Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.

Converging collimation increases the geometric efficiency for imaging small organs, such as the heart, but also increases the difficulty of correcting for the physical effects of attenuation, geometric response and scatter in SPECT. In this paper, 3D first-order Compton scatter in non-uniform scattering media is modelled by using an efficient slice by-slice incremental blurring technique in both parallel and converging beam SPECT. The scatter projections are generated by first forming an effective scatter source image (ESSI), then forward-projecting the ESSI. The Compton scatter cross section described by the Klein-Nishina formula is used to obtain spatial scatter response functions (SSRFs) of scattering slices which are parallel to the detector surface. Two SSRFs of neighbouring scattering slices are used to compute two small orthogonal 1D blurring kernels used for the incremental blurring from the slice which is further from the detector surface to the slice which is closer to the detector surface. First-order Compton scatter point response functions (SPRFs) obtained using the proposed model agree well with those of Monte Carlo (MC) simulations for both parallel and fan beam SPECT. Image reconstruction in fan beam SPECT MC simulation studies shows increased left ventricle myocardium-to-chamber contrast (LV contrast) and slightly improved image resolution when performing scatter compensation using the proposed model. Physical torso phantom fan beam SPECT experiments show increased myocardial uniformity and image resolution as well as increased LV contrast. The proposed method efficiently models the 3D first-order Compton scatter effect in parallel and converging beam SPECT.

Background. A novel three-dimensional (3D) iterative image reconstruction method (3D-OSEM) has been developed that in phantom studies yielded comparable image quality at one half the imaging time. In this study, we compared standard (STD) and rapid (nSPEED) protocols for diagnostic quality of images and quantitation of end-diastolic volume (EDV), endsystolic volume (ESV), left ventricular ejection fraction (LVEF), and perfusion defect severity.Methods. At 11 US community centers, 448 patients prospectively underwent rest-stressgated SPECT imaging using Tc-99m-labeled agent. The difference in quality and diagnostic equivalence of STD and nSPEED images were blindly evaluated by three experts. Defect intensity was quantitated as %normal in the three coronary artery territories.Results. Studies were abnormal in 40% of patients. In 98.7% of stress and 98% of rest images, the nSPEED image quality was identical to or better than the STD images. nSPEED images were diagnostically equivalent to the STD in 444/448 (99%) patients. A high correlation was observed between nSPEED and STD studies for measurement of EDV (Y = 0.957X, R 2 5 0.99), ESV (Y = 0.962X, R 2 5 0.99), and LVEF (Y = 1.005X, R 2 5 0.96). STD and nSPEED studies were not significantly different (P = ns) for quantitative perfusion defect severity.Conclusion. Rapid, gated rest-stress myocardial perfusion upright SPECT imaging may be achieved without compromising perfusion and function information. (J Nucl Cardiol 2009;16:351-7.)

No abstract