Multimodal emotion recognition in conversations is inherently challenging due to ambiguous cues, modality conflicts, and temporal dynamics, all of which contribute to complex and diverse uncertainty sources. While some recent methods incorporate uncertainty modeling, they often focus on overall prediction confidence, without explicitly distinguishing the different sources of uncertainty introduced by underlying factors. To address these challenges, we propose a novel Emotion-Specific Evidence Decomposition framework (ESED) that leverages evidential deep learning to explicitly model and disentangle multimodal emotional uncertainty. Rather than directly fusing features, ESED decomposes each modality's evidence into three interpretable components: (1) emotion-consistent evidence, capturing shared emotional cues across modalities; (2) emotion-specific evidence, highlighting the unique emotional role of each modality; and (3) dynamic evidence, modeling utterance-level temporal variations. These components are adaptively weighted based on emotional intensity, ambiguity, and dynamicity, quantified via prediction entropy, inter-modal divergence, and temporal variance. The final prediction is obtained through an adaptive fusion of these weighted components. Extensive experiments demonstrate that ESED outperforms the state-of-the-art methods on the MELD and IEMOCAP datasets, demonstrating the effectiveness of our proposed method.

Existing wheelset measurement methods primarily rely on one or several single-line lasers, which provide only limited information. Their measurement reliability and accuracy are insufficient to meet the requirements for high-speed train wheelset measurements. To accurately measure a wheel’s parameters online, we propose a novel 3-D reconstruction framework driven by a multiline laser vision sensor array. For local 3-D profile reconstruction, we propose multiline laser calibration, local joint calibration, and moving multitarget joint calibration to achieve the local stitching of multiline laser profiles. For global 3-D profile reconstruction, a global dynamic calibration method is proposed to concatenate local wheel 3-D profiles with varying positions and poses to a complete wheel 3-D profile. Field experimental results show maximum errors of 0.15 mm for flange height, 0.21 mm for flange thickness, and 0.38 mm for diameter. To our knowledge, this is the highest accuracy achieved in the measurement of wheelset geometric parameters.

To detect the wheelset deformation and wear, an intuitive method is to first collect wheelset multi-line laser stripe images by monitors, and then extract the centerlines to construct 3D contours that are transferred to the cloud data center by 6G communication. The images, however, contain flairs and fractures due to the influence of environmental interference and reflected light on the smooth surfaces. The image defects affect the accurate extraction of stripe centerlines. To segment the defects and inpaint them, we propose a new lightweight U-shaped segmentation model URS. A target-shaped receptive field is designed to efficiently extract the details of the local, the ring-shaped, and the cross-shaped context around the local, which facilitates segmenting various defects. A scale-select sub-module is designed to adjust the weights of features from different receptive fields. To train the model, a multi-line laser image defect segmentation dataset MLIDSD is constructed. Experiments demonstrate that the performance of our model surpasses twelve SOTA models explicitly and can achieve a balance between the accuracy and the lightweight requirement.

Wheelset fault detection with high accuracy is challenging due to poor image quality. Specifically, the wheelset images are collected dynamically outdoors and suffer from diffuse reflection and environmental interference. Thus, the images contain light stripe adhesions (light flairs) and local fractures to be inpainted. The existing inpainting models are inapplicable to restore grayscale wheelset images. They are also too heavy to be deployed in an embedded wheelset monitoring equipment. In this paper, we propose a lightweight high-precision inpainting model that consists of a recurrent similarity network with the ghost convolution (RSG-Net) to remove light flairs and repair local fractures. RSG-Net replaces standard Pconv (partial convolutional) layers with soft-coding ones that can improve the feature representational ability. To reduce the influence of the background region features on image restoration, an asymmetrical similarity measure is designed to calculate not only the angle difference between the target and the source feature vectors but also the activation of the source ones. The multi-scale structural similarity (MS-SSIM) loss term is introduced to precisely guide the structural information restoration, such as the stripe edges. Moreover, the ghost convolution is introduced in RSG-Net to realize the model compression that can retain the core features of wheelset images and remove the redundant features. We conduct three groups of experiments that demonstrate the accuracy superiority of the proposed RSG-Net over the baseline methods, and the number of parameters is reduced by about 50%.

It is significant to accurately predict the epidemic trend of COVID-19 due to its detrimental impact on the global health and economy. Although machine learning based approaches have been applied to predict epidemic trend, standard models have shown low accuracy for long-term prediction due to a high level of uncertainty and lack of essential training data. This paper proposes an improved machine learning framework employing Generative Adversarial Network (GAN) and Long Short-Term Memory (LSTM) for adversarial training to forecast the potential threat of COVID-19 in countries where COVID-19 is rapidly spreading. It also investigates the most updated COVID-19 epidemiological data before October 18, 2020 and model the epidemic trend as time series that can be fed into the proposed model for data augmentation and trend prediction of the epidemic. The proposed model is trained to predict daily numbers of cumulative confirmed cases of COVID-19 in Italy, USA, China, Germany, UK, and across the world. Paper further analyzes and suggests which populations are at risk of contracting COVID-19.

News recommendation aims to alleviate the big explosion of news information and helps users find their interesting news. Existing news recommendation models model users' historical click news as users' interests. Although they have achieved acceptable recommendation accuracy, they suffer from severe data sparse problems because of the limited news clicked by users. Further, the user's historical click sequence information has different effects on the user's interest, and simply combining them can not reflect this difference. Therefore, we propose an attention-based graph neural network news recommendation model. In our model, muti-channel convolutional neural network is used to generate news representations, and recurrent neural network is used to extract the news sequence information that users clicked on. Users, news, and topics are modeled as three types of nodes in a heterogeneous graph, and their relationships are modeled as edges. Graph neural network is used to effectively extract the structural information from heterogeneous graph, and helps to solve the problem of sparse data. Taking into account the different effects of different information on recommendation results, we use the attention mechanism to fuse this information distinctively. Extensive experiments conducted on the real online news datasets show that our model is superior to advanced deep learning-based recommendation methods.

Our global economy increasingly depends on our ability to gather, analyze, link, and compare very large data sets. Keeping up with such big data poses challenges in terms of both computational performance and energy efficiency, and motivates different approaches to explore data center systems and architectures. To better understand the processor design decisions in context of data analytics in data centers, we conduct comprehensive evaluations using representative data analaytics workloads on representative conventional multi-core and many-core processors. After a comprehensive analysis of performance, power, energy efficiency and performance-cost efficiency, we have the following observations: contrasted with the conventional wisdom that uses wimpy many-core processors to improve energy-efficiency, the brawny multi-core processors with SMT (simultaneous multithreading) and dynamic overclocking technologies outperform the counterparts in terms of not only execution time, but also energy-efficiency for most of data analytics workloads in our experiments.

An information cascade occurs when a person observes the actions of others and then engages in the same acts. Cascades may break out if a large population of nodes in the network get affected. The outbreaks of cascades will often bring influential events, which leads to an open research problem: how to accurately predict the cascading outbreaks in social networks? Although there have been some existing works on cascading outbreak prediction, they ignore the structure information of cascades. In this paper, we propose to use subcascades as features for cascade outbreak prediction. We use frequent sequential pattern mining to extract subcascades and then propose a max-margin based classifier to select at most B features for prediction. The proposed model is empirically evaluated on both synthetic and real-world networks. Experimental results demonstrate the effectiveness of the proposed model.