Action unit (AU) occurrence detection refers to the recognition of the presence or absence of the AU, and it is a challenging task due to rigid and non-rigid facial motion, subtle facial changes, and short duration. Recently, most studies focus on automatic AU detection by local representation learning or exploiting the correlation of AU to enhance recognition performance, and it has made significant

In this paper, we propose the Glyph-Semanteme fusion Embedding (GSE) for Chinese character and apply it to Offline Handwritten Chinese Text Recognition (offline-HCTR). It is well known that the number of Chinese characters is very large and the glyphs of these characters are complex, but few researchers realize that the underlying reason for this phenomenon is that Chinese is a form of ideogram, which

Today’s classification task is getting more and more complex. This inevitably renders unanticipated compromises on the quality of data labels. In this paper, we consider learning label noise robust classifiers with focus on the tasks with limited training examples relative to the number of data classes and data dimensionality. In such cases, the existing label noise models tend to inaccurately estimate

In recent years, tensor data appear more frequently in machine learning. Tucker decomposition is a powerful tool for processing tensor data. However, from the perspective of dimensionality reduction, Tucker decomposition without any regularization is only a tensor version of principal component analysis (PCA) that learning a linear subspace to minimize the distance between the data and their projections

Hierarchical multilabel classification (HMC) aims to classify the complex data such as text with multiple topics and image with multiple semantics, in which the multiple labels are organized in hierarchical structures such as trees and direct acyclic graphs (DAG). To reduce the computational complexity, HMC methods generally assume that the class labels of different branches in a hierarchical structure

In order to improve the efficiency of antenna optimization design, a surrogate model is often used to replace the full-wave electromagnetic simulation software. Broad learning system (BLS) provides an alternative method for deep structure, aiming to overcome the drawback of excessive time-consuming training process, however, usually not with satisfactory accuracy. In order to further improve the performance

Multi-view graph-based clustering (MGC) aims to cluster multi-view data via a graph learning scheme, and has aroused widespread research interests in behavior detection, face recognition, and information retrieval in recent years. However, most of the existing MGC methods usually learn the affinity graph in the original space, such that they are inevitably hindered by the curse of dimensionality and

The star-structured high-order heterogeneous data is ubiquitous, such data represent objects of a certain type, connected to other types of data, or the features, so that the overall data schema forms a star-structure of inter-relationships. In this paper, we study the problem of co-clustering of star-structured high-order heterogeneous data. We present a new solution, a Hierarchical High-order Co-clustering

The trust on network of Chinese public database is involved many factors in sociology, economics, technology, social psychology and so on, which resulted in the complexity of trust mechanism. The construction of trust mechanism plays a decisive role in public data governance via theoretical analysis. In the view of system science, trust is the key feedback control variable of data exchanging in the

Deep reinforcement learning has achieved superhuman performance in zero-sum games such as Go and Poker in recent years. In the real world, however, many scenarios are non-zero-sum settings, meaning that success feels the necessity for cooperation and communication rather than competition. Hanabi game has been established as an ideal benchmark for agents to learn to cooperate adequately with other agents

This paper investigates the adaptive fuzzy leader-following consensus problem of multi-agent systems (MASs) with unknown nonlinear dynamics via state-constraint impulsive control. The fuzzy logic systems(FLSs) are established to estimate the unknown nonlinear dynamics. Meanwhile, the purpose of designing one adaptive parameter is to reduce the impact on uncertain factors of FLSs, where this parameter

Recently the density peaks clustering algorithm (DPC) has received a lot of attention from researchers. The DPC algorithm is able to find cluster centers and complete clustering tasks quickly. It is also suitable for different kinds of clustering tasks. However, deciding the cutoff distance \({d}_{c}\) largely depends on human experience which greatly affects clustering results. In addition, the selection

Cross-modal hashing has recently attracted considerable attention in the large-scale retrieval task due to its low storage cost and high retrieval efficiency. However, the existing hashing methods still have some issues that need to be further solved. For example, most existing cross-modal hashing methods convert the original data into a common Hamming space to learn unified hash codes, which ignores

The performance of mixed \(H_{\infty }\) and passivity for T-S fuzzy system under the non-fragile memory sampled-data controller is considered in this paper. We construct a non-fragile memory sampled-data controller, which includes a constant signal transmission delay. And by constructing an augment Lyapunov–Krasovskii functional (LKF), taking into account Wirtinger-based integral inequality and the

In compressed sensing applications, self-learning generative models have attracted increasing attention because they provide guarantees that are similar to those of standard compressed sensing without employing sparsity. However, improving the performances of a generative model is challenging. In this paper, we improve the recovery performances of generative models (generative adversarial networks)

Electrocardiography (ECG) signals play an important role in the cardiac disorder diagnosis and arrhythmia detection since they reflect all the electrical activities of the heart and include information about heart function and heart conditions. Due to the subtle alterations in the amplitude, duration and morphology of the ECG, the development of computer-based intelligent system in the arrhythmia diagnosis

More and more attention has been paid to microservices from traditional monolithic workflows. How to rent on-demand and spot instances for microservice tasks in cloud computing is crucial to save rental costs for customers. According to the out-of-bid failure risks of spot instances and application deadline constraints, it is challenging to adaptively determine the number of on-demand and spot instances

In this paper, we focus on how to boost the semi-supervised classification performance by exploring the multi-view graph learning. The key of multi-view graph learning is to learn a discriminative and informative graph from the multiple input graphs. However, we observe that existing multi-view graph learning methods do not sufficiently consider the diversity among views. This results in giving great

Internet of Things (IoT) can provide the interconnection and data sharing among devices, vehicles, buildings via various sensors with the development of 5G, and it has been widely used in different services such as e-commerce, heath-care, smart buildings. In the meantime, various cyber-attacks for IoT have increased and caused huge losses. Lots of security mechanisms are rapidly being proposed to prevent

Visual urban perception has recently attracted a lot of research attention owing to its importance in many fields. Traditional methods for visual urban perception mostly need to collect adequate training instances for newly-added perception attributes. In this paper, we consider a novel formulation, zero-shot learning, to free this cumbersome curation. Based on the idea of different images containing

The optimization of continuous action control is an important research field. It aims to find optimal decisions by the experience of making decisions in a continuous action control task. This process can be done via reinforcement learning to train an agent for learning a policy by maximizing cumulative rewards of making decisions in a dynamic environment. Exploration–exploitation tradeoff is a key

Underdetermined blind source separation of speech mixtures is a challenging issue in the classical “Cocktail-party” problem. Recently, there has been attention to use dictionary learning to solve this problem. In this paper, we build a novel framework to solve the underdetermined blind separation of speech mixtures as a sparse signal recovery problem by using a compressed sensing model. First, to eliminate

During the past years, multi-view clustering algorithms have demonstrated satisfactory clustering results by fusing the multiple views of the dataset. Nowadays, the researches of dimensionality reduction and learning discriminative features from multi-view data have soared in the literatures. As for clustering, generating the suitable subspace of the high dimensional multi-view data is crucial to boost

Deep networks are widely used in few-shot learning methods, but deep networks suffer from large-scale network parameters and computational effort. Aiming at the above problems, we present a novel few-shot learning method with deep balanced network and acceleration strategy. Firstly, a series of simple linear operations are applied to few original features to obtain the more features. More features

Gradual pattern extraction is a field in Knowledge Discovery in Databases that maps correlations between attributes of a data set as gradual dependencies. A gradual dependency may take the form: “the more Attribute\(_{K}\), the less Attribute\(_{L}\)”. Classical approa-ches for extracting gradual patterns extend either a breath-first search or a depth-first search strategy. However, these strategies

The subway ridership is related with the social activities, such as, commuting, festival, holiday, and so on, which makes the time series of subway ridership presents seasonal characteristic. This characteristic inspires us to decompose the time series into a seasonal component and an epoch component, and employ a combination forecasting method to estimate the future ridership. We first transform the

Traditional methods for unsupervised domain adaptation often leverage a projection matrix or a neural network as the feature extractor or classifier, where the feature extractor shared by the source and target domains enables the sample distributions to be aligned in the feature space, and simultaneously makes the source domain features separability enough for the classifier. However, only the alignment

A three-way approximation of a fuzzy set, as a generalization of the core and the support of the fuzzy set, provides a generalized qualitatively interpretation of a fuzzy set. An intuitionistic fuzzy set (IFS) generalizes a fuzzy set by using jointly a membership function and a nonmembership function. In this paper, we present a model for constructing a three-way approximation of an IFS according to

A correction to this paper has been published: https://doi.org/10.1007/s13042-021-01350-4

In some cases, the decision process of three-way decisions (3WD) is costly, and sequential three-way decisions (S3WD) may cause errors beyond tolerance. To solve the above problems, in this paper, democratic three-way decisions based on voting mechanism (D3WD-VM) is proposed from the perspective of all conditional attributes. By obtaining decision opinions of different attributes at the coarse granularity

In this paper, we study the unsupervised person re-identification (re-ID) problem, which does not require any annotation information. Our approach considers three aspects in unsupervised re-ID task, i.e., variance across various cameras, label allocation to unlabeled images and hard negative mining. First, an unsupervised style transfer model is adopted to generate style-transferred images with different

The random drift particle swarm optimization (RDPSO) algorithm is an effective random search technique inspired by the trajectory analysis of the canonical PSO and the free electron model in metal conductors placed in an external electric field. However, like other PSO variants, the RDPSO algorithm also inevitably encounters premature convergence when solving multimodal problems. To address this issue

Pose estimation based on RGB-D images is a hot issue that has attracted much attention in recent years. A key technical challenge is to extract features from depth information and image information separately and fully leverage the two complementary data sources. The previous methods ignored the internal connection of local features and the feature fusion of heterogeneous data, limiting the robustness

Currently, gesture recognition is like a problem of feature extraction and pattern recognition, in which a movement is labeling as belonging to a given class. A gesture recognition system’s response could solve different problems in various fields, such as medicine, robotics, sign language, human–computer interfaces, virtual reality, augmented reality, and security. In this context, this work proposes

This paper proposes a new robust truncated L\(_2\)-norm twin support vector machine (T\(^2\)SVM), where the truncated L\(_2\)-norm is used to measure the empirical risk to make the classifiers more robust when encountering lots of outliers. Meanwhile, chance constraints are also employed to specify false positive and false negative error rates. T\(^2\)SVM considers a pair of chance constrained nonconvex

Formal concept analysis as an effective tool for data analysis and knowledge acquisition can be used to describe the potential relation between objects and attributes. In order to handle linguistic uncertainty information with comparability and incomparability, we propose a kind of linguistic-valued formal concept analysis approach based on lattice implication algebra. Firstly, by setting different

The embedding representation of the case text represent text as vector which consist information of original texts abundantly. Text embedding representation usually uses text statistical features or content features alone. However, case texts have characteristics that include similar structure, repeated words, and different text lengths. And the statistical feature or content feature cannot represent

Speech synthesis, an artificial intelligence technology that employs computers to imitate human speech, has played a crucial role in human–computer interaction since it can automatically convert text into speech with satisfactory intelligibility and naturalness. Tacotron2 is the second generation end-to-end English speech synthesis model developed by Google. As Mandarin becomes more and more popular

Intuitionistic fuzzy numbers possess the ability to model the bipolarity of practical objects and phenomena. The positive and negative opinions of decision makers (DMs) could be captured by intuitionistic multiplicative preference relations (IMPRs). In this study, the known consistency definitions of IMPRs are reviewed and the underlying ideas are analyzed. By considering the uncertainty shown by IMPRs

Considering the uncertainties of multi-attribute group decision-making (MAGDM) problems, we put forward the concept of q-rung orthopair fuzzy rough numbers, which is obtained by integrating q-rung orthopair fuzzy numbers and rough numbers. Further a weight calculation method based on q-rung orthopair fuzzy rough number is investigated and a new decision making approach is designed to solve MAGDM problems

Low-rank matrix recovery aims to recover a matrix of minimum rank that subject to linear system constraint. It arises in various real world applications, such as recommender systems, image processing, and deep learning. Inspired by compressive sensing, the rank minimization can be relaxed to nuclear norm minimization. However, such a method treats all singular values of target matrix equally. To address

Massive volumes of high-dimensional data that evolve over time are continuously collected by contemporary information processing systems, which bring up the problem of organizing these data into clusters, i.e. achieving the purpose of dimensional reduction, and meanwhile learning their temporal evolution patterns. In this paper, a framework for evolutionary subspace clustering, referred to as LSTM–ESCM

Although the existing numerical table-to-text generation models have achieved remarkable progress, the idea of generating an accurate analysis of the input table is not well explored. Most existing table-to-text generation algorithms for generating table related information only copy the table record directly but ignore reasoning or calculating over table records. One of the key steps to achieve this

Texts and emoticons expressing sentiment can be used to analyse emotion. In an Internet environment, emoticons are frequently used, which have explicated information for emotion analysis. Considering the characteristics of short texts including sparseness, non-standardization and ambiguities in a subject, two models based on word embedding, emotion-dictionary and fuzzy reasoning are proposed: the low-dimensional

The second-order cone programming support vector machine (SOCP-SVM) formulations have received much attention as the robust and efficient framework for classification. In this paper, we formulate the SOCP-SVM as the convex quadratic circular cone programming support vector machine (CCP-SVM). A projection and contraction method is used to solve the CCP-SVM. Experiments on the benchmark datasets from

Bayesian decision making (DM) quantifies information by the probability density (pd) of treated variables. Gradual accumulation of information during acting increases the DM quality reachable by an agent exploiting it. The inspected accumulation way uses a parametric model forecasting observable DM outcomes and updates the posterior pd of its unknown parameter. In the thought multi-agent case, a neighbouring

A decision-making (DM) agent models its environment and quantifies its DM preferences. An adaptive agent models them locally nearby the realisation of the behaviour of the closed DM loop. Due to this, a simple tool set often suffices for solving complex dynamic DM tasks. The inspected Bayesian agent relies on a unified learning and optimisation framework, which works well when tailored by making a

Multi-class and multi-attribute are two important features of classification problems and have different effects on the requirements and performance of the classifier. Decomposition strategy and overlap function are two effective ways to enhance the performance of classifiers, because the former decomposes a complex multi-class problem into multiple simple sub-problems; the latter uses various functions

The rapid development of Internet of Things (IoT) brings an urgent requirement on intelligent human–device interactions using natural language, which are critical for facilitating people to use IoT devices. The efficient interactive approaches depend on various natural language understanding technologies. Among them, sentence pair modeling (SPM) is essential, where neural networks have achieved great

Metric learning aims to learn a distance to measure the difference between two samples, and it plays an important role in pattern recognition tasks. Most of the existing metric learning methods rely on pairs of samples. However, the importance of sample pairs varies greatly because of possible noise and the difference between samples and the decision boundaries. In this paper, we propose a robust hierarchical

In multi-label learning, exploiting label correlation, alleviating class imbalance and learning label-specific features have been hot topics to increase classification performance. In the paper, we propose a method to address the three issues simultaneously. The method, named LPLC-LA, builds a Bayesian model by exploiting the local positive and negative label correlations with label awareness. LPLC-LA

For the first time, the ensemble feature selection is modeled as a Multi-Criteria Decision-Making (MCDM) process in this paper. For this purpose, we used the VIKOR method as a famous MCDM algorithm to rank the features based on the evaluation of several feature selection methods as different decision-making criteria. Our proposed method, EFS-MCDM, first obtains a decision matrix using the ranks of

The nonnegative matrix factorization (NMF) has been widely used because it can accomplish both feature representation learning and dimension reduction. However, there are two critical and challenging issues affecting the performance of NMF models. One is the selection of matrix factorization rank, while most of the existing methods are based on experiments or experience. For tackling this issue, an

Session-based recommendation (SR) is important in online applications for its ability to predict user’s next interactions solely based on ongoing sessions. To recommend proper items at proper time are two key aspects in SR. The sequence of items in a session implies user’s preferences shift, which may give us clues about when the user interacted. The graph constructed based on a session can give latent

Three different examinations for any course are primarily defined in higher education in Turkey: midterm, final and make-up exams. Whether a student has passed a course is decided by using the scores of midterm and final exams. If this student fails the course as a result of these exams, he can take a make-up exam of this course, and the score of the make-up exam is replaced with the final exam. However

Sarcasm is a common way of rhetoric in our daily life. It is used to express the opposite of the literal meaning, which makes it a challenging task in sentiment analysis of natural language processing (NLP). The formation mechanism of sarcasm is usually caused by the contrast between the positive sentiment and the negative situation. In this paper, we propose a contextual dual-view attention network

Latent factor models (LFMs) have been widely applied in many rating recommendation systems because of their prediction rating capability. Nevertheless, LFMs may not fully leverage rating information and lack good recommendation performance. Furthermore, many subsequent works have often used auxiliary text information, such as user attributes, to improve the prediction effect. However, they did not

In this paper, the design of a fractional-order hyperbolic adaptive neuro-fuzzy backstepping sliding mode controller (HANFBSMC) has been addressed for a class of fractional-order chaotic systems with time-varying delays in their states, control inputs, disturbances and uncertainties. In the proposed controller, adaptive rules are used both in a neuro-fuzzy estimator to estimate the unknown system dynamics

In the following study, an innovative domain adaptation technique is proposed. dCor based Domain Adaptation or dDA technique is based on maximum mean discrepancy (MMD) and distance correlation (dCor); a powerful yet general correlation measure which is applicable to arbitrary-dimensional random variables. By projecting the samples to a common latent feature space, dDA minimizes the discrepancy between