检索结果-内蒙古大学图书馆

Improving machine learning models through explainable AI for predicting the level of dietary diversity among Ethiopian preschool children

引用

ITALIAN JOURNAL OF PEDIATRICS 2025年第1期51卷 1-11页

作者： Setegn, Gizachew Mulu Dejene, Belayneh Endalamaw Debark Univ Dept Comp Sci Debark 90 Ethiopia Univ Gondar Gondar 196 Ethiopia

BackgroundChild nutrition in Ethiopia is a significant concern, particularly for preschool-aged children. Children must have a varied diet to ensure they receive all the essential nutrients for good health. Unfortunately, many children in Ethiopia lack access to a range of foods, which can lead to malnutrition and other health issues. While machine learning (ML) has the potential to analyse extensive datasets, the lack of transparency in these models can impede their effectiveness in real-world applications, especially in public health. This research aims to enhance machine learning models by integrating Explainable AI (XAI) methods to more accurately predict the level of dietary diversity in Ethiopian preschool *** Improve the ML Model for Predicting the Level of Dietary Diversity among Ethiopian Preschool Children. We employed an ensemble ML approach with XAI. The Ethiopian demographic health survey collected a dataset consisting of dietary information and relevant socioeconomic variables. The data were preprocessed to obtain quality data that are suitable for the ensemble ML algorithms to develop a model. We applied filter (chi-square and mutual information) and wrapper (sequential backwards) feature selection methods to identify the most influential factors for dietary diversity (DD). Ethiopia demographic health survey (from 2011 to 2019). Datasets were used. We developed a predictive model using a decision tree, random forest, gradient boosting, light gradient boosting, CatBoost, and XGBClassifier. We evaluated it using accuracy, precision, recall, F1_score, and receiver operating characteristic (ROC)-based evaluation *** ensemble ML models exhibited robust predictive performance, and light gradient boosting outperformed the other ensemble ML algorithms by 95.3%. The explainability of the Light Gradient Boosting Ensemble Model was determined using Eli5 and LIME. The child's age, household wealth index, household region, source o

关键词： Dietary diversity Ethiopia Explanatory AI Food group Predicting level Preschool children machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning based androgen receptor regulatory gene-related random forest survival model for precise treatment decision in prostate cancer

引用

HELIYON 2024年第17期10卷 e37256页

作者： Li, Qinyu Wang, Yanan Chen, Junjie Zeng, Kai Wang, Chengwei Guo, Xiangdong Hu, Zhiquan Hu, Jia Liu, Bo Xiao, Jun Zhou, Peng Huazhong Univ Sci & Technol Tongji Hosp Tongji Med Coll Dept Oncol Wuhan 430030 Hubei Peoples R China Huazhong Univ Sci & Technol Tongji Hosp Tongji Med Coll Dept Urol Wuhan 430030 Hubei Peoples R China Huazhong Univ Sci & Technol Tongji Hosp Tongji Med Coll Dept Thyroid & Breast Surg Wuhan 430030 Hubei Peoples R China Chongqing Med Univ Affiliated Hosp 1 Dept Urol Chongqing 400016 Peoples R China

Background: It has been demonstrated that aberrant androgen receptor (AR) signaling contributes to the pathogenesis of prostate cancer (PCa). To date, the most efficacious strategy for the treatment of PCa remains to target the AR signaling axis. However, numerous PCa patients still face the issue of overtreatment or undertreatment. The establishment of a precise risk prediction model is urgently needed to distinguish patients with high-risk and select appropriate treatment modalities. Methods: In this study, a consensus AR regulatory gene-related signature (ARS) was developed by integrating a total of 101 algorithm combinations of 10 machine learning algorithms. We evaluated the value of ARS in predicting patient prognosis and the therapeutic effects of the various treatments. Additionally, we conducted a screening of therapeutic targets and agents for high-risk patients, followed by the verification in vitro and in vivo. Results: ARS was an independent risk factor for biochemical recurrence and distant metastasis in PCa patients. The enhanced and consistent prognostic predictive capability of ARS across various platforms was confirmed when compared with 44 previously published signatures. More importantly, PCa patients in the ARS high group benefit more from PARP inhibitors and immunotherapy, while chemotherapy, radiotherapy, and AR-targeted therapy are more effective for ARSlow low patients. The results of in silico screening suggest that AURKB could potentially serve as a promising therapeutic target for ARS high patients. Conclusions: Collectively, this prediction model based on AR regulatory genes holds great clinical translational potential to solve the dilemma of treatment choice and identify potential novel therapeutic targets in PCa.

关键词： Prostate cancer Androgen receptor regulatory genes machine learning algorithm Clinical translation Precision therapy

来源：评论

学校读者我要写书评

暂无评论

machine learning and financial big data control using IoT

引用

INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS 2024年第4期18卷 2657-2670页

作者： Xiao, Jian Zhejiang Fash Inst Technol Sch Business Ningbo Zhejiang Peoples R China

machine learning algorithms have been widely used in risk prediction management systems for financial data. Early warning and control of financial risks are important areas of corporate investment decision-making, which can effectively reduce investment risks and ensure companies' stable development. With the development of the Internet of Things, enterprises' financial information is obtained through various intelligent devices in the enterprise financial system. Big data provides high-quality services for the economy and society in the high-tech era of information. However, the amount of financial data is large, complex and variable, so the analysis of financial data has huge difficulties, and with the in-depth application of machine learning algorithms, its shortcomings are gradually exposed. To this end, this paper collects the financial data of a listed group from 2005 to 2020, and conducts data preprocessing and Feature selection, including removing missing values, Outlier and unrelated items. Next, these data are divided into a training set and a testing set, where the training set data is used for model training and the testing set data is used to evaluate the performance of the model. Three methods are used to build and compare data control models, which are based on machine learning algorithm, based on deep learning network and the model based on artificial intelligence and Big data technology proposed in this paper. In terms of risk event prediction comparison, this paper selects two indicators to measure the performance of the model: accuracy and Mean squared error (MSE). Accuracy reflects the predictive ability of the model, which is the proportion of all correctly predicted samples to the total sample size. Mean squared error is used to evaluate the accuracy and error of the model, that is, the square of the Average absolute deviation between the predicted value and the true value. In this paper, the prediction results of the three methods are compared

关键词： machine learning algorithm financial risk control big data control cyborg sensation Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A novel compressive strength estimation approach for 3D printed fiber-reinforced concrete: integrating machine learning and gene expression programming

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第5期7卷 4889-4910页

作者： Uddin, Md Nasir Ye, Junhong Haque, M. Aminul Yu, Kequan Li, Lingzhi Tongji Univ Coll Civil Engn Dept Disaster Mitigat Struct Shanghai Peoples R China Texas State Univ Ingram Sch Engn San Marcos TX 78666 USA Southwest Jiaotong Univ Inst Smart City & Intelligent Transportat Chengdu Peoples R China

3D concrete printing (3DCP) is crucial in the construction because of the low labor cost, eco-friendly behavior;however, getting a proper mixture is always a challenge. This study focuses on predicting the compressive strength (CS) of fiber-reinforced concrete produced with 3DCP using eight machine learning (ML) algorithms to get optimized mixture. The ML models were trained and tested using a comprehensive database on CS collected from literature considering the various fiber-reinforced cementitious composites, comprising over 299 mixtures with 11 features. The results show that the trained ML models could predict CS with R2 ranging from 0.927 to 0.990 and 0.914 to 0.988 for the training and testing dataset, respectively. Furthermore, supplementary experiments were conducted to create a new dataset to validate the predictive model's accuracy, with the extreme gradient boosting (XGB) and gene expression programming (GEP). Based on the GEP, a novel empirical equation was proposed and rigorously validated using experiments. The equation exhibits a high accuracy with the GEP algorithm (R2 = 0.89), providing real-world field applications that might be improve decision-making and mixture optimization, which contributes to advancements, efficiency, and innovative solutions in 3D printing practical domains.

关键词： Fiber-reinforced concrete 3D concrete printing machine learning algorithm Hyperparameter optimization Gene expression programming

来源：评论

学校读者我要写书评

暂无评论

machine learning-driven prognostic analysis of cuproptosis and disulfidptosis-related lncRNAs in clear cell renal cell carcinoma: a step towards precision oncology

引用

EUROPEAN JOURNAL OF MEDICAL RESEARCH 2024年第1期29卷 1页

作者： Chen, Ronghui Wu, Jun Che, Yinwei Jiao, Yuzhuo Sun, Huashan Zhao, Yinuo Chen, Pingping Meng, Lingxin Zhao, Tao Shandong Second Med Univ Sch Clin Med Weifang 261053 Peoples R China Peoples Hosp Rizhao Dept Oncol Rizhao 276826 Peoples R China Peoples Hosp Rizhao Dept Cent Lab Shandong Prov Key Med & Hlth Lab Rizhao Key Lab Basic Res Anesthesia & Resp Intens Rizhao 276826 Shandong Peoples R China Peoples Hosp Rizhao Dept Pathol Rizhao 276826 Peoples R China

Cuproptosis and disulfidptosis, recently discovered mechanisms of cell death, have demonstrated that differential expression of key genes and long non-coding RNAs (lncRNAs) profoundly influences tumor development and affects their drug sensitivity. Clear cell renal cell carcinoma (ccRCC), the most common subtype of kidney cancer, presently lacks research utilizing cuproptosis and disulfidptosis-related lncRNAs (CDRLRs) as prognostic markers. In this study, we analyzed RNA-seq data, clinical information, and mutation data from The Cancer Genome Atlas (TCGA) on ccRCC and cross-referenced it with known cuproptosis and disulfidptosis-related genes (CDRGs). Using the LASSO machine learning algorithm, we identified four CDRLRs-ACVR2B-AS1, AC095055.1, AL161782.1, and MANEA-DT-that are strongly associated with prognosis and used them to construct a prognostic risk model. To verify the model's reliability and validate these four CDRLRs as significant prognostic factors, we performed dataset grouping validation, followed by RT-qPCR and external database validation for differential expression and prognosis of CDRLRs in ccRCC. Gene function and pathway analysis were conducted using Gene Ontology (GO) and Gene Set Enrichment Analysis (GSEA) for high- and low-risk groups. Additionally, we have analyzed the tumor mutation burden (TMB) and the immune microenvironment (TME), employing the oncoPredict and Immunophenoscore (IPS) algorithms to assess the sensitivity of diverse risk categories to targeted therapeutics and immunosuppressants. Our predominant objective is to refine prognostic predictions for patients with ccRCC and inform treatment decisions by conducting an exhaustive study on cuproptosis and disulfidptosis.

关键词： Clear cell renal cell carcinoma Prognostic risk model machine learning algorithm Cuproptosis Disulfidptosis Long non-coding RNA Targeted drugs Immune inhibitors

来源：评论

学校读者我要写书评

暂无评论

Image reconstruction method of gamma emission tomography based on prior-aware information and machine learning for partial-defect detection of PWR-type spent nuclear fuel

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2024年第11期56卷 4770-4781页

作者： Choi, Hyung-Joo Jeong, Jaewon Lee, Hakjae Kim, Seong Gon Ahn, Jae Joon Lee, Hyun Cheol Min, Chul Hee Yonsei Univ Dept Radiat Convergence Engn Seoul South Korea ARALE Lab Co Ltd Seoul South Korea Samsung Elect Co Ltd Suwon South Korea Yonsei Univ Div Data Sci Wonju South Korea Korea Inst Nucl Nonproliferat & Control KINAC Nucl Mat Anal Team Daejon South Korea

Spent nuclear fuel (SNF) requires accurate and effective supervision to prevent radiation release to the public and the environment. Gamma emission tomography (GET) has been used to inspect partial-defects at the pin-by-pin level through the acquisition of tomographic images. However, due to the high density of nuclear fuel rods, GET shows relatively low accuracy for the central region. This study proposes an image reconstruction method for the internal fuels based on Monte Carlo simulation and machine learning algorithm. The gammas from the SNF were measured with the GET device and the sinograms were reconstructed with Maximum-Likelihood Expectation- Maximization (MLEM) with prior-aware information of SNF, and image quality was improved with the machine learning technique. Our results show that the MLEM with prior-aware information could dramatically improve the image quality and the denoising technique with the machine learning could clearly correct the over-and under-estimation. Based on the results of quantitative validation of the proposed reconstruction method, the pattern classification accuracy was calculated to be about 100 %. These techniques enabled the image acquisition of the central fuel rod and increased accuracy in partial defect detection. For further study, the performance of the proposed reconstruction method will be evaluated based on the experiment data.

关键词： Safeguards Spent nuclear fuel Partial defect Gamma emission tomography Monte Carlo simulation machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Tree species identification in ex situ conservation areas using WorldView-2 Satellite Data and machine learning Methods: a case study in the Bogor Botanic Garden

引用

TROPICAL ECOLOGY 2024年第1期65卷 81-91页

作者： Yudaputra, Angga Yuswandi, Ade Yusuf Witono, Joko Ridho Cropper, Wendell P. Usmadi, Didi Natl Res & Innovat Agcy Bot Gardens & Forestry Res Ctr Plant Conservat KST Soekarno Jalan Raya Jakarta-Bogor Km 46 Cibinong 16911 West Java Indonesia Natl Res & Innovat Agcy Directorate Sci Collect Management KST Soekarno Jalan Raya Jakarta-Bogor Km 46 Cibinong 16911 West Java Indonesia Natl Res & Innovat Agcy Res Ctr Biosystemat & Evolut KST Soekarno Jalan Raya Jakarta-Bogor Km 46 Cibinong 16911 West Java Indonesia Univ Florida Sch Forest Fisheries & Geomat Sci Gainesville FL 32611 USA Natl Res & Innovat Agcy Res Ctr Ecol & Ethnobiol KST Soekarno Jalan Raya Jakarta-Bogor Km 46 Cibinong 16911 West Java Indonesia

Spatially-explicit data on the species composition of forest plants can be an important tool for forest management and conservation. One specific application of these data is for identifying tropical tree species through machine learning techniques to classify satellite remote sensing images. This study aims to examine the ability to use Worldview-2 high-resolution data with various machine learning methods to identify tree species in the Bogor Botanic Garden. Eighteen species from 11 families were selected as samples representing an ecologically and taxonomically diverse data set. Using aggregated image variables, each tree species was found to have different reflectance, texture, and spectral vegetation index variable values. Cluster analysis showed that the 18 tree species could be separated into three clusters that partly reflected taxonomic relationships. Four machine learning algorithms (Support Vector machine (SVM), Random Forest (RF), K-nearest neighbor (KNN), and Bayesian) were used to predict the species identity of pixels in the image data. A multicollinearity test using a Variance Inflation Factor method reduced the predictor variables from 54 to 9. The highest accuracy (0.96) was observed using SVM, followed by RF (0.91), KNN (0.86), and Bayesian (0.74). The implementation of high-resolution satellite imagery and machine learning for species identification in tropical ex situ plant conservation areas, such as botanic gardens is reported here for the first time.

关键词： Classification Conservation machine learning algorithm Modeling ecology Remote sensing Tropical tree Urban forest

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study

引用

PEERJ COMPUTER SCIENCE 2022年 8卷 e898页

作者： Islam, Saima Sharleen Haque, Md Samiul Miah, M. Saef Ullah Bin Sarwar, Talha Nugraha, Ramdhan Amer Int Univ Bangladesh AIUB Fac Sci & Technol Dept Comp Sci Dhaka Bangladesh Univ Malaysia Pahang Coll Comp & Appl Sci Fac Comp Pahang Malaysia Telkom Univ Fac Elect Engn Bandung Indonesia

Thyroid disease is the general concept for a medical problem that prevents one's thyroid from producing enough hormones. Thyroid disease can affect everyone-men, women, children, adolescents, and the elderly. Thyroid disorders are detected by blood tests, which are notoriously difficult to interpret due to the enormous amount of data necessary to forecast results. For this reason, this study compares eleven machine learning algorithms to determine which one produces the best accuracy for predicting thyroid risk accurately. This study utilizes the Sick-euthyroid dataset, acquired from the University of California, Irvine's machine learning repository, for this purpose. Since the target variable classes in this dataset are mostly one, the accuracy score does not accurately indicate the prediction outcome. Thus, the evaluation metric contains accuracy and recall ratings. Additionally, the F1-score produces a single value that balances the precision and recall when an uneven distribution class exists. Finally, the F1-score is utilized to evaluate the performance of the employed machine learning algorithms as it is one of the most effective output measurements for unbalanced classification problems. The experiment shows that theANNClassifier with an F1-score of 0.957 outperforms the other nine algorithms in terms of accuracy.

关键词： Thyroid Disease Thyroid Risk Prediction machine learning algorithm machine learning Classifier Sick-euthyroid

来源：评论

学校读者我要写书评

暂无评论

Predictive Role of Serum C-Peptide in New-Onset Renal Dysfunction in Type 2 Diabetes:A Longitudinal Observational Study Using machine learning algorithms

Predictive Role of Serum C-Peptide in New-Onset Renal Dysfun...

引用

浙江省免疫学会第十三次学术大会

作者： Huabin Wang Dongmei Sun Yifei Hu Yongjun Ma Department of Clinical Laboratory Affiliated Jinhua HospitalZhejiang University School of Medicine

Background:Our previous cross-sectional study has demonstrated the independently non-linear relationship between fasting C-peptide with renal dysfunction odds in patients with type 2 diabetes(T2 D) in ***,the role of serum C-peptide in in predicting the risk of new-onset renal dysfunction remains unclear and needs to be further ***:This longitudinal observational study aims to explore the role of serum C-peptide in risk prediction of new-onset renal dysfunction,then construct and select the optimal predictive model based on serum C-peptide and other clinical parameters using machine learning *** and methods:The patients with T2 D and normal renal function at baseline were recruited in this *** LASSO algorithm was performed to filter potential predictors from the baseline *** classical machine learning algorithms were used to construct predictive models for new-onset renal dysfunction *** performances of these five models were compared to select a optimal predictive *** analysis was performed to assess the statistical power of the ***:During a 2-year follow-up period,21.08%(35/166) of subjects with T2 D and normal renal function at baseline progressed to renal *** predictors were determined using LASSO regression,including baseline albumin-to-creatinine ratio,glycated hemoglobin,hypertension,retinol-binding protein-tocreatinine ratio,quartiles of fasting C-peptide,and quartiles of fasting C-peptide to 2 h postprandial C-peptide *** 6 predictors were incorporated to develop models for renal dysfunction risk prediction using 5 machine learning ***,logistic regression(LR) model had the highest efficiency,with an AUC of 0.83,an accuracy of 75.80%,a sensitivity of88.60%,and a specificity of 70.80%.According to the power analysis,the statistical power of the LR model was found to be 0.81,which was at a relatively high ***,A nomogram was develo

关键词： type 2 diabetes renal dysfunction serum C-peptide machine learning algorithm new-onset

来源：评论

学校读者我要写书评

暂无评论

Predicting the prevalence of cardiovascular diseases using machine learning algorithms

引用

Intelligence-Based Medicine 2025年 11卷 100199-100199页

作者： Sianga, Bernada E. Mbago, Maurice C. Msengwa, Amina S. Department of Official Statistics Eastern Africa Statistical Training Centre P.O. Box 35103 Tanzania Department of Statistics University of Dar es Salaam P.O. Box 35047 Dar es Salaam Tanzania

Cardiovascular Diseases (CVDs) are the major cause of morbidity, disability, and mortality worldwide and are the most life-threatening diseases. Early detection and appropriate action can significantly reduce the effects and complications of CVD. Prediction of the likelihood that an individual can develop CVD adverse outcomes is essential. machine learning methods are used to predict the risk of CVD incidences. Optimal model parameters were obtained using the grid search and randomized search methods. A hyperparameter tuning method with the highest accuracy was used to find the optimal parameters for the six algorithms used in this study. Two experiments were deployed: the first was training and testing the CVD dataset using hyperparameterized ML algorithms excluding geographical features, and the second included geographical features. The geographical features are air humidity, temperature and education status of a location. The performances of the two experiments were compared using classification metrics. The findings revealed that the performance of the second experiment outperformed the first experiment. XGBoost achieved the highest accuracy of 95.24 %, followed by the decision tree 93.87 % and support vector machine 92.87 % when geographical features were included (second experiment). Including geographical risk factors in predicting CVD is crucial as they contribute to the probability of developing CVD incidences. © 2025 The Authors

关键词： And XGBoost Cardiovascular disease machine learning algorithm

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：