fusion community and a review of current activities in the field of Earth observation, this article provides a holistic view of generic data fusion concepts and their applicability to the remote sensing domain.