检索结果-内蒙古大学图书馆

Evaluating the Effect of Training Data Size and Composition on the Accuracy of Smallholder Irrigated Agriculture Mapping in Mozambique Using Remote Sensing and machine learning algorithms

引用

REMOTE SENSING 2023年第12期15卷 3017-3017页

作者： Weitkamp, Timon Karimi, Poolad Resilience BV NL-6703 AA Wageningen Netherlands Wageningen Univ & Res Water Resource Management WRM Dept NL-6708 PB Wageningen Netherlands IHE Delft NL-2611 AX Delft Netherlands

Mapping smallholder irrigated agriculture in sub-Saharan Africa using remote sensing techniques is challenging due to its small and scattered areas and heterogenous cropping practices. A study was conducted to examine the impact of sample size and composition on the accuracy of classifying irrigated agriculture in Mozambique's Manica and Gaza provinces using three algorithms: random forest (RF), support vector machine (SVM), and artificial neural network (ANN). Four scenarios were considered, and the results showed that smaller datasets can achieve high and sufficient accuracies, regardless of their composition. However, the user and producer accuracies of irrigated agriculture do increase when the algorithms are trained with larger datasets. The study also found that the composition of the training data is important, with too few or too many samples of the "irrigated agriculture" class decreasing overall accuracy. The algorithms' robustness depends on the training data's composition, with RF and SVM showing less decrease and spread in accuracies than ANN. The study concludes that the training data size and composition are more important for classification than the algorithms used. RF and SVM are more suitable for the task as they are more robust or less sensitive to outliers than the ANN. Overall, the study provides valuable insights into mapping smallholder irrigated agriculture in sub-Saharan Africa using remote sensing techniques.

关键词： irrigated agriculture training data sub-Saharan Africa machine-learning algorithms class imbalance

来源：评论

学校读者我要写书评

暂无评论

Synergistic Application of Multiple machine learning algorithms and Hyperparameter Optimization Strategies for Net Ecosystem Productivity Prediction in Southeast Asia

引用

REMOTE SENSING 2024年第1期16卷 17-17页

作者： Huang, Chaoqing Chen, Bin Sun, Chuanzhun Wang, Yuan Zhang, Junye Yang, Huan Wu, Shengbiao Tu, Peiyue Nguyen, MinhThu Hong, Song He, Chao Yangtze Univ Coll Resources & Environm Wuhan 434023 Peoples R China Wuhan Univ Sch Resource & Environm Sci Wuhan 430079 Peoples R China Wuhan Univ Key Lab Geog Informat Syst Minist Educ Wuhan 430079 Peoples R China Univ Hong Kong Fac Architecture Dept Architecture Div Landscape ArchitectureFuture Urban & Sustaina Hong Kong Peoples R China South China Agr Univ Sch Publ Management Guangzhou 510642 Peoples R China Jiangxi Normal Univ Sch Geog & Environm Nanchang 330022 Peoples R China Minist Nat Resources & Environm Vietnam Inst Meteorol Hydrol & Climate Change Hanoi 100803 Vietnam

The spatiotemporal patterns and shifts of net ecosystem productivity (NEP) play a pivotal role in ecological conservation and addressing climate change. For example, by quantifying the NEP information within ecosystems, we can achieve the protection and restoration of natural ecological balance. Monitoring the changes in NEP enables a more profound understanding and prediction of ecosystem alterations caused by global warming, thereby providing a scientific basis for formulating policies aimed at mitigating and adapting to climate change. The accurate prediction of NEP sheds light on the ecosystem's response to climatic variations and aids in formulating targeted carbon sequestration policies. While traditional ecological process models provide a comprehensive approach to predicting NEP, they often require extensive experimental and empirical data, increasing research costs. In contrast, machine-learning models offer a cost-effective alternative for NEP prediction;however, the delicate balance in algorithm selection and hyperparameter tuning is frequently overlooked. In our quest for the optimal prediction model, we examined a combination of four mainstream machine-learning algorithms with four hyperparameter-optimization techniques. Our analysis identified that the backpropagation neural network combined with Bayesian optimization yielded the best performance, with an R2 of 0.68 and an MSE of 1.43. Additionally, deep-learning models showcased promising potential in NEP prediction. Selecting appropriate algorithms and executing precise hyperparameter-optimization strategies are crucial for enhancing the accuracy of NEP predictions. This approach not only improves model performance but also provides us with new tools for a deeper understanding of and response to ecosystem changes induced by climate change.

关键词： machine-learning algorithms hyperparameter optimization remote sensing Southeast Asia net ecosystem productivity

来源：评论

学校读者我要写书评

暂无评论

The Kullback-Leibler Divergence Used in machine learning algorithms for Health Care Applications and Hypertension Prediction: A Literature Review

引用

Procedia Computer Science 2018年 141卷 448-453页

作者： Antonio Clim Răzvan Daniel Zota Grigore TinicĂ Bucharest Academy of Economic Studies 15-17 Dorobanti Bucharest 010552 ROMANIA University of Medicine and Pharmacy "Grigore T.Popa" 16 Universitatii Street Iași 700115 ROMANIA

Kullback-Leibler divergence class or relative entropy is an exceptional instance of a more extensive divergence. It is an estimation of how a particular dissemination wanders from another, normal likelihood appropriation. Kullback-Leibler divergence has a considerable measure of ongoing applications. Despite the fact that there is an advance in the drug field, it still requires a measurable examination for supporting developing prerequisites. This paper discusses the use of Kullback-Leibler divergence as a conceivable technique to foresee hypertension, utilizing chest sound accounts and machine-learning calculations. It would have a unique, elevated advantage in the crisis medical services framework. Interpreting the chest sound example gives a wide and varying degree of recognition concerning different abnormalities and prosperity conditions of the restorative field. The proposed technique to estimate circulatory strain is chest sound examination, using a strategy that makes a record of sounds conveyed by the contracting heart, coming to fruition in view of valves and related vessel vibration, finally investigating it with the assistance of Kullback-Leibler divergence and machine calculation. An investigation employing the Kullback-Leibler divergence strategy will permit finding the distinction in chest sound chronicles, which can be assessed by a machine-learning calculation. Likewise, the report proposes the strategy for examining the chest sound accounts in Kullback-Leibler divergence class.

关键词： Kullback-Leibler Divergence Class chest sound analysis machine-learning algorithms continuous monitoring of hypertension probability distribution Clinical Decision Support

来源：评论

学校读者我要写书评

暂无评论

Using Feature-Assisted machine learning algorithms to Boost Polarity in Lead-Free Multicomponent Niobate Alloys for High-Performance Ferroelectrics

引用

ADVANCED SCIENCE 2022年第13期9卷 e2104569页

作者： Oh, Seung-Hyun Victor Hwang, Woohyun Kim, Kwangrae Lee, Ji-Hwan Soon, Aloysius Yonsei Univ Dept Mat Sci & Engn Seoul 03722 South Korea Yonsei Univ Ctr Artificial Synesthesia Mat Seoul 03722 South Korea

To expand the unchartered materials space of lead-free ferroelectrics for smart digital technologies, tuning their compositional complexity via multicomponent alloying allows access to enhanced polar properties. The role of isovalent A-site in binary potassium niobate alloys, (K,A)NbO3 using first-principles calculations is investigated. Specifically, various alloy compositions of (K,A)NbO3 are considered and their mixing thermodynamics and associated polar properties are examined. To establish structure-property design rules for high-performance ferroelectrics, the sure independence screening sparsifying operator (SISSO) method is employed to extract key features to explain the A-site driven polarization in (K,A)NbO3. Using a new metric of agreement via feature-assisted regression and classification, the SISSO model is further extended to predict A-site driven polarization in multicomponent systems as a function of alloy composition, reducing the prediction errors to less than 1%. With the machine learning model outlined in this work, a polarity-composition map is established to aid the development of new multicomponent lead-free polar oxides which can offer up to 25% boosting in A-site driven polarization and achieving more than 150% of the total polarization in pristine KNbO3. This study offers a design-based rational route to develop lead-free multicomponent ferroelectric oxides for niche information technologies.

关键词： computational materials feature engineering ferroelectric oxides machine-learning algorithms multicomponent alloys

来源：评论

学校读者我要写书评

暂无评论

PSXI-23 Development of sub-models to estimate protein requirements and supply of lactating dairy cows using machine learning algorithms

引用

Journal of Animal Science 2024年第SUPPLEMENT_3期102卷 764–765页

作者： Lee, Mingyung Seo, Seongwon Tedeschi, Luis O Texas A&M University Chungnam National University Texas A&M university department of Animal Science

The objectives of this study were to develop sub-models for predicting protein requirements and supply, encompassing 1) net protein for maintenance (NPm), 2) lactation (NPl), 3) rumen undegradable protein (RUP), and 4) duodenal microbial nitrogen (MicN) from the feed protein. The dataset used in this study was constructed by integrating in vivo experimental data collected from open databases (the National Animal Nutrition Program) and articles (Journal of Dairy Science), which includes a total of 1,779 observations from 436 publications. In the development of the model, animal information and feed chemical components were used as candidate variables, and two types of machine learning algorithms, Random Forest Regression (RFR) and Support Vector Regression (SVR) were employed. After testing, the following predictors were selected for predicting: 1) NPm: body weight (BW) and dry matter intake (DMI), 2) NPl: BW, DMI, days in milk (DIM), and dietary organic matter (OM) and crude protein (CP) contents, 3) RUP: DIM, DMI, dietary DM content, and CP fraction intake (B and C), and 4) MicN: DIM, DMI, DM, dietary neutral detergent fiber (NDF) content, CP fraction intake (A, B, and C). The selected models were assessed using a cross-validation method with the following statistical metrics including the coefficient of determination (R2), root-mean-square error of prediction (RMSEP), residual analyses, and concordance correlation coefficient (CCC). For the RUP and MicN models, they were compared with the NASEM (2021) model. In predicting NPm, both SVR and RFR algorithms demonstrated increased precision (R2= 0.965 vs. 0.969) and accuracy (RMSEP = 9.7 vs. 9.2 g/d); however, during residual analysis, the RFR model showed a statistically significant slope bias (P< 0.05). In the NPl prediction, the RFR algorithm showed slightly greater performance compared with SVR (R2= 0.864 vs. 0.814 and RMSEP = 86.7 vs. 98.5 g/d). However, similar to the NPm prediction, the RFR model displayed a st

关键词： machine-learning algorithms modeling protein requirements and supply

来源：评论

学校读者我要写书评

暂无评论

machine learning approaches for the prediction of hydrogen uptake in metal-organic-frameworks: A comprehensive review

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2025年 98卷 1131-1154页

作者： Yamde, Aryan Anil Lade, Vikesh Gurudas Bindwal, Ankush Babarao Tiwari, Manishkumar S. Birmod, Ramesh Pandharinath Laxminarayan Innovat Technol Univ Dept Chem Engn Nagpur 440033 Maharashtra India CSIR Indian Inst Petr Distillate & Heavy Oil Proc Div Haridwar Rd Dehra Dun 248005 Uttarakhand India SVKMs NMIMS Mukesh Patel Sch Technol Management & Dept Data Sci Mumbai 400056 Maharashtra India

Hydrogen (H2) is a potential energy source for achieving net-zero carbon emissions. Metal Organic Frameworks (MOFs) are promising for hydrogen storage due to their high specific surface area, large pore volume, and adaptable structure. machine learning (ML) offers adaptability, scalability, and automation, making it effective for analyzing MOF performance in H2 storage prediction. Databases like HyMARC and CoRE MOF 2019 provide suitable data for this purpose. ML-based screening techniques outperform HTCS and GCMC calculations. Key descriptors influencing hydrogen uptake include pressure, temperature, pore volume, and BET surface area. ML algorithms such as LASSO, MLR, RF, ERT, GB, MLP, DNN, LS-SVM, and CMIS have shown superior prediction performance with R2 values over 0.95. This review highlights the impact of MOF datasets, screening methodologies, and ML algorithms on predicting MOF hydrogen absorption capabilities, offering insights and guidance for future ML-based MOF research.

关键词： Metal-organic frameworks Hydrogen storage machine-learning algorithms Uptake predictions Ensemble models Deep learning

来源：评论

学校读者我要写书评

暂无评论

A machine learning-based nuclear magnetic resonance profiling model to authenticate 'Jerez-Xere`s-Sherry' wines☆

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2025年 337卷 126102页

作者： Hiniesta-Valero, Jaime Guerra-Castellano, Alejandra Fernandez-Veloso, Andrea De la Rosa, Miguel A. Diaz-Moreno, Irene Univ Seville Ctr Invest Cient Isla Cartuja cicCartuja Consejo Super Invest Cient CSIC Inst Invest Quim IIQ Avda Americo Vespucio 49 Seville 41092 Spain

Traditionally, wine quality and certification have been assessed through sensory analysis by trained tasters. However, this method has the limitation of relying on highly specialized individuals who are typically trained to evaluate only specific types of products, such as those associated with a particular Denomination of Origin (D. O.), etc. While tasters can often identify instances of fraud, they are generally unable to pinpoint its origins or explain the mechanisms behind it. On the other hand, classical biochemistry has made significant progress in understanding various aspects of winemaking. However, it has yet to identify the specific metabolites responsible for the unique characteristics of wines, particularly those influenced by complex variables involving multiple compounds, such as geographical differences between regions or vineyards. The concept of the "Terroir fingerprint" has emerged as a novel approach to wine certification. The concept refers to the unique characteristics imparted to a wine by its geography, climate, and aging process. Nuclear Magnetic Resonance (NMR) technology plays a pivotal role in establishing this "Terroir fingerprint" because it enables precise identification, quantification, and differentiation of the compounds present in wine. NMR provides a highly reproducible and specific method for certification. This work introduces an innovative project that combines NMR technology with Artificial Intelligence to create a profiling model for certifying the authenticity and quality of 'Jerez-Xere`s-Sherry' wines.

关键词： machine-learning algorithms Metabolomics Nuclear magnetic resonance Wine

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of spatial distribution modeling of plant species in mountainous environments: Implications for biodiversity conservation and climate change assessment

KUWAIT JOURNAL OF SCIENCE

引用

KUWAIT JOURNAL OF SCIENCE 2025年第1期52卷

作者： Safdar, Sadaf Younes, Isma Ahmad, Adeel Sastry, Srikumar Univ Punjab Inst Geog Lahore 54590 Pakistan Taylor Geospatial Inst St. Louis MO 63103 USA Washington Univ St Louis Dept Comp Sci & Engn St. Louis MO 63130 USA

Species Distribution Modelling (SDM) techniques, developed in the 1980s, have gained significant attention in recent years. These techniques are increasingly recognized as powerful tools to support forest management strategies in the context of climate change. This study presents a comprehensive literature review of SDM techniques in mountainous environments, utilizing remote sensing techniques and data. Forty-one published papers were reviewed, covering 25 years (1997-2022). The review explores various SDM techniques, the use of remotely sensed data, accuracy assessments, environmental variables, and the limitations and challenges of species distribution modeling in mountainous environments across different spatial scales. The study revealed that the most widely used SDM techniques were Maximum Entropy (MaxEnt), Random Forest (RF), and Generalized Linear Models (GLMs), with recent studies emphasizing machine learning. We describe different modeling algorithms, including presence-only and presence/absence modeling algorithms, machine-learning algorithms, distance-based algorithms, and regression-based algorithms. This study presents the first global literature review of SDM techniques in mountainous environments, emphasizing the necessity of considering the uncertainties associated with climate change scenarios. This study also argues the strengths and limitations of SDM techniques in mountainous environments. Despite limitations of SDM techqniues, the study found an increasing trend in their application in mountainous environments. Finally, this review aims to provide a valuable resource for forest managers, researchers, practitioners, and policymakers employed in forest conservation in mountainous environments around the globe.

关键词： Literature review Mountainous environments MaxEnt machine-learning algorithms Forest ecosystem

来源：评论

学校读者我要写书评

暂无评论

machine-learning-Based Predictive Model for Bothersome Stress Urinary Incontinence Among Parous Women in Southeastern China

引用

INTERNATIONAL UROGYNECOLOGY JOURNAL 2025年第2期36卷 391-401页

作者： Wang, Qi Jiang, Xiaoxiang Li, Xiaoyan Que, Yanzhen Lin, Chaoqin Fujian Matern & Child Hlth Hosp Dept Gynecol 18 Dao Shan St Fuzhou 350000 Peoples R China Fujian Med Univ Coll Clin Med Obstet & Gynecol & Pediat Fuzhou Peoples R China Fujian Prov Key Lab Women & Childrens Crit Dis Res Fuzhou Peoples R China Shaxian Gen Hosp Dept Gynecol & Obstet Sanming Peoples R China

Introduction and HypothesisAccurate identification of female populations at high risk for urinary incontinence (UI) and early intervention are potentially effective initiatives to reduce the prevalence of UI. We aimed to apply machine-learning techniques to establish, internally validate, and provide interpretable risk assessment *** from a cross-sectional epidemiological survey of female urinary incontinence conducted in 2022 were used. Sociodemographic and obstetrics-related characteristics, comorbidities, and urinary incontinence questionnaire results were used to develop multiple prediction models. Seventy percent of the individuals in the study cohort were employed in model training, and the remainder were used for internal validation. Model performance was characterized by area under the receiver-operating characteristic curve (AUC) and calibration curves, as well as Brier scores. The best-performing model was finally selected to develop an online prediction *** results showed that bothersome stress urinary incontinence (BSUI) occurred in 9.6% (849 out of 8,830) of parous women. The XGBoost model achieved the best prediction performance (training set: AUC 0.796, 95% confidence interval [CI]: 0.778-0.815, validation set: AUC 0.720, 95% CI: 0.686-0.754). Additionally, the XGBoost model achieved the lowest (best) Brier score among the models, with sensitivity of 0.657, specificity of 0.690, accuracy of 0.688, positive predictive value of 0.231, and negative predictive value of 0.948. Based on this model, the top five risk factors for the development of BSUI among parous women were ranked as follows: body mass index, age, vaginal delivery, constipation, and maximum fetal birth weight. An online calculator was provided for clinical *** application of machine-learning algorithms provides an acceptable, though not perfect, prediction of BSUI risk among parous women, requiring further validation and improvement in future researc

关键词： Bothersome stress urinary incontinence Big data machine-learning algorithms Parous women Prediction model

来源：评论

学校读者我要写书评

暂无评论

Development of a machine-learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy

ADVANCED INTELLIGENT SYSTEMS

引用

ADVANCED INTELLIGENT SYSTEMS 2025年第1期7卷

作者： Hermoso-Duran, Sonia Fraunhoffer, Nicolas Millastre-Bocos, Judith Sanchez-Gracia, Oscar Garrido, Pablo F. Vega, Sonia Lanas, Angel Iovanna, Juan Velazquez-Campoy, Adrian Abian, Olga Univ Zaragoza Inst Biocomputat & Phys Complex Syst BIFI Joint Unit IQFR CSIC BIFI Zaragoza 50018 Spain Univ Zaragoza Inst Biocomputat & Phys Complex Syst BIFI Joint Unit GBsC CSIC BIFI Zaragoza 50018 Spain Inst Invest Sanitaria Aragon IIS Aragon Zaragoza 50009 Spain Ctr Invest Biomed Red Area Temat Enfermedades Hepa Madrid 28029 Spain Aix Marseille Univ Ctr Interdisciplinaire Nanosci Marseille Equipe Labelisee Ligue Natl Canc CNRS F-13288 Marseille France Hosp Clin Univ Lozano Blesa Zaragoza 50009 Spain Univ Zaragoza Dept Ingn Elect & Comunicac Zaragoza 50018 Spain Univ Oslo Dept Phys N-0316 Oslo Norway Univ Oslo Ctr Lifespan Changes Brain & Cognit N-0371 Oslo Norway Hosp Alta Complej Cruce B1888 Florencio Varela Buenos Aires Argentina Univ Arturo Jauretche B1888 Florencio Varela Buenos Aires Argentina Univ Zaragoza Dept Bioquim & Biol Mol Zaragoza 50009 Spain

Pancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scanning calorimetry (DSC) of blood serum samples, thermal liquid biopsy (TLB), combined with machine-learning (ML) analysis, may offer a more efficient method for diagnosing PDAC. Serum samples from a cohort of 212 PDAC patients and 184 healthy controls are studied. DSC thermograms are analyzed using ML models. The generated models are built applying algorithms based on penalized regression, resampling, categorization, cross validation, and variable selection. The ML-based model demonstrates outstanding ability to discriminate between PDAC patients and control subjects, with a sensitivity of 90% and an area under the ROC receiver operating characteristic curve of 0.83 in the training and test groups. Application of the model to an independent validation cohort of 113 PDAC patients confirms its robustness and utility as a diagnosis tool. The application of ML to serum TLB data emerges as a promising methodology for early diagnosis, representing a significant advance for detecting and managing PDAC, envisaging a minimally invasive and more efficient methodology for identifying biomarkers. A new methodology is proposed to analyze serum thermograms applying AI tools (switchBox and ncvreg libraries from R). A classification model (intelligent thermal liquid biopsy, iTLB, model) differentiates PDAC patients from healthy controls with a receiver operating characteristic AUC of 0.83. Validation of the iTLB model in an external validation PDAC patient cohort confirms these *** (c) 2024 WILEY-VCH GmbH

关键词： biomarkers diagnoses machine-learning algorithms pancreatic ductal adenocarcinomas (PDACs) thermal liquid biopsies (TLBs)

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：