Facial Expression Recognition (FER) has achieved significant success in recent years due to the rise of deep learning. Meanwhile, latent semantic information is crucial for recognizing facial expressions with subtle differences. Inspired by inconsistencies in learning intensity across different layers of deep learning networks — where shallow-layer features lack generalization and task relevance compared to deep-layer features — we propose a novel Hierarchical Semantic Transfer (HST) method. This method uses attention maps from deep-layer features to regularize the model, enabling it to effectively capture the necessary semantic information and align the latent semantics between shallow and deep features, while ignoring irrelevant noise. Furthermore, to address the issue of class imbalance present in FER datasets, we introduce a Batch-wise Similarity Attention (BSA) mechanism to learn the similarity relationships between features of different samples. Extensive experiments on different datasets and backbones demonstrate that HSBS can work together to significantly improve model performance and achieve state-of-the- art results on those FER datasets.

Time series clustering is usually an essential unsupervised task in cases when category information is not available and has a wide range of applications. However, existing time series clustering methods usually either ignore temporal dynamics of time series or isolate the feature extraction from clustering tasks without considering the interaction between them. In this article, a time series clustering framework named self-supervised time series clustering network (STCN) is proposed to optimize the feature extraction and clustering simultaneously. In the feature extraction module, a recurrent neural network (RNN) conducts a one-step time series prediction that acts as the reconstruction of the input data, capturing the temporal dynamics and maintaining the local structures of the time series. The parameters of the output layer of the RNN are regarded as model-based dynamic features and then fed into a self-supervised clustering module to obtain the predicted labels. To bridge the gap between these two modules, we employ spectral analysis to constrain the similar features to have the same pseudoclass labels and align the predicted labels with pseudolabels as well. STCN is trained by iteratively updating the model parameters and the pseudoclass labels. Experiments conducted on extensive time series data sets show that STCN has state-of-the-art performance, and the visualization analysis also demonstrates the effectiveness of the proposed model.

We introduce the idea of inter-slice image augmentation whereby the numbers of the medical images and the corresponding segmentation labels are increased between two consecutive images in order to boost medical image segmentation accuracy. Unlike conventional data augmentation methods in medical imaging, which only increase the number of training samples directly by adding new virtual samples using simple parameterized transformations such as rotation, flipping, scaling, etc., we aim to augment data based on the relationship between two consecutive images, which increases not only the number but also the information of training samples. For this purpose, we propose a frame-interpolation-based data augmentation method to generate intermediate medical images and the corresponding segmentation labels between two consecutive images. We train and test a supervised U-Net liver segmentation network on SLIVER07 and CHAOS2019, respectively, with the augmented training samples, and obtain segmentation scores exhibiting significant improvement compared to the conventional augmentation methods.

Time series with missing values (incomplete time series) are ubiquitous in real life on account of noise or malfunctioning sensors. Time-series imputation (replacing missing data) remains a challenge due to the potential for nonlinear dependence on concurrent and previous values of the time series. In this paper, we propose a novel framework for modeling incomplete time series, called a linear memory vector recurrent neural network (LIME-RNN), a recurrent neural network (RNN) with a learned linear combination of previous history states. The technique bears some similarity to residual networks and graph-based temporal dependency imputation. In particular, we introduce a linear memory vector [called the residual sum vector (RSV)] that integrates over previous hidden states of the RNN, and is used to fill in missing values. A new loss function is developed to train our model with time series in the presence of missing values in an end-to-end way. Our framework can handle imputation of both missing-at-random and consecutive missing inputs. Moreover, when conducting time-series prediction with missing values, LIME-RNN allows imputation and prediction simultaneously. We demonstrate the efficacy of the model via extensive experimental evaluation on univariate and multivariate time series, achieving state-of-the-art performance on synthetic and real-world data. The statistical results show that our model is significantly better than most existing time-series univariate or multivariate imputation methods.

Orthogonal Frequency Division Multiple Access (OFDMA) introduced in IEEE 802.11ax amendment promises to improve spectral efficiency by grouping subcarriers into resource units (RUs). It is important to design RU assignment to improve throughput for the OFDMA-based WLAN. In this paper, we present the High Throughput RU Assignment Scheme (HiTRAS) and formulate the optimization problem maximizing network throughput for the HiTRAS. The solution of the optimization problem leads to the optimal RU assignment that allocates RUs to multiple mobile stations (STAs) so that the STAs can transmit their uplink traffic simultaneously and thus high throughput is gained. The simulation results show that the HiTRAS outperforms the existing schemes in terms of throughput.

Previous studies have shown that attention mechanisms and shortest dependency paths have a positive effect on relation classification. In this paper, a keyword-attentive sentence mechanism is proposed to effectively combine the two methods. Furthermore, to effectively handle the imbalanced classification problem, this paper proposes a new loss function called the synthetic stimulation loss, which uses a modulating factor to allow the model to focus on hard-to-classify samples. The proposed two methods are integrated into a bidirectional gated recurrent unit (BiGRU). As a single model is not strong in noise immunity, this paper applies the mutual learning method to our model and forces the networks to teach each other. Therefore, we call the final model SSL-KAS-MuBiGRU. Experiments on the SemEval-2010 Task 8 data set and the TAC40 data set demonstrate that the keyword-attentive sentence mechanism and synthetic stimulation loss are useful for relation classification, and our model achieves state-of-the-art results.

Recognizing human actions represented by 3D trajectories of skeleton joints is a challenging machine learning task. In this paper, the 3D skeleton sequences are regarded as multivariate time series, and their dynamics and multiscale features are efficiently learned from action echo states. Specifically, first the skeleton data from the limbs and trunk are projected into five high dimensional nonlinear spaces, that are randomly generated by five dynamic, training-free recurrent networks, i.e., the reservoirs of echo state networks (ESNs). In this way, the history of the time series is represented as nonlinear echo states of actions. We then use a single multiscale convolutional layer to extract multiscale features from the echo states, and maintain multiscale temporal invariance by a max-over-time pooling layer. We propose two multi-step fusion strategies to integrate the spatial information over the five parts of the human physical structure. Finally, we learn the label distribution using softmax. With one training-free recurrent layer and only layer of convolution, our Convolutional Echo State Network (ConvESN) is a very efficient end-to-end model, and achieves state-of-the-art performance on four skeleton benchmark data sets.

A new learning algorithm for categorical data, named CRN (Classification by Rule-based Neighbors) is proposed in this paper. CRN is a nonmetric and parameter-free classifier, and can be regarded as a hybrid of rule induction and instance-based learning. Based on a new measure of attributes quality and the separate-and-conquer strategy, CRN learns a collection of feature sets such that for each pair of instances belonging to different classes, there is a feature set on which the two instances disagree. For an unlabeled instance I and a labeled instance I', I' is a neighbor of I if and only if they agree on all attributes of a feature set. Then, CRN classifies an unlabeled instance I based on I's neighbors on those learned feature sets. To validate the performance of CRN, CRN is compared with six state-of-the-art classifiers on twenty-four datasets. Experimental results demonstrate that although the underlying idea of CRN is simple, the predictive accuracy of CRN is comparable to or better than that of the state-of-the-art classifiers on most datasets.

Automatic keyphrase extraction from documents is a task with many applications in information retrieval and natural language processing. Previously, several keyphrase extraction methods have been proposed based on different techniques. In this paper, a keyphrase extraction algorithm based on the least squares support vector machine is proposed. In order to determine whether a phrase is a keyphrase or not, the following features of a phrase in a given document are adopted: its TF (term frequency) and IDF (inverted document frequency), whether or not it appears in the title or headings (subheadings) of the given document, and its distribution in the paragraphs of the given document. The algorithm is evaluated by the standard information retrieval metrics of precision and recall and human assessment. Experiment results show that this approach is competitive with other known methods.