Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data.

Predicting traffic data on traffic networks is essential to transportation management. It is a challenging task due to the complicated spatial-temporal dependency. The latest studies mainly focus on capturing temporal and spatial dependencies with spatially dense traffic data. However, when traffic data become spatially sparse, existing methods cannot capture sufficient spatial correlation information and thus fail to learn the temporal periodicity sufficiently. To address these issues, we propose a novel deep learning framework, Multi-component Spatial-Temporal Graph Attention Convolutional Networks (MSTGACN), for traffic prediction, and we successfully apply it to predicting traffic flow and speed with spatially sparse data. MSTGACN mainly consists of three independent components to model three types of periodic information. Each component in MSTGACN combines dilated causal convolution, graph convolution layer, and the weight-shared graph attention layer. Experimental results on three real-world traffic datasets, METR-LA, PeMS-BAY, and PeMSD7-sparse, demonstrate the superior performance of our method in the case of spatially sparse data.

Comparative study on the catalytic electrooxidative abilities of RuO(x)-PdO-TiO(2)/Ti and RuO(x)-PdO/Ti anode.

Comparative study of the catalytic electrooxidative abilities of RuO(x)-PdO/Ti and RuO(x)-PdO-TiO(2)/Ti were conducted using Active Orange 5R solution as simulated wastewater. RuO(x)-PdO-TiO(2)/Ti anode possesses higher catalytic oxidation ability, as compared to RuO(x)-PdO/Ti, in both direct oxidation and indirect oxidation processes. RuO(x)-PdO-TiO(2)/Ti could provide a discoloration rate of 98.14% within 30 min, while the COD removal could reach 51.43% in 120 min. It was indicated that higher electrooxidation ability could be achieved at RuO(x)-PdO-TiO(2)/Ti anode, which exhibited lower chlorine evolution potential and higher oxygen evolution potential probably resulted from the higher oxidation states of Ru and Pd.

The determination of trace lead in drinking water by flow injection spectrophotometry.

Lead is the non-essential trace element in the human body, and it has been confirmed that drinking water is one of the sources of lead in human body. In the research, based on the sensitive colour reaction of lead with I(-)-EV(+)-PVA, a simple, sensitive, accurate and portable method for the determination of trace lead in drinking waters was proposed. Chemicals and physicals had been optimized in detail. The apparent molar absorption coefficient was up to 7.4x10(5) mol L(-1) cm(-1). The developed method provided a linearity range over 5-80 microg L(-1). The regression deviation was between 0.71% and 2.33%. The 3sigma detection limit was 0.9 microg L(-1). Close to the quantitation limit for the analyte the relative standard deviation was 1.10% (n=10) at 40 microg L(-1). The method developed here for analysis of lead yielded results that were comparable with those of the GFAAS.