Growing evidence links intra-urban gradients in atmospheric fine particles (PM_2.5), a complex and variable cocktail of toxic chemicals, to adverse health outcomes. Here, we propose an improved hierarchical deep learning model framework to estimate the hourly variation of PM_2.5 mass concentration at the street level. By using a full-year monitoring data (including meteorological parameters, hourly concentrations of PM_2.5, and gaseous precursors) from multiple stations in Shanghai, the largest city in China, as a training dataset, we first apply a convolutional neural network to obtain cross-domain and time-series features so that the inherent features of air quality and meteorological data associated with PM_2.5 can be effectively extracted. Next, a Gaussian weight calculation layer is used to determine the potential interaction effects between different regions and neighboring stations. Finally, a long and short-term memory model layer is used to efficiently extract the temporal evolution characteristics of PM_2.5 concentrations from the previous output layer. Further comparative analysis reveals that our proposed model framework significantly outperforms previous benchmark methods in terms of the stability and accuracy of PM_2.5 prediction, which has important implications for the intra-urban health assessment of PM_2.5-related pollution exposures.

This paper addresses the problem where optimizing a single production shop within a production chain may not improve the overall performance of the entire chain. To overcome this and synchronize the efficiency of each shop, methods are proposed to align the output rate of an upstream shop with the limited intake rate of its downstream shop. In the proposed methods, the output rate of the upstream shop is used to guide job scheduling, processing, and resource allocation in the shop. Simulation results from a real-world case study demonstrate that implementing this pull-based system reduces job earliness and tardiness by over 90% in the tested factory, where the upstream shop is a flexible job shop, leading to lower inventory costs, idling costs, and labor costs.

A new method for speech noise reduction by using empirical mode decomposition (EMD) and least mean square (LMS) filters is proposed in this paper. Due to its simplicity and robustness, the LMS algorithm has been widely used in many applications. The EMD method is used before the LMS algorithm to form the EMD-LMS algorithm, which shows better results than using only the LMS algorithm.

Named Entity Recognition (NER) can be divided into three subtasks: Flat, Nested, and Discontinuous. They are usually handled separately and independently, and most traditional approaches rely on representations in the form of Token and Span, which limits the flexibility of the models.Although Seq2Seq-based models have recently been proposed to handle these three NER tasks in a unified way, they usually focus too much on independent verification of entity spans while ignoring the label dependencies and detailed word-word relations in the modeling process. To this end, we propose the MLSU (Multi-level Semantic Understanding) model for unified NER tasks. The overall architecture leverages an Encoder-Decoder structure that integrates sequence and grid-level semantic blocks, enhancing the model’s ability to process complex text structures effectively. The model combines entity labels attention with pre-trained GloVe embeddings at the sequence level to optimize encoding and enhance context comprehension. Subsequently, the grid-level semantic extraction employs Conditional Layer Normalization(CLN) and Dilated CNNs. This enables MLSU to capture the interaction between text and labels effectively and enhances the ability to process complex text. We conducted experiments on six popular NER datasets and our MLSU model achieved generally good performance at or near the SOTA results, validating its effectiveness and advantages in handling various NER tasks.

The post-equalizer in the Underwater Visible Light Communication (UVLC) system can overcome the nonlinear distortion existing in the system. The existing nonlinear post-equalizer based on deep learning still has problems such as the number of data nodes has a great influence on the effect, the equalization effect decreases significantly when the data rate becomes higher and too complex a model leads to slow training time. In this paper, we propose a Dual Self-Attention Network (DSANet) as a post equalizer in the CAP modulated UVLC system. Experiments show that the DSANet-based post equalizer can achieve good equalization performance at different data rates; it shows strong robustness when the number of data nodes changes; its training speed is close to that of the plainest nonlinear post-equalizer.

In order to improve the athletic performance of rowers in China, this paper proposes a comprehensive design of an intelligent propeller pool digitization system based on multisource data fusion. The current level of digitization in the propeller pool system is low, lacking overall consistency in research and system development, and heavily relying on subjective judgments from coaches for evaluation. By focusing on real-time collection of key parameters such as internal load, rowing force, and rowing trajectory, as well as analysis of historical data, this system facilitates continuous adjustments during training for both coaches and athletes. Moreover, the system incorporates image processing techniques to analyze athletes' movements, combining data and image processing to better enhance the athletic performance of rowers.