Search

This paper applies a deep learning approach to model the mechanism of path loss based on the path profile in urban propagation environments for 5G cellular communication systems. The proposed method combines the log-distance path loss model for line-of-sight propagation scenarios and a deep-learning-based model for non-line-of-sight cases. Simulation results show that the proposed path loss model outperforms the conventional models when operating in the 3.5 GHz frequency band. The standard deviation of prediction error was reduced by 34% when compared to the conventional models. To explain the internal behavior of the proposed deep-learning-based model, which is a black box in nature, eight relevant features were selected to model the path loss based on a linear regression approach. Simulation results show that the accuracy of the explanatory model reached 72% when it was used to explain the proposed deep learning model. Furthermore, the proposed deep learning model was also evaluated in a non-standalone 5G New Radio network in the urban environment of Taipei City. The real-world measurements show that the standard deviation of prediction error can be reduced by 30–43% when compared to the conventional models. In addition, the transparency of the proposed deep learning model reached 63% in the realistic 5G network. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Under weak geological conditions, soil deformation and surface settlement are the key factors affecting the success of shallow-buried rectangular excavation. To investigate this issue, an underpass of Zhongxiao East Road in Taipei City was used as a case study. The surface settlement and lateral deformation of an underground diaphragm wall caused by the excavation of a rectangular pedestrian underpass using the pipe-roof preconstruction method (PPM) were investigated by 3D finite element analysis. The numerical analysis results showed that the constructed numerical analysis model had considerable accuracy. The use of PPM combined with a box culvert structure to form a pedestrian underpass could effectively control the surface displacement above the box culvert. Under the condition of the same sectional area, the smaller the width of the pipe-roof structure, the more the impact on the ground surface was reduced. The maximum positive bending moment and maximum negative bending moment on the pipe roof produced by excavation at each stage were roughly inversely related to the height per the width of the cross-section of the pipe diaphragm structure. The results showed that the pipe-roof structure was suitable for underground excavation with shallow-buried depth in the soft soil of the Taipei Basin. Moreover, the shallow-buried box culvert was more sensitive to the subsidence caused by construction than the deep-buried box culvert. [ABSTRACT FROM AUTHOR]

Aim: To investigate the effect of whole-body vibration on older people with sarcopenia, and their physical capability, activities of daily living, and sleep quality. Methods: This study is quasi-experimental and adopts single-group pretest–posttest design. The study included participants aged older than 65 years who lived in nursing homes and care centers in Taipei, Taiwan. The whole-body vibration training was performed for 3 months, and during each training session, a participant received ten cycles of 60-sec vibration with 30-sec breaks between the cycles. The physical capability, activities of daily living, and sleep quality of the participants were examined to understand the pretest and posttest results of whole-body vibration training. Concerning the statistical methods adopted, nonparametric method-based tests were employed. Results: In addition to sleep quality (z = 7.367, p > 0.05), significant differences were observed between before and after whole-body vibration training intervention for one-foot balance (z = −2.447, p < 0.05), shoulder and arm flexibility (z = −3.159, p < 0.05), walking speed (z = −2.692, p < 0.05), right-hand grip (z = −3.388, p < 0.05), left-hand grip (z = −3.264, p < 0.05), five sit–stand repetitions (z = −2.936, p < 0.05), skeletal muscle mass index (z = −3.621, p < 0.05), and activities of daily living (z = 1.163, p < 0.05). Conclusions: According to this study, with the 12-week whole-body vibration training in older people with sarcopenia, their physical capability and activities of daily living have improved, though sleeping quality is not statistically significant. [ABSTRACT FROM AUTHOR]