Decision Fusion Approach Research Articles

Analysis of several decision fusion strategies for clustering validation. Strategy definition, experiments and validation

In the unsupervised learning environment, the correct partition of data is not available, making it difficult to evaluate the performance of clustering algorithms. Therefore, one of the biggest challenges in this area is the validation of the results obtained by the algorithms. Amongst the various proposals currently under discussion, one of the most popular approaches is the one based on internal cluster validity indexes (CVIs). Comparative studies of such indexes show that there is no optimal CVI able to cope successfully with all the contexts. The aim of this work is to implement and analyse several decision fusion strategies over the CVIs studied in an extensive comparative work published in the bibliography, motivated by the success achieved by voting strategies in supervised learning. Thus, this experimental work consists of designing and implementing different CVI decision fusion strategies and then evaluating their performance in order to discover which of them are promising and eventually select the best one. Experiments with several strategies showed that the majority of the decision fusion approaches designed cope with the diversity of contexts more effectively than single CVIs.

Estimation of Performance in Multimodal Biometric based Authentication System using Various Clustering

Objectives: A swift growth of awareness in biometric based applications can be currently seen in the world. It includes different approaches to solve problems at hand. Methods: In this paper, Rough set with different classifiers are discussed to improve the performance of biometric system based authentication. This paper presents software systems based on rough sets comparing performance evaluation with different classifier techniques, fusion methods, filtering techniques and it provide sophisticated graphical environment. The decision fusion approach of multi modal biometric authentication gives the excellent performance in security system. Findings: A special place among different extensions is taken by the loom that replaces imperceptible relation. In the point of many simplification techniques, variant and extension of rough sets in a consistent appearance of the theory and implementation methodology is in place. This paper is meant to fulfil the specified necessitates and various challenges available in multimodal biometric authentication systems. Applications: This is used in National Secure the borders, Organizational/Enterprise, Identity and access management, Personal, Preventing impersonation (ID theft).

Superpixels for Spatially Reinforced Bayesian Classification of Hyperspectral Images

This letter presents a novel superpixel-based approach to hyperspectral image analysis which exploits spatial context within spectrally similar contiguous pixels for robust hyperspectral classification. The proposed approach entails two key steps-first, as a preprocessing step, we compute groupings (superpixels) through graph-based segmentation, following which an object-level classification is undertaken using a decision fusion approach that merges per-pixel outcomes from an ensemble of “per-pixel” Bayesian classifiers. The proposed method provides a robust way to exploit spatial contextual information. Every pixel in a superpixel is classified using statistical Bayesian classification independently, and the decisions are merged to obtain a unique class label for each superpixel. Experimental results with hyperspectral imagery indicate that the proposed method consistently provides a robust classification framework, even when using very limited training data.

HMM-Based Decision Fusion in Wireless Sensor Networks With Noncoherent Multiple Access

We develop a novel decision fusion (DF) approach which exploits time-correlation of the unknown binary source under observation through a wireless sensor network (WSN) reporting local decisions to a fusion center (FC) over interfering Rayleigh fading channels. The system is modeled via a hidden Markov model (HMM): both learning and detection phases are developed. The learning phase is blind, i.e. it requires only a set of observations without knowledge of the corresponding source states. Remarkably, the approach allows the FC to take decisions without knowledge of the local sensor performance. Numerical results confirm the effectiveness of the proposed approach.

Decision fusion for dual-window-based hyperspectral anomaly detector

In hyperspectral anomaly detection, the dual-window-based detector is a widely used technique that employs two windows to capture nonstationary statistics of anomalies and back- ground. However, its detection performance is usually sensitive to the choice of window sizes and suffers from inappropriate window settings. In this work, a decision-fusion approach is pro- posed to alleviate such sensitivity by merging the results from multiple detectors with different window sizes. The proposed approach is compared with the classic Reed-Xiaoli (RX) algorithm as well as kernel RX (KRX) using two real hyperspectral data. Experimental results demonstrate that it outperforms the existing detectors, such as RX, KRX, and multiple-window-based RX. The overall detection framework is suitable for parallel computing, which can greatly reduce computational time when processing large-scale remote sensing image data. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or repro- duction of this work in whole or in part requires full attribution of the original publication, including its DOI. (DOI: 10.1117/1.JRS.9.097297) tional probability density functions under the two hypotheses (without and with anomaly) are assumed to be Gaussian. The solution turns out to be an adaptive Mahalanobis distance between the pixel under test and the local background. It is preferred to use local background to capture nonstationary statistics, and its advantage of using a global background covariance matrix has been demonstrated in the literature. 11-13 The RX detector has become the benchmark of anomaly detection algorithms in HSI. Obviously, the key to success is an appropriate estimate of a local background covariance matrix for effective background suppression. An adaptive RX detector employs a dual-window strategy: the inner window is slightly larger than the pixel size, the outer window is even larger than the inner one, and only the samples in the outer region (i.e., between the frames of inner and outer windows) are used to estimate the background covariance matrix to avoid the use of the potential anomalous pixels. Intuitively, the number of pixels in the outer region (related to the sizes of inner and outer windows) should be more than the number of bands so that the resulting covariance matrix can be full-rank for inverse matrix operation. However, even when the covariance matrix is ill-rank, its inversion can still be computed by several strategies, such

CFAR Decision Fusion Approaches in the Clustered Radar Sensor Networks Using LEACH and HEED

We propose two constant-false-alarm-rate (CFAR) decision fusion approaches, the low-SNR and likelihood-ratio-based decision fusion in the central limit theory (LLDFCLT) and high-SNR and likelihood-ratio-based decision fusion in Kaplan-Meier estimator (HLDFKE). They are based on the clustered RSN model which combines clustering structure, target detection model, and fusion scheme. We mainly apply the clustering performances by low energy adaptive clustering hierarchy (LEACH) and hybrid energy-efficient distributed clustering approach (HEED) to RSN. Their CFAR detection performances in LLDFCLT and HLDFKE are analyzed and compared. Our analyses are verified through extensive simulations in different CFARs and various numbers of initial RSs and residual RSs in RSN. Monte Carlo simulations show that LLDFCLT can provide higher probability of detection (PD) than HLDFKE; and compared to LEACH, HEED not only prolongs the lifetime of ad hoc RSN but also improves target detection performances for different CFARs.

Android based malware detection using a multifeature collaborative decision fusion approach

Smart mobile device usage has expanded at a very high rate all over the world. Since the mobile devices nowadays are used for a wide variety of application areas like personal communication, data storage and entertainment, security threats emerge, comparable to those which a conventional PC is exposed to. Mobile malware has been growing in scale and complexity as smartphone usage continues to rise. Android has surpassed other mobile platforms as the most popular whilst also witnessing a dramatic increase in malware targeting the platform. In this work, we have considered Android based malware for analysis and a scalable detection mechanism is designed using multifeature collaborative decision fusion (MCDF). The different features of a malicious file like the permission based features and the API call based features are considered in order to provide a better detection by training an ensemble of classifiers and combining their decisions using collaborative approach based on probability theory. The performance of the proposed model is evaluated on a collection of Android based malware comprising of different malware families and the results show that our approach give a better performance than state-of-the-art ensemble schemes available.

Decision Fusion Based on Hyperspectral and Multispectral Satellite Imagery for Accurate Forest Species Mapping

This study investigates the effectiveness of combining multispectral very high resolution (VHR) and hyperspectral satellite imagery through a decision fusion approach, for accurate forest species mapping. Initially, two fuzzy classifications are conducted, one for each satellite image, using a fuzzy output support vector machine (SVM). The classification result from the hyperspectral image is then resampled to the multispectral’s spatial resolution and the two sources are combined using a simple yet efficient fusion operator. Thus, the complementary information provided from the two sources is effectively exploited, without having to resort to computationally demanding and time-consuming typical data fusion or vector stacking approaches. The effectiveness of the proposed methodology is validated in a complex Mediterranean forest landscape, comprising spectrally similar and spatially intermingled species. The decision fusion scheme resulted in an accuracy increase of 8% compared to the classification using only the multispectral imagery, whereas the increase was even higher compared to the classification using only the hyperspectral satellite image. Perhaps most importantly, its accuracy was significantly higher than alternative multisource fusion approaches, although the latter are characterized by much higher computation, storage, and time requirements.

Classification Based on 3-D DWT and Decision Fusion for Hyperspectral Image Analysis

In this letter, a fusion-classification system is proposed to alleviate ill-conditioned distributions in hyperspectral image classification. A windowed 3-D discrete wavelet transform is first combined with a feature grouping-a wavelet-coefficient correlation matrix (WCM)-to extract and select spectral-spatial features from the hyperspectral image dataset. The adjacent wavelet-coefficient subspaces (from the WCM) are intelligently grouped such that correlated coefficients are assigned to the same group. Afterwards, a multiclassifier decision-fusion approach is employed for the final classification. The performance of the proposed classification system is assessed with various classifiers, including maximum-likelihood estimation, Gaussian mixture models, and support vector machines. Experimental results show that with the proposed fusion system, independent of the classifier adopted, the proposed classification system substantially outperforms the popular single-classifier classification paradigm under small-sample-size conditions and noisy environments.

Cooperative Spectrum Sensing Performance-overhead Tradeoff in Cognitive Radio Network under Bandwidth Constraint

In cognitive radio network unlicensed users continuously scan a vast range of frequencies to detect ‘white spaces’ or ‘spectrum holes’ that are temporarily and spatially not being used for communications by licensed user and this process is known as spectrum sensing. In order to execute the cooperative spectrum sensing among cognitive radio users, data fusion schemes are superior to that of decision fusion ones in terms of the detection performance but suffer from the disadvantage of huge traffic overhead when bandwidth constraint of communication channels is taken into account. In this study, a cluster-based data and decision fusion approach is implemented to jointly exploit the advantages of both and a selective optimal weight setting algorithm is proposed by utilizing normal and modified deflection coefficients maximization under Neyman-Pearson criterion in order to obtain a final decision about the presence of primary users. The simulations show promising results as the novel hybridization process visibly reduces the network traffic overhead while exhibiting a highly satisfactory detection performance in CRN. Impairments in wireless network environment like shadowing, fading and noise uncertainty are also taken into consideration while optimizing performance of proposed model.

A new adaptive decentralized soft decision combining rule for distributed sensor systems with data fusion

A new adaptive decentralized soft decision combining rule for multiple-sensor distributed detection systems with data fusion is proposed. Unlike previously published rules, the proposed combining rule fuses soft decisions of sensors rather than hard decisions of sensors and does not require the knowledge of the false alarm and detection probabilities of the distributed sensors. Such a fusion rule is adaptive, insensitive to the instabilities of the sensor thresholds, and has the advantage of soft decision fusion. The proposed combination rule is derived: (1) for the case where the fusion center estimates the error probabilities of the sensors and (2) for the case where the fusion center does not estimate the error probabilities of the sensors. The performance of the proposed approach is evaluated, and illustrative examples are presented in the cases of Gaussian and Rayleigh distributed observations. Comparisons with the optimum centralized fusion, the optimum soft decision fusion, a soft decision fusion approach based on fusing confidence levels, and the optimum decentralized hard decision fusion are also presented. The results indicate that the proposed approach significantly outperforms the optimum decentralized hard decision fusion, is better than the approach based on fusing confidence levels, and has a performance similar to that of the optimum soft decision fusion.

Building Detection With Decision Fusion

A novel decision fusion approach to building detection problem in VHR optical satellite images is proposed. The method combines the detection results of multiple classifiers under a hierarchical architecture, called Fuzzy Stacked Generalization (FSG). After an initial segmentation and pre-processing step, a large variety of color, texture and shape features are extracted from each segment. Then, the segments, represented in K different feature spaces are classified by K different base-layer classifiers of the FSG architecture. The class membership values of the segments, which represent the decisions of different base-layer classifiers in a decision space, are aggregated to form a fusion space which is then fed to a meta-layer classifier of the FSG to label the vectors in the fusion space. The paper presents the performance results of the proposed decision fusion model by a comparison with the state of the art machine learning algorithms. The results show that fusing the decisions of multiple classifiers improves the performance, when they are ensembled under the suggested hierarchical learning architecture.

A Reputation Based Tactical Fusion Approach in Wireless Sensor Networks

Abstract To address the issues of the coexistence of the noisy signal channels, the vulnerability of sensor nodes and the limited coverage redundancy of monitoring, which is very common in actual application scenarios, a new decision fusion approach for distributed detection in wireless sensor networks is developed in this paper. A reputation weight is given to every sensor node by the fusion center when fusing their local decisions which then is modified according to the global decision to grade the reliability of the sensing nodes. By adopting this approach, the noise in the signal channels and the potential damage of the sensor nodes that may affect the accuracy of the sensing result are taken into account. Meanwhile, by using the reputation strategy, less sensor nodes are required to monitor the region of interest to achieve the accuracy of sensing, which can greatly save the energy consumption of the networks. The advantages of proposed fusion strategy are demonstrated by simulation results.

Enhanced Face Recognition using Data Fusion

In this paper we scrutinize the influence of fusion on the face recognition performance. In pattern recognition task, benefiting from different uncorrelated observations and performing fusion at feature and/or decision levels improves the overall performance. In features fusion approach, we fuse (concatenate) the feature vectors obtained using different feature extractors for the same image. Classification is then performed using different similarity measures. In decisions fusion approach, the fusion is performed at decisions level, where decisions from different algorithms are fused using majority voting. The proposed method was tested using face images having different facial expressions and conditions obtained from ORL and FRAV2D databases. Simulations results show that the performance of both feature and decision fusion approaches outperforms the single performances of the fused algorithms significantly.

A Bayesian decision fusion approach for microRNA target prediction.

MicroRNAs (miRNAs) are 19-25 nucleotides non-coding RNAs known to have important post-transcriptional regulatory functions. The computational target prediction algorithm is vital to effective experimental testing. However, since different existing algorithms rely on different features and classifiers, there is a poor agreement among the results of different algorithms. To benefit from the advantages of different algorithms, we proposed an algorithm called BCmicrO that combines the prediction of different algorithms with Bayesian Network. BCmicrO was evaluated using the training data and the proteomic data. The results show that BCmicrO improves both the sensitivity and the specificity of each individual algorithm. All the related materials including genome-wide prediction of human targets and a web-based tool are available at http://compgenomics.utsa.edu/gene/gene_1.php.

A multilevel decision fusion approach for urban mapping using very high-resolution multi/hyperspectral imagery

A novel multilevel decision fusion approach is proposed for urban mapping using very-high-resolution (VHR) multi/hyperspectral imagery. The proposed framework consists of three levels: (1) at level I, we first propose a self-dual filter for extracting structural features from the VHR imagery–subsequently, the spectral and structural features are integrated based on a weighted probability fusion; (2) level II extends level I by implementing the spectral–structural fusion in an object-based framework; and (3) at level III, the object-based probabilistic outputs at level II are used to identify unreliable objects, and shape attributes of these unreliable objects are then considered for refinement of classification. At this level, a decision-level object merging is used to improve the initial segmentation, since shape feature extraction is highly dependent on the quality of segmentation. Experiments were conducted on a Hyperspectral Digital Imagery Collection Experiment (HYDICE) DC Mall image and a QuickBird Beijing data set. The results revealed that the proposed approach provided progressively increasing accuracies when the multilevel features were gradually considered in the processing chain.

MULTI-MODAL DATA FUSION SCHEMES FOR INTEGRATED CLASSIFICATION OF IMAGING AND NON-IMAGING BIOMEDICAL DATA.

With a wide array of multi-modal, multi-protocol, and multi-scale biomedical data available for disease diagnosis and prognosis, there is a need for quantitative tools to combine such varied channels of information, especially imaging and non-imaging data (e.g. spectroscopy, proteomics). The major problem in such quantitative data integration lies in reconciling the large spread in the range of dimensionalities and scales across the different modalities. The primary goal of quantitative data integration is to build combined meta-classifiers; however these efforts are thwarted by challenges in (1) homogeneous representation of the data channels, (2) fusing the attributes to construct an integrated feature vector, and (3) the choice of learning strategy for training the integrated classifier. In this paper, we seek to (a) define the characteristics that guide the 4 independent methods for quantitative data fusion that use the idea of a meta-space for building integrated multi-modal, multi-scale meta-classifiers, and (b) attempt to understand the key components which allowed each method to succeed. These methods include (1) Generalized Embedding Concatenation (GEC), (2) Consensus Embedding (CE), (3) Semi-Supervised Multi-Kernel Graph Embedding (SeSMiK), and (4) Boosted Embedding Combination (BEC). In order to evaluate the optimal scheme for fusing imaging and non-imaging data, we compared these 4 schemes for the problems of combining (a) multi-parametric MRI with spectroscopy for prostate cancer (CaP) diagnosis in vivo, and (b) histological image with proteomic signatures (obtained via mass spectrometry) for predicting prognosis in CaP patients. The kernel combination approach (SeSMiK) marginally outperformed the embedding combination schemes. Additionally, intelligent weighting of the data channels (based on their relative importance) appeared to outperform unweighted strategies. All 4 strategies easily outperformed a naïve decision fusion approach, suggesting that data integration methods will play an important role in the rapidly emerging field of integrated diagnostics and personalized healthcare.

Decision Fusion on Supervised and Unsupervised Classifiers for Hyperspectral Imagery

A decision fusion approach is developed to combine the results from supervised and unsupervised classifiers. The final output takes advantage of the power of a support-vector-machine-based supervised classification in class separation and the capability of an unsupervised classifier, such as K -means clustering, in reducing trivial spectral variation impact in homogeneous regions. This approach can simply adopt the majority voting (MV) rule to achieve the same objective of object-based classification. In this letter, we propose a weighted MV (WMV) rule for decision fusion, where pixels in the same segment contribute differently according to their distance to the spectral centroid. The WMV rule can further improve the performance of the original MV rule. A series of unsupervised classifiers is investigated in the use of decision fusion, and recommendations are provided on the best unsupervised classifiers to be selected.

Gender recognition: A multiscale decision fusion approach

Gender recognition from face images has many applications and is thus an important research topic. This paper presents an approach to gender recognition based on shape, texture and plain intensity features gathered at different scales. We also propose a new dataset for gender evaluation based on images from the UND database. This allows for precise comparison of different algorithms over the same data. The experiments showed that information from different scales, even if just from a single feature, is more important than having information from different features at a single scale. The presented approach is quite competitive with above 90% accuracy in both evaluated datasets.

Hypertemporal Classification of Large Areas Using Decision Fusion

A novel multiannual land-cover-classification scheme for classifying hypertemporal image data is suggested, which is based on a supervised decision fusion (DF) approach. This DF approach comprises two steps: First, separate support vector machines (SVMs) are trained for normalized difference vegetation index (NDVI) time-series and mean annual temperature values of three consecutive years. In the second step, the information of the preliminary continuous SVM outputs, which represent posterior probabilities of the class assignments, is fused using a second-level SVM classifier. We tested the approach using the 10-day maximum-value NDVI composites from the ldquoMediterranean Extended Daily One-km Advanced Very High Resolution Radiometer Data Setrdquo (MEDOKADS). The approach increases the classification accuracy and robustness compared with another DF method (simple majority voting) and with a single SVM expert that is trained for the same multiannual periods. The results clearly demonstrate that DF is a reliable technique for large-area mapping using hypertemporal data sets.