Majority Voting Rule Research Articles

Identification of the source camera of images based on convolutional neural network

Identification of the source of images is an indispensable part of digital forensics that involve images. Although the correlation between images and imaging devices could be characterized using some features and would thus make it possible to identify the sources of images, the efficiency of extracting features as well as estimating and matching of the pattern of the features in current methods are less than satisfactory and could be improved by automatic features extraction. This paper proposes a method for identifying the source camera of digital images based on convolutional neuron network. The method replies on designing a new network that involves an input layer, three convolutional layers with max pooling and normalization, two fully-connected layers and the Softmax classifier to test the task of identifying the source camera following the procedure of digital forensics. The original images are cropped into small-sized patches that the designed network would analyze, lowering the requirement of the network to use a large quantity of sample images from the targeting camera as the training data. A local-to-global strategy is also adopted that would respect the rule of majority voting of the image patches in determining the source camera. Testing results show that the proposed method can achieve accuracy of up to 99.8%, which assures the effectiveness of the majority voting. In addition, we can train an SVM classifier with the deep convolutional features of images that are extracted from the network that could achieve testing performance that is even better than Softmax.

Refining Land Cover Classification Maps Based on Dual-Adaptive Majority Voting Strategy for Very High Resolution Remote Sensing Images

Land cover classification that uses very high resolution (VHR) remote sensing images is a topic of considerable interest. Although many classification methods have been developed, the accuracy and usability of classification systems can still be improved. In this paper, a novel post-processing approach based on a dual-adaptive majority voting strategy (D-AMVS) is proposed to improve the performance of initial classification maps. D-AMVS defines a strategy for refining each label of a classified map that is obtained by different classification methods from the same original image, and fusing the different refined classification maps to generate a final classification result. The proposed D-AMVS contains three main blocks. (1) An adaptive region is generated by gradually extending the region around a central pixel based on two predefined parameters (T1 and T2) to utilize the spatial feature of ground targets in a VHR image. (2) For each classified map, the label of the central pixel is refined according to the majority voting rule within the adaptive region. This is defined as adaptive majority voting. Each initial classified map is refined in this manner pixel by pixel. (3) Finally, the refined classified maps are used to generate a final classification map, and the label of the central pixel in the final classification map is determined by applying AMV again. Each entire classified map is scanned and refined pixel by pixel based on the proposed D-AMVS. The accuracies of the proposed D-AMVS approach are investigated with two remote sensing images with high spatial resolutions of 1.0 m and 1.3 m. Compared with the classical majority voting method and a relatively new post-processing method called the general post-classification framework, the proposed D-AMVS can achieve a land cover classification map with less noise and higher classification accuracies.

Supervised Committee of Convolutional Neural Networks in Automated Facial Expression Analysis

Automated emotion recognition from facial images is an unsolved problem in computer vision. Although recent methods achieve close to human accuracy in controlled scenarios, the recognition of emotions in the wild remains a challenging problem. Recent advances in Deep learning have supposed a significant breakthrough in many computer vision tasks, including facial expression analysis. Particularly, the use of Deep Convolutional Neural Networks has attained the best results in the recent public challenges. The current state-of-the-art algorithms suggest that the use of ensembles of CNNs can outperform individual CNN classifiers. Two key considerations influence these results: (i) The design of CNNs involves the adjustment of parameters that allow diversity and complementarity in the partial classification results, and (ii) the final classification rule that assembles the result of the committee. In this paper we propose to improve the assembling of the committee by introducing supervised learning on the ensemble computation. We train a CNN on the posterior-class probabilities resulting from the individual members allowing to capture non-linear dependencies among committee members, and to learn this combination from data. The validation shows an accuracy 5 percent higher with respect to previous state-of-the art results based on averaging classifiers, and 4 percent to the majority voting rule.

Protein Secondary Structure Prediction Based on Data Partition and Semi-Random Subspace Method

Protein secondary structure prediction is one of the most important and challenging problems in bioinformatics. Machine learning techniques have been applied to solve the problem and have gained substantial success in this research area. However there is still room for improvement toward the theoretical limit. In this paper, we present a novel method for protein secondary structure prediction based on a data partition and semi-random subspace method (PSRSM). Data partitioning is an important strategy for our method. First, the protein training dataset was partitioned into several subsets based on the length of the protein sequence. Then we trained base classifiers on the subspace data generated by the semi-random subspace method, and combined base classifiers by majority vote rule into ensemble classifiers on each subset. Multiple classifiers were trained on different subsets. These different classifiers were used to predict the secondary structures of different proteins according to the protein sequence length. Experiments are performed on 25PDB, CB513, CASP10, CASP11, CASP12, and T100 datasets, and the good performance of 86.38%, 84.53%, 85.51%, 85.89%, 85.55%, and 85.09% is achieved respectively. Experimental results showed that our method outperforms other state-of-the-art methods.

A Novel Change Detection Approach for Multi-Temporal High-Resolution Remote Sensing Images Based on Rotation Forest and Coarse-to-Fine Uncertainty Analyses

In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness.

Negotiating a uniform emissions tax in international environmental agreements

A consensus appears to be emerging that a global carbon tax is the best policy for managing greenhouse gas emissions. Emissions tax systems are relatively straightforward, cost effective and can generate revenues used to offset other distortionary taxes. Moreover, recent theoretical research (Weitzman, 2014) has demonstrated that under some conditions the globally efficient tax rate can be implemented through a majority voting rule. We extend this area of research by examining a uniform emissions tax system in the framework of an international environmental agreement in which only countries that voluntarily participate are subject to the tax. We show that in the simplest situation in which countries have identical marginal benefit and cost functions, the largest stable agreement consists of two countries and the tax system has little impact on abatement levels. Our analysis highlights that by ignoring the participation decision and assuming commitment by all parties, the efficiency gains from a uniform emissions tax system are overstated.

Palmprint recognition with an efficient data driven ensemble classifier

Palmprint recognition is an important and widely used modality in biometric systems. It has a high reliability, stability and user acceptability. This paper proposes a new and effective ensemble classifier for palmprint recognition based on Random Subspace Method (RSM). The method relies on 2DPCA to build nearly incoherent random subspaces. As 2DPCA is an unsurpevised technique, features are extracted in each subspace using 2DLDA. A simple 1-Nearest Neighbor classifier is associated to each subspace, the final decision rule being obtained by a majority voting rule. Extensive experiments on three public palmprint datasets have been conducted to compare the proposed approach to existing methods. The experimental results demonstrate that our method improves on the state-of-the-art. It turns out that for this kind of data, the use of weak classifiers learned over nearly incoherent features is very efficient. Besides these findings, we provide an empirical analysis of the parameters involved in the random subspace technique to guide the user in the choice of the appropriate hyper-parameters.

Patch-based face recognition using a hierarchical multi-label matcher

This paper proposes a hierarchical multi-label matcher for patch-based face recognition. In signature generation, a face image is iteratively divided into multi-level patches. Two different types of patch divisions and signatures are introduced for 2D facial image and texture-lifted image, respectively. The matcher training consists of three steps. First, local classifiers are built to learn the local matching of each patch. Second, the hierarchical relationships defined between local patches are used to learn the global matching of each patch. Three ways are introduced to learn the global matching: majority voting, ℓ1-regularized weighting, and decision rule. Last, the global matchings of different levels are combined as the final matching. Experimental results on different face recognition tasks demonstrate the effectiveness of the proposed matcher at the cost of gallery generalization. Compared with the UR2D system, the proposed matcher improves the Rank-1 accuracy significantly by 3% and 0.18% on the UHDB31 dataset and IJB-A dataset, respectively.

Increasing the Accuracy of Crowdsourced Information on Land Cover via a Voting Procedure Weighted by Information Inferred from the Contributed Data

Simple consensus methods are often used in crowdsourcing studies to label cases when data are provided by multiple contributors. A basic majority vote rule is often used. This approach weights the contributions from each contributor equally but the contributors may vary in the accuracy with which they can label cases. Here, the potential to increase the accuracy of crowdsourced data on land cover identified from satellite remote sensor images through the use of weighted voting strategies is explored. Critically, the information used to weight contributions based on the accuracy with which a contributor labels cases of a class and the relative abundance of class are inferred entirely from the contributed data only via a latent class analysis. The results show that consensus approaches do yield a classification that is more accurate than that achieved by any individual contributor. Here, the most accurate individual could classify the data with an accuracy of 73.91% while a basic consensus label derived from the data provided by all seven volunteers contributing data was 76.58%. More importantly, the results show that weighting contributions can lead to a statistically significant increase in the overall accuracy to 80.60% by ignoring the contributions from the volunteer adjudged to be the least accurate in labelling.

Object-wise joint-classification change detection for remote sensing images based on entropy query-by fuzzy ARTMAP

The pixel-wise post-classification comparison (PCC) method is widely used in remote sensing images change detection. However, it is affected by the significant cumulative error caused by single image classification error. What’s more, the pixel-wise change detection method always produces “salt and pepper” effect. To solve the excessive evaluation of changed types and quantity caused by cumulative error and “salt and pepper” effect, a novel remote sensing image change detection method called entropy query-by fuzzy ARTMAP object-wise joint classification comparison (EQFAM-OBJCC) is presented in this article. Firstly, entropy query-by measurement of active learning is integrated with the fuzzy ARTMAP neural network to choose training samples which contain large amounts of information to improve the classification accuracy. Secondly, joint classification comparison is introduced to obtain the pixel-wise classification results. Finally, the object-wise classification and change detection results are produced by superpixel segmentation method, majority voting rule, and comparison of each superpixels. Experimental results demonstrate the validity of the proposed method. The classification and change detection results show that the proposed method can reduce the cumulative error with an average classification accuracy of 94.12% and a total detection error of 27.03%, and effectively resolve the “salt and pepper” problem. The proposed method was used to monitor the reclamation status of Liaohe estuary wetland via 10 time series remote sensing images from 1987 to 2014.

Cooperation and Endogenous Repetition in an Infinitely Repeated Social Dilemma

Exogenously imposed infinite repetition is known to mitigate people’s uncooperative behaviors in dilemma situations with partner matching through personal enforcement. One as yet unanswered question is whether people collectively choose to interact with each other under the partner matching condition when there exists an alternative possibility under random matching. In an indefinitely repeated public goods game framework, I let subjects democratically choose whether to (i) play with pre-assigned specific others for all rounds or to (ii) play with randomly matched counterparts in every round. The experimental results revealed that most groups collectively opt for the partner matching protocol. The data also indicated that groups achieve a higher level of cooperation when they democratically select the partner matching protocol by voting, relative to when the same option is exogenously imposed. These findings imply that people’s equilibrium selection may be affected by how the basic rules of games are introduced (endogenously or exogenously). The paper provides further evidence to suggest that the positive effect of democratic decision-making is stronger when the majority voting rule, rather than the unanimity rule, is applied.

A multiscale modified minimum spanning forest method for spatial-spectral hyperspectral images classification

This paper aimed to present a new method for the spectral-spatial classification of hyperspectral images, based on the idea of modified minimum spanning forest (MMSF). MMSF works on the obtained regions of pre-segmentation step that are considered as nodes of an image graph. In the proposed method, the image is first smoothed by the multiscale edge-preserving filter (MSEPF) and then the MMSF is built in each scale. Finally, all the classification maps of each scale are combined with a majority vote rule. The suggested method, named as MSEPF-MMSF, is performed on four hyperspectral images with different properties, and the experiments deal with the impacts of parameters of filter and the number of markers. The results demonstrate that the proposed method has improved the classification accuracies with respect to the previous methods.

An automatic detection of green tide using multi-windows with their adaptive threshold from Landsat TM/ETM plus image

Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of green tide is presented from Landsat TM/ETM plus image which needs not the atmospheric correction. In order to achieve an automatic detection of green tide, a linear relationship (y =0.723x+0.504) between detection threshold y and subtraction x (x=λ nir–λ red) is found from the comparing Landsat TM/ETM plus image with the field surveys. Using this relationship, green tide patches can be detected automatically from Landsat TM/ETM plus image. Considering there is brightness difference between different regions in an image, the image will be divided into a plurality of windows (sub-images) with a same size firstly, and then each window will be detected using an adaptive detection threshold determined according to the discovered linear relationship. It is found that big errors will appear in some windows, such as those covered by clouds seriously. To solve this problem, the moving step k of windows is proposed to be less than the window width n. Using this mechanism, most pixels will be detected [n/k]×[n/k] times except the boundary pixels, then every pixel will be assigned the final class (green tide or sea water) according to majority rule voting strategy. It can be seen from the experiments, the proposed detection method using multi-windows and their adaptive thresholds can detect green tide from Landsat TM/ETM plus image automatically. Meanwhile, it avoids the reliance on the accurate atmospheric correction.

Contingent valuation analysis of willingness to pay for beach erosion control through the stabiplage technique: A study in Djerba (Tunisia)

Beach erosion can have major economic implications because of the potential impact on coastal recreation demand – particularly for countries where coastal tourism is one of the main sources of external revenue. Djerba Island (Tunisia) falls in that category. With about 125km of coastline, Djerba Island is one of the most important Tunisian destinations. However, the island is experiencing coastal erosion problems. The Tunisia government launched a project to fight costal erosion through the Stabiplage technique. This study provides the first economic valuation of beach erosion control in Tunisia and is the first one that focuses on the Stabiplage technique. Specifically, a contingent valuation survey is carried out to elicit the public willingness to pay (WTP) for the project. An interval payment card question format is used to obtain information about WTP from representative samples of residents and tourists in Djerba. The results reveal a positive WTP for the project. Aggregate WTP estimates range from €133,459 (median value) to €5,180,269 (mean value). These values can help inform decisions about whether to undertake the project based on either the benefit-cost ratio rule or majority voting rule.

The principle of solidarity in asylum and migration within the context of the European Union accession process

This article addresses the question of the principle of solidarity in the fields of asylum and migration within the context of accession negotiations between the European Union and the candidate countries for EU membership. When a candidate country fulfils the membership conditions, it is expected that they will share the values of solidarity, mutual assistance and burden sharing in the fields of asylum and migration which will naturally impinge on their state sovereignty. This article is based on the hypothesis that solidarity in the field of asylum and migration has not been discussed within the enlargement process, meaning that the ‘new’ Member States were not aware of the concrete forms that this principle could take in the future. This hypothesis was tested on three case studies by analysing the accession documents of one candidate country from each of the three enlargement cycles (Slovenia, Bulgaria and Croatia respectively). This article concludes by showing that by agreeing to the EU Treaties, its solidarity clause and the majority vote rules, either as Member States or candidates, the states undertook the duty to transpose obligations in the fields of asylum and migration, even if they did not necessarily agree with them.

Spectral–Spatial Rotation Forest for Hyperspectral Image Classification

Rotation Forest (RoF) is a recent powerful decision tree (DT) ensemble classifier of hyperspectral images. RoF exploits random feature selection and data transformation techniques to improve both the diversity and accuracy of DT classifiers. Conventional RoF only considers data transformation on spectral information. To overcome this limitation, we propose a spectral and spatial RoF (SSRoF), to further improve the performance. In SSRoF, pixels are first smoothed by the multiscale (MS) spatial weight mean filtering. Then, spectral–spatial data transformation, which is based on a joint spectral and spatial rotation matrix, is introduced into the RoF. Finally, classification results obtained from each scale are integrated by a majority voting rule. Experimental results on two datasets indicate the competitive performance of the proposed method when compared to other state-of-the-art methods.

A Hybrid Multi-scale Spatial Filtering and Minimum Spanning Forest for Spectral–Spatial Hyperspectral Image Classification

Integration of spatial and spectral information is an effective way in improving classification accuracy. In this article a new framework, based on multi-scale spatial weighted mean filtering (MSWMF) and minimum spanning forest, is proposed for the spectral–spatial classification of hyperspectral images. In the proposed framework, at first the image is smoothed by MSWMF and then the first eight principal components are extracted. Using support vector machine, at each scale of MSWMF, a classification map is produced in order to generate a marker map in the next step. Then, the minimum spanning forest is built on the marker map. Finally, in order to create a final classification map, all the classification maps of each scale are merged with a majority vote rule. The experimental results of the hyper-spectral images indicate that the suggested framework enhances the classification accuracy, in comparison with previously classification techniques. So, it is interesting for hyperspectral images classification.

A novel Single-phase-to-ground fault identification and isolation strategy in wind farm collector line

The collector system of wind farm is a non-effectively grounding (small current grounding) system, where the single-phase-to-ground fault can easily develop into a three-phase fault, and without timely identification and isolation, it may cause incalculable hazard to wind farms. In fact, the present fault identification methods based on single fault characteristic quantity or majority voting rule all have certain limitations when dealing with some certain faults theoretically. Furthermore, the wind turbine could be possibly exposed to overvoltage several times of the rated voltage after the fault isolation by direct switching off the grid-side breaker in collector line. To solve these problems, this paper first analyzes the mechanism of overvoltage by constructing the resonance model of wind farm with distributed parameter. A novel single-phase-to-ground fault identification method based on D-S evidence theory is proposed. Then two flexible fault isolation methods are further proposed. Simulation results verify the validity and superiority of the proposed strategy.

Book Reviews

Karine Van der Straeten of the Toulouse School of Economics and Institute for Advanced Study reviews “The Economics of Voting: Studies of Self-Interest, Bargaining, Duty and Rights,” by Dan Usher. The Econlit abstract of this book begins: “Examines four key terms in the economics of voting--self-interest, bargaining, duty, and rights--and presents the case that they are indispensable requirements for the maintenance of government by majority-rule voting. Discusses voting patterns; voting about the redistribution of income; determining how high the revenue-maximizing tax rate might be; bargaining and voting; bargaining unexplained; what a duty to vote is, exactly; an alternative explanation of the chance of casting a pivotal vote; the problem of equity; voting rights, property rights, and civil rights; assessing the citizen-candidate model; and the significance of the probabilistic voting theorem.”

Predicting pregnancy rate following multiple embryo transfers using algorithms developed through static image analysis

Single-embryo image assessment involves a high degree of inaccuracy because of the imprecise labelling of the transferred embryo images. In this study, we considered the entire transfer cycle to predict the implantation potential of embryos, and propose a novel algorithm based on a combination of local binary pattern texture feature and Adaboost classifiers to predict pregnancy rate. The first step of the proposed method was to extract the features of the embryo images using the local binary pattern operator. After this, multiple embryo images in a transfer cycle were considered as one entity, and the pregnancy rate was predicted using three classifiers: the Real Adaboost, Gentle Adaboost, and Modest Adaboost. Finally, the pregnancy rate was determined via the majority vote rule based on classification results of the three Adaboost classifiers. The proposed algorithm was verified to have a good predictive performance and may assist the embryologist and clinician to select embryos to transfer and in turn improve pregnancy rate.