Search for: All records

Despite numerous studies on trajectory prediction, existing approaches often fail to adequately capture the multifaceted and individual nature of driving behavior. In recognition of this gap and based on DenseTNT, an end-to-end and goal-based trajectory prediction method, our study developed a new version of DenseTNT that incorporates personalized nodes within the graph neural network in VectorNet as context encoder. Throughout the neural network computations, these nodes represent individual driver labels, allowing a more granular understanding of diverse driving behaviors to be gained. Based on comparative analysis, our model has a 11.4% reduction in minADE when compared to baseline models that do not have personalized labels. 

Abstract Digital‐resolution biosensing based on resonant reflection from photonic crystals (PC) has demonstrated significant potential for detection of proteomic and genomic biomarkers in serology, infectious disease diagnostics, and cancer diagnostics. An important intrinsic characteristic of resonant metamaterial surfaces is that enhanced electromagnetic fields are not uniformly distributed, resulting in spatially variable light‐matter interactions with nanoparticle tags that signal the presence of biomarker molecules. In this work, the spatial uniformity of resonantly enhanced, surface‐confined electromagnetic fields of a 1D PC is compared with a 2D PC with fourfold symmetry. When illuminated with unpolarized light, the simultaneously excited electromagnetic fields of transverse electric and transverse magnetic modes of the 2D PC present equally strong but complementary spatial distribution, leading to a >100% increased average near‐field intensity accompanied with a >50% compressed standard deviation compared to the 1D PC. Utilizing Photonic Resonator Absorption Microscopy (PRAM) to experimentally measure the absorption uniformity of ≈80 nm gold nanoparticles distributed upon the PC surface, a >100% improvement of the signal uniformity is observed when using the 2D PC. Overall, improvement in AuNP detection contrast, uniformity, and point spread function is demonstrated by PRAM performed upon a 2D PC surface.