Information Fusion Theory Research Articles

Analysis on dynamic feature of cross arm light weighting for photovoltaic panel cleaning device in power station based on power correlation

AbstractThe surface cleanliness of photovoltaic (PV) panel has an important impact on the efficiency of power generation. The excessive mass of cross arm has always affected the use of cleaning device. Based on the power correlation analysis, the dynamic characteristics of cross arm lightweight of PV panel cleaning device in the power station are proposed. Using the theory of information fusion to weigh it as a comprehensive influence factor, the power prediction value of the model output is transmitted to the cleaning device in real time: design the cleaning device of PV panel and optimize the topology of the mechanical cross arm. The experimental results show that the PV power is related to many meteorological factors, and the lightweight design of the cross arm is more conducive to the natural frequency and mode shape analysis of each mode of the cross arm structure.

An intelligent fault diagnosis approach based on Dempster-Shafer theory for hydraulic valves

Detecting faults in hydraulic valves are of great significance to improve the reliability and security of the whole hydraulic system. However, it is difficult to detect multiple faults in hydraulic valves using existing approaches due to closed structural components and complex hydraulic system itself. Therefore, an intelligent fault diagnosis approach based on Dempster-Shafer (DS) theory is proposed specifically for detecting several faults occurred in hydraulic valves. Actually, it is classified in the ensemble learning in terms of the information fusion theory. In this approach, signal segments containing fault information are selected to structure sample sets firstly. Then sample sets are simultaneously fed into the single classifier including long short-term memory networks (LSTM), convolutional neural network (CNN) and random forests (RF). Through learning spontaneously in these intelligent classification approaches, fault features are concluded and the probability of each type fault is respectively revealed. All probabilities are constructed as basic probability assignment (BPA) functions, which are further calculated in the information fusion process in terms of DS theory. Finally, the fault types are identified by the final fusion results. Experimental investigations are performed to validate performance of the present approach (taken a solenoid controlled pilot operated directional valve as an example). It is shown that the average accuracy ratio of proposed intelligent fault diagnosis approach is 98.5% for six fault types detection. The study does provide an effective access to detect faults in hydraulic valves.

M-BSRM: Multivariate BayeSian Runtime QoS Monitoring Using Point Mutual Information

Quality of Service (QoS) is well acknowledged as a decisive means for ascertaining the performance of third-party Web services. QoS has high uncertainty in complex and dynamic network environments. QoS monitoring is considered as one of the most effective techniques to detect QoS violations at runtime. However, existing QoS monitoring approaches only consider single QoS attribute and do not provide a promising solution for comprehensively monitoring multivariate QoS attributes. To overcome this problem, a novel QoS monitoring approach, named M-BSRM (Multivariate BayeSian Runtime Monitoring), is proposed. First, M-BSRM adopts the point mutual information theory to initialize the weights of different environmental impact factors and solves the problem of uneven distribution between classes brought by traditional algorithms. Second, each single QoS attribute is integrated with user preference using the information fusion theory. Finally, a Bayesian classifier is used to comprehensively evaluate multivariate QoS attributes at runtime. The experimental results on both the real-world and simulated data sets show that M-BSRM is more effective, practical and efficient than the other approaches.

Prediction of maximal water bursting discharge from coal seam floor based on multiple nonlinear regression analysis

Aimed at the influences of various complicated factors for water inrush from a coal seam floor during coal seam mining, the prediction of the maximal water bursting discharge from a coal seam floor is regarded as a problem of pattern identification with nonlinear, high dimensions, and finite samples. Based on information fusion theory and regarding the prediction of maximal water bursting discharge from a coal seam floor as a process of multisource information fusion and state estimation, an evaluation system of the main controlling factors for predicting the maximal water bursting discharge from a coal seam floor was established. An evaluation model for forecasting the maximal water bursting discharge from a coal seam floor was also structured according to multiple nonlinear regression theory. Considering the major coal mines of Xinwen coalfield as the research background, six factors are selected as the basic discriminant factors, i.e., aquifer thickness, unit water inflow, water pressure, aquiclude thickness, fault influencing factor, and depth of a coal seam floor destroyed by rock pressure. Deng’s grey relational theory was used to analyze the correlation degrees between each main controlling factor and the maximal water bursting discharge from a coal seam floor. A structural equation model was adopted to reveal the internal connecting links among the key influencing factors and determine the weights of each main controlling factor for predicting the maximal water bursting discharge from a coal seam floor. An SPSS scatter plot and MATLAB functional programming were applied to fit the correlativity curves between each main controlling factor and the maximal water bursting discharge from a coal seam floor in the Xinwen Mining Area. The optimal unitary nonlinear regression models between the maximal water bursting discharge from the coal seam floor and each main control factor were established. A multiple nonlinear regression–modified model for predicting the maximal water bursting discharge from the coal seam floor was acquired using a multiple nonlinear regression analysis with the combined weights of each main control factor. Compared with the bivariant multiple regression equation and the measured data, the results showed that the average values of forecasting errors predicted by the multiple nonlinear regression–modified model and bivariant multiple regression equation are 10.53% and 16.76%, respectively, which indicates that the multiple nonlinear regression–modified model and the bivariant multiple regression equation have higher prediction accuracy and relatively smaller error ranges, with comparatively better application value in the prediction of maximal water bursting discharge from a coal seam floor.

A Fusion Measurement Approach to Improve Quantum State Tomography Efficiency and Accuracy

Quantum state tomography (QST) is an important tool for estimating an unknown quantum state, which includes a measurement process and a reconstruction process. The state estimation error involves the measurement-induced (probability estimation) error in the measurement process and the calculation error in the reconstruction process. Via the mean-square error methods, we propose two fusion measurement schemes with multiple measurement devices (MMDs) to improve the efficiency and accuracy of quantum state measurement and QST by using information fusion theory. These two schemes are founded on the parallel synchronous measurements of MMDs and, therefore, can improve the efficiency of quantum state measurement and tomography. At the same time, by fusing measurement data from different measurement devices in optimal and suboptimal manners, the proposed multiple-measurement-device fusion measurement schemes achieve the improvement of quantum state measurement and tomography accuracy. Numerical simulations are presented to demonstrate the proposed method.

Gesture recognition algorithm based on image information fusion in virtual reality

Combining image information fusion theory with machine learning for biometric recognition is an important field in computer vision research in recent years. Based on this, a gesture recognition algorithm based on image information fusion in virtual reality is proposed. Firstly, it introduces the basic concepts and principles of virtual reality and information fusion technology, analyzes the characteristics and basic components of virtual environment system, points out the relationship between human and virtual environment and the impact of virtual environment on people, and gives a virtual reality. Then, the multi-sensor information fusion model of the virtual environment for gesture recognition is proposed. The membership degree and template matching algorithm are further selected for data correlation and gesture recognition in the fusion model. Finally, the design comparison experiment verifies the proposed method. The results show that the proposed multi-sensor information fusion model in the interactive virtual environment achieves the highest recognition success rate of 96.17% and is better than several comparison machine learning methods in recognition time.

A survey of type-2 fuzzy aggregation and application for multiple criteria decision making

Type-2 fuzzy sets (T2FSs) exhibit evident merits when it comes to representing the complex and high uncertainty, which has been encountered in fuzzy optimization and multiple criteria decision making (MCDM) problems. Since T2FSs theory was proposed by Zadeh in 1975, then a series of theories and methods were investigated by more scholars. Type-2 fuzzy aggregation operators, contributing to the fundamental information fusion theory, have been paid more attention and applied to different areas during the last two decades. In this paper, a survey of type-2 fuzzy aggregation and application for MCDM is carried out. We first review some basic knowledge including definitions, operations, type reduction and ranking methods of T2FSs. Then the definitions and properties of some main aggregation operators are introduced. Furthermore, some application categories under type-2 fuzzy environment are given. Finally, we identify some existing shortcomings and point at future research directions on this topic.

Intelligent acquisition model of traffic congestion information in the vehicle networking environment based on multi-sensor fusion

Aiming at the problems of low bandwidth, poor anti-interference ability and low-detection accuracy of traditional multi-path coherent vehicle network model, an intelligent acquisition model of traffic congestion information in vehicle network environment based on multi-features is proposed. The model clusters the traffic congestion information in the vehicle network and uses the multi-sensor fusion identification method to mine the traffic flow. In the vehicle networking environment, the vehicle traffic congestion information is analysed by information fusion theory, cross-fusion, text information, location information, image, audio, video and other information-aware technologies, and the coherent matching filter detector is used to realise the detection of traffic congestion information. And data collection, combined with knowledge base and database construction, is used to achieve intelligent collection and storage of traffic congestion information. The simulation results show that the model has high traffic congestion information acquisition accuracy and good feature matching ability, improves the intelligent acquisition ability, and detects the traffic congestion information in the vehicle network environment, thus guiding traffic scheduling.

Determination of ethanol content in ethanol-gasoline based on derivative absorption spectrometry and information fusion

The ethanol content in ethanol-gasoline is respectively detected by the first-order derivative UV/vis absorption spectrum, the first-order derivative near infrared (NIR) absorption spectrum and the information fusion method. The backward interval partial least squares (BiPLS) algorithm is used as the feature extraction method, which is established by the partial least squares (PLS) regression model. Based on the information fusion theory, the low level data fusion (LLDF) and mid-level data fusion (MLDF) models are established by the first-order derivative UV/vis and NIR spectra. The analytical results are compared with the related textual references. Thereby, the single-spectral model based on the first-order derivative NIR absorption spectrum has the optimal results, where R p 2 =0.999 1 and RMSEP=0.324 5, while the LLDF after vector normalization (LLDF-VN2) is the optimal multi-spectral fusion model, where R p 2 =0.998 3 and RMSEP=0.498 2. The proposed method can be used to detect the ethanol content in ethanol-gasoline rapidly and provides a better choice for the component detection in mixed oils.

Approaches to Multiple Attribute Decision Making with Interval-Valued 2-Tuple Linguistic Pythagorean Fuzzy Information

The Maclaurin symmetric mean (MSM) operator is a classical mean type aggregation operator used in modern information fusion theory, which is suitable to aggregate numerical values. The prominent characteristic of the MSM operator is that it can capture the interrelationship among multi-input arguments. Motivated by the ideal characteristic of the MSM operator, in this paper, we expand the MSM operator, generalized MSM (GMSM), and dual MSM (DMSM) operator with interval-valued 2-tuple linguistic Pythagorean fuzzy numbers (IV2TLPFNs) to propose the interval-valued 2-tuple linguistic Pythagorean fuzzy MSM (IV2TLPFMSM) operator, interval-valued 2-tuple linguistic Pythagorean fuzzy weighted MSM (IV2TLPFWMSM) operator, interval-valued 2-tuple linguistic Pythagorean fuzzy GMSM (IN2TLPFGMSM) operator, interval-valued 2-tuple linguistic Pythagorean fuzzy weighted GMSM (IV2TLPFWGMSM) operator, interval-valued 2-tuple linguistic Pythagorean fuzzy DMSM (IN2TLPFDMSM) operator, Interval-valued 2-tuple linguistic Pythagorean fuzzy weighted DMSM (IV2TLPFWDMSM) operator. Then the multiple attribute decision making (MADM) methods are developed with these three operators. Finally, an example of green supplier selection is used to show the proposed methods.

A fusion algorithm of target dynamic information for asynchronous multi-sensors

Radar and automatic identification system (AIS) are the important navigation equipment to obtain targets information in marine traffic. For obtaining more reliable and precise target information, it is necessary to develop a fusion method, where the target track correlation judgment and track fusion filtering are the key issue. In this investigation, we have proposed a target association algorithm of the radar and AIS based on the BP neural network algorithm and multi-sensor information fusion theory, and introduced the Kalman filter and particle filter to achieve the nonlinear track filter. By the simulation and analysis based on the measured data, it can be found that the algorithm will be accurately implemented the track correlation and effectively improve the track precision in this work.

Pythagorean Fuzzy Maclaurin Symmetric Mean Operators in Multiple Attribute Decision Making

The Maclaurin symmetric mean (MSM) operator is a classical mean type aggregation operator used in modern information fusion theory, which is suitable to aggregate numerical values. The prominent characteristic of the MSM operator is that it can capture the interrelationship among the multiinput arguments. In this paper, we extend MSM to Pythagorean fuzzy environment to propose the Pythagorean fuzzy Maclaurin symmetric mean and Pythagorean fuzzy weighted Maclaurin symmetric mean operators. Then, some desirable properties and special cases of these operators are discussed in detail. Finally, a numerical example is provided to illustrate the feasibility of the proposed methods and deliver a comparative analysis.

A sensor fusion and support vector machine based approach for recognition of complex machining conditions

During the machining process of thin-walled parts, machine tool wear and work-piece deformation always co-exist, which make the recognition of machining conditions very difficult. Existing machining condition monitoring approaches usually consider only one single condition, i.e., either tool wear or work-piece deformation. In order to close this gap, a machining condition recognition approach based on multi-sensor fusion and support vector machine (SVM) is proposed. A dynamometer sensor and an acceleration sensor are used to collect cutting force signals and vibration signals respectively. Wavelet decomposition is utilized as a signal processing method for the extraction of signal characteristics including means and variances of a certain degree of the decomposed signals. SVM is used as a condition recognition method by using the means and variances of signals as well as cutting parameters as the input vector. Information fusion theory at the feature level is adopted to assist the machining condition recognition. Experiments are designed to demonstrate and validate the feasibility of the proposed approach. A condition recognition accuracy of about 90 % has been achieved during the experiments.

Hesitant Fuzzy Maclaurin Symmetric Mean Operators and Its Application to Multiple-Attribute Decision Making

In this paper, we investigate the multiple-attribute decision-making (MADM) problems based on traditional Maclaurin symmetric mean operator operating under hesitant fuzzy environment. The Maclaurin symmetric mean (MSM) operator is a classical mean type aggregation operator and has strong modeling capability in modern information fusion theory, which has particular advantages for aggregating multi-dimension arguments. The prominent characteristic of the MSM operator is that it can capture the interrelationship among the multi-input arguments. Motivated by the idea of MSM operator, we develop the hesitant fuzzy Maclaurin symmetric mean (HFMSM) operator for aggregating the hesitant fuzzy information. Some desirable properties such as monotonicity, boundedness, idempotency are studied. Furthermore, we have discussed some special cases with respect to different parameter values of the HFMSM operator in detail. For the situations where the input arguments have different importance, we further develop the weighted hesitant fuzzy Maclaurin symmetric mean operator to aggregate hesitant fuzzy information. Based on which, an approach to MADM problems with hesitant fuzzy information is developed. Finally, a practical example with paper quality evaluation of sciencepaper online in China is provided to illustrate the practicality and effectiveness of the proposed method.

A Flexible Framework for Assessing the Quality of Information in Wireless Sensor Networks

As wireless sensor networks (WSNs) often provide incorrect and outdated information about the events in a monitored environment, quality of information (QoI) assessment is invaluable for users to manage and use the information in particular applications. In this paper, we propose a flexible framework to dynamically assess the QoI in different WSN applications, with focus on accuracy and timeliness. Our framework is constructed on the infrastructure of an information aggregation procedure under some assumptions about the network. Based on information fusion theory, two processing models are adopted to assess the accuracy of low-level measurement data and high-level decision information without the need for Ground Truth (GT). Meanwhile, our framework generally exploits two respective models according to the specific category of the information timeliness in different delay-sensitive applications. To quantify the timeliness, we utilize a practical measurement method by means of timestamp to determine the information acquisition time. The framework is evaluated by simulations, including accuracy assessment in two environmental monitoring application scenarios, and timeliness assessment in two delay-sensitive application scenarios. The simulation results show that our framework is effective and flexible for quantitative assessment of the QoI in different WSN applications.

Evidence fusion procedure based on hybrid DSm model

Dezert-Smarandache (DSm) theory, a new information fusion theory, is widely applied in image processing, multiple targets tracking identification, and other areas for its excellent processing ability of imperfect information. However, earlier research on DSm theory mainly focused on one sort of questions. An evidence fusion procedure is proposed based on the hybrid DSm model to compensate for a lack of research on the entire information procedure of DSm theory. This paper analyzes the evidence fusion procedure, as well as correlative node input and output information. Key steps and detailed procedures of evidence fusion are also discussed. Finally, an experiment illustrates the efficiency of the proposed evidence fusion procedure.

Study on the precession orbit shape analysis-based linear fault qualitative identification method for rotating machinery

The vibration responses of different linear faults all possess some common features, which make fault diagnosis very difficult. Based on the multi-sensor information fusion theory, this paper presents a new qualitative identification method for the diagnosis of linear faults. The excitation–response dynamic equation is constructed and system balancing response with full consideration of system anisotropy is analyzed. Through discussion of the precession orbit shape difference and its dispersive situation, the orbit shape average difference coefficient and the corresponding dispersion term are estimated to obtain the theoretical balancing effect. Finally, the qualitative identification of linear fault can be done according to whether the calculated balancing effect meets the safe operation requirement or not. The dynamic characteristic of the system difference coefficients is verified by a simulation experiment and the case study further testifies the capability and reliability of the proposed method.

The Research on Fault Diagnosis of Civil Aircraft Information Fusion Based on the Evidence Theory

In this paper, information fusion theory based on the evidence theory is used in the fault diagnosis field of civil aircraft. Considering the conflict resulted from information fusion in some certain conditions, two improved methods, including Similarity Coefficient and Full Factor are put forward to solve the conflict problems. In a nutshell, the methods are pretty effective and reliable, and the maintenance cost of airlines can be reduced obviously.

A Gas Pipeline Leakage Diagnosis of Fusing BP Neural Network Basing on WSN and D-S Theory

For reasons of low accuracy of artificial survey leakage, a gas pipeline leakage diagnosis method based on BP neural networks and D-S theory is presented by introducing WSN and information fusion theory. Two sub-neural networks are established at normal node to simplify network structure. The leakage characteristic parameters of negative pressure wave and acoustic emission signals are used as input eigenvector respectively for primary diagnosis. Through making preliminary fusion result s as the basic probability assignment of evidence, the impersonal valuations are realized. Finally, all evidences are aggregated at normal and sink node respectively by using the improved combination rules. The method makes full use of redundant and complementary leakage information. Numerical example shows that the proposed improves the leakage diagnosis accuracy and decreases the recognition uncertainty.

Safety Assessment Method for Equipment of Urban Rail Transit Network Operation

Based on the multi-source information fusion and complex network theory, through studying the effective matching and integration of safety equipment and spatial information of urban rail transit network operation, a safety assessment model is proposed: through equipment fusion and the node fusion, the global safety parameter is obtained, which is accurate in description and evaluation of urban rail transit operating than the partial safety factors and realize the transform from microscopic description to macroscopic description.