Competitive Classification Research Articles

E2TNet: Efficient enhancement Transformer network for hyperspectral image classification

Recently, Convolutional Transformer-based models have become popular in hyperspectral image (HSI) classification tasks and gained competitive classification performance. However, some Convolutional Transformer-based models fail to effectively mine the global correlations of coarse-grained and fine-grained features, which is adverse to recognizing the refined scale variation information of land-cover. The combination of convolution operations and multihead self-attention mechanisms also increases the computational cost, leading to low classification efficiency. In addition, shallow spectral–spatial features are directly input into the encoder, which inevitably incurs redundant spectral information. Therefore, this paper proposes an efficient enhancement Transformer network (E2TNet) for HSI classification. Specifically, this paper first designs a spectral–spatial feature fusion module to extract spectral and spatial features from HSI cubes and fuse them. Second, considering that redundant spectral information has a negative impact on classification performance, this paper designs a spectral–spatial feature weighted module to improve the feature representation of critical spectral information. Finally, to explore the global correlations of coarse-grained and fine-grained features and improve classification efficiency, an efficient multigranularity information fusion module is embedded in the encoder of E2TNet. The experiment is conducted on four benchmark hyperspectral datasets, and the experimental results demonstrate that the proposed E2TNet is better than several Convolutional Transformer-based classification models in terms of classification accuracy and classification efficiency.

Efficient learning with projected histograms

High dimensional learning is a perennial problem due to challenges posed by the “curse of dimensionality”; learning typically demands more computing resources as well as more training data. In differentially private (DP) settings, this is further exacerbated by noise that needs adding to each dimension to achieve the required privacy. In this paper, we present a surprisingly simple approach to address all of these concerns at once, based on histograms constructed on a low-dimensional random projection (RP) of the data. Our approach exploits RP to take advantage of hidden low-dimensional structures in the data, yielding both computational efficiency, and improved error convergence with respect to the sample size—whereby less training data suffice for learning. We also propose a variant for efficient differentially private (DP) classification that further exploits the data-oblivious nature of both the histogram construction and the RP based dimensionality reduction, resulting in an efficient management of the privacy budget. We present a detailed and rigorous theoretical analysis of generalisation of our algorithms in several settings, showing that our approach is able to exploit low-dimensional structure of the data, ameliorates the ill-effects of noise required for privacy, and has good generalisation under minimal conditions. We also corroborate our findings experimentally, and demonstrate that our algorithms achieve competitive classification accuracy in both non-private and private settings.

Hebbian spatial encoder with adaptive sparse connectivity

Biologically plausible neural networks have demonstrated efficiency in learning and recognizing patterns in data. This paper proposes a general online unsupervised algorithm for spatial data encoding using fast Hebbian learning. Inspired by the Hierarchical Temporal Memory (HTM) framework, we introduce the SpatialEncoder algorithm, which learns the spatial specialization of neurons’ receptive fields through Hebbian plasticity and k-WTA (k winners take all) inhibition. A key component of our model is a two-part synaptogenesis algorithm that enables the network to maintain a sparse connection matrix while adapting to non-stationary input data distributions. In the MNIST digit classification task, our model outperforms the HTM SpatialPooler in terms of classification accuracy and encoding stability. Compared to another baseline, a two-layer artificial neural network (ANN), our model achieves competitive classification accuracy with fewer iterations required for convergence. The proposed model offers a promising direction for future research on sparse neural networks with adaptive neural connectivity.

Continuous Dictionary of Nodes Model and Bilinear-Diffusion Representation Learning for Brain Disease Analysis.

Brain networks based on functional magnetic resonance imaging (fMRI) provide a crucial perspective for diagnosing brain diseases. Representation learning has recently attracted tremendous attention due to its strong representation capability, which can be naturally applied to brain disease analysis. However, traditional representation learning only considers direct and local node interactions in original brain networks, posing challenges in constructing higher-order brain networks to represent indirect and extensive node interactions. To address this problem, we propose the Continuous Dictionary of Nodes model and Bilinear-Diffusion (CDON-BD) network for brain disease analysis. The CDON model is innovatively used to learn the original brain network, with its encoder weights directly regarded as latent features. To fully integrate latent features, we further utilize Bilinear Pooling to construct higher-order brain networks. The Diffusion Module is designed to capture extensive node interactions in higher-order brain networks. Compared to state-of-the-art methods, CDON-BD demonstrates competitive classification performance on two real datasets. Moreover, the higher-order representations learned by our method reveal brain regions relevant to the diseases, contributing to a better understanding of the pathology of brain diseases.

How Much Competition is Enough Competition for Regulatory Forbearance?

Abstract Critical loss analysis is used to define product markets for merger analysis and determine if market forces are sufficient to discipline prices in transitionally competitive regulated markets. Unlike the approval of a merger, however, regulatory forbearance is a reversible act. The threat of future (re)-regulation, or regulatory contestability, in combination with high price-cost margins and complementary demands can lower the critical loss (elasticity) necessary to justify the competitive classification of regulated services. This suggests that the intensity of competition sufficient to forbear from regulation can be considerably less than what regulators may believe is required a priori.

A Human-Machine Agent Based on Active Reinforcement Learning for Target Classification in Wargame.

To meet the requirements of high accuracy and low cost of target classification in modern warfare, and lay the foundation for target threat assessment, the article proposes a human-machine agent for target classification based on active reinforcement learning (TCARL_H-M), inferring when to introduce human experience guidance for model and how to autonomously classify detected targets into predefined categories with equipment information. To simulate different levels of human guidance, we set up two modes for the model: the easier-to-obtain but low-value-type cues simulated by Mode 1 and the labor-intensive but high-value class labels simulated by Mode 2. In addition, to analyze the respective roles of human experience guidance and machine data learning in target classification tasks, the article proposes a machine-based learner (TCARL_M) with zero human participation and a human-based interventionist with full human guidance (TCARL_H). Finally, based on the simulation data from a wargame, we carried out performance evaluation and application analysis for the proposed models in terms of target prediction and target classification, respectively, and the obtained results demonstrate that TCARL_H-M can not only greatly save labor costs, but achieve more competitive classification accuracy compared with our TCARL_M, TCARL_H, a purely supervised model-long short-term memory network (LSTM), a classic active learning algorithm-Query By Committee (QBC), and the common active learning model-uncertainty sampling (Uncertainty).

A Global and Local Surrogate-Assisted Genetic Programming Approach to Image Classification

Genetic programming (GP) has achieved promising performance in image classification. However, GP-based methods usually require a long computation time for fitness evaluations, posing a challenge to real-world applications. Surrogate models can be efficiently computable approximations of expensive fitness evaluations. However, most existing surrogate methods are designed for evolutionary computation techniques with a vector-based representation consisting of numerical values, thus cannot be directly used for GP with a tree-based representation consisting of functions/operators. The variable sizes of GP trees further increase the difficulty of building the surrogate model for fitness approximations. To address these limitations, we propose a new surrogate-assisted GP approach including global and local surrogate models, which can accelerate the evolutionary learning process and achieve competitive classification performance simultaneously. The global surrogate model can assist GP in exploring the entire search space, while the local surrogate model can speed up convergence and further improve performance. Furthermore, a new surrogate training set is constructed to assist in establishing the relationship between the GP tree and its fitness, and effective surrogate models can be built accordingly. Experimental results on ten datasets of varying difficulty show that the new approach significantly reduces the computational cost of the GP-based method without sacrificing the classification accuracy. The comparisons with other state-of-the-art methods also demonstrate the effectiveness of the new approach. Further analysis reveals the significance of the global and local surrogates and the new surrogate training set on improving or maintaining the performance of the proposed approach while reducing the computational cost.

EchoTap: Non-Verbal Sound Interaction with Knock and Tap Gestures

The growing demand for highly accessible interaction technologies to effectively interact with smart devices has led to the increasing popularity of voice user interfaces (VUIs). However, VUIs face interpretation challenges stemming from the variability of natural language input, such as speech clarity issues, linguistic variability, and speech impediments. As an alternative, non-verbal sound-based interaction techniques emerge as highly advantageous for smart device control, mitigating the inherent challenges of VUIs. In this article, we introduce EchoTap, a novel audio interface that harnesses the distinctive sound responses generated by knock and tap gestures on target objects. Employing deep neural networks, EchoTap recognizes both the type and location of these gestures based on their unique sound signatures. Through offline evaluation, EchoTap demonstrated competitive classification accuracy (88% on average) and localization precision (93% on average). Moreover, a user study involving 12 participants validated EchoTap’s practical effectiveness and user-friendliness in real-world scenarios. This study highlights EchoTap’s potential for various daily interaction contexts and discusses further design implications for leveraging auditory interfaces based on simple gestures.

Individual entity induced label concept set for classification: An information fusion viewpoint

Formal concept analysis has seldom been employed for classification. This is mainly due to (1) the high time and space complexity of concept lattice construction, and (2) the difficulty of concept lattice based prediction. Inspired by information fusion, this paper introduces a new algorithm named CECS, which constructs a concept set instead of a lattice to ensure efficiency and enable direct classification. Regarding concept set construction, we define sub-formal context by grouping objects with the same label within the labeled formal context. Subsequently, we induce the label concept from the sub-formal context based on each individual entity (object or attribute). In this way, the information intrinsic to each label can be clearly expressed. At the same time, it reduces time consumption. Regarding classification, we define label confidence through fusing object and attribute induced concept sets. Respective calculation does not require additional prediction methods, thus becoming more efficient. Experiments are conducted on fifteen public datasets from UCI and KEEL in comparison with eight classical classification algorithms. Results validate the time complexity analysis, and show competitive classification performance of our algorithm. The source code is available at https://github.com/swpuzeng/cecs.

A novel cost-sensitive three-way intuitionistic fuzzy large margin classifier

Three-way decision (3WD) has been widely applied in diverse fields in tackling uncertainty, particularly in classification domain. As a discriminative learning algorithm, Large Margin Distribution Machine (LDM) aims to maximize the inter-class margin by leveraging the marginal distribution of samples, which captures the underlying structure and achieves superior classification performance. However, existing LDMs still suffer from some inherent flaws, including: i) the neglect of fuzzy decision items, leading to the inadequate handling of uncertainty; ii) the utilization of a cost-insensitive mechanism, resulting in high misclassification costs; and iii) the disregard of sample credibility, contributing to the noise susceptibility. To address these limitations, we introduce the intuitionistic fuzzy (IF) and cost-sensitive 3WD (CS3WD), presenting an innovative model known as the CS3W-IFLMC model. The IF theory is employed to quantify sample confidence levels, augmenting noise suppression in our proposed model. Moreover, the integration of the CS3WD method effectively reduces the overall decision cost and further improves the handling of uncertainty in datasets. Consequently, the CS3W-IFLMC model demonstrates superior noise resilience and generalization performance. Our comparative experiments validate the efficacy of the proposed CS3W-IFLMC model in achieving robustness to noise while upholding a competitive classification performance.

Semi-supervised multiview fuzzy broad learning

Semi-supervised learning models often rely on restricted assumptions, and can easily suffer from covariate shift or noise. Few studies have investigated the use of fuzzy rule-based methods in the semi-supervised discipline. To improve model accuracy against covariate shift and to introduce fuzzy methods for interpretability, we first build a semi-supervised fuzzy broad learning model named SSFBLS, which employs a Mean-Teacher framework. Then, a trusted multiview semi-supervised classification method, termed TMSSC, is proposed by integrating the SSFBLS with a multiview fusion network to enhance the robustness of the model. Under the Mean-Teacher framework, SSFBLS involves the Takagi-Sugeno-Kang fuzzy model which can effectively deal with imprecision and uncertainty, and broad learning system which has strong learning ability and high computational efficiency. TMSSC utilizes a trusted mechanism to blend multiple views, so as to enhance its learning ability in semi-supervised scenarios. Experiments on the benchmark datasets demonstrate that the proposed methods have better anti-noise ability, competitive classification accuracy, as well as fast running speed.

Reverse Graph Learning for Graph Neural Network.

Graph neural networks (GNNs) conduct feature learning by taking into account the local structure preservation of the data to produce discriminative features, but need to address the following issues, i.e., 1) the initial graph containing faulty and missing edges often affect feature learning and 2) most GNN methods suffer from the issue of out-of-example since their training processes do not directly generate a prediction model to predict unseen data points. In this work, we propose a reverse GNN model to learn the graph from the intrinsic space of the original data points as well as to investigate a new out-of-sample extension method. As a result, the proposed method can output a high-quality graph to improve the quality of feature learning, while the new method of out-of-sample extension makes our reverse GNN method available for conducting supervised learning and semi-supervised learning. Experimental results on real-world datasets show that our method outputs competitive classification performance, compared to state-of-the-art methods, in terms of semi-supervised node classification, out-of-sample extension, random edge attack, link prediction, and image retrieval.

Data and knowledge-driven deep multiview fusion network based on diffusion model for hyperspectral image classification

It is a crucial means for humans to perceive geomorphic features and landscape architectures by classifying ground objects in hyperspectral images (HSIs). Currently, the exponential development of neural networks has provided a powerful support for the accurate HSI classification. However, existing neural network-based methods usually rely solely on the data to drive the classification model, lacking attention to valuable land-cover distribution knowledge in HSIs. In view of this, to utilize hyperspectral data and distribution knowledge simultaneously, a data and knowledge-driven deep multiview fusion network based on diffusion model (DKDMN) is proposed in this paper. DKDMN extracts knowledge from unlabeled data in HSIs through a diffusion model-based knowledge learning framework (DMKLF), and combines raw hyperspectral data with the acquired knowledge through a designed deep multiview network architecture (DMNA) to mine complicated land-cover distribution information and reflect sample relationships. First, the proposed DMKLF utilizes the data distribution reconstructed by the diffusion model as a knowledge source for one view to enhance the network cross-sample awareness ability. On the other hand, the original HSI patches are considered a data source for another view, which co-drives DMNA with the unsupervised diffusion knowledge extracted by DMKLF to perform effective feature extraction. Second, taking into account the characteristics of each view and the feature similarity between these two views, a joint loss function specifically for DMNA is suggested to minimize the difference between the model predictions and the real labels. Finally, a multi-backbone integration classification framework (MBICF) is designed by deeply fusing three vision architectures to capture multi-scale spectral features and local–global features, thereby achieving pixel-wise classification effectively. Experimental results on four publicly available HSI datasets demonstrate that the proposed DKDMN achieves competitive classification accuracy compared with other state-of-the-art methods. For instance, the proposed DKDMN achieves an overall accuracy improvement of 1.62% and 2.18% on the Indian Pines and Salinas Valley datasets, respectively, compared to the multiple vision architecture-based hybrid network (MVAHN). The related code will be released at https://github.com/ZJier/DKDMN.

Multiple instance learning framework can facilitate explainability in murmur detection.

Cardiovascular diseases (CVDs) account for a high fatality rate worldwide. Heart murmurs can be detected from phonocardiograms (PCGs) and may indicate CVDs. Still, they are often overlooked as their detection and correct clinical interpretation require expert skills. In this work, we aim to predict the presence of murmurs and clinical outcomes from multiple PCG recordings employing an explainable multitask model. Our approach consists of a two-stage multitask model. In the first stage, we predict the murmur presence in single PCGs using a multiple instance learning (MIL) framework. MIL also allows us to derive sample-wise classifications (i.e. murmur locations) while only needing one annotation per recording ("weak label") during training. In the second stage, we fuse explainable hand-crafted features with features from a pooling-based artificial neural network (PANN) derived from the MIL framework. Finally, we predict the presence of murmurs and the clinical outcome for a single patient based on multiple recordings using a simple feed-forward neural network. We show qualitatively and quantitatively that the MIL approach yields useful features and can be used to detect murmurs on multiple time instances and may thus guide a practitioner through PCGs. We analyze the second stage of the model in terms of murmur classification and clinical outcome. We achieved a weighted accuracy of 0.714 and an outcome cost of 13612 when using the PANN model and demographic features on the CirCor dataset (hidden test set of the George B. Moody PhysioNet challenge 2022, team "Heart2Beat", rank 12 / 40). To the best of our knowledge, we are the first to demonstrate the usefulness of MIL in PCG classification. Also, we showcase how the explainability of the model can be analyzed quantitatively, thus avoiding confirmation bias inherent to many post-hoc methods. Finally, our overall results demonstrate the merit of employing MIL combined with handcrafted features for the generation of explainable features as well as for a competitive classification performance.

Interpretable deep learning methods for multiview learning

BackgroundTechnological advances have enabled the generation of unique and complementary types of data or views (e.g. genomics, proteomics, metabolomics) and opened up a new era in multiview learning research with the potential to lead to new biomedical discoveries.ResultsWe propose iDeepViewLearn (Interpretable Deep Learning Method for Multiview Learning) to learn nonlinear relationships in data from multiple views while achieving feature selection. iDeepViewLearn combines deep learning flexibility with the statistical benefits of data and knowledge-driven feature selection, giving interpretable results. Deep neural networks are used to learn view-independent low-dimensional embedding through an optimization problem that minimizes the difference between observed and reconstructed data, while imposing a regularization penalty on the reconstructed data. The normalized Laplacian of a graph is used to model bilateral relationships between variables in each view, therefore, encouraging selection of related variables. iDeepViewLearn is tested on simulated and three real-world data for classification, clustering, and reconstruction tasks. For the classification tasks, iDeepViewLearn had competitive classification results with state-of-the-art methods in various settings. For the clustering task, we detected molecular clusters that differed in their 10-year survival rates for breast cancer. For the reconstruction task, we were able to reconstruct handwritten images using a few pixels while achieving competitive classification accuracy. The results of our real data application and simulations with small to moderate sample sizes suggest that iDeepViewLearn may be a useful method for small-sample-size problems compared to other deep learning methods for multiview learning.ConclusioniDeepViewLearn is an innovative deep learning model capable of capturing nonlinear relationships between data from multiple views while achieving feature selection. It is fully open source and is freely available at https://github.com/lasandrall/iDeepViewLearn.

An Interpretable and Accurate Deep-Learning Diagnosis Framework Modeled With Fully and Semi-Supervised Reciprocal Learning.

The deployment of automated deep-learning classifiers in clinical practice has the potential to streamline the diagnosis process and improve the diagnosis accuracy, but the acceptance of those classifiers relies on both their accuracy and interpretability. In general, accurate deep-learning classifiers provide little model interpretability, while interpretable models do not have competitive classification accuracy. In this paper, we introduce a new deep-learning diagnosis framework, called InterNRL, that is designed to be highly accurate and interpretable. InterNRL consists of a student-teacher framework, where the student model is an interpretable prototype-based classifier (ProtoPNet) and the teacher is an accurate global image classifier (GlobalNet). The two classifiers are mutually optimised with a novel reciprocal learning paradigm in which the student ProtoPNet learns from optimal pseudo labels produced by the teacher GlobalNet, while GlobalNet learns from ProtoPNet's classification performance and pseudo labels. This reciprocal learning paradigm enables InterNRL to be flexibly optimised under both fully- and semi-supervised learning scenarios, reaching state-of-the-art classification performance in both scenarios for the tasks of breast cancer and retinal disease diagnosis. Moreover, relying on weakly-labelled training images, InterNRL also achieves superior breast cancer localisation and brain tumour segmentation results than other competing methods.

Scalable Label Distribution Learning for Multi-Label Classification.

Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric, which is violated in many real-world scenarios. Moreover, most existing methods design learning processes associated with the number of labels, which makes their computational complexity a bottleneck when scaling up to large-scale output space. To tackle these issues, we propose a novel method named scalable label distribution learning (SLDL) for MLC, which can describe different labels as distributions in a latent space, where the label correlation is asymmetric and the dimension is independent of the number of labels. Specifically, SLDL first converts labels into continuous distributions within a low-dimensional latent space and leverages the asymmetric metric to establish the correlation between different labels. Then, it learns the mapping from the feature space to the latent space, resulting in the computational complexity is no longer related to the number of labels. Finally, SLDL leverages a nearest neighbor-based strategy to decode the latent representations and obtain the final predictions. Extensive experiments illustrate that SLDL achieves very competitive classification performances with little computational consumption.

Simultaneous classification and out-of-distribution detection for wafer bin maps

Defect pattern classification of wafer bin maps (WBMs) assists in identifying the causes of semiconductor manufacturing process failures, thus contributing to the search for appropriate solutions. However, new previously unobserved defect patterns may be generated in real applications, which require classification methods with out-of-distribution (OOD) pattern detection capabilities. In this paper, we propose a novel method called a spectral-normalized neural radial basis function (SNRBF) network to classify defect patterns in WBMs while simultaneously detecting OOD defect patterns by quantifying the predictive uncertainty of a deep neural network. The SNRBF network adds spectral normalization to the weights in each layer of a deep neural network and replaces the output layer with a radial basis function kernel, facilitating high-quality uncertainty quantification and efficient computation. Additionally, we propose a novel regularization method based on singular values of the representation matrix to improve uncertainty quantification. Furthermore, we propose a new noise-filtering method capable of effectively eliminating random defects in WBMs by considering various defect pattern sizes. The proposed method is evaluated on a real WBM dataset and is demonstrated to outperform other competing methods in OOD detection while presenting competitive classification performance.

Learning bayesian multinets from labeled and unlabeled data for knowledge representation

The Bayesian network classifiers (BNCs) learned from labeled training data are expected to generalize to fit unlabeled testing data based on the independent and identically distributed (i.i.d.) assumption, whereas the asymmetric independence assertion demonstrates the uncertainty of significance of dependency or independency relationships mined from data. A highly scalable BNC should form a distinct decision boundary that can be especially tailored to specific testing instance for knowledge representation. To address the issue of asymmetric independence assertion, in this paper we propose to learn k-dependence Bayesian multinet classifiers in the framework of multistage classification. By partitioning training set and pseudo training set according to high-confidence class labels, the dependency or independency relationships can be fully mined and represented in the topologies of the committee members. Extensive experimental results indicate that the proposed algorithm achieves competitive classification performance compared to single-topology BNCs (e.g., CFWNB, AIWNB and SKDB) and ensemble BNCs (e.g., WATAN, SA2DE, ATODE and SLB) in terms of zero-one loss, root mean square error (RMSE), Friedman test and Nemenyi test.

Enhancing economic competitiveness analysis through machine learning: Exploring complex urban features.

Urban economic competitiveness is a fundamental indicator for assessing the level of urban development and serves as an effective approach for understanding regional disparities. Traditional economic competitiveness research that relies solely on traditional regression models and assumes feature relationship theory tends to fall short in fully exploring the intricate interrelationships and nonlinear associations among features. As a result, the study of urban economic disparities remains limited to a narrow range of urban features, which is insufficient for comprehending cities as complex systems. The ability of deep learning neural networks to automatically construct models of nonlinear relationships among complex features provides a new approach to research in this issue. In this study, a complex urban feature dataset comprising 1008 features was constructed based on statistical data from 283 prefecture-level cities in China. Employing a machine learning approach based on convolutional neural network (CNN), a novel analytical model is constructed to capture the interrelationships among urban features, which is applied to achieve accurate classification of urban economic competitiveness. In addition, considering the limited number of samples in the dataset owing to the fixed number of cities, this study developed a data augmentation approach based on deep convolutional generative adversarial network (DCGAN) to further enhance the accuracy and generalization ability of the model. The performance of the CNN classification model was effectively improved by adding the generated samples to the original sample dataset. This study provides a precise and stable analytical model for investigating disparities in regional development. In the meantime, it offers a feasible solution to the limited sample size issue in the application of deep learning in urban research.