Recent developments in Unmanned Aircraft Vehicles (UAVs), thermal imaging, and Auto-machine learning (AutoML) have shown high potential for precise wildlife surveys but have rarely been studied for habitat assessment. Here, we propose a framework that leverages these advanced techniques to achieve cost-effective habitat quality assessment from the perspective of actual wildlife community usage. The framework exploits vision intelligence hidden in the UAV thermal images and AutoML methods to achieve cost-effective wildlife distribution mapping, and then derives wildlife use indicators to imply habitat quality variance. We conducted UAV-based thermal wildlife surveys at three wetlands in the Rainwater Basin, Nebraska. Experiments were set to examine the optimal protocols, including various flight designs (61 and 122 m), feature types, and AutoML. The results showed that UAV images collected at 61 m with a spatial resolution of 7.5 cm, combined with Faster R-CNN, returned the optimal wildlife mapping (more than 90% accuracy). Results also indicated that the vision intelligence exploited can effectively transfer the redundant AutoML adaptation cycles into a fully automatic process (with around 33 times efficiency improvement for data labeling), facilitating cost-effective AutoML adaptation. Eventually, the derived ecological indicators can explain the wildlife use status well, reflecting potential within- and between-habitat quality variance.

The aim of this study was to investigate the relationships between skin test, specific immunoglobulin (Ig) E and cytokines in penicillin allergy. We collected the sera of 259 patients with historical positive skin test to penicillins, with immediate positive skin test and with a negative skin test results. The positive rate of specific IgE antibodies in 259 patients was 62.2% (161) by using radioallergosorbent test (RAST). Of the eight kinds of antigenic determinants, the positive rates of specific IgE to major and minor determinants were 43.63% (113) and 52.51% (136), respectively (p < 0.05). In 122 patients with immediate positive skin test, when the degrees of skin test were +, 2+, 3+ and 4+, the positive rates of specific IgE were 45.7, 57.1, 85.2 and 100%, respectively. The levels of interleukin (IL)-4, IL-13 and interferon (IFN)-gamma in the sera of patients with positive skin test were significantly increased with the degree of positive skin test (p < 0.05). The combined use of major and minor determinants in RAST offers the better test for the detection of penicillin-specific IgE antibodies. IL-4, IL-13 and IFN-gamma play important roles in penicillin allergy.

Constructing high-speed railways (HSRs) is critical for developing countries to stimulate economic growth and urbanization. This study focuses on the Lao section of the China–Laos Railway (CLR) and employs explicitly spatial remote sensing images to investigate the urban development surrounding HSR stations. Data-driven machine learning and causal inference approaches are integrated to quantify the spatial–temporal evolution and discover its driving factors. The results suggest that the CLR has had positive spatial spillover effects on the development of the surrounding urban space. These spillover effects have exhibited a distance attenuation pattern, reflecting obvious development in 2D rather than in 3D urban space. Meanwhile, the distance to stations and adjacent city centers as well as functional urban characteristics, such as land use patterns and industrialization level, have significantly influences the surrounding spatial development. Specifically, in industrial-dominated cities, the surrounding spatial changes have been most significant under the influence of the HSR. Change related to industrial and residential land use has shown significant land expansion patterns and increased utilization efficiency, reflecting that industrialization and urbanization have been the primary drivers of land demand surrounding the HSR. The findings offer valuable insights and references for developing nations to formulate and implement spatial management policies and initiatives related to HSR.

Accurate temperature prediction is essential for economic production and human society’s daily life. However, most current methods only focus on time-series temperature modeling and prediction, ignoring the complex interplay of meteorological variables in the spatial domain. In this paper, a novel temperature prediction model (D3AT-LSTM) is proposed by combining the three-dimensional convolutional neural network (3DCNN) and the attention-based gated cyclic network. Firstly, the historical meteorological series of eight surrounding pixels are combined to construct a multi-dimensional feature tensor that integrates variables from the temporal domain as the input data. Convolutional units are used to model and analyze the spatiotemporal patterns of the local sequence in CNN modules by combining them with parallel attention mechanisms. The fully connected layer finally makes the final temperature prediction. This method is subsequently compared with both classical and state-of-art prediction models such as ARIMA (AR), long short-term memory network (LSTM), and Transformer using three indices: the root mean square error (RMSE), the mean absolute error (MAE), and the coefficient of determination ($R^2)$. The results indicate that the D3AT-LSTM model can achieve good prediction accuracy compared to AR, LSTMs, and Transformer.

To extend the scale limits within which a template watermark remains detectable, this paper proposes a template watermarking algorithm for remote sensing images based on a radial spectral barcode (RSB). The RSB is a new geometry of template watermark whose inner and outer boundaries are separated along the radial direction of the discrete Fourier transform magnitude spectrum. In the embedding stage, the spectrum is divided into angular slots, a synchronization sequence generated from the secret key and the watermark are assigned to alternate slots, and the magnitude within the radial interval of each slot is modulated according to its sign. In the detection stage, the angular profile of the received spectrum is computed under a set of geometric hypotheses, the synchronization sequence is located by circular correlation, and the watermark is read from the synchronized profile without correcting the image. The experimental results demonstrate that the proposed method extends the detectable scale interval well beyond that of the ring-template methods while retaining robustness against rotation, translation, cropping, affine transformation, map reprojection, and signal-processing attacks. It outperforms the comparative algorithms in robustness at an equal or higher PSNR, with a low false detection rate.