In recent years, recommender systems have been widely adopted in various applications. Such systems predict user preferences for items based on past behavior and attribute information, determining which items to present. However, if recommendations are repeatedly made based on limited data, users may be exposed only to a narrow selection of items. This can result in many items remaining undiscovered, preventing users from finding new interests and potentially leading to a less satisfying long-term experience. To address this, “Exploration” deliberately recommends items with uncertain user preferences, promoting discovery. While beneficial in the long term, exploration can negatively impact short-term user experience by suggesting items of lower immediate preference. Thus, accurately measuring exploration’s effects is crucial. Existing evaluation methods based on diversity, novelty, and serendipity face challenges as their appropriate definitions depend on user and item characteristics. This research introduces a novel approach by defining exploration from the system’s perspective using Bayesian Information Gain. We propose an evaluation metric that quantifies exploration based on how much the system improves its understanding of user preferences. This metric, relying on the uncertainty of estimated preference distributions, offers greater universality than conventional methods. Through experiments on artificial and real datasets, we demonstrate its effectiveness, providing a new, broadly applicable framework for assessing exploration in recommender systems. Implementations are available at: https://github.com/tishii2479/big-pu .

The Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) identifies persistent scatterers (PS) for surface deformation study. The selection of PS is important for obtaining reliable phase information. A novel deep convolutional neural network, namely PSNet, for identifying PS has been studied. The significant advantage of the PSNet lies in its deep architecture to learn characteristics of PS from enormous training images with different topography and landscapes. With the combined feature images composed of the average amplitude, amplitude dispersion, and coherence of interferograms as inputs, the PSNet was trained to classify the PS and non-PS. The results demonstrated that the PSNet delineated PS and non-PS pixels well. The number of PS obtained by the PSNet is more than doubled compared to the number of PS detected by the StaMPS algorithm.

Interferometric phase denoising is a vital procedure for interferometric synthetic aperture radar (InSAR)-based remote sensing techniques because it can improve the accuracy of the final InSAR product. Here, we propose a deep convolutional neural network (DCNN)-based InSAR phase denoising method, abbreviated PDNet. Given an ideal wrapped phase, φ, the PDNet learns the self-similarity function of φ from the input interferogram. After training, the PDNet obtains filtered wrapped phases using the maximum-likelihood approach by exhausting all φs from –π to π. Unlike a boxcar-based filtering method, the PDNet does not consist of an “averaging operation” on the spatial domain, and the resolution loss and interferometric fringe distortion will not directly affect the PDNet result. Thus, the PDNet can be considered a nonlocal phase denoising approach. Analyses and results show that the PDNet is an almost near-real-time denoising algorithm. Its denoising accuracy is higher than that of the available model- and learning-based InSAR phase denoising methods.

Collaborative exploration in an unknown environment without external positioning under limited communication is an essential task for multi-robot applications. For inter-robot positioning, various Distributed Simultaneous Localization and Mapping (DSLAM) systems share the Place Recognition (PR) descriptors and sensor data to estimate the relative pose between robots and merge robots’ maps. As maps are constantly shared among robots in exploration, we design a map-based DSLAM framework, which only shares the submaps, eliminating the transfer of PR descriptors and sensor data. Our framework saves 30% of total communication traffic. For exploration, each robot is assigned to get much unknown information about environments with paying little travel cost. As the number of sampled points increases, the goal would change back and forth among sampled frontiers, leading to the downgrade in exploration efficiency and the overlap of trajectories. We propose an exploration strategy based on Multi-robot Multi-target Potential Field (MMPF), which can eliminate goal’s back-and-forth changes, boosting the exploration efficiency by 1.03 ×∼1.62 × with 3 % ∼ 40 % travel cost saved. Our SubMap-based Multi-robot Exploration method (SMMR-Explore) is evaluated on both Gazebo simulator and real robots. The simulator and the exploration framework are published as an open-source ROS project at https://github.com/efc-robot/SMMR-Explore.

The spatiotemporal fractional vegetation cover (FVC) variations from 2000 to 2020 in the Changjiang basin, China, were studied. With Google Earth Engine (GEE), thousands of Landsat-5, 7, and 8 images were analyzed. In 2000, 2010, and 2020, the FVC increased roughly from the west to the east, crossing the basin. The low FVC areas were mainly around the Qinghai-Tibet Plateau and Changjiang Delta. The basin was well-vegetated from 2000 to 2020, with a minimum yearly average FVC of 67.45%. The FVC increased. At the pixel level, 60.14% of locations had a positive slope of the FVC versus time. Thus, the ecological environments assessed by FVC were healthy for the last 20 years, and the health improved. As shown in this study, GEE is an efficient and effective platform to study natural environments and environmental changes at a large spatial extent and over a long time.