Feature-level Information Fusion Research Articles

Multisource Information Fusion for Autoformer: Soft Sensor Modeling of FeO Content in Iron Ore Sintering Process

As a key thermal-state indicator of the iron ore sintering process, the content of ferrous oxide (FeO) in the finished sinter is directly related to product quality. Based on the massive data of sintering process, the data-driven soft sensor model provides a good choice for real-time FeO content detection. However, the complex characteristics of the data, including dynamics, nonlinearity, and multi-source heterogeneity, are still the main obstacles to improving the modeling accuracy. To solve this problem, a multi-source information fusion Autoformer (MIF-Autoformer) model is introduced in this paper. Firstly, feature-level information fusion and data-level information fusion are implemented based on the MIF strategy. Then, the comprehensive information of the sintering process is fed to the downstream Autoformer model in a serial manner, which not only improves the information capacity, but also provides additional prior information about the FeO content grade. This is helpful for Autoformer to capture the complex temporal distributions in the sintering process. Finally, the proposed model is applied to a real sintering plant. Experimental results show that the hybrid image features provided by the MIF strategy have a general optimization effect on different competitive models, and MIF-Autoformer exhibits the lowest prediction error on the test set.

Automated atrial fibrillation and ventricular fibrillation recognition using a multi-angle dual-channel fusion network

Atrial fibrillation (AFIB) and ventricular fibrillation (VFIB) are two common cardiovascular diseases that cause numerous deaths worldwide. Medical staff usually adopt long-term ECGs as a tool to diagnose AFIB and VFIB. However, since ECG changes are occasionally subtle and similar, visual observation of ECG changes is challenging. To address this issue, we proposed a multi-angle dual-channel fusion network (MDF-Net) to automatically recognize AFIB and VFIB heartbeats in this work. MDF-Net can be seen as the fusion of a task-related component analysis (TRCA)-principal component analysis (PCA) network (TRPC-Net), a canonical correlation analysis (CCA)-PCA network (CPC-Net), and the linear support vector machine-weighted softmax with average (LS-WSA) method. TRPC-Net and CPC-Net are employed to extract deep task-related and correlation features, respectively, from two-lead ECGs, by which multi-angle feature-level information fusion is realized. Since the convolution kernels of the above methods can be directly extracted through TRCA, CCA and PCA technologies, their training time is faster than that of convolutional neural networks. Finally, LS-WSA is employed to fuse the above features at the decision level, by which the classification results are obtained. In distinguishing AFIB and VFIB heartbeats, the proposed method achieved accuracies of 99.39 % and 97.17 % in intra- and inter-patient experiments, respectively. In addition, this method performed well on noisy data and extremely imbalanced data, in which abnormal heatbeats are much less than normal heartbeats. Our proposed method has the potential to be used as a diagnostic tool in the clinic.

A Feature-Level Fusion-Based Target Localization Method with the Hough Transform for Spatial Feature Extraction

Traditional two-step localization methods and direct localization methods have practical problems when they are used for underwater acoustic source localization. In this paper, a localization method based on the feature-level information fusion is proposed, in which the Hough Transform is exploited to detect the line characteristics of the spatial features of the target. A secondary accumulation procedure is proposed to extract and fuse the good features instead of fusing all features. The possibility to produce a ghost target is greatly reduced. Hence, the robustness of the proposed method in low SNR scenarios is improved. Experimental results validate the efficiency of exploiting the Hough Transform to eliminate interfering spatial features without sacrificing the localization accuracy.

Correlation-based identification approach for multimodal biometric fusion

AbstractInformation fusion is a key step in multimodal biometric systems. The feature-level fusion is more effective than the score-level and decision-level method owing to the fact that the original feature set contains richer information about the biometric data. In this paper, we present a multiset generalized canonical discriminant projection (MGCDP) method for feature-level multimodal biometric information fusion, which maximizes the correlation of the intra-class features while minimizes the correlation of the between-class. In addition, the serial MGCDP (S-MGCDP) and parallel MGCDP (P-MGCDP) strategy were also proposed, which can fuse more than two kinds of biometric information, so as to achieve better identification effect. Experiments performed on various biometric databases shows that MGCDP method outperforms other state-of-the-art feature-level information fusion approaches.

Information-Theoretic Performance Analysis of Sensor Networks via Markov Modeling of Time Series Data.

This paper presents information-theoretic performance analysis of passive sensor networks for detection of moving targets. The proposed method falls largely under the category of data-level information fusion in sensor networks. To this end, a measure of information contribution for sensors is formulated in a symbolic dynamics framework. The network information state is approximately represented as the largest principal component of the time series collected across the network. To quantify each sensor's contribution for generation of the information content, Markov machine models as well as x-Markov (pronounced as cross-Markov) machine models, conditioned on the network information state, are constructed; the difference between the conditional entropies of these machines is then treated as an approximate measure of information contribution by the respective sensors. The x-Markov models represent the conditional temporal statistics given the network information state. The proposed method has been validated on experimental data collected from a local area network of passive sensors for target detection, where the statistical characteristics of environmental disturbances are similar to those of the target signal in the sense of time scale and texture. A distinctive feature of the proposed algorithm is that the network decisions are independent of the behavior and identity of the individual sensors, which is desirable from computational perspectives. Results are presented to demonstrate the proposed method's efficacy to correctly identify the presence of a target with very low false-alarm rates. The performance of the underlying algorithm is compared with that of a recent data-driven, feature-level information fusion algorithm. It is shown that the proposed algorithm outperforms the other algorithm.

Coupling analysis-based false monitoring information identification of production system in process industry

False monitoring information is a major problem in process production system and several ineffective methods have been proposed to identify false monitoring information in the production system. In this paper, a new method is proposed to identify false monitoring information based on system coupling analysis and collision detection from the perspective of data analysis. Coupling multifractal features are extracted to reflect the changes in coupling relationship by utilizing the multifractal detrended cross-correlation analysis (MF-DXA). Each monitoring variable in process production system has more than one coupled variable, which can be regarded as multi-source. To achieve low redundancy in features and uniform description of coupling relationship, the feature level information fusion is studied based on modified Mahalanobis Taguchi system (MTS). False alarms are identified when the coupling relationships among the coupled monitoring variables collide. Analysis results of coupled Rossler and Henon datasets indicate the feasibility of this method for selecting the effective coupling feature and uniform description of coupling relationship. The compressor system case of Coal Chemical Ltd. Group is studied and false monitoring information is identified.

Two Feature-Level Fusion Methods with Feature Scaling and Hashing for Multimodal Biometrics

ABSTRACTThis paper presents a new feature-level information fusion mechanism based on shuffle coding, called shuffle coding-based feature-level fusion (SC-FLF), for personal authentication. Our approach (SC-FLF) aims at constructing an information fusion mechanism to integrate features from the same or different feature spaces in which the ranges of feature values from different traits differ largely. In this mechanism, the shuffle-coding operator includes dimension adjustment, feature standardization, and fusion coding. This paper addresses two distinct methods, such as feature scaling and hashing, to standardize the range of independent features of data. The shuffle encoder of the SC-FLF in Method 1 uses a feature scaling and the resulting binary code represents the distance between a set of normalized feature values with 2’s complement. On the other hand, in Method 2, the shuffle encoder of the SC-FLF with hashing uses a projection framework for maximizing the features on a hyperplane and then quantizes the hash values as a sequence of binary codes. A XOR operation works as the fusion coding to produce the resulting fusion code. Three different types of fusion are designed to evaluate the fusion performance. Experimental validation illustrates that the proposed fusion methods for combining features in multimodal biometrics advances the recognition performance significantly.

Boosting paraphrase detection through textual similarity metrics with abductive networks

A number of metrics have been proposed in the literature to measure text re-use between pairs of sentences or short passages. These individual metrics fail to reliably detect paraphrasing or semantic equivalence between sentences, due to the subjectivity and complexity of the task, even for human beings. This paper analyzes a set of five simple but weak lexical metrics for measuring textual similarity and presents a novel paraphrase detector with improved accuracy based on abductive machine learning. The objective here is 2-fold. First, the performance of each individual metric is boosted through the abductive learning paradigm. Second, we investigate the use of decision-level and feature-level information fusion via abductive networks to obtain a more reliable composite metric for additional performance enhancement. Several experiments were conducted using two benchmark corpora and the optimal abductive models were compared with other approaches. Results demonstrate that applying abductive learning has significantly improved the results of individual metrics and further improvement was achieved through fusion. Moreover, building simple models of polynomial functional elements that identify and integrate the smallest subset of relevant metrics yielded better results than those obtained from the support vector machine classifiers utilizing the same datasets and considered metrics. The results were also comparable to the best result reported in the literature even with larger number of more powerful features and/or using more computationally intensive techniques.

Intelligent ZHENG Classification of Hypertension Depending on ML-kNN and Information Fusion

Hypertension is one of the major causes of heart cerebrovascular diseases. With a good accumulation of hypertension clinical data on hand, research on hypertension's ZHENG differentiation is an important and attractive topic, as Traditional Chinese Medicine (TCM) lies primarily in “treatment based on ZHENG differentiation.” From the view of data mining, ZHENG differentiation is modeled as a classification problem. In this paper, ML-kNN—a multilabel learning model—is used as the classification model for hypertension. Feature-level information fusion is also used for further utilization of all information. Experiment results show that ML-kNN can model the hypertension's ZHENG differentiation well. Information fusion helps improve models' performance.

Multichannel Image Registration by Feature-Based Information Fusion

This paper proposes a novel nonrigid inter-subject multichannel image registration method which combines information from different modalities/channels to produce a unified joint registration. Multichannel images are created using co-registered multimodality images of the same subject to utilize information across modalities comprehensively. Contrary to the existing methods which combine the information at the image/intensity level, the proposed method uses feature-level information fusion method to spatio-adaptively combine the complementary information from different modalities that characterize different tissue types, through Gabor wavelets transformation and Independent Component Analysis (ICA), to produce a robust inter-subject registration. Experiments on both simulated and real multichannel images illustrate the applicability and robustness of the proposed registration method that combines information across modalities. This inter-subject registration is expected to pave the way for subsequent unified population-based multichannel studies.