查看更多>>摘要：By now people's opinions and actions are more and more strongly influenced by what is posted and shared on the various social networks. Thus, malicious users can purposely manipulate other users posting fake news/reviews. In order to face this challenge, modern online social networks are beginning to adopt tool for user trustworthiness assessment. Current assessment solutions mainly adopt multi-criteria frameworks for user trustworthiness assessment but fail at properly dealing with uncertainty and vagueness in computed/collected scores and aggregating them in a robust manner. In this paper, we propose a larger set of criteria than existing related works, and the use of subjective logic to represent and combine subjective and objective scores. Specifically, several of assessment criteria are introduced for verifying user trust from different point of views (usefulness and quality of user reviews, users' influence/importance in terms of activities and centrality within the social network, time dependent crown consensus investigating aspect-based sentiments and opinions of reviews w.r.t. the majority), aiming at improving accuracy and precision in trust estimation. The available fusion operators in the literature of subjective logic have been compared so as to find the best one fitting the needs of trust estimation. The proposed solution has been implemented and evaluated against public Yelp data-sets so as to prove its effectiveness and efficiency w.r.t. existing related works within the literature.
查看更多>>摘要：Polarization imaging can retrieve inaccurate objects' 3D shapes with fine textures, whereas coarse but accurate depths can be provided by binocular stereo vision. To take full advantage of these two complementary techniques, we investigate a novel 3D reconstruction method based on the fusion of polarization imaging and binocular stereo vision for high quality 3D reconstruction. We first generate the polarization surface by correcting the azimuth angle errors on the basis of registered binocular depth, to solve the azimuthal ambiguity in the polarization imaging. Then we propose a joint 3D reconstruction model for depth fusion, including a data fitting term and a robust low-rank matrix factorization constraint. The former is to transfer textures from the polarization surface to the fused depth by assuming their relationship linear, whereas the latter is to utilize the low-frequency part of binocular depth to improve the accuracy of the fused depth considering the influences of missing-entries and outliers. To solve the optimization problem in the proposed model, we adopt an efficient solution based on the alternating direction method of multipliers. Extensive experiments have been conducted to demonstrate the efficiency of the proposed method in comparison with state-of-the-art methods and to exhibit its wide application prospects in 3D reconstruction.
查看更多>>摘要：Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at unboxing how AI systems' black-box choices are made. This research field inspects the measures and models involved in decision-making and seeks solutions to explain them explicitly. Many of the machine learning algorithms cannot manifest how and why a decision has been cast. This is particularly true of the most popular deep neural network approaches currently in use. Consequently, our confidence in AI systems can be hindered by the lack of explainability in these black-box models. The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend in performance. The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are uncommon. In this study, we first surveyed the current progress of XAI and in particular its advances in healthcare applications. We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios. Comprehensive quantitative and qualitative analyses can prove the efficacy of our proposed XAI solutions, from which we can envisage successful applications in a broader range of clinical questions.
查看更多>>摘要：Graph Convolutional Networks (GCNs) are widely applied in classification tasks by aggregating the neighborhood information of each sample to output robust node embedding. However, conventional GCN methods do not update the graph during the training process so that their effectiveness is always influenced by the quality of the input graph. Moreover, previous GCN methods lack the interpretability to limit their real applications. In this paper, a novel personalized diagnosis technique is proposed for early Alzheimer's Disease (AD) diagnosis via coupling interpretable feature learning with dynamic graph learning into the GCN architecture. Specifically, the module of interpretable feature learning selects informative features to provide interpretability for disease diagnosis and abandons redundant features to capture inherent correlation of data points. The module of dynamic graph learning adjusts the neighborhood relationship of every data point to output robust node embedding as well as the correlations of all data points to refine the classifier. The GCN module outputs diagnosis results based on the learned inherent graph structure. All three modules are jointly optimized to perform reliable disease diagnosis at an individual level. Experiments demonstrate that our method outputs competitive diagnosis performance as well as provide interpretability for personalized disease diagnosis.
查看更多>>摘要：Multi-channel and single-channel image denoising are on two important development fronts. Integrating multi-channel and single-channel image denoisers for further improvement is a valuable research direction. A natural assumption is that using more useful information is helpful to the output results. In this paper, a novel multi-channel and single-channel fusion paradigm (MSF) is proposed. The proposed MSF works by fusing the estimates of a multi-channel image denoiser and a single-channel image denoiser. The performance of recent multi-channel image denoising methods involved in the proposed MSF can be further improved at low additional time-consuming cost. Specifically, the validity principle of the proposed MSF is that the fused single-channel image denoiser can produce auxiliary estimate for the involved multi-channel image denoiser in a designed underdetermined transform domain. Based on the underdetermined transformation, we create a corresponding orthogonal transformation for fusion and better restore the multi-channel images. The quantitative and visual comparison results demonstrate that the proposed MSF can be effectively applied to several state-of-the-art multi-channel image denoising methods.
Hassan, Md RafiulHuda, ShamsulHassan, Mohammad MehediAbawajy, Jemal...
11页
查看更多>>摘要：The conventional diagnostic process and tools of cardiovascular autonomic neuropathy (CAN) can easily identify the two main categories of the condition: severe/definite CAN and normal/healthy without CAN. Conventional techniques encounter significant challenges when identifying CAN in its early or atypical stages due to the inherent imbalanced and incompleteness condition in the collected clinical multimodal data, including electrocardiogram (ECG) data from ECG sensors, blood chemistry, podiatry, and endocrinology features. Therefore, most detection tools and techniques are limited to binary CAN classification. However, early diagnosis of CAN or diagnosis of the atypical stages of CAN is more important than the diagnosis of severe CAN, which, in fact, is easily identifiable with a few diagnostic reports. In this paper, we propose a novel multi-class classification approach for timely CAN detection. The proposed classification algorithm develops a multistage fusion model by combining feature selection and multimodal feature fusion techniques. The proposed method develops a performance criterion-based feature selection technique to guarantee highly significant features. A multimodal feature fusion technique was developed using deep learning feature fusion and selected original features. The experimental results obtained from testing with a large CAN dataset indicate that the proposed algorithm significantly improved the diagnostic accuracy of CAN compared to conventional Ewing battery features. The algorithm also identified the early or atypical stages of CAN with an AUC score of 0.931 using leave-one-out cross-validation.
查看更多>>摘要：Establishing reliable correspondences by a deep neural network is an important task in computer vision, and it generally requires permutation-equivariant architecture and rich contextual information. In this paper, we design a Permutation-Equivariant Split Attention Network (called PESA-Net), to gather rich contextual information for the feature matching task. Specifically, we propose a novel "Split-Squeeze-Excitation-Union"(SSEU) module. The SSEU module not only generates multiple paths to exploit the geometrical context of putative correspondences from different aspects, but also adaptively captures channel-wise global information by explicitly modeling the interdependencies between the channels of features. In addition, we further construct a block by fusing the SSEU module, Multi-Layer Perceptron and some normalizations. The proposed PESA-Net is able to effectively infer the probabilities of correspondences being inliers or outliers and simultaneously recover the relative pose by essential matrix. Experimental results demonstrate that the proposed PESA-Net relative surpasses state-of-the-art approaches for pose estimation and outlier rejection on both outdoor scenes and indoor scenes (i.e., YFCC100M and SUN3D). Source codes: https://github.com/x-gb/PESA-Net.
查看更多>>摘要：This study proposes a non-threshold consensus model that combines the minimum cost and maximum consensus increasing for multi-attribute large group decision-making (MALGDM). First, the large-scale experts is classified into several clusters via the combination of the similarities of evaluation information, unit consensus cost, and adjustment willingness. Then, a more sensitive consensus measure method that combines the mean value and variance of the similarities among clusters is presented. Next, a comprehensive identification rule is put forward to determine the cluster with a low consensus level, low unit consensus cost, and high adjustment willingness for information adjustment. An optimization model that combines the minimization of the cost of the cluster and the maximization of the increase of the global consensus level is then constructed to obtain the adjusted information. Also, the adjustment willingness is considered in the constraints to limit the adjustment range. Moreover, instead of the use of a predefined threshold and a maximum number of iterations, a termination index is developed to terminate the consensus reaching process (CRP) to make the CRP more objective and rational. Finally, an application example is presented, and comparison and simulation analyses are performed to validate the feasibility and effectiveness of the proposed model.
查看更多>>摘要：Emotion recognition is a crucial application in human-computer interaction. It is usually conducted using facial expressions as the main modality, which might not be reliable. In this study, we proposed a multimodal approach that uses 2-channel electroencephalography (EEG) signals and eye modality in addition to the face modality to enhance the recognition performance. We also studied the use of facial images versus facial depth as the face modality and adapted the common arousal-valence model of emotions and the convolutional neural network, which can model the spatiotemporal information from the modality data for emotion recognition. Extensive experiments were conducted on the modality and emotion data, the results of which showed that our system has high accuracies of 67.8% and 77.0% in valence recognition and arousal recognition, respectively. The proposed method outperformed most state-of-the-art systems that use similar but fewer modalities. Moreover, the use of facial depth has outperformed the use of facial images. The proposed method of emotion recognition has significant potential for integration into various educational applications.
查看更多>>摘要：This study focuses on linguistic information operational realization through information granulation in group decision-making (GDM) scenarios where the preference information offered by decision-makers over alternatives is described using distributed linguistic preference relations (DLPRs). First, an information granulation model is proposed to arrive at the operational realization of linguistic information in the GDM with DLPRs. The information granulation is formulated as a certain optimization problem where a combination of consistency degree of individual DLPRs and consensus degree among individuals is regarded as the underlying performance index. Then, considering that the proposed model is a constrained optimization problem (COP) with an adjustable parameter, which is difficult to be effectively solved using general optimization methods, we develop a novel approach towards achieving the optimal solution, referred to as penalty function-based co-evolutionary particle swarm optimization (PFCPSO). Within the PFCPSO setting, the designed penalty function is used to transform the COPs into unconstrained ones. Besides, the penalty factors and the adjustable parameter, as well as the decision variables of the optimization problems, are simultaneously optimized through the co-evolutionary mechanism of two populations in co-evolutionary particle swarm optimization (CPSO). Finally, a comprehensive evaluation problem about car brands is studied using the proposed model and the newly developed PFCPSO approach, which demonstrates their applicability. Two comparative studies are also conducted to show the effectiveness of the proposals. Overall, this study exhibits two facets of originality: the presentation of the linguistic information granulation model, and the development of the PFCPSO approach for solving the proposed model.
NSTL
Elsevier