检索结果-内蒙古大学图书馆

Interpretable vertical federated learning with privacy-preserving multi-source data integration for prognostic prediction

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 148卷

作者： Wang, Qingyong Anhui Agr Univ Sch Informat & Artificial Intelligence Hefei Peoples R China

Digital healthcare is entering a new era characterized by the availability of extensive biomedical data. This wealth of data not only facilitates clinical diagnosis research but also enables the customization of appropriate treatments by incorporating various aspects of patient data. Advanced deep learning methods have the potential to improve clinical diagnosis and treatment efficient significantly. However, a major challenge lies in collecting datasets that are sufficiently large and diverse to train robust prognostic prediction models. Although various types of multi-source data can provide comprehensive insights for medical diagnosis, patient data are often collected by different institutions. Collaborations among multiple institutions involve sharing such data, which raises significant concerns regarding privacy protection and ownership. To address these challenges, this study proposes an interpretable vertical federated learning with meta-optimization (VerFedMeo) that integrates private multi-source data and improves the accuracy of cancer prognosis prediction. Specifically, VerFedMeo employs a partial likelihood function approximation as a its learning objective and derives gradient formulas to achieve more accurate approximations. Meta-optimization has been developed to enhance the model's learning capacities by automatically identifying optimal hyperparameters. The experimental results demonstrate that VerFedMeo approach significantly outperforms existing methods, achieving improvements of 5.8% in F1-score and 3.5% in area under the curve(AUC) compared to the suboptimal method. Moreover, we presented an interpretable consequence of the potential summaries that could be used by clinicians to predict disease prognosis.

关键词： Deep learning Vertical federated learning Meta-optimization multi-source data integration Interpretable disease prognosis

来源：评论

学校读者我要写书评

暂无评论

Innovation and Growth of multi-source data integration in Visual Communication Design

Innovation and Growth of Multi-Source data Integration in Vi...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Zhang, Yingyu Sun, Hongbo Changchun Humanities College Visual Communication Design Changchun China

ISBN: (纸本)9798350313413

In visual communication design (VCD), multi-source data integration plays an important role in innovation and growth. This paper studies and discusses the means of information dissemination in the new media era by analyzing typical digital interaction methods and combining current social hotspots. With the guiding ideology of 'multiple sources', this paper proposes a brand-new, efficient method that meets the needs of the public, aiming to achieve a visual communication art form with multiple expressive effects and a design language system with rich connotations. In the process of conception, this paper covers the technical level of image digital conversion and fusion and interactive data integration, designs a VCD model, and conducts testing and research on multi-source data integration algorithms. The test results show that the data processing time of the multi-source data integration algorithm is within 6 seconds, and the fastest time is 3 seconds. The application of these technologies makes it possible to continuously change and enrich the content and form of VCD. The research on the integration of multi-source data in visual communication design covers multiple important findings. The research needs to explore data processing and integration methods in order to effectively process and integrate data from different data sources. It also considers users' feedback and evaluation of multi-source data integration visual communication design to understand their perception and attitude towards design effectiveness, usability, and information presentation. © 2023 IEEE.

关键词： multi-source data integration visual communication visual design visual innovation

来源：评论

学校读者我要写书评

暂无评论

Characterization of the 3D geometry of flow-like landslides: A methodology based on the integration of heterogeneous multi-source data

引用

ENGINEERING GEOLOGY 2012年 128卷 30-48页

作者： Travelletti, J. Malet, J-P Univ Strasbourg Inst Phys Globe Strasbourg CNRS UMR 7516 F-67084 Strasbourg France Univ Caen Basse Normandie GEOPHEN LETG CNRS UMR 6554 F-14032 Caen France

The geometry of the bedrock, internal layers and slip surfaces control the deformation pattern and the mechanisms of landslides. A challenge to progress in understanding landslide behavior is to construct accurate 3D geometrical models from different surveying techniques. The objective of this work is to present a methodology for integrating multi-source and multi-resolution data in a 3D geometrical model using geostatistical tools. The methodology consists in integrating the data by extracting relevant information on the internal structure of the landslide and in detecting possible incoherencies between different interpretations. A simple method to classify the input data and to control their influence on the model interpolation is proposed through the development of an expert reliability index. The methodology is applied for the creation of a 3D geometrical model of the Super-Sauze mudslide (South French Alps) for which an extensive dataset is available. Error calculation and expert geomorphological interpretation allow one to select the most suitable interpolation algorithm and to define the volumes of each layer. The proposed 3D geometrical model highlights the influence of the bedrock geometry on the observed kinematic pattern. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Landslide 3D geometry multi-source data integration Geostatistical model

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a fast integration method for multi-source data in high-speed network

引用

JOURNAL OF HIGH SPEED NETWORKS 2023年第3期29卷 251-263页

作者： Ma, Lei Zhang, Yanning Garcia-Diaz, Vicente Beijing Polytech Sch Telecommun Engn Beijing Peoples R China Univ Oviedo Dept Comp Sci Oviedo Spain

The data collected by the distributed high-speed network has multiple sources. Therefore, in order to realize the rapid integration of multi-source data, this paper designs a rapid data integration method based on the characteristics of the distributed high-speed network. First, we use linear regression analysis to build a distributed perceptual data model, so that network nodes can only transmit the parameter information of the regression model, so as to simplify the data collection. Then, a dead band amplitude limiting nonlinear link is added at the high frequency channel side to filter and assimilate the data. Finally, the data feature vectors are extracted as the training samples of the neural network to obtain the mapping relationship between different feature vectors, and then the decision level data integration is achieved by training the neural network. The experimental results show that this method can accurately collect high-speed network data, and the data collection deviation is always less than 5 mu rad;This method has good filtering effect on data and can eliminate the interference of burr signal;The convergence speed of this method is fast, and the data assimilation can be completed within 0.4 s, which is conducive to improving the speed of data integration;With the increase of network size, the average traffic load of this method increases less.

关键词： Distributed system data acquisition high-speed network multi-source data integration nonlinear filtering heterogeneous assimilation

来源：评论

学校读者我要写书评

暂无评论

data-driven safety management of worker-equipment interactions using visual relationship detection and semantic analysis

引用

AUTOMATION IN CONSTRUCTION 2025年 175卷

作者： Liu, Yipeng Wang, Junwu Torbaghan, Mehran Eskandari Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572025 Peoples R China Wuhan Univ Technol Sch Civil Engn & Architecture Wuhan 430070 Peoples R China Univ Birmingham Dept Civil Engn Birmingham B15 2TT England

Existing technologies struggle to accurately identify interactions between workers and equipment, as well as the deep semantics of complex construction scenes. To address these limitations, this paper proposes an automated construction site safety management system designed to enhance scene understanding and identify safety hazards while focusing on hazard-area and personal protective equipment (PPE) interaction. The system transforms image information into worker-centric triplets and generates precise textual descriptions through semantic enhancement, enabling effective scene analysis. By comparing the generated descriptions with predefined hazard statements, the system identifies potential risks. Experimental results demonstrate a 9.6 % improvement in recall for Ng-mR@K metrics (K = 20, 50, 100). Additionally, the system successfully filters over 90 % of invalid relationships, achieving 83.7 % accuracy in semantic similarity matching, significantly enhancing detection precision and semantic understanding. By advancing from object detection to a structured image-to-triplet-to-text framework, this paper offers an efficient and reliable solution for automated construction site safety management.

关键词： Construction site safety multi-source data integration Visual relationship detection Semantic triplets Image-to-text transformation Semantic enhancement

来源：评论

学校读者我要写书评

暂无评论

Path-ComDim multi-block data analysis in the cachaça investigation: Integrating sensory analysis with electronic and vibrational spectroscopies

引用

FOOD CHEMISTRY 2025年 481卷 143894页

作者： Cruz, Eduarda Barbieri da Silva Baqueta, Michel Rocha Rutledge, Douglas N. Valderrama, Patricia Univ Tecnol Fed Parana Campus Campo Mourao UTFPR CM Campo Mourao Parana Brazil Univ Paris Saclay Orsay France CNRS Museum Natl Hist Nat MCAM UMR7245 Paris France

Cacha & ccedil;a consumption is valued for its unique characteristics, many of which stem from aging in various wooden barrels, imparting specific flavors and aromas. However, whether unaged cacha & ccedil;as with artificial flavoring exhibit attributes similar to those of naturally aged cacha & ccedil;as remains unclear. This study examined sensory and chemical aspects of both aged and flavored cacha & ccedil;as through an integrated approach combining sensory analysis with ultraviolet, visible, mid-infrared, and near-infrared spectroscopies. In the chemometric domain, PathComDim was employed to integrate and interpret multi-source data, revealing sensory-spectral correlations to characterize cacha & ccedil;a samples derived from aging and flavoring processes. Although the production regions of the cacha & ccedil;as were known beforehand, this factor did not distinguish them. Overall, the findings indicate that flavored and aged cacha & ccedil;as may share sensory similarities because some flavored cacha & ccedil;as can exhibit sensory attributes similar to those aged in Oak, Balsamo, and Umburana woods.

关键词： Brazilian cacha & ccedil a Chemometrics multi-source data integration Sensory dimensions Spectral techniques Sugarcane spirits

来源：评论

学校读者我要写书评

暂无评论

Digital twin comprehensive models: a study of ancient tree ecological environment quality assessment based on a cyber-physical system

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2025年第4期197卷 1-28页

作者： Chen, Yansheng Huang, Huazhi Li, Jie Zheng, Zejiong Gao, Fengjun Han, Xiaoge Gao, Yanglin Guangdong Ind Polytech Univ Dept Inst Big Data & Artificial Intelligence Appli Guangzhou 510300 Peoples R China Guangdong Ind Polytech Sch Ecoenvironm Technol Guangzhou 510300 Peoples R China Guangdong Ind Polytech Sch Finance & Trade Guangzhou 510300 Peoples R China

This study leverages cyber-physical system (CPS) technology to create a digital twin model for assessing the ecological quality of ancient trees. Integrating multi-source data and machine learning, our model provides tailored conservation strategies, supports ecological restoration, and enhances disaster response capabilities. Key findings illustrate that the model is precise in monitoring tree health, managing water resources, and predicting the impacts of natural disasters. This innovative approach provides significant advantages in real-time monitoring and long-term ecological management, ensuring the sustainability of ancient tree ecosystems. Our results highlight the model's potential to transform ecological conservation practices and offer a reliable tool for researchers and practitioners in environmental science.

关键词： Ancient tree conservation Real-time monitoring Machine learning in ecology Ecosystem sustainability Habitat quality assessment multi-source data integration

来源：评论

学校读者我要写书评

暂无评论

Optimization of Dynamic Pricing Models for Consumer Segmentation Markets and Analysis of Big data-Driven Marketing Strategies

引用

JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING 2025年第1期37卷

作者： Zhang, Qi Shi, Qiang Alatas, Bilal Yuan, Yu-His ANHUI Int Studies Univ Hefei Peoples R China Firat Univ Elazig Turkiye Natl Taiwan Univ Arts Taipei Taiwan

In response to the challenges posed by globalization and rapid technological advancements, traditional static pricing models are no longer sufficient to capture the dynamic nature of consumer behavior and market fluctuations. This study proposes a "multi-dimensional Dynamic Pricing Optimization and Consumer Behavior Prediction Model Driven by Big data," which integrates multi-source data and reinforcement learning to improve dynamic pricing strategies. Through a hybrid model architecture using Random Forest and LSTM, it captures both static and time-series features. Experimental results show that the proposed model significantly outperforms baseline models, achieving a 43% reduction in Mean Squared Error (MSE), a 28% decrease in Mean Absolute Percentage Error (MAPE), a 6.5% increase in Accuracy, and a 14.7% increase in Cumulative Revenue. These findings confirm the model's ability to enhance prediction accuracy, optimize pricing strategies, and maximize revenue, demonstrating its potential for real-world applications in industries like e-commerce, finance, and advertising.

关键词： Dynamic Pricing Consumer Behavior Prediction Reinforcement Learning multi-source data integration Real-Time Strategy Optimization

来源：评论

学校读者我要写书评

暂无评论

A novel multi-source data-driven energy consumption prediction model for Venlo-type greenhouses in China

引用

SMART AGRICULTURAL TECHNOLOGY 2025年 10卷

作者： Chen, Yangda Bao, Aiqun Li, Yapeng Xiang, Yingfeng Cai, Wanlong Xia, Zhaoqiang Li, Jialei Ning, Mingyang Sun, Jing Zhang, Haixi Sun, Xianpeng Wei, Xiaoming Northwest A&F Univ Coll Hort Yangling 712100 Shaanxi Peoples R China Northwest A&F Univ Coll Informat Engn Yangling 712100 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Human Settlements & Civil Engn Xian 710049 Shaanxi Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Shaanxi Peoples R China Beijing Acad Agr & Forestry Sci Res Ctr Intelligent Equipment Beijing 100097 Peoples R China Minist Agr Key Lab Hort Engn Northwest Facil Yangling 712100 Shaanxi Peoples R China Facil Agr Engn Technol Res Ctr Shaanxi Prov Yangling 712100 Shaanxi Peoples R China

The high energy consumption characteristic of multi-span glass greenhouses significantly limits their widespread adoption. Optimizing energy strategies and implementing predictive models for energy consumption are essential for more efficient management and reduction of greenhouse operational energy costs. Existing methods rely on single-element approaches to predict energy consumption, but this reliance often results in severe performance limitations. Therefore, energy consumption prediction methods that incorporate multi-source data are necessary. To overcome the challenges concerning heterogeneity, redundancy, and interdependence among different data sources, this paper proposed a novel energy consumption method that integrates multi-source data through feature engineering and machine learning techniques, which significantly enhances the efficiency of data utilization and improves prediction accuracy. The final experimental results indicated that the proposed energy consumption prediction method demonstrates excellent performance with high prediction accuracy (R2 = 0.9388) and low computational resource consumption (runtime = 926.91s), outperforming other models. Finally, the model was interpreted using SHAP (SHapley Additive exPlanations) values, and ablation experiments were conducted to validate the effectiveness of the proposed method in greenhouse energy consumption prediction, thereby providing strong support for greenhouse management.

关键词： Greenhouse energy consumption multi-source data integration Feature engineering Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Enhancing monthly precipitation forecasting by integrating multi-source data with machine learning models: a study in the Upper Blue Nile Basin

引用

MODELING EARTH SYSTEMS AND ENVIRONMENT 2025年第1期11卷 1-16页

作者： Mohammed, Juhar Mengiste, Yenesew Gebremichael, Mekonnen Addis Ababa Univ Addis Ababa Ethiopia Addis Ababa Sci & Technol Univ Addis Ababa Ethiopia Univ Calif Los Angeles Los Angeles CA USA

This study developed a novel framework to improve monthly precipitation forecasts by integrating multi-source data with machine-learning techniques. The framework used a blend of gauge, satellite, and reanalysis data to train the model with high-quality spatial-temporal precipitation information. Predictors such as local meteorological variables, large-scale climate indices, soil moisture data, and lagged precipitation data were used for one-month ahead precipitation forecasting. Five machine learning algorithms, including Artificial Neural Networks (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGboost), and Random Forest (RF), are evaluated in the framework for their forecasting performance across five monitoring stations in the upper Blue Nile basin. The results demonstrate that the novel forecasting framework integrating multi-source data with machine learning techniques significantly improved the monthly precipitation forecasts. All models exhibited higher R2, closer agreement with observed data measured by Wilmot's index (d), and lower MAE and RMSE values. During testing phase, the models recorded 0.64-0.87 R 2, 0.62-2.95 RMSE, 0.18-2.42 MAE and 0.7-0.85 d values across stations. Among the models evaluated in the framework ANN, SVM, and KNN consistently showcased better performance both in the training and testing phases, with ANN exhibiting the most promising results overall. However, Extreme Gradient Boosting and Random Forests exhibited comparatively weaker performance across stations. Additionally, the models' performance under different climate categories (dry, normal, and wet months) was also explored. The models excel during normal and dry months, but, during wet months their performance diminishes relatively. Furthermore, the proposed framework forecast skills compared with NCEP and ECMWF global precipitation prediction and showed a better performance. Overall, the findings highlight the potential of the deve

关键词： multi-source data integration Machine learning models Monthly precipitation forecasting Global precipitation predictions Upper Blue Nile Basin

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：