Accurate time series forecasting is essential for proactive management and resource allocation in intelligent IoT systems, where data are often affected by sensor noise, multi-scale periodicity, and cross-frequency interactions. Although decomposition-based frameworks are widely adopted, most existing approaches rely on time-domain modeling with limited nonlinear capacity or treat frequency decomposition as a generic preprocessing step. Such designs fail to align model inductive bias with the intrinsic multi-scale structure of seasonal dynamics, leading to incomplete seasonal representations and degraded forecasting performance. To address this limitation, we propose Detail-aware Wavelet Decomposition and Mixing (DWDMixer), a seasonal-centric forecasting architecture built on multi-scale representation learning and seasonal-trend decomposition, where trend components serve as complementary signals. To enable fine-grained seasonal modeling, we propose a Detail-aware Wavelet Transform Hybrid (DWTH) block that performs hierarchical wavelet decomposition guided by detail-sensitive representations. DWTH captures cross-scale and cross-frequency interactions while jointly modeling temporal and spectral information, yielding expressive multi-resolution representations. Extensive experiments on 10 benchmark datasets demonstrate that DWDMixer significantly outperforms state-of-the-art models, achieving error reductions of up to 9% in MSE for long-term forecasting and 22% in MAE for short-term forecasting. Our code is available at https://github.com/zpc2002zpc/DWDMixer.

MOTIVATION: Computational prediction of drug-target affinity (DTA) plays a critical role in modern drug discovery. However, the limited interpretability of traditional deep learning models and the heterogeneity of multimodal data from compounds and proteins hinder their reliability in practical drug development applications. RESULTS: We propose a novel Uncertainty-aware Multimodal Representation Learning (UAMRL) framework to address these challenges. UAMRL employs a dual-stream encoder to learn cross-modal association mappings between drugs and targets in a latent space and integrates heterogeneous information from different modalities. Moreover, an uncertainty quantification mechanism based on the Normal-Inverse-Gamma distribution is introduced to model the reliability of heterogeneous information and suppress less trustworthy contributions during fusion. Experiments show that UAMRL achieves superior predictive accuracy on multiple public DTA datasets, improving both prediction performance and decision transparency. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/Astraea2xu/UAMRL.

This paper presents a novel approach for aspect-level sentiment analysis by leveraging the relationships between dependent types and aspects. The proposed method involves simplifying the type-aware graph convolutional network and designing a graph convolution module specifically for extracting relations between aspect words. The process begins with constructing an ordinary dependency graph for each sentence using a dependency tree. This graph is then refined by considering syntactic dependencies between context words and aspect-specific words, resulting in an aspect-focused graph. The aspect-focused graph, along with the corresponding embedding matrices, is fed into the aspect-focused GCN to capture the essential aspects and context words. Moreover, an inter-aspect GCN is employed to extract the dependencies between aspect words and other aspect words, utilizing the representations learned by the focused aspect GCN based on the inter-aspect graph. The L-layer of the GCN incorporates a bidirectional attentional mechanism to extract interrelationships, thus enhancing sentiment polarity judgment. Through interactive learning of aspect-specific affective features, the model acquires an understanding of the relationships between important text and aspect words, as well as the relationships among aspect words. Experimental results on five benchmark datasets demonstrate the superior performance of our proposed method compared to state-of-the-art approaches, exhibiting a significant improvement over the regular GCN model.

Multimodal video sentiment analysis aims to integrate multiple modal information to analyze the opinions and attitudes of speakers. Most previous work focuses on exploring the semantic interactions of intra- and inter-modality. However, these works ignore the reliability of multimodality, i.e., modalities tend to contain noise, semantic ambiguity, missing modalities, etc. In addition, previous multimodal approaches treat different modalities equally, largely ignoring their different contributions. Furthermore, existing multimodal sentiment analysis methods directly regress sentiment scores without considering ordinal relationships within sentiment categories, with limited performance. To address the aforementioned problems, we propose a trustworthy multimodal sentiment ordinal network (TMSON) to improve performance in sentiment analysis. Specifically, we first devise a unimodal feature extractor for each modality to obtain modality-specific features. Then, an uncertainty distribution estimation network is customized, which estimates the unimodal uncertainty distributions. Next, Bayesian fusion is performed on the learned unimodal distributions to obtain multimodal distributions for sentiment prediction. Finally, an ordinal-aware sentiment space is constructed, where ordinal regression is used to constrain the multimodal distributions. Our proposed TMSON outperforms baselines on multimodal sentiment analysis tasks, and empirical results demonstrate that TMSON is capable of reducing uncertainty to obtain more robust predictions.

Multi-modal Named Entity Recognition (MNER), which mainly focuses on enhancing text-only NER with visual information, has recently attracted considerable attention. Most current MNER models have made significant progress by jointly understanding visual and language modalities through layers of cross-modality attention. However, these approaches largely ignore the visual bias brought by the image contents and barely consider exploiting the multi-granularity representations and the interactions between visual objects, which are essential in recognizing ambiguous entities. In this paper, we propose aScene graph drivenMulti-modalMulti-granularityMulti-task learning (M3S) framework to better exploit visual and textual information in MNER. Specifically, to explicitly alleviate visual bias, we present a novel multi-task approach by employing the task of Named Entity Segmentation (NES) cascade with Named Entity Categorization (NEC). To obtain detailed visual semantics by explicitly modeling objects and relationships between paired objects, we construct scene graphs as a structured representation of the visual contents. Furthermore, a well-designed Multi-granularity Gated Aggregation (MGA) mechanism is introduced to capture inter-modality interactions and extract critical features for named entity recognition. Extensive experiments on two real public datasets demonstrate the effectiveness of our proposed M3S.

Feature selection, as an effective dimensionality reduction technique, is favored in preprocessing data. However, most existing algorithms are solely liable for labeled or unlabeled data, whereas a limited portion of real-world data is annotated with labels. In this article, we therefore propose a novel scheme named SemiFREE, i.e., semisupervised feature selection with fuzzy relevance and redundancy. First, both labeled and unlabeled samples are assigned with fuzzy decisions that allow class membership to naturally express the fuzziness or uncertainty in data labeling. Second, sample similarities in feature space and fuzzy decision are captured to induce fuzzy information measures for redefining the feature relevance and redundancy. Finally, adhering to the principle of relevance-maximization and redundancy-minimization, SemiFREE leverages the forward sequential searching strategy to identify qualified features progressively. Extensive experiments demonstrate the superiority of SemiFREE in the presence of partially labeled data against some other well-established feature selection algorithms.