Frequency-Spatial Domain Information Fusion Network for Pan-Sharpening

The wireless sensor network has developed rapidly in recent years. It is formed by the intersection of multiple disciplines. It integrates embedded technology, sensor technology, distributed technology, wireless communication technology, and modern networks. It is a brand new information acquisition platform. The characteristics of sensor networks determine that information fusion technology is a hot spot in the research of wireless sensor networks. Information fusion can achieve high performance and low cost in terms of energy and communication, which is of great significance to the research of sensor networks. This paper is aimed at studying the semantic‐based sports music information fusion and retrieval research in wireless sensor networks. WSNs may face various attacks including eavesdropping attacks, replay attacks, Sybil attacks, and DOS attacks. Therefore, they are designing sensor network solutions. It is necessary to consider the network security issues. This article summarizes and analyzes the existing WSN security data fusion solutions for this issue and compares them by classification. This paper proposes methods and theories such as the spatial correlation detection algorithm, CBA algorithm, FTD algorithm, and DFWD algorithm, which enriches the research of information fusion and retrieval in wireless sensor networks, which is of exploratory significance, and it also establishes this problem. The model was studied, and reliable data was obtained. The experimental results of this paper show that when using these methods to diagnose faults in WSN, the correct rate of model diagnosis is higher than 77%.

The rapidly growing requirement for data has put forward Compressed Sensing (CS) to realize low-ratio sampling and to reconstruct complete signals. With the intensive development of Deep Neural Network (DNN) methods, performance in image reconstruction from CS measurements is constantly increasing. Currently, many network structures pay less attention to the relevance of before- and after-stage results and fail to make full use of relevant information in the compressed domain to achieve interblock information fusion and a great receptive field. Additionally, due to multiple resamplings and several forced compressions of information flow, information loss and network structure redundancy inevitably result. Therefore, an Information Enhancement and Fusion Network for CS reconstruction (IEF-CSNET) is proposed in this work, and a Compressed Information Extension (CIE) module is designed to fuse the compressed information in the compressed domain and greatly expand the receptive field. The Error Comprehensive Consideration Enhancement (ECCE) module enhances the error image by incorporating the previous recovered error so that the interlink among the iterations can be utilized for better recovery. In addition, an Iterative Information Flow Enhancement (IIFE) module is further proposed to complete the progressive recovery with loss-less information transmission during the iteration. In summary, the proposed method achieves the best effect, exhibits high robustness at this stage, with the peak signal-to-noise ratio (PSNR) improved by 0.59 dB on average under all test sets and sampling rates, and presents a greatly improved speed compared with the best algorithm.

Unmanned aerial vehicles (UAVs) are now widely used in many fields. Due to the randomness of UAV flight height and shooting angle, UAV images usually have the following characteristics: many small objects, large changes in object scale, and complex background. Therefore, object detection in UAV aerial images is a very challenging task. To address the challenges posed by these characteristics, this paper proposes a novel UAV image object detection method based on global feature aggregation and context feature extraction named the multi-scale feature information extraction and fusion network (MFEFNet). Specifically, first of all, to extract the feature information of objects more effectively from complex backgrounds, we propose an efficient spatial information extraction (SIEM) module, which combines residual connection to build long-distance feature dependencies and effectively extracts the most useful feature information by building contextual feature relations around objects. Secondly, to improve the feature fusion efficiency and reduce the burden brought by redundant feature fusion networks, we propose a global aggregation progressive feature fusion network (GAFN). This network adopts a three-level adaptive feature fusion method, which can adaptively fuse multi-scale features according to the importance of different feature layers and reduce unnecessary intermediate redundant features by utilizing the adaptive feature fusion module (AFFM). Furthermore, we use the MPDIoU loss function as the bounding-box regression loss function, which not only enhances model robustness to noise but also simplifies the calculation process and improves the final detection efficiency. Finally, the proposed MFEFNet was tested on VisDrone and UAVDT datasets, and the mAP0.5 value increased by 2.7% and 2.2%, respectively.

Rolling bearing fault diagnosis based on information fusion and parallel lightweight convolutional network

The goal of this paper is to find a general model of information fusion network that may prove useful in adapting information fusion to NCW (Network centric warfare) and coordinated development. Based on the OSI reference model, our study presents a layered model for information fusion that is integrated with a network’s function; likewise, we describe herein its topology structure. We were able to find a no-scaling function in the information fusion network by examining its structure function. We also propose an improved Barabási-Albert model for the information fusion network based on its strict demand for reliability and anti-attack. The results imply that the model possesses a realistic guide meaning for the design of the information fusion network. Moreover, it enables the developer to adequately utilize the existing resource.

Wireless sensor networks (WSNs) are commonly treated as a distributed database system that is accessed by means of a query language. However, the computation of such queries are usually performed by information fusion techniques. Information fusion has been used by applications to detect/classify events, track targets, and filter noisy measurements. In this tutorial, we discuss some of the information fusion techniques that are currently used in WSNs.

This paper reinvestigate the cooperative localization problem based on the information fusion of the GPS and the time of arrival (TOA) measurements in vehicular ad-hoc networks. The formulation based on the Maximum-Likelihood method is a non-convex and NP-hard problem. The existed semidefinite relaxation (SDR) method can provide an approximate solution but with quite poor efficiency. Therefore, an improved SDR method with local TOA information fusion is proposed in this paper, which can efficiently decrease the computational complexity. The Monte Carlo simulations are carried out and the results demonstrate that the localization accuracy of the proposed method is nearly the same with that of the SDR method without local fusion, but its computation time is considerably less than that of the previous SDR method.

Distributed information fusion in tangle networks

A semantic framework for information fusion in sensor networks for object and situation assessment is proposed. The overall vision is to construct machine representations that would enable human-like perceptual understanding of observed scenes via fusion of heterogeneous sensor data. In this regard, a hierarchical framework is proposed that is based on the Data Fusion Information Group (DFIG) model. Unlike a simple set-theoretic information fusion methodology that leads to loss of information, relational dependencies are modeled as cross-machines called relational Probabilistic Finite State Automata using the xD-Markov machine construction. This leads to a tractable approach for modeling composite patterns as structured sets for both object and scene representation. An illustrative example demonstrates the superior capability of the proposed methodology for pattern classification in urban scenarios.

We provide an axiomatic characterization of information fusion, on the basis of which we define an information fusion network. Our construction is reminiscent of tangle diagrams in low dimensional topology. Information fusion networks come equipped with a natural notion of equivalence. Equivalent networks 'contain the same information', but differ locally. When fusing streams of information, an information fusion network may adaptively optimize itself inside its equivalence class. This provides a fault tolerance mechanism for such networks.

Abstract. In order to diagnose the fault of rolling bearing by the vibration signal, a new method of fault diagnosis based on weighted fusion and BP (Back Propagation) neural network was put forward. At first, the vibration signal from the sensors was wave filtered through the method of correlation function, then the fused signal was obtained by the classical adaptive weighted fusion method, the multi-type characteristics parameters was to be as a neural network input. Finally, the fault diagnosis of rolling bearing was realized by the BP neural network, and the results show that the multi-sensor information fusion fault diagnosis method can be proved effectively to achieve the fault diagnosis of rolling bearing.

Digital image forensics is a crucial emerging technique, as image editing tools can modify them easily. Most of the latest methods can determine whether a specific operator has edited an image. These methods are suitable for high-resolution uncompressed images. In practice, more than one operator is used to modify image contents repeatedly. In this paper, a reliable scheme using information fusion and deep network networks is presented to recognize manipulation operators and the operator’s series on two operators. A transposed convolutional layer improves the performance of low-resolution JPEG compressed images. In addition, a bottleneck technique is utilized to extend the number of transposed convolutional layers. One average pooling layer is employed to preserve the optimal information flow and evade the overfitting concern among the layers. Moreover, the presented scheme can detect two operator series with various factors without including them in training. The experimental outcomes of the suggested scheme are encouraging and better than the existing schemes due to the availability of sufficient statistical evidence.

With the development of NC Equipment for the direction of high-speed, high power and high reliability, there are lots of complicated and coupling relationship as well as uncertain elements and information between and among the components. Two theory methods that are combined based on information fusion technology and Bayesian network are proposed in this paper. Firstly, more information fusion method can increase the completeness of the fault information to overcome the disadvantages of the single sensor; Secondly, Bayesian network is one of most effective means which not only can decrease the ambiguity of fault information but also improve the speed of fault diagnosis. At last, the experimental study of NC tool-machines is verified to be valid, which strengthens the practical value.

A driver fatigue recognition model based on information fusion and dynamic Bayesian network

With the development of information technology, it has become increasingly important to use intelligent algorithms to diagnose mechanical equipment faults based on vibration signals of rolling bearings. However, with the application of high-performance sensors in the Internet of Things, the complexity of real-time classification of multichannel, multidimensional sensor signals is increasing. In view of the need for intelligent methods for fault diagnosis methods of mechanical equipment, the generalization ability of fault diagnosis models also needs to be further strengthened. In this context, in order to make fault diagnosis intelligent and efficient, a bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network (CNN) is proposed. First, short-time Fourier transform (STFT) is used to analyze the multichannel vibration signal of the rolling bearing and obtain the frequency domain information of the signal over a period of time. Second, the information fusion is converted into two-dimensional (2D) images, which are input into CNN for training, and the bearing fault identification model is obtained. Next, the frequency domain information of each signal is converted into a 2D spectrum map, which is used as a CNN training dataset to train a bearing fault identification model. Finally, the diagnostic model is validated using the existing datasets. The results show that the accuracy of fault diagnosis using the proposed bearing is greater than 99.4% and can even reach 100%. The proposed method considerably reduces the workload of the diagnosis process, with strong robustness and generalization ability.