Decision Fusion Algorithm Research Articles

Decision Fusion for IoT-Based Wireless Sensor Networks

This article presents a novel decision fusion algorithm for Internet-of-Things-based wireless sensor networks, where multiple sensors transmit their decisions about a certain phenomenon to a remote fusion center (FC) over a wide area network. The proposed algorithm denoted as the individual likelihood approximation (ILA) can significantly reduce the decision fusion error probability performance while maintaining the low computational complexity of other state-of-the-art fusion algorithms. The performance of the ILA rule is evaluated in terms of the global fusion probability of error, and an efficient analytical expression is derived in terms of a single integral. The analytical results corroborated by Monte Carlo simulation show that the ILA significantly outperforms all other considered rules, such as the Chair–Varshney (CV) and MaxLog rules. Moreover, the impact of the link from the cluster head to the FC, which is modeled as a binary symmetric channel with unknown transition probabilities, has been investigated. It is shown that the probability of error over such links should not exceed 10−3 to avoid severe performance degradation. Furthermore, we derive a closed-form expression for the system fusion error probability of the CV rule for the most general system parameters.

AUTOMATIC VEHICLE RECOGNITION FOR URBAN TRAFFIC MANAGEMENT

Abstract. Automatic vehicle recognition has an important role for many applications such as supervision, traffic management and rescue tasks. The ability of online supervision on the distribution of vehicles in urban environments prevents traffic, which in turn reduces air pollution and noise. However, this is extremely challenging due to the small size of vehicles, their different types and orientations, and the visual similarity to some other objects in very high resolution images. In this paper, an automatic vehicle recognition algorithm is proposed based on very high spatial resolution aerial images. In the first step of the proposed method, by generating the image pyramid, the candidate regions of the vehicles are recognized. Then, performing reverse pyramid, decision level fusion of the vehicle candidates and the land use/cover classification results of the original image resolution are performed in order to modify recognized vehicle regions. For evaluating the performance of the proposed method in this study, Ultracam aerial imagery with spatial resolution of 11 cm and 3 spectral bands have been used. Comparing the obtained vehicle recognition results from the proposed decision fusion algorithm with some manually selected vehicle regions confirm the accuracy of about %80. Moreover, the %78.87 and 0.71 are respectively the values for overall accuracy and Kappa coefficient of the obtained land use/cover classification map from decision fusion algorithm.

Multichannel Cooperative Spectrum Sensing That Integrates Channel Decoding With Fusion-Based Decision

This paper considers coded multichannel cooperative spectrum sensing (MC-CSS) employing local Neyman–Pearson testing at each sensor and channel decoding integrated with fusion-based decision. A joint multichannel decoding and decision fusion (JMCDDF) algorithm for performing a likelihood ratio test at the fusion center is derived based on the belief propagation technique. For benchmark comparison, we also derive the analytical performance of MC-CSS with error-free reporting channels that do not require channel coding, employing equal decision thresholds at each sensor. Using the JMCDDF algorithm, we compare the performance between uncoded and coded MC-CSS schemes when applying low-density parity-check (LDPC) codes in the presence of reporting channel errors. Monte–Carlo simulation results show considerable performance gains when using the proposed coded MC-CSS schemes. A 3-dB saving in link budget can be achieved by such coded MC-CSS schemes with a short (3, 6) regular LDPC code of codeword length $n_c=\text{200}$ , over uncoded MC-CSS. Finally, it is shown that in some cases, protecting the primary user (PU) channels by using variable nodes of higher degrees improves the performance. To equalize the performance for all sensed PU channels, we introduce a simple permutation technique, where, in each transmission, different variable nodes are used to protect local decisions.

Simultaneous Recognition and Assessment of Post-Stroke Hemiparetic Gait by Fusing Kinematic, Kinetic, and Electrophysiological Data.

Gait analysis for the patients with lower limb motor dysfunction is a useful tool in assisting clinicians for diagnosis, assessment, and rehabilitation strategy making. Implementing accurate automatic gait analysis for the hemiparetic patients after stroke is a great challenge in clinical practice. This study is to develop a new automatic gait analysis system for qualitatively recognizing and quantitatively assessing the gait abnormality of the post-stroke hemiparetic patients. Twenty-one post-stroke patients and twenty-one healthy volunteers participated in the walking trials. Three of the most representative gait data, i.e., marker trajectory (MT), ground reaction force (GRF), and electromyogram, were simultaneously acquired from these subjects during their walking. A multimodal fusion architecture is established by using these different modal data to qualitatively distinguish the hemiparetic gait from normal gait by different pattern recognition techniques and to quantitatively estimate the patient's lower limb motor function by a novel probability-based gait score. Seven decision fusion algorithms have been tested in this architecture, and extensive data analysis experiments have been conducted. The results indicate that the recognition performance and estimation performance of the system become better when more modal gait data are fused. For the recognition performance, the random forest classifier based on the GRF data achieves an accuracy of 92.26% outperformed other single-modal schemes. When combining two modal data, the accuracy can be enhanced to 95.83% by using the support vector machine (SVM) fusion algorithm to fuse the MT and GRF data. When integrating all the three modal data, the accuracy can be further improved to 98.21% by using the SVM fusion algorithm. For the estimation performance, the absolute values of the correlation coefficients between the estimation results of the above three schemes and the Wisconsin gait scale scores for the post-stroke patients are 0.63, 0.75, and 0.84, respectively, which means the clinical relevance becomes more obvious when using more modalities. These promising results demonstrate that the proposed method has considerable potential to promote the future design of automatic gait analysis systems for clinical practice.

Reliability based impact localization in composite panels using Bayesian updating and the Kalman filter

Abstract In this work, a reliability based impact detection strategy for a sensorized composite structure is proposed. Impacts are localized using Artificial Neural Networks (ANNs) with recorded guided waves due to impacts used as inputs. To account for variability in the recorded data under operational conditions, Bayesian updating and Kalman filter techniques are applied to improve the reliability of the detection algorithm. The possibility of having one or more faulty sensors is considered, and a decision fusion algorithm based on sub-networks of sensors is proposed to improve the application of the methodology to real structures. A strategy for reliably categorizing impacts into high energy impacts, which are probable to cause damage in the structure (true impacts), and low energy non-damaging impacts (false impacts), has also been proposed to reduce the false alarm rate. The proposed strategy involves employing classification ANNs with different features extracted from captured signals used as inputs. The proposed methodologies are validated by experimental results on a quasi-isotropic composite coupon impacted with a range of impact energies.

Logarithmic reweighting nonnegative least mean square algorithm

System identification based on least mean square (LMS) adaptive filters is effective due to their simplicity and robustness. Inherent physical characteristic of intended system usually make nonnegativity constraint desirable. In other words, imposing nonnegativity constraint on optimization problem leads to more feasible unknown parameter estimation. Hence, nonnegative least mean square (NNLMS) and its variants were proposed to adaptively solve the Wiener filtering problem considering constraint that makes filter weights nonnegative. In this paper, we propose a new variant of nonnegative least mean square for which its performance is analyzed both theoretically and experimentally. The proposed algorithm behavior is investigated in sparse system identification by Monte Carlo simulations in order to show validation of analysis and theory models. We compare our method with IP-NNLMS and NNLMS in order to prove the advantage of our proposed algorithm. Our proposed algorithm is also used in classification problem, and it is compared with entropy function-based online adaptive decision fusion (EADF) algorithm.

Online adaptive decision fusion based torque ripple reduction in permanent magnet synchronous motor

In this paper, new methods for reducing the torque ripple in permanent magnet synchronous motor are proposed. The methods are based on injection of appropriate current harmonics to motor by using adaptive decision fusion algorithms. Three different methods are used in determining injection of current harmonics based on q-axis current, q-axis voltage and reference value of the q-axis current. In these methods, the decision values are linearly combined with weights, which are updated online according to an active fusion method, based on performing orthogonal projections onto convex sets describing these values. The validity of the proposed methods is tested with experimental studies under different operating conditions.

Condition Assessment of Timber Utility Poles Based on a Hierarchical Data Fusion Model

AbstractThis paper proposes a novel hierarchical data fusion technique for the non-destructive testing (NDT) and condition assessment of timber utility poles. The new method analyzes stress wave data from multisensor and multiexcitation guided wave testing using a hierarchical data fusion model consisting of feature extraction, data compression, pattern recognition, and decision fusion algorithms. The researchers validate the proposed technique using guided wave tests of a sample of in situ timber poles. The actual health states of these poles are known from autopsies conducted after the testing, forming a ground-truth for supervised classification. In the proposed method, a data fusion level extracts the main features from the sampled stress wave signals using power spectrum density (PSD) estimation, wavelet packet transform (WPT), and empirical mode decomposition (EMD). These features are then compiled to a feature vector via real-number encoding and sent to the next level for further processing. Princi...

Multitarget detection in heterogeneous radar sensor network with energy constraint

Heterogeneous radar sensor networks (HRSNs) are gaining popularity due to the superior detection performance compared to conventional homogeneous radar sensor networks. In this paper, under the assumption that radar sensors perform differently in target detection and energy management, we propose optimized energy allocation scheme based on different fusion approaches for both single moving target and multiple moving targets. For one target detection situation, two decision fusion algorithms, the optimized energy allocation – likelihood ratio (OEA-LR) and the optimized energy allocation – approximate likelihood ratio (OEA-ALR) are proposed to improve the system detection performance given system energy constraint. In multi-target detecting environment, two decision fusion algorithms, namely likelihood ratio with ML function (LR-ML) and approximate likelihood ratio with ML function (ALR-ML) are also investigated and the optimized energy allocation scheme, the algorithm of likelihood function with the minimum Bayes risk (LF-BR) are also proposed. Performances are compared and analyzed in terms of probability of detection, probability of false alarm, detection probability of multiple hypothesis, number of local RSs, etc. via simulations. The proposed approaches not only optimize the energy allocation in HRSNs, but also offer an appropriate tradeoff between resource consumption and target detection performance.

Segmentation Fusion for Building Detection Using Domain-Specific Information

Segment-based classification is one of the popular approaches for object detection, where the performance of the classification task is sensitive to the accuracy of the output of the initial segmentation. Majority of the object detection systems directly use one of the generic segmentation algorithms, such as mean shift or k-means. However, depending on the problem domain, the properties of the regions such as size, color, texture, and shape, which are suitable for classification, may vary. Besides, fine tuning the segmentation parameters for a set of regions may not provide a globally acceptable solution in remote sensing domain, since the characteristic properties of a class in different regions may change due to the cultural and environmental factors. In this study, we propose a domain-specific segmentation method for building detection, which integrates information related to the building detection problem into the detection system during the segmentation step. Buildings in a remotely sensed image are distinguished from the highly cluttered background, mostly, by their rectangular shapes, roofing material and associated shadows. The proposed method fuses the information extracted from a set of unsupervised segmentation outputs together with this a priori information about the building object, called domain-specific information (DSI), during the segmentation process. Finally, the segmentation output is provided to a two-layer decision fusion algorithm for building detection. The advantage of domain-specific segmentation over the state-of-the-art methods is observed both quantitatively by measuring the segmentation and detection performances and qualitatively by visual inspection.

New structure for multi-aspect SAR image target recognition with multi-level joint consideration

A new structure for SAR target recognition using multi-aspect SAR images is proposed. The new structure applies new approaches in the two levels of SAR image target recognition, which are data level and decision level, and combines the benefits of the two. Projections onto convex sets (POCS) super-resolution reconstruction algorithm is used in the data level of the new structure, which is to advance the resolution of the SAR image by using a series of multi-aspect SAR images. Weighted Bayes decision fusion algorithm is proposed in the decision level to jointly consider the benefit from the data level. All outcomes from the classifiers are fused in the decision level to generate the final result, which combines the multi-level benefits. Verification and analysis is performed to the proposed structure with multi-target image data in MSTAR database. Experimental results indicate that using the proposed structure for multi-aspect SAR images with multi-level joint consideration, the recognition rate is significantly advanced than that using single SAR target image. Meanwhile, the recognition rate by this structure is also higher than that using individual level approach.

Coded Collaborative Spectrum Sensing With Joint Channel Decoding and Decision Fusion

This paper considers the integration of channel decoding with fusion based decision, for coded collaborative spectrum sensing (CSS) employing local Neyman-Pearson (NP) testing at each sensor. We derive a belief-propagation (BP) algorithm for joint channel decoding and decision fusion (JCDDF), based on a factor graph model for coded CSS schemes. Using the Lloyd-Max method, we also propose a new methodology for the local sensor to quantize its observation. The design of the quantizer embeds the binary NP test outcome in the quantization bits. Using the JCDDF algorithm, we show that coded CSS paired even with a short (8,4) extended Hamming code outperforms not only uncoded CSS, but also schemes where channel decoding and decision fusion are executed separately. Then, we consider the design of good channel codes for such CSS schemes. We demonstrate that the JCDDF algorithm employing unequal error protection (UEP) coding improves performance and outperforms equal error protection coding. Furthermore, we present a simple code search algorithm for identifying short UEP codes. Using such UEP codes, we finally show that a performance improvement over uncoded CSS can be attained also without bandwidth expansion using higher order modulations.

Intelligent wheelchair system based on sEMG and head gesture

Because the single channel surface electromyographic (sEMG) signals easily caused a complex operation during the real-time operation, an intelligent wheelchair system based on sEMG and head gesture was proposed in this paper. A distributed parallelly decision fusion algorithm fused classification results of the two signals to form a final judgment. After sEMG was decomposed by wavelet packet, feature information of some subspace was weaken, because subspace dimension was very large. To solve the problem, the paper proposed an improved wavelet packet decomposition algorithm, which extracted sample entropy from four subspaces of improved wavelet packet decomposition and took it as the feature information. Experimental results show that the intelligent wheelchair system based on sEMG and head gesture has not only a simple operation and shorter operating time, but also a better stability and security.

Weight-Based Clustering Decision Fusion Algorithm for Distributed Target Detection in Wireless Sensor Networks

We use a great deal of wireless sensor nodes to detect target signal that is more accurate than the traditional single radar detection method. Each local sensor detects the target signal in the region of interests and collects relevant data, and then it sends the respective data to the data fusion center (DFC) for aggregation processing and judgment making whether the target signal exists or not. However, the current judgment fusion rules such as Counting Rule (CR) and Clustering-Counting Rule (C-CR) have the characteristics on high energy consumption and low detection precision. Consequently, this paper proposes a novel Weight-based Clustering Decision Fusion Algorithm (W-CDFA) to detect target signal in wireless sensor network. It first introduces the clustering method based on tree structure to establish the precursor-successor relationships among the clusters in the region of interests and then fuses the decision data along the direction from the precursor clusters to the successor clusters gradually, and DFC (i.e., tree root) makes final determination by overall judgment values from subclusters and ordinary nodes. Simulation experiments show that the fusion rule can obtain more satisfactory system level performance at the environment of low signal to noise compared with CR and C-CR methods.

Scheme of Cooperative Spectrum Sensing Based on Adaptive Decision Fusion Algorithm

Spectrum sensing is one of the core technologies for cognitive radios (CR), where reliable detection of the signals of primary users (PUs) is precondition for implementing the CR systems. A cooperative spectrum sensing scheme based on an adaptive decision fusion algorithm for spectrum sensing in CR is proposed in this paper. This scheme can estimate the PU prior probability and the miss detection and false alarm probabilities of various secondary users (SU), and make the local decision with the Chair-Varshney rule so that the decisions fusion can be done for the global decision. Simulation results show that the false alarm and miss detection probabilities resulted from the proposed algorithm are significantly lower than those of the single SU, and the performance of the scheme outperforms that of the cooperative detection by using the conventional decision fusion algorithms.

Entropy-Functional-Based Online Adaptive Decision Fusion Framework With Application to Wildfire Detection in Video

In this paper, an entropy-functional-based online adaptive decision fusion (EADF) framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several subalgorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular subalgorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing entropic projections onto convex sets describing subalgorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system was developed to evaluate the performance of the decision fusion algorithm. In this case, image data arrive sequentially, and the oracle is the security guard of the forest lookout tower, verifying the decision of the combined algorithm. The simulation results are presented.

A novel method for prediction of protein interaction sites based on integrated RBF neural networks

Protein interactions are very important for control life activities. If we want to study the principle of protein interactions, we have to find the seats of a protein which are involved in the interactions called interaction sites firstly. In this paper, a novel method based on an integrated RBF neural networks is proposed for prediction of protein interaction sites. At first, a number of features were extracted, i.e., sequence profiles, entropy, relative entropy, conservation weight, accessible surface area and sequence variability. Then 6 sliding windows about these features were made, and they contained 1, 3, 5, 7, 9 and 11 amino acid residues respectively. These sliding windows were put into the input layers of six radial basis functional neural networks that were optimized by Particle Swarm Optimization. Thus, six group results were obtained. Finally, these six group results were integrated by decision fusion (DF) and Genetic Algorithm based Selective Ensemble (GASEN). The experimental results show that the proposed method performs better than the other related methods such as neural networks and support vector machine.

Clinical charge profiles prediction for patients diagnosed with chronic diseases using Multi-level Support Vector Machine

This research utilizes the national Healthcare Cost & Utilization Project (HCUP-3) databases to construct Support Vector Machine (SVM) classifiers to predict clinical charge profiles, including hospital charges and length of stay (LOS), for patients diagnosed with heart and circulatory disease, diabetes and cancer, respectively. Clinical charge profiles predictions can provides relevant clinical knowledge for healthcare policy makers to effectively manage healthcare services and costs at the national, state, and local levels. Despite its solid mathematical foundation and promising experimental results, SVM is not favorable for large-scale data mining tasks since its training time complexity is at least quadratic to the number of samples. Furthermore, traditional SVM classification algorithms cannot build an effective SVM when different data distribution patterns are intermingled in a large dataset. In order to enhance SVM training for large, complex and noisy healthcare datasets, we propose the Multi-level Support Vector Machine (MLSVM) that organizes the dataset as clusters in a tree to produce better partitions for more effective SVM classification. The MLSVM model utilizes multiple SVMs, each of which learns the local data distribution patterns in a cluster efficiently. A decision fusion algorithm is used to generate an effective global decision that incorporates local SVM decisions at different levels of the tree. Consequently, MLSVM can handle complex and often conflicting data distributions in large datasets more effectively than the single-SVM based approaches and the multiple SVM systems. Both the combined 5 × 2-fold cross validation F test and the independent test show that classification performance of MLSVM is much superior to that of a CVM, ACSVM and CSVM based on three popular performance evaluation metrics. In this work, CSVM and MLSVM are parallelized to speed up the slow SVM training process for very large and complex datasets. Running time analysis shows that MLSVM can accelerate SVM’s training process noticeably when the parallel algorithm is employed.

Signal fusion-based target detection algorithm for spatial diversity radar

Signal fusion-based radar target detection algorithms are studied in this article for spatial diversity multiple input multiple output (MIMO) radar based on the generalised likelihood ratio test (GLRT) algorithm, under the assumption that covariance matrices of clutter signals received by different radar sites are different. Two signal fusion-based target detection algorithms are proposed, which can be applied in signal fusion networks (SFNs) with typical structures, at a low communication and computation cost. Simulation experiments in several scenarios indicate that two proposed signal fusion algorithms have better detection performances than decision fusion algorithms.

Parallel microscopic cell image segmentation and multiple fusions

Segmenting cells reliably and correctly in a microscopic image is a pretty difficult task. We have developed a set of cell segmentation algorithms in parallel and a decision fusion algorithm to make the detection more robust. The distance and watershed transforms have also been used to separate the connected cells. Experimental results have proved that these algorithms are pretty robust to variable microscopy image data, and variable cell densities, and with the proposed fusion and false removal algorithms, the cell detection rate has increased significantly to above 97% with the false detection rate about 7%.