In the field of physical oceanography, the temperature and pressure of seawater are important fundamental parameters. In order to realize the simultaneous measurement of the temperature and pressure in seawater, a reflective optical fiber sensor based on polydimethylsiloxane (PDMS)-sealed optical microfiber coupler combined with a sagnac loop (OMCSL) is proposed. Benefiting from the high thermo-optical coefficient and large elasticity of PDMS, and the large-scale swift field transmission characteristics of optical microfiber coupler (OMC), the sensitivity and structural stability of our sensor is largely improved. The response performance of the sensor is further analyzed by numerical simulation calculations and theoretical modeling. Experimental results show that the temperature and pressure sensitivity of the sensor could reach −2.133 nm/°C and 3.416 nm/Mpa, respectively, about one order higher than that of bare fiber OMCSL. Furthermore, via inversely calculating the cross-sensitivity matrix, the temperature and pressure sensing can be demodulated simultaneously, and the average errors of the preliminary experimental settlements are 1.61% and 5.02%, respectively. Due to the merits of compact structure, easy fabrication, high sensitivity, fast response speed and high stability, the basic performance of this dual parametric sensor is comparable to the existing electrical temperature-depth (TD) sensor, which is expected to meet the practical application requirements of marine environmental monitoring and ocean dynamics research.
With the rapid advancement of deep learning, 3D human pose estimation has largely freed itself from reliance on manually annotated methods. The effective utilization of joint features has become significant. Utilizing 2D human joint information to predict 3D human skeletons is of paramount importance. Effectively leveraging 2D joint data can improve the accuracy of 3D human skeleton prediction. In this paper, we propose the SCGFormer model to reduce the error in predicting human skeletal poses in three-dimensional space. The network architecture of SCGFormer encompasses Transformer and two distinct types of graph convolution, organized into two interconnected modules: SGraAttention and AcChebGconv. SGraAttention extracts global feature information from each 2D human joint, thereby augmenting local feature learning by integrating prior knowledge of human joint relationships. Simultaneously, AcChebGconv broadens the receptive field for graph structure information and constructs implicit joint relationships to aggregate more valuable adjacent features. SCGraFormer is tested on widely recognized benchmark datasets such as Human3.6M and MPI-INF-3DHP and achieves excellent results. In particular, on Human3.6M, our method achieves the best results in 9 actions (out of a total of 15 actions), with an overall average error reduction of about 1.5 points compared to state-of-the-art methods, demonstrating the excellent performance of SCGFormer.
Time series forecasting is extensively utilised in meteorology, transportation, finance, and industrial domains. Precisely recognising cyclical trends and abrupt local changes in time series is essential for enhancing forecasting accuracy. Frequency-domain representations are adept at identifying periodic traits, whereas time-domain approaches are superior for spotting localised quick changes. Traditional techniques sometimes prioritise a single domain, overlooking the advantages of integration. This paper introduces a novel hybrid model, FFTNet, that simultaneously pulls characteristics from both domains to optimise their respective benefits. Theoretical examination indicates that the 2D CNN utilises dual-axis convolution kernels to jointly describe global cross-patch structures and local temporal patterns, whilst the frequency-domain MLP enhances spectral components in accordance with Parseval’s Theorem and the Convolution Theorem. A frequency-domain MLP is employed to discern periodic and trend characteristics, while a 2D CNN in the time domain identifies localised abrupt changes. This hybrid methodology differentiates itself from previous methods that depend exclusively on a single domain, providing a more thorough comprehension of the underlying patterns in time series data. Experiments on seven real-world datasets indicate that FFTNet surpasses existing techniques, attaining state-of-the-art performance with enhancements of 11.8% and 4.7% in MSE and MAE, respectively.
The point clouds obtained directly from three-dimensional scanning devices are often sparse and noisy. Therefore, point cloud upsampling plays an increasingly crucial role in fields such as point cloud reconstruction and rendering. However, point cloud upsampling methods are primarily supervised and fixed-rate, which restricts their applicability in various scenarios. In this paper, we propose a novel point cloud upsampling method, named RE-PU, which is based on the point cloud reconstruction and achieves self-supervised upsampling at arbitrary rates. The proposed method consists of two main stages: the first stage is to train a network to reconstruct the original point cloud from a prior distribution, and the second stage is to upsample the point cloud data by increasing the number of sampled points on the prior distribution with the trained model. The experimental results demonstrate that the proposed method can achieve comparable outcomes to supervised methods in terms of both visual quality and quantitative metrics.