Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

Region-level traffic information can characterize dynamic changes of urban traffic at the macro level. Real-time region-level traffic prediction help city traffic managers with traffic demand analysis, traffic congestion control, and other activities, and it has become a research hotspot. As more vehicles are equipped with GPS devices, remote sensing data can be collected and used to conduct data-driven region-level-based traffic prediction. However, due to dynamism and randomness of urban traffic and the complexity of urban road networks, the study of such issues faces many challenges. This paper proposes a new deep learning model named TmS-GCN to predict region-level traffic information, which is composed of Graph Convolutional Network (GCN) and Gated Recurrent Unit (GRU). The GCN part captures spatial dependence among regions, while the GRU part captures the dynamic change of traffic within the region. Model verification and comparison are carried out using real taxi GPS data from Shenzhen. The experimental results show that the proposed model outperforms both the classic time series prediction model and the deep learning model at different scales.

Testing the Fit of Regression Models Estimated with Extremely Small Samples: Application in Pharmaceutical Stability Studies

Pharmaceutical stability studies are conducted to estimate the shelf life, i.e. the period during which the drug product maintains its identity and stability. In the evaluation of process, regression curve is fitted on the data obtained during the study and the shelf life is determined using the fitted curve. The evaluation process suggested by ICH considers only the case of the true relationship between the measured attribute and time being linear. However, no method is suggested for the practitioner to decide if the linear model is appropriate for their dataset. This is a major problem, as a falsely selected model may distort the estimated shelf life to a great extent, resulting in unreliable quality control. The difficulty of model misspecification detection in stability studies is that very few observations are available. The conventional methods applied for model verification might not be appropriate or efficient due to the small sample size. In this paper, this problem is addressed and some developed methods are proposed to detect model misspecification. The methods can be applied for any process where the regression estimation is performed on independent small samples. Besides stability studies, frequently performed construction of single calibration curves for an analytical measurement is another case where the methods may be applied. It is shown that our methods are statistically appropriate and some of them have high efficiency in the detection of model misspecification when applied in simulated situations which resemble pre-approval and post-approval stability studies.

Simulation analysis of environmental pollution based on parallel data model

Through model verification and algorithm correction, many factors unfavorable to environmental protection existing in the production of export products abroad are analyzed. The growth trend of export trade volume of industrial industries and regions with a high degree of openness is generally consistent with the emission trend of environmental pollutants. Environmental pollution restricts China's economic growth and brings certain negative effects on China's economic growth, The relevant data analysis suggestions for improving the impact of export product production on environmental pollution are put forward.

Analysis of Coupled Thermal and Electromagnetic Processes in Linear Induction Motors Based on a Three-Dimensional Thermal Model

The article describes a mathematical model of interconnected electromechanical and thermal processes in a linear induction motor (LIM). Here, we present the structure of the thermal model and provide the calculation formulas of the model. The thermal model consisted of eight control volumes on each tooth pitch of the LIM. Moreover, we also present a model of electromechanical processes and its interaction with the thermal model. The electromechanical model was based on the detailed magnetic and electrical equivalent circuits of the LIM. Model verification was performed using a model based on the finite element method and using experimental data. We also conducted a study focused on the necessity of considering the influence of various features of the thermal processes. We herein discuss the application of the model implemented in the MATLAB/Simulink, which was used to analyze the thermal performance of linear transport and technological induction motors. For the traction single-sided linear induction motor, we determined limits of safe operation by considering the unevenness of heating along the length in two cases: natural cooling and forced cooling. For forced cooling, required values of air flow were determined. For the arc induction motor of the screw press, the influence of various factors (i.e., reduction of the stroke, the use of a soft start, and the use of a forced cooling) on heating was evaluated.

COMPREHENSIVE RADAR DATA FOR THE CONTIGUOUS UNITED STATES: MULTI-YEAR REANALYSIS OF REMOTELY SENSED STORMS

The Multi-Year Reanalysis of Remotely Sensed Storms (MYRORSS) data set blends radar data from the WSR-88D network and Near-Storm Environmental (NSE) model analyses using the Multi-Radar Multi-Sensor (MRMS) framework. The MYRORSS data set uses the WSR-88D archive starting in 1998 through 2011, processing all valid single-radar volumes to produce a seamless three-dimensional reflectivity volume over the entire contiguous United States with an approximate 5-min update frequency. The three-dimensional grid has an approximate 1-km by 1-km horizontal dimension and is on a stretched vertical grid that extends to 20 km MSL with a maximal vertical spacing of 1 km. Several reflectivity-derived, severe storm related products are also produced, which leverage the ability to merge the MRMS and NSE data. Two Doppler velocity-derived azimuthal shear layer maximum products are produced at a higher horizontal resolution of approximately 0.5-km by 0.5-km. The initial period of record for the data set is 1998-2011. The data set underwent intensive manual quality control to ensure that all available and valid data were included while excluding highly problematic radar volumes that were a negligible percentage of the overall data set, but which caused large data errors in some cases. This data set has applications towards radar-based climatologies, post-event analysis, machine learning applications, model verification, and warning improvements. Details of the manual quality control process are included and examples of some of these applications are presented.

Universal Model to Support the Quality Improvement of Industrial Products

Improving the quality of industrial products quality still is a challenge. Despite using quality control, there is a constant need to support this process to achieve an effective, precise, and complex analysis of product quality. The purpose was to develop a universal model that supports improving the quality of products via the consistent and repetitive determination of the causes of product incompatibilities and actions leading to their elimination; the model can be integrated with any quality control of the product. The model verification was carried out for the incompatibility of the mechanical seal in alloy 410, in which the porosity cluster was identified by the fluorescence method (FPI). The purpose of the analysis was created by the SMART(-ER) method. Then, a team of experts was selected from which the brainstorming (BM) was realized. After the BM method, the source of incompatibility and initial causes were identified. Then, the Ishikawa diagram (according to rule 5M + E) was developed to group the initial causes. Next, during the BM method, the main causes were selected. In the last stage, the 5Why method was used to determine improvement actions, i.e., adjust clotting parameters, introduce the obligation to undergo periodic training, and set aside a separate place for storing the electrodes. Originality is the combination of selected quality management tools in a coherent model, the main aim of which is to identify the main causes of incompatibility and improvement actions. Additionally, this model is universal and has applications with analyzing any product and the causes of its incompatibility, and it can be integrated with any product quality control. Therefore, the model can be useful for improving the quality of products in any enterprise.

The Characterization of Haze and Dust Processes Using MAX-DOAS in Beijing, China

Haze and dust pollution have a significant impact on human production, life, and health. In order to understand the pollution process, the study of these two pollution characteristics is important. In this study, a one-year observation was carried out at the Beijing Southern Suburb Observatory using the MAX-DOAS instrument, and the pollution characteristics of the typical haze and dust events were analyzed. First, the distribution of aerosol extinction (AE) and H2O concentrations in the two typical pollution events were studied. The results showed that the correlation coefficient (r) between H2O and AE at different heights decreased during dust processes and the correlation slope (|k|) increased, whereas r increased and |k| decreased during haze periods. The correlation slope increased during the dust episode due to low moisture content and increased O4 absorption caused by abundant suspended dry crustal particles, but decreased during the haze episode due to a significant increase of H2O absorption. Secondly, the gas vertical column density (VCD) indicated that aerosol optical depth (AOD) increased during dust pollution events in the afternoon, while the H2O VCD decreased; in haze pollution processes, both H2O VCD and AOD increased. There were significant differences in meteorological conditions during haze (wind speed (WD) was <2 m/s, and relative humidity (RH) was >60%) and dust pollution (WD was >4 m/s, and RH was <60%). Next, the vertical distribution characteristics of gases during the pollution periods were studied. The AE profile showed that haze pollution lasted for a long time and changed slowly, whereas the opposite was true for dust pollution. The pollutants (aerosols, NO2, SO2, and HCHO) and H2O were concentrated below 1 km during both these typical pollution processes, and haze pollution was associated with a strong temperature inversion around 1.0 km. Lastly, the water vapor transport fluxes showed that the water vapor transport from the eastern air mass had an auxiliary effect on haze pollution at the observation location. Our results are of significance for exploring the pollution process of tropospheric trace gases and the transport of water vapor in Beijing, and provide a basis for satellite and model verification.

Modelling of Soil Profile Pollutant Yield on Slaughterhouse Wastes Deposited Land

Aim: The study aimed at modeling the concentration of pollutants along soil profile using finite element method. Study Design: Data was generated from the laboratory on the concentrations of selected heavy metals at varying depths of land discharged slaughterhouses. This was used to estimate the level of nutrient build-up in the soil within these environs, hence, used to verify and validate the finite element analysis. The model upon validation was used to predict the rate of pollutant build-up in the soil within the slaughterhouses discharge areas. Methodology: A total of twelve composite samples were collected from three different land discharged locations. The three composite samples each were collected from the sampling locations at a depth of 0 to 10cm, 10 to 20cm, 20 to 30cm and 30 to 40cm. Four composite samples each were collected for analysis from the three sampling locations on specified sampling dates. The samples were then placed in sterile polythene bags and transported to the laboratory for processing. The laboratory results obtained for heavy metals were used for the generated model verification and validation, hence predictions for pollutants accumulation was done on a time step. Results: Model verification showed a good fit of a nonlinear polynomial curve for both the measured and predicted values with R² values of 0.9978 to 0.9985 for zinc and 0.9978 to 0.9984 for lead at a selected time step of 15years. It was observed however, that there was an increasing tendency to uniformity of concentration as the time step increased; this was due to parameters build-up with time in the soil. Conclusion: Finite element results revealed a high build-up in the concentration of pollutants (Zinc and Lead) in the land discharged slaughterhouses.