In this paper, a parallel decoder and a word group prediction module are proposed to speed up decoding and improve the effect of captions. The features of the image extracted by the encoder are linearly projected to different word groups, and then a unique relaxed mask matrix is designed to improve the decoding speed and the caption effect. First, since image captioning is composed of many words, sentences can also be broken down into word groups or words according to their syntactic structure, and we achieve this function through constituency parsing. Second, we make full use of the extracted features to predict the size of word groups. Then, a new embedding representing the information of the word is proposed based on word embedding. Finally, with the help of word groups, we design a mask matrix to modify the decoding process so that each step of the model can produce one or more words in parallel. Experiments on public datasets demonstrate that our method can reduce the time complexity while maintaining competitive performance.

Deep learning-based video coding methods have demonstrated superior performance compared to classical video coding standards in recent years. The vast majority of the existing deep video coding (DVC) networks are based on convolutional neural networks (CNNs), and their main drawback is that since CNNs are affected by the size of the receptive field, they cannot effectively handle long-range dependencies and local detail recovery. Therefore, how to better capture and process the overall structure as well as local texture information in the video coding task is the core issue. Notably, the transformer employs a self-attention mechanism that captures dependencies between any two positions in the input sequence without being constrained by distance limitations. This is an effective solution to the problem described above. In this paper, we propose end-to-end transformer-based adaptive video coding (TAVC). First, we compress the motion vector and residuals through a compression network built on the vision transformer (ViT) and design the motion compensation network based on ViT. Second, based on the requirement of video coding to adapt to different resolution inputs, we introduce a position encoding generator (PEG) as adaptive position encoding (APE) to maintain its translation invariance across different resolution video coding tasks. The experiment shows that for multiscale structural similarity index measurement (MS-SSIM) metrics, this method exhibits significant performance gaps compared to conventional engineering codecs, such as [Formula: see text], [Formula: see text], and VTM-15.2. We also achieved a good performance improvement compared to the CNN-based DVC methods. In the case of peak signal-to-noise ratio (PSNR) evaluation metrics, TAVC also achieves good performance.

The State Estimation (SE) method is troubled by heavy computational tasks and poor estimation tracking capability for the large-scale active distribution network. Given the aforementioned difficulty, this paper proposed a novel multi-area Forecasting Aided State Estimation (FASE) strategy to perceive the state of the system effectively. The proposed strategy begins with the implementation of an improved multi-area FASE model. The processing of multi-source measurement data, such as Micro Phasor Measurement Units (μPMUs) and Supervisory Control and Data Acquisition (SCADA), and equivalent load based information interaction reliably complete the FASE of multi areas. Especially, a 3rd degree dimensionality reduction SR-CKF algorithm is designed for local FASE model considering the influence of large-scale distribution networks data on the numerical stability of the estimator. The case study shows the advantages of the proposed strategy in estimation accuracy, efficiency, and numerical stability compared with the existing ones.

Modeling and inferring the intricate stochastic variations of the manufacturing quality still remain a significant challenge, especially when dealing with non-Euclidean functional data, which emerge ubiquitous in manufacturing processes. To address this issue, this study proposes the deep wavelet neural process (DWNP), an innovative deep learning model leveraging the exceptional potential of neural processes (NPs) for modeling high-dimensional stochastic variations and the superiority of geometric deep learning in analyzing non-Euclidean functional data, to facilitate typical manufacturing quality inference tasks characterized by non-Euclidean functional data. Three major works have been done in this study. First, the Laplace–Beltrami operator was manipulated and a fast spectral graph wavelet transform was performed to derive a tailored graph wavelet neural network (GWNN), which possesses the ability to capture and decouple complex variation patterns in typical non-Euclidean functional data in manufacturing. Second, based on the theoretical and structural prototype of NPs, the DWNP was derived and built up, exploiting the GWNN to model the stochastic variations of non-Euclidean functional data. Finally, an experiment was conducted on a real automotive manufacturing process to verify the effectiveness and superiority of the proposed DWNP model, in which two typical non-Euclidean functional data types were investigated.

This article develops a proactive and reactive service composition (PRSC) method for CMfg based on digital thread. First, the digital thread-driven information interaction architecture is established, based on which the detailed process of PRSC and the constitution of digital thread are designed. Then, the strategy of proactive SC and the process of reactive service adjustment are proposed: the former selectively allocate alternative services for subtasks to balance the quality of service (QoS) and robustness of the composite manufacturing service, the latter implements the decision-making for service exception handling based on digital thread. Finally, a group of simulation experiments and a practical case study are conducted. The results show that the proposed digital thread-driven PRSC method integrates the advantages of proactive planning and reactive adjustment, effectively reduces the service reservation cost of robust service composition and improves the actual QoSs under uncertainties based on the support of near real-time information interaction.

Remaining useful life (RUL) prediction can provide a foundation for the operation and maintenance of industrial equipment. In order to improve the predictive ability for the complex degradation trajectory, a new dual-thread gated recurrent unit (DTGRU) is explored. It uses a dual-thread learning strategy to mine the stationary and nonstationary information from the input data and the difference of hidden states at two adjacent time steps. Then the state transition updating formulas of DTGRU are derived. Using the collected gear vibration signals and degradation-trend-constrained variational autoencoder, the gear health indicator (HI) is constructed. Based on the constructed HI and DTGRU, a novel RUL prediction method is developed. Via multiple gear life-cycle datasets, the effectiveness of the DTGRU-based RUL prediction approach is verified. Furthermore, compared with the existing typical prediction methods, the experimental results show that DTGRU has higher predictive ability in terms of HI fitting precision and RUL prediction performance.

Accurate traffic prediction is a critical yet challenging task in Intelligent Transportation Systems, benefiting a variety of smart services, e.g., route planning and traffic management. Although extensive efforts have been devoted to this problem, it is still not well solved due to the flexible dependency within traffic data along both spatial and temporal dimensions. In this paper, we explore the flexibility from three aspects, namely the time-varying local spatial dependency, the dynamic temporal dependency, and the global spatial dependency. Then we propose a novel Dual Graph Gated Recurrent Neural Network (DG2RNN) to effectively model all these dependencies and offer flexible (multi-step) predictions for future traffic flow. Specifically, we design a Dual Graph Convolution Module to capture the local spatial dependency from two perspectives, namely road distance and adaptive correlation. To model the dynamic temporal dependency, we firstly develop a Bidirectional Gated Recurrent Layer to capture the forward and backward sequential contexts of historical traffic flow, then combine the derived hidden states with their various contributions learned by a temporal attention mechanism. Besides, we further design a spatial attention mechanism to learn the latent global spatial dependency among all locations to facilitate the prediction. Extensive experiments on three types of real-world traffic datasets demonstrate that our model outperforms state-of-the-arts. Results also show our model has more stable performance for the flexible prediction with varying prediction horizons.

Fog manufacturing (FMfg) is an emerging real-life cloud manufacturing (CMfg) paradigm based on digital twin models, which perceive finely dynamic processes and provide on-demand optimization services. Service composition as a core plays a vital role in achieving the optimization goal. Service composition issues in actual CMfg are mostly multitask problems that need considering dynamic factors. Otherwise, the planned production process will deviate significantly from actual situations. However, such multitask service composition (MTSC) models have scarcely been studied. Thus, this article formulates a multiobjective MTSC model considering the crucial resource competition process between multitasks under multiple practical constraints (MPC). Then, to solve the MTSC–MPC, this article develops an adaptive multiobjective whale optimization algorithm (AMOWOA) containing well-designed strategies. Numerical experiments and application cases verify that AMOWOA outperforms the comparison algorithms. AMOWOA continually can optimize and adaptively adjust the service composition process based on the crucial manufacturing resource available time under actual constraints in FMfg environment.