Classification and segmentation of point clouds have attracted increasing attention in recent years. On the one hand, it is difficult to extract local features with geometric information. On the other hand, how to select more important features correctly also brings challenges to the research. Therefore, the main challenge in classifying and segmenting the point clouds is how to locate the attentional region. To tackle this challenge, we propose a graph-based neural network with an attention pooling strategy (AGNet). In particular, local feature information can be extracted by constructing a topological structure. Compared to existing methods, AGNet can better extract the spatial information with different distances, and the attentional pooling strategy is capable of selecting the most important features of the topological structure. Therefore, our model can aggregate more information to better represent different point cloud features. We conducted extensive experiments on challenging benchmark datasets including ModelNet40 for object classification, as well as ShapeNet Part and S3DIS for segmentation. Both the quantitative and qualitative experiments demonstrated a consistent advantage for the tasks of point set classification and segmentation.

The new generations of global navigation satellite system (GNSS) space vehicles can transmit three or more frequency signals. Multi-frequency observations bring a significant improvement to precise point positioning ambiguity resolution (PPP AR). However, the multi-frequency satellite code and phase biases need to be properly handled before conducting PPP AR. The traditional satellite bias correction methods, for example, the commonly used differential code biases (DCB), are limited to the dual-frequency ionosphere-free (IF) case and become more and more difficult to extend to multi-GNSS and multi-frequency cases. In this contribution, we propose the observable-specific signal bias (OSB) correction method for un-differenced and uncombined (UDUC) PPP AR. The OSB correction method, which includes observable-specific satellite code and phase bias correction, can directly apply kinds of OSBs to GNSS original observation data, thus, it is more appropriate for multi-GNSS and multi-frequency cases. In order to verify the performance of multi-frequency UDUC-PPP AR based on the OSB correction method, triple-frequency GPS observation data provided by 142 Multi-GNSS Experiment (MGEX) stations were used to estimate observable-specific satellite phase biases at the PPP service end and some of them were also used to conduct AR at the PPP user end. The experiment results showed: the averaged time-to-first-fix (TTFF) of triple-frequency GPS kinematic UDUC-PPP AR with observable-specific satellite code bias (SCB) corrections could reach about 22 min with about 29% improvement, compared with that without observable-specific SCB corrections; TTFF of triple-frequency static UDUC-PPP AR with observable-specific phase-specific time-variant inter-frequency clock bias (IFCB) corrections took about 15.6 min with about 64.3% improvement, compared with that without observable-specific IFCB corrections.

The inland aquaculture environment is an artificial ecosystem, where the water quality is a key factor which is closely related to the economic benefits of inland aquaculture and the quality of aquatic products. Compared with marine aquaculture, inland aquaculture is normally smaller and susceptible to pollution, with poor self-purification capacity. Considering its low cost and large-scale monitoring ability, many researches have developed spectrum sensor on-board satellite platforms to allow remote monitoring of inland water surface. However, there remain many problems, such as low image resolution, poor flexible data acquisition, and anti-interference. Apart from that, the conventional forecasting model is of weak generalization ability and low accuracy. In our study, we combine unmanned aerial vehicles system (UAVs) with the wireless sensor network (WSN) to design a new ground water quality parameter and drone spectrum information acquisition approach, and to propose a novel dynamic network surgery-deep neural networks (DNS-DNNs) model based on multi-source feature fusion to forecast the distribution of dissolved oxygen (DO) and turbidity (TUB) in inland aquaculture areas. The result of using fused features, including characteristic spectrum, Gray-level co-occurrence matrix (GLCM) texture feature, and convolutional neural network (CNN) texture feature to build a model is that the characteristic spectrum+ CNN texture fusion features were the best input items for DNS-DNNs when forecasting DO, with the determination coefficient $R^2$ of the vertical set arriving at 0.8741, while the characteristic spectrum+ GLCM texture+ CNN texture fusion features were the best for TUB, with the $R^2$ reaching 0.8531. Compared with a variety of conventional models, our model had a better performance in the inversion of DO and TUB, and there was a strong correlation between predicted and real values: $R^2$ reached 0.8042 and 0.8346, whereas the root mean square error (RMSE) were only 0.1907 and 0.1794, separately. Our study provides a new insight about using remote sensing to rapidly monitor water quality in inland aquaculture regions.