Remote-sensing images constitute an important means of obtaining geographic information. Image super-resolution reconstruction techniques are effective methods of improving the spatial resolution of remote-sensing images. Super-resolution reconstruction networks mainly improve the model performance by increasing the network depth. However, blindly increasing the network depth can easily lead to gradient disappearance or gradient explosion, increasing the difficulty of training. This report proposes a new pyramidal multi-scale residual network (PMSRN) that uses hierarchical residual-like connections and dilation convolution to form a multi-scale dilation residual block (MSDRB). The MSDRB enhances the ability to detect context information and fuses hierarchical features through the hierarchical feature fusion structure. Finally, a complementary block of global and local features is added to the reconstruction structure to alleviate the problem that useful original information is ignored. The experimental results showed that, compared with a basic multi-scale residual network, the PMSRN increased the peak signal-to-noise ratio by up to 0.44 dB and the structural similarity to 0.9776.

For WLAN fingerprint-based indoor localization approach, Wi-Fi received signal strength (RSS) is widely focused because it is easy to obtain and inexpensive. However, RSS measurements are vulnerable to environmental fluctuations and there is a lot of noise in the measured signal, which seriously affects the stability of RSS-based positioning systems. Meanwhile, the unreasonable value of K will also cause large positioning errors in the fingerprint-based K-nearest neighbors (KNN) and weighted KNN algorithms. Therefore, a novel FCLoc (Flexible reference points and Confidence access points Localization) method is proposed in this paper, to enhance the robustness of the system while improving positioning accuracy. First, considering that there is outlier noise in the sampling data, this article proposes to filter out noise by the robust principal. Then, the more reliable APs are selected according to the stability of the online data, as a more stable AP should have more weight to reduce the impact of the weak APs. When at least three APs are available, the system can work normally. Finally, the Jenks natural breaks algorithm in statistics is introduced to realize a flexible RP selection, that is, a more reasonable value of K is adaptively selected for position estimation to improve the positioning accuracy. The proposed method only applies to scenarios where at least three APs are available. Simulation and the real-world experimental results show that the proposed algorithm is superior to those existing algorithms in terms of robustness and positioning accuracy.

For mobile users, the ability to accurately acquire their own location is critical. By locating, mobile users can get information about their environment and access location-related services. RSS fingerprint-based indoor localization method collects a training database of measurement fingerprints and uses a machine learning classifier to determine a person’s location from a new fingerprint. However, as the environment changes over time due to furniture or other objects being moved, the new fingerprints diverge from those in the original database. Therefore, an RSS-difference based localization system is designed to deal with the above problem. This method combines back-propagation neural network (BPNN) and weighted K-Nearest Neighbor (WKNN) method to improve the fingerprint similarity based indoor location method (FSIL). We train BPNN in the off-line stage to obtain the optimal BPNN parameter settings. In the online stage, K nearest neighbor points are firstly selected based on the improved FSIL algorithm, and then the difference of signal strength values between the K nearest neighbor points and the target user is input into the BPNN network, to obtain the Euclidean distance between the K nearest neighbor points and the target user, and finally the WKNN algorithm is used to obtain the user’s ultimate location. Simulation experiments based on the LDPL model and the Wireless Insite software, as well as the test results based on the indoor localization dataset IPIN2016, show that the localization accuracy in complex indoor scenarios can be improved by at least 11% when using the method proposed in this paper.

For indoor positioning methods based on Wi-Fi fingerprint, a high-density location fingerprint database usually needs to be constructed to ensure high-precision positioning requirements. At the same time, when the indoor area is huge or the number of reference points (RPs) is large and densely distributed, the computational burden of the on-line phase will be increased. To solve the above two problems, we propose an indoor location fingerprinting algorithm based on path loss parameter estimation and Bayesian inference (FA-PEBI). In the off-line phase, firstly, we collect location fingerprints from a few RPs in different rooms, next, the location fingerprints collected are filtered, then the path loss parameters (PLPs) in different rooms is trained by using a logarithmic distance path loss model (LDPL), and at last, predict the fingerprint information of the other locations in that room based on the trained parameters. In the on-line phase, the real-time fingerprint information of the user is firstly filtered, then the room where the user is located is predetermined by using the Bayesian inference method, subsequently, the corresponding fingerprint database is selected to match based on the regional adaptive selection (RAS) algorithm, eventually, the ultimate location of the user is obtained based on Manhattan distance. The experimental results show that the proposed algorithm improves the localization accuracy by at least 16% compared with other existing methods, both in Wireless Insite simulation data and MAN dataset, and still outperforms the KNN algorithm when the fingerprint collection effort in the off-line phase is reduced by half.

Aspect Sentiment Triplet Extraction (ASTE) is a complex and important task in aspect-based sentiment analysis task, which aims to extract aspect-sentiment-opinion triplets from review sentences, to acquire comprehensive information for sentiment analysis. Most of the existing methods use pipeline approaches or end-to-end sequence tagging approaches to solve the ASTE task. However, the pipeline approaches suffer from error accumulation in practical applications. The existing sequence tagging approaches ignore the feature information of the three elements themselves, and cannot model and infer the three elements effectively by placing each word in the same position as importance. Based on this, a multi-task dual-encoder framework is proposed. First, a dual-encoder is constructed to encode and fuse sentence information and semantic information, respectively. Then, the signs and constraints implied between word pairs are used to complete multi-task inference and triplet decoding. Meanwhile, two grid tagging methods and their corresponding inference strategies are designed for the multi-task. The auxiliary task is used as a regularization of the main task, which improves the correct inference ability of the inference strategy for the main task and the robustness of the framework. Extensive testing on two benchmark datasets shows that the proposed framework is simple and effective, and significantly outperforms the existing methods.