Search

Abstract: Cluster ensemble approaches make use of a set of clustering solutions which are derived from different data sources to gain a more comprehensive and significant clustering result over conventional single clustering approaches. Unfortunately, not all the clustering solutions in the ensemble contribute to the final result. In this paper, we focus on the clustering solution selection strategy in the cluster ensemble, and propose to view clustering solutions as features such that suitable feature selection techniques can be used to perform clustering solution selection. Furthermore, a hybrid clustering solution selection strategy (HCSS) is designed based on a proposed weighting function, which combines several feature selection techniques for the refinement of clustering solutions in the ensemble. Finally, a new measure is designed to evaluate the effectiveness of clustering solution selection strategies. The experimental results on both UCI machine learning datasets and cancer gene expression profiles demonstrate that HCSS works well on most of the datasets, obtains more desirable final results, and outperforms most of the state-of-the-art clustering solution selection strategies. [Copyright &y& Elsevier]

Abstract: Image clustering is a critical step for the applications of content-based image retrieval, image annotation and other high-level image processing. To achieve these tasks, it is essential to obtain proper representation of the images. Non-negative Matrix Factorization (NMF) learns a part-based representation of the data, which is in accordance with how the brain recognizes objects. Due to its psychological and physiological interpretation, NMF has been successfully applied in a wide range of application such as pattern recognition, image processing and computer vision. On the other hand, manifold learning methods discover intrinsic geometrical structure of the high dimension data space. Incorporating manifold regularizer to standard NMF framework leads to novel performance. In this paper, we proposed a novel algorithm, call Hyper-graph regularized Non-negative Matrix Factorization (HNMF) for this purpose. HNMF captures intrinsic geometrical structure by constructing a hyper-graph instead of a simple graph. Hyper-graph model considers high-order relationship of samples and outperforms simple graph model. Empirical experiments demonstrate the effectiveness of the proposed algorithm in comparison to the state-of-the-art algorithms, especially some related works based on NMF. [Copyright &y& Elsevier]

Abstract: In this paper, we improve the minimum squared error (MSE) algorithm for classification by modifying its classification rule. Differing from the conventional MSE algorithm which first obtains the mapping that can best transform the training sample into its class label and then exploits the obtained mapping to predict the class label of the test sample, the modified minimum squared error classification (MMSEC) algorithm simultaneously predicts the class labels of the test sample and the training samples nearest to it and combines the predicted results to ultimately classify the test sample. Besides this paper, for the first time, proposes the idea to take advantage of the predicted class labels of the training samples for classification of the test sample, it devises a weighted fusion scheme to fuse the predicted class labels of the training sample and test sample. The paper also interprets the rationale of MMSEC. As MMSEC generalizes better than conventional MSE, it can lead to more robust classification decisions. The face recognition experiments show that MMSEC does obtain very promising performance. [Copyright &y& Elsevier]

Abstract: Extracting local rotation invariant features is a popular method for the classification of rotation invariant texture. To address the issue of local rotation invariance, many algorithms based on anisotropic features were proposed. Usually a dominant orientation is found out first, and then anisotropic feature is extracted by this orientation. To validate whether local dominant orientation is necessary for the classification of rotation invariant texture, in this paper, two isotropic statistical texton based methods are proposed. These two methods are the counterparts of two state-of-the-art anisotropic texton based methods: maximum response 8 (MR8) and gray value image patch. Experimental results on three public databases show that local dominant orientation plays an important role when the training set is less; when training samples are enough, local dominant orientation may not be necessary. [Copyright &y& Elsevier]

• Propose a novel encoder-decoder framework for vessel segmentation in retinal imaging. • A new multi-scale upsample attention module is proposed to enhance vessel segmentation in a hierarchical structure. • Proposed model achieves state-of-the-art performance of vessel segmentation on DRIVE, STARE, CHASE_DB1, HRF and IOSTAR datasets. • Experimental results demonstrate the robustness of our method in handling fundus image with lesions and microvessels. This paper presents a new nested U-shape attention network (NUA-Net) with improved robustness of lesions for effective vascular segmentation in retinal imaging. Unlike most of the current deep learning approaches which rely on vanilla upsample module to recover distinguishable features for segmentation, our attention-based multi-scale network extends the U-shape segmentation network by introducing a novel multi-scale upsample attention (MSUA) module to enhance vessel features in a hierarchical structure. The new approach connects encoder-decoder branches through a nested skip-connection pyramid architecture to extract discriminating retinal features from the rich local details. Experimental evaluations on five publicly available databases DRIVE, STARE, CHASE_DB, IOSTAR and HRF show the NUA-Net achieves 0.8043–0.8511 (Sensitivity), 0.9741–0.99 (Specificity) and 0.9646–0.9794 (Accuracy) respectively. The benchmark by cross-testing and separate-testing presents a state-of-the-art performance and better vessel preservation compared with other approaches. [ABSTRACT FROM AUTHOR]

How to extract effective expression representations that invariant to the identity-specific attributes is a long-lasting problem for facial expression recognition (FER). Most of the previous methods process the RGB images of a sequence, while we argue that the off-the-shelf and valuable expression-related muscle movement is already embedded in the compression format. In this paper, we target to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possibly extract identity factors from the I frame with a pre-trained face recognition network. By enforcing the marginal independence of them, the expression feature is expected to be purer for the expression and be robust to identity shifts. Specifically, we propose a novel collaborative min-min game for mutual information (MI) minimization in latent space. We do not need the identity label or multiple expression samples from the same person for identity elimination. Moreover, when the apex frame is annotated in the dataset, the complementary constraint can be further added to regularize the feature-level game. In testing, only the compressed residual frames are required to achieve expression prediction. Our solution can achieve comparable or better performance than the recent decoded image-based methods on the typical FER benchmarks with about 3 times faster inference. [ABSTRACT FROM AUTHOR]

Purpose: ChatGPT is a commonly used source of information by patients and clinicians. However, it can be prone to error and requires validation. We sought to assess the quality and accuracy of information regarding corneal transplantation and Fuchs dystrophy from 2 iterations of ChatGPT, and whether its answers improve over time., Methods: A total of 10 corneal specialists collaborated to assess responses of the algorithm to 10 commonly asked questions related to endothelial keratoplasty and Fuchs dystrophy. These questions were asked from both ChatGPT-3.5 and its newer generation, GPT-4. Assessments tested quality, safety, accuracy, and bias of information. Chi-squared, Fisher exact tests, and regression analyses were conducted., Results: We analyzed 180 valid responses. On a 1 (A+) to 5 (F) scale, the average score given by all specialists across questions was 2.5 for ChatGPT-3.5 and 1.4 for GPT-4, a significant improvement ( P < 0.0001). Most responses by both ChatGPT-3.5 (61%) and GPT-4 (89%) used correct facts, a proportion that significantly improved across iterations ( P < 0.00001). Approximately a third (35%) of responses from ChatGPT-3.5 were considered against the scientific consensus, a notable rate of error that decreased to only 5% of answers from GPT-4 ( P < 0.00001)., Conclusions: The quality of responses in ChatGPT significantly improved between versions 3.5 and 4, and the odds of providing information against the scientific consensus decreased. However, the technology is still capable of producing inaccurate statements. Corneal specialists are uniquely positioned to assist users to discern the veracity and application of such information., Competing Interests: The authors have no funding or conflicts of interest to disclose., (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)

Changes in an individual's digestive system, hormones, senses of smell and taste, and energy requirement accompanying aging could lead to impaired appetite, but older adults may not notice their risk of nutrient deficiency. When assessing the dietary intake of older adults, it was found that they had more difficulties with short-term recall and open-ended recall and would experience greater fatigue and frustration when compared to younger individuals when completing a lengthy questionnaire. There is a need to develop a brief dietary assessment tool to examine the nutritional needs of older adults. In this study, we aimed to assess the diet of Hong Kong older adults using the short FFQ and examine its reproducibility and relative validity as a dietary assessment tool. Dietary data of 198 older adults were collected via FFQs and three-day dietary records. Correlation analyses, cross-tabulation, one-sample t -tests, and linear regression analyses were used to evaluate the relative validity of the short FFQ. In general, the short FFQ was accurate in assessing the intake of phosphorus, water, grains, and wine, as shown by a significant correlation (>0.7) between values reported in the FFQs and dietary records; good agreement (more than 50% of observations belonged to the same quartile) and insignificant differences detected with the one-sample t -tests and linear regression analyses were observed for the above four variables. Additionally, the intake of proteins, carbohydrates, total fat, magnesium, and eggs in terms of the values reported in the FFQs and dietary records showed good agreement.

Unsupervised domain adaptation (UDA) has been successfully applied to transfer knowledge from a labeled source domain to target domains without their labels. Recently introduced transferable prototypical networks (TPNs) further address class-wise conditional alignment. In TPN, while the closeness of class centers between source and target domains is explicitly enforced in a latent space, the underlying fine-grained subtype structure and the cross-domain within-class compactness have not been fully investigated. To counter this, we propose a new approach to adaptively perform a fine-grained subtype-aware alignment to improve the performance in the target domain without the subtype label in both domains. The insight of our approach is that the unlabeled subtypes in a class have the local proximity within a subtype while exhibiting disparate characteristics because of different conditional and label shifts. Specifically, we propose to simultaneously enforce subtype-wise compactness and class-wise separation, by utilizing intermediate pseudo-labels. In addition, we systematically investigate various scenarios with and without prior knowledge of subtype numbers and propose to exploit the underlying subtype structure. Furthermore, a dynamic queue framework is developed to evolve the subtype cluster centroids steadily using an alternative processing scheme. Experimental results, carried out with multiview congenital heart disease data and VisDA and DomainNet, show the effectiveness and validity of our subtype-aware UDA, compared with state-of-the-art UDA methods.

Label noise is ubiquitous in many real-world scenarios which often misleads training algorithm and brings about the degraded classification performance. Therefore, many approaches have been proposed to correct the loss function given corrupted labels to combat such label noise. Among them, a trend of works achieve this goal by unbiasedly estimating the data centroid, which plays an important role in constructing an unbiased risk estimator for minimization. However, they usually handle the noisy labels in different classes all at once, so the local information inherited by each class is ignored which often leads to unsatisfactory performance. To address this defect, this paper presents a novel robust learning algorithm dubbed "Class-Wise Denoising" (CWD), which tackles the noisy labels in a class-wise way to ease the entire noise correction task. Specifically, two virtual auxiliary sets are respectively constructed by presuming that the positive and negative labels in the training set are clean, so the original false-negative labels and false-positive ones are tackled separately. As a result, an improved centroid estimator can be designed which helps to yield more accurate risk estimator. Theoretically, we prove that: 1) the variance in centroid estimation can often be reduced by our CWD when compared with existing methods with unbiased centroid estimator; and 2) the performance of CWD trained on the noisy set will converge to that of the optimal classifier trained on the clean set with a convergence rate [Formula: see text] where n is the number of the training examples. These sound theoretical properties critically enable our CWD to produce the improved classification performance under label noise, which is also demonstrated by the comparisons with ten representative state-of-the-art methods on a variety of benchmark datasets.

There has been a growing interest in unsupervised domain adaptation (UDA) to alleviate the data scalability issue, while the existing works usually focus on classifying independently discrete labels. However, in many tasks (e.g., medical diagnosis), the labels are discrete and successively distributed. The UDA for ordinal classification requires inducing non-trivial ordinal distribution prior to the latent space. Target for this, the partially ordered set (poset) is defined for constraining the latent vector. Instead of the typically i.i.d. Gaussian latent prior, in this work, a recursively conditional Gaussian (RCG) set is proposed for ordered constraint modeling, which admits a tractable joint distribution prior. Furthermore, we are able to control the density of content vectors that violate the poset constraint by a simple "three-sigma rule". We explicitly disentangle the cross-domain images into a shared ordinal prior induced ordinal content space and two separate source/target ordinal-unrelated spaces, and the self-training is worked on the shared space exclusively for ordinal-aware domain alignment. Extensive experiments on UDA medical diagnoses and facial age estimation demonstrate its effectiveness.

Healthcare question answering (HQA) system plays a vital role in encouraging patients to inquire for professional consultation. However, there are some challenging factors in learning and representing the question corpus of HQA datasets, such as high dimensionality, sparseness, noise, nonprofessional expression, etc. To address these issues, we propose an inception convolutional autoencoder model for Chinese healthcare question clustering (ICAHC). First, we select a set of kernels with different sizes using convolutional autoencoder networks to explore both the diversity and quality in the clustering ensemble. Thus, these kernels encourage to capture diverse representations. Second, we design four ensemble operators to merge representations based on whether they are independent, and input them into the encoder using different skip connections. Third, it maps features from the encoder into a lower-dimensional space, followed by clustering. We conduct comparative experiments against other clustering algorithms on a Chinese healthcare dataset. Experimental results show the effectiveness of ICAHC in discovering better clustering solutions. The results can be used in the prediction of patients' conditions and the development of an automatic HQA system.

Multiview learning has been widely studied in various fields and achieved outstanding performances in comparison to many single-view-based approaches. In this paper, a novel multiview learning method based on the Gaussian process latent variable model (GPLVM) is proposed. In contrast to existing GPLVM methods which only assume that there are transformations from the latent variable to the multiple observed inputs, our proposed method simultaneously takes a back constraint into account, encoding multiple observations to the latent variable by enjoying the Gaussian process (GP) prior. Particularly, to overcome the difficulty of the covariance matrix calculation in the encoder, a linear projection is designed to map different observations to a consistent subspace first. The obtained variable in this subspace is then projected to the latent variable in the manifold space with the GP prior. Furthermore, different from most GPLVM methods which strongly assume that the covariance matrices follow a certain kernel function, for example, radial basis function (RBF), we introduce a multikernel strategy to design the covariance matrix, being more reasonable and adaptive for the data representation. In order to apply the presented approach to the classification, a discriminative prior is also embedded to the learned latent variables to encourage samples belonging to the same category to be close and those belonging to different categories to be far. Experimental results on three real-world databases substantiate the effectiveness and superiority of the proposed method compared with state-of-the-art approaches.

Conventional k -nearest neighbor (KNN) classification approaches have several limitations when dealing with some problems caused by the special datasets, such as the sparse problem, the imbalance problem, and the noise problem. In this paper, we first perform a brief survey on the recent progress of the KNN classification approaches. Then, the hybrid KNN (HBKNN) classification approach, which takes into account the local and global information of the query sample, is designed to address the problems raised from the special datasets. In the following, the random subspace ensemble framework based on HBKNN (RS-HBKNN) classifier is proposed to perform classification on the datasets with noisy attributes in the high-dimensional space. Finally, the nonparametric tests are proposed to be adopted to compare the proposed method with other classification approaches over multiple datasets. The experiments on the real-world datasets from the Knowledge Extraction based on Evolutionary Learning dataset repository demonstrate that RS-HBKNN works well on real datasets, and outperforms most of the state-of-the-art classification approaches.

Microaneurysms are regarded as the first signs of diabetic retinopathy (DR), but the microaneurysms are not clear in the color retinal images, and many researches were studied to detect and locate these lesions. In this paper, a new hierarchical computing-aided diagnosis approach is proposed for the microaneurysms detection by using the multi-scale and multi-orientation sum of matched filter (MMMF) and machine learning, where 37 dimensional features are extracted from each candidate. Furthermore, several classifiers such as the k-nearest neighbor (kNN), local linear discrimination analysis (LLDA) and support vector machine (SVM) are modified to distinguish the true microaneurysms from the false ones, which is a typical unbalanced classification problem. The effectiveness of the proposed method is verified through the training set of a publicly available database, and the experiment results show that the proposed method has better detection performance including the receiver operating characteristic (ROC) curve and the free-response receiver operating characteristic (FROC) curve. Moreover, the proposed method with 37 dimensional features outperforms that with other features and has a sensitivity from 1/8 to 8 with the average of all seven points being 0.286 tested on the same database.

The early diagnosis of proliferative diabetic retinopathy (PDR), a common complication of diabetes that damages the retina, is crucial to the protection of the vision of diabetes sufferers. The onset of PDR is signaled by the appearance of neovascular net. Such neovascular nets might be identified using retinal vessel extraction techniques. The commonly used matched filter methods often produce false positive detections of neovascular nets due to their proneness to detect nonline edges as well as lines. In this paper, we propose a modified matched filter for retinal vessel extraction that applies a local vessel cross-section analysis using double-sided thresholding to reduce false responses to nonline edges. Our proposed modified matched filters demonstrated higher true positive rate and lesser false detection than existing matched-filter-based schemes in vessel extraction.