Search

AbstractCellulose nanofibers (CNFs) are the newly introduced plant-based materials in the construction industry to ensure sustainable development. The use of artificial intelligence (AI) techniques especially machine learning (ML) models has assisted to economized civil engineering. This research aims to determine the compressive strength of cellulose nanofibers reinforced concrete by using supervised regression machine learning techniques for analysis before adopting to utilize. To achieve this task, the machine learning models: Random Forest (RF), Linear Regression (LR), Support Vector Regressor (SVR), Gradient Boosting Regressor (GBR), Ada Boosting Regressor (ABR), K-Neighbor Regressor (KNN), Bagging Regressor (BR), XG Boost Regressor (XGBR), Decision Tree (DT), and Pruned Decision Tree (PDT) were implemented. An experimental-based dataset containing 695 data points was prepared and split into two categories (Training dataset = 70%, Testing dataset = 30%) for the evolution of ML models. There were seven independent variables: cement (kg/m3), water (kg/m3), CNFs (kg/m3), superplasticizer (kg/m3), fine aggregate (kg/m3), coarse aggregate (kg/m3), and age (Day) variables as an input and one dependent variable: compressive strength fc of CNFs reinforced concrete (MPa) as an output. The following metrics were employed to gauge the ability of the model: R2, MAPE, MAE, MSE, and RMSE. The findings specified that seven out of ten models (RF, BR, XGBR, DT, GBR, ABR, and KNN) to predict the compressive strength of CNFs concrete had a firm capability (R2 >0.72, MAPE ≤ 0.1, and MAE ≤ 5) confirming to the standard of R2 value greater than 0.60 and metrics values very less, close to one. According to the sensitivity analysis of Random Forest model, water and cement were the factors with the biggest effects on the prediction of CNFs reinforced concrete, while the smallest effecting variable was coarse aggregate. It was concluded that the RF, BR, and DT were the premier predicting models.

This paper reviews the novel azimuthal multi-angle spaceborne Synthetic Aperture Radar (SAR) technique. First, the development status and trend of SAR satellites are analyzed, and their observation capacities are compared considering different aspects. Furthermore, the novel azimuthal multi-angle observation SAR imaging modes are presented based on the application requirements, and the imaging mechanism is analyzed in detail. Moreover, the advantages of the azimuthal multi-angle observation spaceborne SAR system for obtaining full scattering information, geometry information, and motion information of ground targets are analyzed. Detailed conclusions are provided, and experiment results are presented. Finally, the azimuthal multiangle observation spaceborne SAR technique is summarized, and its prospects are highlighted.

Co-prime-sampling space-borne Synthetic Aperture Radar (SAR) replaces the traditional uniform sampling by performing co-prime sampling in azimuth, which effectively alleviates the conflict between spatial resolution and effective swath width, while also improving the ground detection performance of the SAR system. However, co-prime-sampling in azimuth causes the echo signal to exhibit azimuthal under sampling and non-uniform sampling characteristics, which means the traditional SAR image-processing method can not effectively image co-prime-sampled SAR. In this paper, an imaging method based on Two-Dimensional (2D) sparse-signal reconstruction is proposed for co-prime-sampling space-borne SAR. Using this method, after range-pulse compression, the 2D observed signal is intercepted and a corresponding sparse dictionary consisting of 2D atoms is constructed according to the Doppler parameters of each range gate. Then, azimuth-focus processing is completed by the improved 2D-signal sparsity adaptive matching pursuit algorithm. The proposed method not only compensates for the 2D coupling between the range and azimuth, but also eliminates the influence of space-varying imaging parameters on sparse reconstruction to achieve accurate reconstruction of the entire scene. The simulation results of the point targets and distribution targets verify that the proposed method can effectively reconstruct sparse scenes at a rate much lower than the Nyquist sampling rate.

As an important tool for acquiring remote sensing information, Synthetic Aperture Radar (SAR) has various modes, including high-resolution wide-swath, multi-angle information acquisition, high temporal observation, and three-dimensional topographic mapping. For any spaceborne SAR system, obtaining high-quality images is a prerequisite for improving the performance of SAR applications. In this paper, we analyze the factors affecting spaceborne SAR imaging and image quality with respect to orbit, platform, payload, and signal processing. We describe high-precision data acquisition techniques, including amplitude-phase compensation, the dynamic adjustment of the central electronic equipment, and antenna pattern estimation. We then present imaging compensation methods based on the improved motion model and tropospheric delay correction, which can achieve resolutions better than 0.3 m. Lastly, we summarize and compare SAR image processing techniques such as speckle noise suppression, azimuth ambiguity suppression, and sidelobe suppression, whereby the equivalent number of looks can be increased to more than 25 and the azimuth ambiguity and sidelobes can both be suppressed by 20 dB.

Azimuth ambiguities appear widely throughout spaceborne Synthetic Aperture Radar (SAR) images. If the ambiguous energy is relatively strong, a large number of brilliant areas or points will emerge, which may be erroneously judged as actual targets. This is a disadvantage in image interpretation. Due to the fact that ambiguous energy is mixed with energy from the main zone in the frequency and time domains, it is difficult to suppress azimuth ambiguity to a reasonable level using the existing approach without loss of resolution. This study proposes an innovative approach for suppressing azimuth ambiguity based on the compressive sensing recovery framework, in which the original image acts as prior information and the corresponding frequency spectrum truncated in a proper ratio acts as measurement information. With the proposed approach, highresolution low-ambiguity images can be obtained by iteration. We used simulation and satellite data to validate the effectiveness of this proposed approach in suppressing azimuth ambiguity.

The contamination status of cold resistant Morganella psychrotolerans in commercially available aquatic products was investigated, and the generation of histamine by its isolates was explored. A total of 100 samples of commercially available fish from Guangdong province were surveyed. The results revealed a widespread distribution of M. psychrotolerans with a contamination rate of 34%. The contamination rates for red-fleshed and white-fleshed fish were 35.9% and 27.3%, respectively. Specifically, the mackerel samples had a contamination rate of 38.24%, and the tuna samples had a contamination rate of 29.41% among all positive samples. Sixteen strains of M. psychrotolerans were isolated from the positive samples, and all isolates produced histamine levels exceeding 1 000 mg/L after 48 h incubation at 20 ℃. Notably, isolate 1 showed higher histamine-producing capacity than the type strain. Although the two strains exhibited no significant differences in growth curves at varying temperatures (4 and 20 ℃), their histamine-producing capacities were different. After 10 days of culture at 4 ℃, histamine production was higher by isolate 1 than the type strain, while the opposite result was observed after 60 h of culture at 20 ℃. These findings offer crucial theoretical support for addressing the problem of histamine accumulation in cold chain aquatic products.