Search

In recent years, with the rise of the Internet, e-commerce has become an important field of commodity sales. However, e-commerce is affected by many factors, and the wrong judgment of supply and marketing relationships will bring huge losses to operators. Therefore, it is of great significance to establish a model that can effectively achieve high precision sales prediction for ensuring the sustainable development of e-commerce enterprises. In this paper, we propose an e-commerce sales forecasting model that considers the features of many aspects of correlation. In the first layer of the model, the temporal convolutional network (TCN) is used to extract the deep temporal characteristics of univariate sales historical data, which ensures the integrity of temporal information of sales characteristics. In the second layer, the feature selection method based on reinforcement learning is used to filter the effective correlation feature set and combine it with the temporal feature after processing, which not only improves the amount of effective information input by the model, but also avoids the high feature dimension. The third layer of the reformer model learns all the features and pays different attention to the features with different degrees of importance, ensuring the stability of the sales forecast. In the experimental part, we compare the proposed model with the current advanced sales forecasting model, and we can find that the proposed model has higher stability and accuracy. [ABSTRACT FROM AUTHOR]

Recently, with the increasing scale of the volume of freight transport and the number of passengers, the study of railway vehicle fault diagnosis and condition management is becoming more significant than ever. The axle temperature plays a significant role in the locomotive operating condition assessment that sudden temperature changes may lead to potential accidents. To realize accurate real-time condition monitoring and fault diagnosis, a new multi-data-driven model based on reinforcement learning and deep learning is proposed in this paper. The whole modeling process contains three steps: In step 1, the feature crossing and reinforcement learning methods are applied to select the suitable features that could efficiently shorten the redundancy of the input. In step 2, the stack denoising autoencoder is employed to extract deep fluctuation information in the features after the reinforcement learning. In step 3, the bidirectional gated recurrent unit algorithm is utilized to accomplish the forecasting model and achieve the final results. These parts of the integrated modeling structure contributed to increased forecasting accuracy than single models. By analyzing the forecasting results of three different data series, it could be summarized that: (1) The proposed two-stage feature selection method and feature extraction method could greatly optimize the input for the predictor and form the optimal axle temperature forecasting model. (2) The proposed hybrid model can achieve satisfactory forecasting results which are better than the contrast algorithms proposed by other researchers. [ABSTRACT FROM AUTHOR]

This paper reviews the current research status of rolling bearing fault diagnosis technology for railway vehicles. Several domains are covered, including vibration fault diagnosis, acoustic signal fault diagnosis, and temperature prediction diagnosis methods on train rolling bearing test principles and related research. The application scenarios, system diagnosis accuracies, and model structures of various studies in the literature are also compared and analyzed. Furthermore, the main technical points to be improved and the analysis of the possible research directions are proposed, which provide new research ideas for subsequent fault diagnosis methods and system innovation research and development. [ABSTRACT FROM AUTHOR]

In recent years, online course learning has gradually become the mainstream of learning. As the key data reflecting the quality of online courses, users' comments are very important for improving the quality of online courses. The sentiment information contained in comments is the guide of course improvement. A new ensemble model is proposed for sentiment analysis. The model takes full advantage of Word2Vec and Glove in word vector representation, and utilizes the bidirectional long and short time network and convolutional neural network to achieve deep feature extraction. Moreover, the multi-objective gray wolf optimization (MOGWO) ensemble method is adopted to integrate the models mentioned above. The experimental results show that the sentiment recognition accuracy of the proposed model is higher than that of the other seven comparison models, with an F1score over 91%, and the recognition results of different emotion levels indicate the stability of the proposed ensemble model. [ABSTRACT FROM AUTHOR]

The axle temperature is an index factor of the train operating conditions. The axle temperature forecasting technology is very meaningful in condition monitoring and fault diagnosis to realize early warning and to prevent accidents. In this study, a data-driven hybrid approach consisting of three steps is utilized for the prediction of locomotive axle temperatures. In stage I, the Complementary empirical mode decomposition (CEEMD) method is applied for preprocessing of datasets. In stage II, the Bi-directional long short-term memory (BILSTM) will be conducted for the prediction of subseries. In stage III, the Particle swarm optimization and gravitational search algorithm (PSOGSA) can optimize and ensemble the weights of the objective function, and combine them to achieve the final forecasting. Each part of the combined structure contributes its functions to achieve better prediction accuracy than single models, the verification processes of which are conducted in the three measured datasets for forecasting experiments. The comparative experiments are chosen to test the performance of the proposed model. A sensitive analysis of the hybrid model is also conducted to test its robustness and stability. The results prove that the proposed model can obtain the best prediction results with fewer errors between the comparative models and effectively represent the changing trend in axle temperature. [ABSTRACT FROM AUTHOR]

The bearing temperature forecasting provide can provide early detection of the gearbox operating status of wind turbines. To achieve high precision and reliable performance in bearing temperature forecasting, a novel hybrid model is proposed in the paper, which is composed of three phases. Firstly, the variational mode decomposition (VMD) method is employed to decompose raw bearing temperature data into several sub-series with different frequencies. Then, the SAE-GMDH method is utilized as the predictor in the subseries. The stacked autoencoder (SAE) is for the low-latitude features of raw data, while the group method of data handling (GMDH) is applied for the sub-series forecasting. Finally, the imperialist competitive algorithm (ICA) optimizes the weights for subseries and combines them to achieve the final forecasting results. By analytical investigation and comparing the final prediction results in all experiments, it can be summarized that (1) the proposed model has achieved excellent prediction outcome by integrating optimization algorithms with predictors; (2) the experiment results proved that the proposed model outperformed other selective models, with higher accuracies in all datasets, including three state-of-the-art models. [ABSTRACT FROM AUTHOR]

Purpose: Molecular residual disease (MRD) is a promising biomarker in colorectal cancer (CRC) for prognosis and guiding treatment, while the whole-exome sequencing (WES) based tumor-informed assay is standard for evaluating MRD based on circulating tumor DNA (ctDNA). In this study, we assessed the feasibility of a fixed-panel for evaluating MRD in CRC., Materials and Methods: Seventy-five patients with resectable stage I-III CRC were enrolled. Tumor tissues obtained by surgery, and preoperative and postoperative day 7 blood samples were collected. The ctDNA was evaluated using the tumor-agnostic and tumor-informed fixed assays, as well as the WES-based and panel-based personalized assays in randomly selected patients., Results: The tumor-informed fixed assay had a higher preoperative positive rate than the tumor-agnostic assay (73.3% vs. 57.3%). The preoperative ctDNA status failed to predict disease-free survival (DFS) in either of the fixed assays, while the tumor-informed fixed assay-determined postoperative ctDNA positivity was significantly associated with worse DFS (hazard ratio [HR], 20.74; 95% confidence interval [CI], 7.19 to 59.83; p < 0.001), which was an independent predictor by multivariable analysis (HR, 28.57; 95% CI, 7.10 to 114.9; p < 0.001). Sub-cohort analysis indicated the WES-based personalized assay had the highest preoperative positive rate (95.1%). The two personalized assays and the tumor-informed fixed assay demonstrated same results in postoperative landmark (HR, 26.34; 95% CI, 6.01 to 115.57; p < 0.001), outperforming the tumor-agnostic fixed panel (HR, 3.04; 95% CI, 0.94 to 9.89; p=0.052)., Conclusion: Our study confirmed the prognostic value of the ctDNA positivity at postoperative day 7 by the tumor-informed fixed panel. The tumor-informed fixed panel may be a cost-effective method to evaluate MRD, which warrants further studies in future.

Background: Pancreatic cancer (PC) is a highly malignant tumor associated with low survival rates. It is challenging to predict the survival of surgically resected patients with PC. A prognostic staging tool could be beneficial to guide treatments and also aid post-treatment surveillance. This study aimed to identify tissue-based DNA methylation risk-score model to predict the prognosis of surgically resected pancreatic cancer patients., Methods: We performed a monocentric, retrospective study that included 50 patients with stage I-II PC from The First Affiliated Hospital of Soochow University (SU cohort). Both tumor and adjacent normal tissues were obtained from each patient and subjected to capture-based targeted methylation profiling., Results: In total, 1,162 DNA methylation blocks (DMBs) were differentially methylated in tumor tissues compared with adjacent long-distance tissues (P<0.05). Least Absolute Shrinkage and Selection Operator (LASSO) and stepwise regression analyses revealed a significant correlation between the methylation signature (risk score) and overall survival (OS). Patients in the high-risk group showed significantly poorer OS than those in the low-risk group in the survival analysis [P≤0.001; area under curve (AUC) at 1 year, 0.789; AUC at 2 years, 0.852]. The risk score was also validated using clinical and methylation data of 166 PC patients from The Cancer Genome Atlas pancreatic ductal adenocarcinoma (TCGA-PDAC) dataset. Patients in the high-risk group showed significantly poorer OS than those in the low-risk group (P=0.004; AUC at 1 years, 0.677; AUC at 3 years, 0.611). When clinical parameters were considered, the risk score was the only independent prognostic parameter (P<0.001) in the Cox regression analysis. Furthermore, low-risk patients had higher levels of immune infiltration, anti-tumor immune activation, and increased sensitivity to gemcitabine and paclitaxel. In contrast, high-risk patients had lower KRAS mutation rates and benefited more from cisplatin., Conclusions: In our study, we constructed and validated a tissue-based DNA methylation risk-score model to predict prognosis and identify PC patients with a high mortality risk at the time of surgery. This model might provide a tissue-based prognostic assessment tool for clinicians to aid their treatment decision-making., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://gs.amegroups.com/article/view/10.21037/gs-22-517/coif). The authors have no conflicts of interest to declare., (2022 Gland Surgery. All rights reserved.)