Construction of and Low-Carbon Optimization Strategies for Block-Level Carbon Emission Control Unit by Wenjie LI, Yingsheng ZHENG, Qingfang ZHANG, Qiuyun ZENG

“…These parameters are then used to develop LCZ classification and urban morphology maps, providing a data foundation for spatial carbon emission modelling. …”
Get full text

Research on distribution characteristics and main controlling factors of rock burst in steeply inclined coal seams by Haodang LI, Xucong HU, Taoping ZHONG, Ruibing YAN, Ende LIU, Xudong LIU, Zhenlei LI

“…Narrower pillar widths result in shorter transmission distances, greater stress amplification in the coal seam, and higher rock burst risk. Field monitoring data show that in areas with wider interlayer pillars, energy release from surrounding rock is dominated by low and medium level micro-seismic events, and few high level micro-seismic events. …”
Get full text

A new dataset for measuring the performance of blood vessel segmentation methods under distribution shifts. by Matheus Viana da Silva, Natália de Carvalho Santos, Julie Ouellette, Baptiste Lacoste, Cesar H Comin

“…Thus, the VessMAP dataset can be used for the development of new active learning methods for selecting relevant samples for manual annotation as well as for analyzing the robustness of segmentation models to distribution shifts of the data.…”
Get full text

Dual-Aspect Active Learning with Domain-Adversarial Training for Low-Resource Misinformation Detection by Luyao Hu, Guangpu Han, Shichang Liu, Yuqing Ren, Xu Wang, Zhengyi Yang, Feng Jiang

“…Although deep learning-based detection methods have achieved promising results, their effectiveness heavily relies on large amounts of labeled data, limiting their applicability in low-resource scenarios. …”
Get full text

Intelligent Analysis of Logistics Information Based on Network Dynamic Data by Honglin Yan

“…Investigate the needs of export shipments, such as external management responsibilities, requirements of management responsibilities, data recovery, and data recovery requirements, based on the current state of the shared platform model integration, and determine the business model. …”
Get full text

Effects of low-flux and high-flux hemodialysis on the survival of elderly maintenance hemodialysis patients by Wanqing Huang, Jiuxu Bai, Yanping Zhang, Dongxia Qiu, Lin Wei, Chen Zhao, Zhuo Ren, Qian Wang, Kaiming Ren, Ning Cao

“…Propensity score matching was used to balance the baseline data of the two groups. Survival rates were compared between the two groups, and the risk factors for death were analyzed by multivariate Cox regression.Results Kaplan–Meier survival analysis revealed no significant difference in all-cause mortality between the low-flux group and the high-flux group (log-rank test, p = 0.559). …”
Get full text

On Predicting Marine Engine Measurements with Synthetic Data in Scarce Dataset by Sandi Baressi Šegota, Igor Poljak, Nikola Anđelić, Vedran Mrzljak

“…The engine load variable remained challenging to predict due to its narrow and low-range distribution. Overall, the study highlights synthetic data as a viable solution for enhancing the performance of ML models in data-scarce maritime applications.…”
Get full text

Small earthquake location via machine learning with insufficient data by Ji Zhang, Aitaro Kato, Huiyu Zhu, Jie Zhang

“…Abstract A comprehensive earthquake catalog plays a crucial role in enhancing our understanding of earthquake activity and generation mechanisms. However, due to the low station density and data quality limitations, numerous small earthquakes remain undetected and unlocated. …”
Get full text

Elucidating the dynamics of carbamazepine uptake using date pit-derived activated carbon: A comprehensive kinetic and thermodynamic analysis by Ramez M. Zayyat, Rim Yahfoufi, Mahmoud Al-Hindi, Michel A. Kordahi, George M. Ayoub, Mohammad N. Ahmad

Get full text

EARTH SURFACE DEFORMATION OF THE SAKHALIN ISLAND FROM GPS DATA by A. S. Prytkov, N. F. Vasilenko

Get full text

Machine learning approaches for imputing missing meteorological data in Senegal by Mory Toure, Nana Ama Browne Klutse, Mamadou Adama Sarr, Md Abul Ehsan Bhuiyan, Annine Duclaire Kenne, Wassila Mamadou Thiaw, Daouda Badiane, Amadou Thierno Gaye, Ousmane Ndiaye, Cheikh Mbow

“…Furthermore, the exclusion of satellite or reanalysis inputs may constrain model generalizability.Ultimately, this study reinforces the role of advanced machine learning methods in improving climate data completeness and reliability in Africa. …”
Get full text

Rapid Diagnosis of Distributed Acoustic Sensing Vibration Signals Using Mel-Frequency Cepstral Coefficients and Liquid Neural Networks by Haitao Liu, Yunfan Xu, Yuefeng Qi, Haosong Yang, Weihong Bi

“…Distributed Acoustic Sensing (DAS) systems face increasing challenges in massive data processing and real-time fault diagnosis due to the growing complexity of industrial environments and data volume. …”
Get full text

State of Health Estimation for Lithium-Ion Batteries Using Electrochemical Impedance Spectroscopy and a Multi-Scale Kernel Extreme Learning Machine by Jichang Peng, Ya Gao, Lei Cai, Ming Zhang, Chenghao Sun, Haitao Liu

“…This study proposes a novel method that combines EIS with an equivalent circuit model (ECM) and distribution of relaxation time (DRT) analysis to extract low-dimensional health features from high-dimensional EIS data. …”
Get full text

High-performance federated continual learning algorithm for heterogeneous streaming data by Hui JIANG, Tianliu HE, Min LIU, Sheng SUN, Yuwei WANG

“…Aiming at the problems of poor model performance and low training efficiency in training streaming data of AI models that provide intelligent services, a high-performance federated continual learning algorithm for heterogeneous streaming data (FCL-HSD) was proposed in the distributed terminal system with privacy data.In order to solve the problem of the current model forgetting old data, a model with dynamically extensible structure was introduced in the local training stage, and an extension audit mechanism was designed to ensure the capability of the AI model to recognize old data at the cost of small storage overhead.Considering the heterogeneity of terminal data, a customized global model strategy based on data distribution similarity was designed at the central server side, and an aggregation-by-block manner was implemented for different modules of the model.The feasibility and effectiveness of the proposed algorithm were verified under various data increment scenarios with different data sets.Experimental results show that, compared with existing works, the proposed algorithm can effectively improve the model performance to classify old data on the premise of ensuring the capability to classify new data.…”
Get full text

An Evolutionary Deep Reinforcement Learning-Based Framework for Efficient Anomaly Detection in Smart Power Distribution Grids by Mohammad Mehdi Sharifi Nevisi, Mehrdad Shoeibi, Francisco Hernando-Gallego, Diego Martín, Sarvenaz Sadat Khatami

“…The increasing complexity of modern smart power distribution systems (SPDSs) has made anomaly detection a significant challenge, as these systems generate vast amounts of heterogeneous and time-dependent data. …”
Get full text

High-performance federated continual learning algorithm for heterogeneous streaming data by Hui JIANG, Tianliu HE, Min LIU, Sheng SUN, Yuwei WANG

“…Aiming at the problems of poor model performance and low training efficiency in training streaming data of AI models that provide intelligent services, a high-performance federated continual learning algorithm for heterogeneous streaming data (FCL-HSD) was proposed in the distributed terminal system with privacy data.In order to solve the problem of the current model forgetting old data, a model with dynamically extensible structure was introduced in the local training stage, and an extension audit mechanism was designed to ensure the capability of the AI model to recognize old data at the cost of small storage overhead.Considering the heterogeneity of terminal data, a customized global model strategy based on data distribution similarity was designed at the central server side, and an aggregation-by-block manner was implemented for different modules of the model.The feasibility and effectiveness of the proposed algorithm were verified under various data increment scenarios with different data sets.Experimental results show that, compared with existing works, the proposed algorithm can effectively improve the model performance to classify old data on the premise of ensuring the capability to classify new data.…”
Get full text

Assessment of Habitat Suitability and Identification of Conservation Priority Areas for Endangered Marco Polo Sheep Throughout Khunjerab National Park (Pakistan) and Tashkurgan Nat... by Ishfaq Karim, Xiaodong Liu, Babar Khan, Tahir Kazmi

Get full text

Spatial distributions and determinants of intimate partner violence among married women in Ethiopia across administrative zones. by Meseret Tadesse Fetene, Senait Cherie Adgeh, Haile Mekonnen Fenta

“…<h4>Background</h4>Intimate partner violence (IPV) against women is highly prevalent in the world, especially in low-middle-income countries including Ethiopia. …”
Get full text

Optimal configuration of multi-microgrid energy system based on historical data by XIU Chunnan, REN Dajiang, LIU Qiang, WANG Meng’en

“…Aiming at the problems of low utilization rate of distributed energy in China, weak interaction between energy microgrids, and unreasonable equipment configuration, a multi-microgrid integrated energy scheduling optimization configuration model based on historical data is established in this paper. …”
Get full text

Spaciotemporal distribution characteristics of glacial lakes and the factors influencing the Southeast Tibetan Plateau from 1993 to 2023 by Yu Mingwei, Guo Yonggang, Zhang Jian, Li Feng, Su Libin, Qin Deshun

“…The distribution of glacial lakes in this region follows a pattern characterized by a relatively high concentration in the southern region and a relatively low concentration in the northern region. …”
Get full text