With the exponential expansion of e-commerce, an immense volume of historical sales data has been generated and amassed. This influx of data has created an opportunity for more accurate sales forecasting. While various sales forecasting methods and models have been applied in practice, existing ones often struggle to fully harness sales data and manage significant fluctuations. As a result, they frequently fail to make accurate predictions, falling short of meeting enterprise needs. Therefore, it is imperative to explore new models to enhance the accuracy and efficiency of sales forecasting. In this paper, we introduce a model tailored for sales forecasting based on a Transformer with encoder–decoder architecture and multi-head attention mechanisms. We have made specific modifications to the standard Transformer model, such as removing the Softmax layer in the last layer and adapting input embedding, position encoding, and feedforward network components to align with the unique characteristics of sales forecast data and the specific requirements of sales forecasting. The multi-head attention mechanism in our proposed model can directly compute the dot product results in a single step, addressing long-term time-dependent computation challenges while maintaining lower time complexity and greater interpretability. This enhancement significantly contributes to improving the model’s accuracy and efficiency. Furthermore, we provide a comprehensive formula representation of the model for the first time, facilitating better understanding and implementation. We conducted experiments using sales datasets that incorporate various factors influencing sales forecasts, such as seasons, holidays, and promotions. The results demonstrate that our proposed model significantly outperforms seven selected benchmark methods, reducing RMSLE, RMSWLE, NWRMSLE, and RMALE by approximately 48.2%, 48.5%, 45.2, and 63.0%, respectively. Additionally, ablation experiments on the multi-head attention and the number of encoder–decoders validate the rationality of our chosen model parameters.

With the ever-increasing demand for marine products with high nutritional value in the sea, rapid and accurate detection of target organisms is highly desired. In this context, a novel underwater object detection algorithm based on improved Single Shot MultiBox Detector (SSD) is proposed to improve the detection accuracy and real-time performance in complex underwater environment. The proposed algorithm employs ResNeXt-50 instead of VGGNet-16 as the backbone network to improve the ability to obtain details and position information of the target object. To be more specific, a channel-spatial attention mechanism is incorporated in the deep layers of the improved XC-SSD model to enhance semantic information of high-level feature maps and reduce missed detection rate and false detection rate. Comprehensive experiments on the URPC-2019 dataset show that the detection accuracy and speed of the proposed algorithm are 79.76% and 18.95 FPS, respectively, which are 3.49% and 2.8 FPS higher than the original SSD algorithm. Experimental results clearly demonstrate that the proposed algorithm is highly efficient and suitable for real-time object detection.

Chronic rhinosinusitis with nasal polyps (CRSwNP) is characterized by heterogeneous inflammatory endotypes of unknown etiology. Invariant natural killer T (iNKT) cells are multifunctional innate T cells that exhibit Th1-, Th2-, and Th17-like characteristics. We investigated functional relationships between iNKT cells and inflammatory subtypes of CRSwNP. Eighty patients with CRSwNP and thirty-two control subjects were recruited in this study. Flow cytometry was used to analyze the frequencies and functions of iNKT cells and their subsets in peripheral blood mononuclear cells (PBMCs) and tissues. Polyp tissue homogenates were used to study the multifunctionality of iNKT cells. iNKT cells were significantly increased in polyps (0.41%) than in control mucosa (0.12%). iNKT cells were determined in the paucigranunlocytic (n=20), eosinophilic (n=22), neutrophilic (n=23), and mixed granulocytic (n=13) phenotypes of CRSwNP. The percentages of iNKT cells and HLA-DR⁺PD-1⁺ subsets were lower in eosinophilic or mixed granulocytic polyps than those of other phenotypes. iNKT cells and subsets were enriched in polyp tissues than in matched PBMCs. The evaluation of surface markers, transcription factors, and signature cytokines indicated that the frequencies of iNKT2 and iNKT17 subsets were significantly increased in eosinophilic and neutrophilic polyps, respectively, than in the paucigranulocytic group. Moreover, the production of type 2 (partially dependent on IL-7) and type 17 (partially dependent on IL-23) iNKT cells could be stimulated by eosinophilic and neutrophilic homogenates, respectively. Our study revealed that type 2 and type 17 iNKT cells were involved in eosinophilic and neutrophilic inflammation, respectively, in CRSwNP, while different inflammatory microenvironments could modulate the functions of iNKT cells, suggesting a role of iNKT cells in feedback mechanisms and local inflammation.