Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.

No abstract

No abstract

No abstract

No abstract

No abstract

Background We investigated whether glycemic control affects the relation between endothelial dysfunction and coronary artery disease in patients with type 2 diabetes mellitus (T2DM). Methods In 102 type 2 diabetic patients with stable angina, endothelial function was evaluated using brachial artery flow-mediated dilation (FMD) with high-resolution ultrasound, and significant stenosis of major epicardial coronary arteries (≥ 50% diameter narrowing) and degree of coronary atherosclerosis (Gensini score and SYNTAX score) were determined. The status of glycemic control was assessed by blood concentration of glycated hemoglobin (HbA1c). Results The prevalence of significant coronary artery stenosis (67.9% vs. 37.0%, P = 0.002) and degree of coronary atherosclerosis (Gensini score: 48.99 ± 48.88 vs. 15.07 ± 21.03, P < 0.001; SYNTAX score: 15.88 ± 16.36 vs. 7.28 ± 10.54, P = 0.003) were higher and FMD was lower (6.03 ± 2.08% vs. 6.94 ± 2.20%, P = 0.036) in diabetic patients with poor glycemic control (HbA1c ≥ 7.0%; n = 56) compared to those with good glycemic control (HbA1c < 7.0%; n = 46). Multivariate regression analysis revealed that tertile of FMD was an independent determinant of presence of significant coronary artery stenosis (OR = 0.227 95% CI 0.056–0.915, P = 0.037), Gensini score (β =  − 0.470, P < 0.001) and SYNTAX score (β =  − 0.349, P = 0.004) in diabetic patients with poor glycemic control but not for those with good glycemic control (P > 0.05). Conclusion Poor glycemic control negatively influences the association of endothelial dysfunction and coronary artery disease in T2DM patients.

No abstract