Search

Accurate traffic flow forecasting is a crucial component of intelligent transportation systems, playing a pivotal role in enhancing transportation intelligence. The integration of Graph Neural Networks (GNNs) and Transformers in traffic flow forecasting has gained significant adoption for enhancing prediction accuracy. Yet, the complex spatial and temporal dependencies present in traffic data continue to pose substantial challenges: (1) Most GNN-based methods assume that the graph structure reflects the actual dependencies between nodes, overlooking the complex dependencies present in the real-world context. (2) Standard time-series models are unable to effectively model complex temporal dependencies, hindering prediction accuracy. To tackle these challenges, the authors propose a novel Transformer-based Spatiotemporal Graph Diffusion Convolution Network (TSGDC) for Traffic Flow Forecasting, which leverages graph diffusion and transformer to capture the complexity and dynamics of spatial and temporal patterns, thereby enhancing prediction performance. The authors designed an Efficient Channel Attention (ECA) that learns separately from the feature dimensions collected by traffic sensors and the temporal dimensions of traffic data, aiding in spatiotemporal modeling. Chebyshev Graph Diffusion Convolution (GDC) is used to capture the complex dependencies within the spatial distribution. Sequence decomposition blocks, as internal operations of transformers, are employed to gradually extract long-term stable trends from hidden complex variables. Additionally, by integrating multi-scale dependencies, including recent, daily, and weekly patterns, accurate traffic flow predictions are achieved. Experimental results on various public datasets show that TSGDC outperforms conventional traffic forecasting models, particularly in accuracy and robustness. [ABSTRACT FROM AUTHOR]

Multilevel thresholding image segmentation is one of the most widely used segmentation methods in the field of image segmentation. This paper proposes a multilevel thresholding image segmentation technique based on an improved whale optimization algorithm. The WOA has been applied to many complex optimization problems because of its excellent performance; however, it easily falls into local optimization. Therefore, firstly, a mixed-strategy-based improved whale optimization algorithm (MSWOA) is proposed using the k-point initialization algorithm, the nonlinear convergence factor, and the adaptive weight coefficient to improve the optimization ability of the algorithm. Then, the MSWOA is combined with the Otsu method and Kapur entropy to search for the optimal thresholds for multilevel thresholding gray image segmentation, respectively. The results of algorithm performance evaluation experiments on benchmark functions demonstrate that the MSWOA has higher search accuracy and faster convergence speed than other comparative algorithms and that it can effectively jump out of the local optimum. In addition, the image segmentation experimental results on benchmark images show that the MSWOA–Kapur image segmentation technique can effectively and accurately search multilevel thresholds. [ABSTRACT FROM AUTHOR]

This work outperforms the previous literatures by proposing a delay-cell-controlled voltage control oscillator (VCO) design for common unipolar, single-gate, and enhancement-mode thin-film transistor (TFT) technologies. A design example with InZnO TFTs is simulated to verify the proposed design. The design example has a 500 μW power consumption, 0.7 mm2 area, 3.8 kHz–8 kHz output frequency range, 600 Hz/V tuning sensitivity, and 4% maximum linear error. This design may have the potential to be used for flexible, low cost, and moderate speed sensor readout interfaces. [ABSTRACT FROM AUTHOR]

NMR spectroscopy is a powerful analytical tool for both qualitative and quantitative analysis. However, accurate quantitative analysis in complex fluids such as human blood plasma is challenging, and analysis using one-dimensional NMR is limited by signal overlap. It is impractical to use heteronuclear experiments involving natural abundance [sup.13]C on a routine basis due to low sensitivity, despite their improved resolution. Focusing on circumventing such bottlenecks, this study demonstrates the utility of a combination of isotope enhanced NMR experiments to analyze metabolites in human blood plasma. [sup.1]H-[sup.15]N HSQC and [sup.1]H-[sup.13]C HSQC experiments on the isotope tugged samples combined with the conventional [sup.1]H one-dimensional and [sup.1]H-[sup.1]H TOCSY experiments provide quantitative information on a large number of metabolites in plasma. The methods were first tested on a mixture of 28 synthetic analogues of metabolites commonly present in human blood; 27 metabolites in a standard NIST (National Institute of Standards and Technology) human blood plasma were then identified and quantified with an average coefficient of variation of 2.4% for 17 metabolites and 5.6% when all the metabolites were considered. Carboxylic acids and amines represent a majority of the metabolites in body fluids, and their analysis by isotope tagging enables a significant enhancement of the metabolic pool for biomarker discovery applications. Improved sensitivity and resolution of NMR experiments imparted by [sup.15]N and 13C isotope tagging are attractive for both the enhancement of the detectable metabolic pool and accurate analysis of plasma metabolites. The approach can be easily extended to many additional metabolites in almost any biological mixture. 10.1021/ac101938w