Objective: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time. Methods: We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors. Results: Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best permanence. Conclusion: The experimental results demonstrate the effectiveness of the proposed models. The proposed models can provide a computer-aided medical diagnostics system by simply using time series of serological indicators.

Although numerous epidemiological studies on appendicitis have been conducted worldwide, only a few studies have paid attention to the effect of socioeconomic status on appendicitis, particularly studies focusing on the low-income population (LIP). We analyzed the epidemiological features of appendicitis in Taiwan using data from the National Health Insurance Research Database from 2003 to 2011. All cases diagnosed as appendicitis were enrolled. Between 2003 and 2011, 2,916 patients from the LIP and 209,206 patients from the normal population (NP) were diagnosed with appendicitis. Our finding revealed that the ratios of comorbidities, complicated appendicitis, and readmissions in LIP patients were slightly higher than those of NP patients. LIP patients were more likely to live in suburban and rural areas, and hence a higher proportion of them were hospitalized in a district or regional hospital compared with NP patients. The crucially finding was that the overall incidence ratios of appendicitis, acute appendicitis, and perforated appendicitis in the LIP were substantially higher than those in the NP (36.25%, 35.33%, and 37.28%, respectively). The mean LOS in LIP patients was longer than that of NP patients. The overall case-fatality ratio of appendectomy in the LIP was higher when compared with the NP (0.41% versus 0.12%, p < 0.05). We also observed that appendicitis was occurred frequently in male patients, with a higher incidence for those aged 15–29 years in both the LIP and NP. The incidences of incidental appendectomy showed a decreasing trend in both the LIP and NP. Finally, a valuable discovery was that the total hospital cost was comparable between the laparoscopic appendectomy (LA) and open appendectomy (OA) (1,178 ± 13 USD versus 1,191 ± 19 USD, p < 0.05) in LIP patients because they saved more hospitalization costs than NP patients when the previous one chose the LA. This study confirmed that a lower socioeconomic status has significantly negative impact on the occurrence and treatment of appendicitis and appendectomy. In terms of hospital costs and LOS, LIP patients benefit more from the LA approach than they do from the OA approach in the treatment of appendicitis.

Metro systems play a key role in meeting urban transport demands in large cities. The close relationship between historical weather conditions and the corresponding passenger flow has been widely analyzed by researchers. However, few studies have explored the issue of how to use historical weather data to make passenger flow forecasting more accurate. To this end, an hourly metro passenger flow forecasting model using a deep long short-term memory neural network (LSTM_NN) was developed. The optimized traditional input variables, including the different temporal data and historical passenger flow data, were combined with weather variables for data modeling. A comprehensive analysis of the weather impacts on short-term metro passenger flow forecasting is discussed in this paper. The experimental results confirm that weather variables have a significant effect on passenger flow forecasting. It is interesting to find out that the previous variables of one-hour temperature and wind speed are the two most important weather variables to obtain more accurate forecasting results on rainy days at Taipei Main Station, which is a primary interchange station in Taipei. Compared to the four widely used algorithms, the deep LSTM_NN is an extremely powerful method, which has the capability of making more accurate forecasts when suitable weather variables are included.

Vehicle re-identification (ReID) focuses on searching for images of the same vehicle across different cameras and can be considered as the most fine-grained ID-level classification task. It is fundamentally challenging due to the significant differences in appearance presented by a vehicle with the same ID (especially from different viewpoints) coupled with the subtle differences between vehicles with different IDs. Spatial attention mechanisms that have been proven to be effective in computer vision tasks also play an important role in vehicle ReID. However, they often require expensive key-point labels or suffer from noisy attention masks when trained without key-point labels. In this work, we propose a transformer-based attention network (TAN) for learning spatial attention information and hence for facilitating learning of discriminative features for vehicle ReID. Specifically, in contrast to previous studies that adopted a transformer network, we designed the attention network as an independent branch that can be flexibly utilized in various tasks. Moreover, we combined the TAN with two other branches: one to extract global features that define the image-level structures, and the other to extract the auxiliary side-attribute features that are invariant to viewpoint, such as color, car type, etc. To validate the proposed approach, experiments were conducted on two vehicle datasets (the VeRi-776 and VehicleID datasets) and a person dataset (Market-1501). The experimental results demonstrated that the proposed TAN is effective in improving the performance of both the vehicle and person ReID tasks, and the proposed method achieves state-of-the-art (SOTA) perfomance.

The rapid growth of transportation network companies (TNCs) has reshaped the traditional taxi market in many modern cities around the world. This study aims to explore the spatiotemporal variations of built environment on traditional taxis (TTs) and TNC. Considering the heterogeneity of ridership distribution in spatial and temporal aspects, we implemented a geographically and temporally weighted regression (GTWR) model, which was improved by parallel computing technology, to efficiently evaluate the effects of local influencing factors on the monthly ridership distribution for both modes at each taxi zone. A case study was implemented in New York City (NYC) using 659 million pick-up points recorded by TT and TNC from 2015 to 2017. Fourteen influencing factors from four groups, including weather, land use, socioeconomic and transportation, are selected as independent variables. The modeling results show that the improved parallel-based GTWR model can achieve better fitting results than the ordinary least squares (OLS) model, and it is more efficient for big datasets. The coefficients of the influencing variables further indicate that TNC has become more convenient for passengers in snowy weather, while TT is more concentrated at the locations close to public transportation. Moreover, the socioeconomic properties are the most important factors that caused the difference of spatiotemporal patterns. For example, passengers with higher education/income are more inclined to select TT in the western of NYC, while vehicle ownership promotes the utility of TNC in the middle of NYC. These findings can provide scientific insights and a basis for transportation departments and companies to make rational and effective use of existing resources.