Explore the vast range of titles available.

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant back-scattering information about objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features input into the deep learning network are the power values of polarimetric channels and contain complete polarimetric information. The other two input data schemes are designed to compare the proposed method. The neural network can utilize the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of the power-based scheme. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has a clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

Sleep stage classification plays an important role in the diagnosis of sleep-related diseases. However, traditional automatic sleep stage classification is quite challenging because of the complexity associated with the establishment of mathematical models and the extraction of handcrafted features. In addition, the rapid fluctuations between sleep stages often result in blurry feature extraction, which might lead to an inaccurate assessment of electroencephalography (EEG) sleep stages. Hence, we propose an automatic sleep stage classification method based on a convolutional neural network (CNN) combined with the fine-grained segment in multiscale entropy. First, we define every 30 seconds of the multichannel EEG signal as a segment. Then, we construct an input time series based on the fine-grained segments, which means that the posterior and current segments are reorganized as an input containing several segments and the size of the time series is decided based on the scale chosen depending on the fine-grained segments. Next, each segment in this series is individually put into the designed CNN and feature maps are obtained after two blocks of convolution and max-pooling as well as a full-connected operation. Finally, the results from the full-connected layer of each segment in the input time sequence are put into the softmax classifier together to get a single most likely sleep stage. On a public dataset called ISRUC-Sleep, the average accuracy of our proposed method is 92.2%. Moreover, it yields an accuracy of 90%, 86%, 93%, 97%, and 90% for stage W, stage N1, stage N2, stage N3, and stage REM, respectively. Comparative analysis of performance suggests that the proposed method is better, as opposed to that of several state-of-the-art ones. The sleep stage classification methods based on CNN and the fine-grained segments really improve a key step in the study of sleep disorders and expedite sleep research.

The major challenges in drug development stem from frequent structure-activity cliffs and unknown drug properties, which are expensive and time-consuming to estimate, contributing to a high rate of failures and substantial unavoidable costs in the clinical phases. Herein, we propose the s elf- c onformation- a ware g raph transform e r (SCAGE), an innovative deep learning architecture pretrained with approximately 5 million drug-like compounds for molecular property prediction. Notably, we develop a multitask pretraining framework, which incorporates four supervised and unsupervised tasks: molecular fingerprint prediction, functional group prediction using chemical prior information, 2D atomic distance prediction, and 3D bond angle prediction, covering aspects from molecular structures to functions. It enables learning comprehensive conformation-aware prior knowledge, thereby enhancing its generalization across various molecular property tasks. Moreover, we design a data-driven multiscale conformational learning strategy that effectively guides the model in understanding and representing atomic relationships at the molecular conformational scale. SCAGE achieves significant performance improvements across 9 molecular properties and 30 structure-activity cliff benchmarks. Case studies demonstrate that SCAGE accurately captures crucial functional groups at the atomic level, which are closely associated with molecular activity, providing valuable insights into quantitative structure-activity relationships. Structure–activity cliffs and property uncertainties raise drug development costs. Here, authors propose a deep learning model capturing key functional groups tied to activity, offering insights into quantitative structure–activity relationships.

Though being fundamental to global diversity distribution, little is known about the geographic pattern of soil microorganisms across different biotas on a large scale. Here, we investigated soil prokaryotic communities from Chinese northern grasslands on a scale up to 4000 km in both alpine and temperate biotas. Prokaryotic similarities increased over geographic distance after tipping points of 1760–1920 km, generating a significant U-shape pattern. Such pattern was likely due to decreased disparities in environmental heterogeneity over geographic distance when across biotas, supported by three lines of evidences: (1) prokaryotic similarities still decreased with the environmental distance, (2) environmental selection dominated prokaryotic assembly, and (3) short-term environmental heterogeneity followed the U-shape pattern spatially, especially attributed to dissolved nutrients. In sum, these results demonstrate that environmental selection overwhelmed the geographic ‘distance’ effect when across biotas, overturning the previously well-accepted geographic pattern for microbes on a large scale.

Grassland remote sensing (GRS) is an important research topic that applies remote sensing technology to grassland ecosystems, reflects the number of grassland resources and grassland health promptly, and provides inversion information used in sustainable development management. A scientometrics analysis based on Science Citation Index-Expanded (SCI-E) was performed to understand the research trends and areas of focus in GRS research studies. A total of 2692 papers related to GRS research studies and 82,208 references published from 1980 to 2020 were selected as the research objects. A comprehensive overview of the field based on the annual documents, research areas, institutions, influential journals, core authors, and temporal trends in keywords were presented in this study. The results showed that the annual number of documents increased exponentially, and more than 100 papers were published each year since 2010. Remote sensing, environmental sciences, and ecology were the most popular Web of Science research areas. The journal Remote Sensing was one of the most popular for researchers to publish documents and shows high development and publishing potential in GRS research studies. The institution with the greatest research documents and most citations was the Chinese Academy of Sciences. Guo X.L., Hill M.J., and Zhang L. were the most productive authors across the 40-year study period in terms of the number of articles published. Seven clusters of research areas were identified that generated contributions to this topic by keyword co-occurrence analysis. We also detected 17 main future directions of GRS research studies by document co-citation analysis. Emerging or underutilized methodologies and technologies, such as unmanned aerial systems (UASs), cloud computing, and deep learning, will continue to further enhance GRS research in the process of achieving sustainable development goals. These results can help related researchers better understand the past and future of GRS research studies.

Electronic health record (EHR) data is crucial in providing comprehensive historical disease information for patients and is frequently utilized in health event prediction. However, current deep learning models that rely on EHR data encounter significant challenges. These include inadequate exploration of higher‐order relationships among diseases, a failure to capture dynamic relationships in existing relationship‐based disease prediction models, and insufficient utilization of patient symptom information. To address these limitations, a novel dynamic HyperGraph‐based deep learning model is introduced for disease prediction (DHGL) in this study. Initially, pertinent symptom information is extracted from patients to assign them with an initial embedding. Subsequently, sub‐hypergraphs are constructed to consider distinct patient cohorts rather than treating them as isolated entities. Ultimately, these hypergraphs are dynamized to gain a more nuanced understanding of patient relationships. The evaluation of DHGL on real‐world EHR datasets reveals its superiority over several state‐of‐the‐art baseline methods in terms of predictive accuracy. A novel dynamic HyperGraph‐based deep learning model is proposed for disease prediction (DHGL) here. The proposed DHGL model is evaluated on real‐world electronic health record datasets and it is demonstrated that it outperforms several state‐of‐the‐art baseline methods in terms of predictive accuracy.

We explore the semantic-rich structured information derived from the knowledge graphs (KGs) associated with the user-item interactions and aim to reason out the motivations behind each successful purchase behavior. Existing works on KGs-based explainable recommendations focus purely on path reasoning based on current user-item interactions, which generally result in the incapability of conjecturing users’ subsequence preferences. Considering this, we attempt to model the KGs-based explainable recommendation in sequential settings. Specifically, we propose a novel architecture called Reinforced Sequential Learning with Gated Recurrent Unit (RSL-GRU), which is composed of a Reinforced Path Reasoning Network (RPRN) component and a GRU component. RSL-GRU takes users’ sequential behaviors and their associated KGs in chronological order as input and outputs potential top-N items for each user with appropriate reasoning paths from a global perspective. Our RPRN features a remarkable path reasoning capacity, which is regulated by a user-conditioned derivatively action pruning strategy, a soft reward strategy based on an improved multi-hop scoring function, and a policy-guided sequential path reasoning algorithm. Experimental results on four of Amazon’s large-scale datasets show that our method achieves excellent results compared with several state-of-the-art alternatives.

Understanding the propagation characteristics of online emergency news communication is of great importance to guiding emergency management and supporting the dissemination of vital information. However, existing methods are limited to the analysis of the dissemination of online information pertaining to a specific disaster event. To study the quantification of the general spreading patterns and unique dynamic evolution of emergency-related information, we build a systematic, comprehensive evaluation framework and apply it to 81 million reposts from Sina Weibo, Chinese largest online microblogging platform, and perform a comparative analysis with four other types of online information (political, social, techs, and entertainment news). We find that the spreading of emergency news generally exhibits a shorter life cycle, a shorter active period, and fewer fluctuations in the aftermath of the peak than other types of news, while propagation is limited to a few steps from the source. Furthermore, compared with other types of news, fewer users tend to repost the same piece of news multiple times, while user influence (which depends on the number of fans) has the least impact on the number of reposts for news of emergencies. These comparative results provide insights that will be useful in the context of disaster relief, emergency management, and other communication path prediction applications.

To address the limitations of single-modality UWB/IMU systems in complex indoor environments, this study proposes a multimodal fusion localization method based on xLSTM. After extracting features from UWB and IMU data, the xLSTM network enables deep temporal feature learning. A three-stage residual fusion module is introduced to enhance cross-modal complementarity, while a multi-head attention mechanism dynamically adjusts the sensor weights. The end-to-end trained network effectively constructs nonlinear multimodal mappings for two-dimensional position estimation under both static and dynamic non-line-of-sight (NLOS) conditions with human-induced interference. Experimental results demonstrate that the localization errors reach 0.181 m under static NLOS and 0.187 m under dynamic NLOS, substantially outperforming traditional filtering-based approaches. The proposed deep fusion framework significantly improves localization reliability under occlusion and offers an innovative solution for high-precision indoor positioning.

Understanding and monitoring soil organic carbon (SOC) stocks is crucial for ecosystem carbon cycling, services, and addressing global environmental challenges. This study employs the BERTopic model and bibliometric trend analysis exploration to comprehensively analyze global SOC estimates. BERTopic, a topic modeling technique based on BERT (bidirectional encoder representatives from transformers), integrates recent advances in natural language processing. The research analyzed 1761 papers on SOC and remote sensing (RS), in addition to 490 related papers on machine learning (ML) techniques. BERTopic modeling identified nine research themes for SOC estimation using RS, emphasizing spectral prediction models, carbon cycle dynamics, and agricultural impacts on SOC. In contrast, for the literature on RS and ML it identified five thematic clusters: spatial forestry analysis, hyperspectral soil analysis, agricultural deep learning, the multitemporal imaging of farmland SOC, and RS platforms (Sentinel-2 and synthetic aperture radar, SAR). From 1991 to 2023, research on SOC estimation using RS and ML has evolved from basic mapping to topics like carbon sequestration and modeling with Sentinel-2A and big data. In summary, this study traces the historical growth and thematic evolution of SOC research, identifying synergies between RS and ML and focusing on SOC estimation with advanced ML techniques. These findings are critical to global ecosystem SOC assessments and environmental policy formulation.