检索结果-内蒙古大学图书馆

predictive modeling OF REAL-TIME COLORECTAL CANCER VIA HYPERPARAMETER CONFIGURATION WITH DEEP LEARNING USING PUBLIC HEALTH INDICATOR ANALYSIS

引用

FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY 2025年第2期33卷

作者： Alsamri, Jamal Quiam, Fatima Maashi, Mashael Alashjaee, Abdullah m. Alamgeer, Mohammad Salama, Ahmed s. Nourah bint Abdulrahman Univ Dept Biomed Engn Coll Engn Princess Riyadh Saudi Arabia Al Zaytoonah Univ Jordan Dept Comp Sci Amman Jordan King Saud Univ Coll Comp & Informat Sci Dept Software Engn POB 103786 Riyadh 11543 Saudi Arabia Northern Border Univ Coll Sci Dept Comp Sci Ar Ar Saudi Arabia King Khalid Univ Appl Coll Mahayil Dept Informat Syst Abha Saudi Arabia Future Univ Egypt Fac Engn & Technol Dept Elect Engn New Cairo 11845 Egypt

Public health indicator analysis plays a crucial part in colorectal cancer (CRC) recognition by leveraging epidemiological data and health metrics to recognize trends, disparities, and risk factors in diagnosis and screening. Public health officials use screening, incidence, and mortality rates to analyze current screening programs, target interventions for underserved populations, and improve early recognition and treatment results. With growing case numbers, CRC ranks second in women and third in men. The growing diagnostic workload and variability in biomarker assessment have prompted the exploration of robust machine-based models for pathology labs. Diagnosing CRC from histopathological images involves analyzing tissue samples for cancerous cellular changes. These images offer elaborate insights into tissue microstructure, aiding pathologists in examining cellular characteristics such as size, shape, and organization. Artificial Intelligence (AI) and fractals algorithms have proven advanced in the healthcare field, having the inherent ability for medical applications. The incorporation of AI in CRC diagnosis aims to improve the efficiency of pathologists, reduce diagnostic errors, and ultimately contribute to better patient outcomes through early and accurate detection of cancerous lesions. The study proposes a Golden Jackal Fractal Optimization with Deep Learning Assisted CRC Detection (GJODL-CRCD) technique on HIs. The GJODL-CRCD technique mainly examines the HIs to recognize and identify the CRC. The GJODL-CRCD method applies the Gabor filtering (GF) approach as a noise removal procedure to achieve this. Furthermore, the GJODL-CRCD technique employs the DenseNet model for learning and capturing intrinsic feature patterns from the preprocessed imageries. For hyperparameter selection of the DenseNet model, the GJODL-CRCD approach uses the GJO fractal algorithm. Finally, the GJODL-CRCD method uses the Elman Neural Network (ENN) model to identify and classify CRC

关键词： predictive modeling Public Health Indicator Colorectal Cancer Histopathological Image Deep Learning Golden Jackal Fractal Optimization

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of Shear Strength of Enzyme-Induced Calcium Carbonate Precipitation (EICP)-Solidified Rubber-Clay Mixtures Using Machine Learning Algorithms

引用

POLYMERS 2025年第7期17卷 976-976页

作者： Ma, Qiang Li, Meng Shu, Hang Xi, Lei Hubei Univ Technol Hubei Key Lab Environm Geotechnol & Ecol Remediat Wuhan 430068 Peoples R China Hubei Univ Technol Minist Educ Key Lab Intelligent Hlth Percept & Ecol Restorat R Wuhan 430068 Peoples R China Hubei Univ Technol Hubei Prov Ecol Rd Engn Technol Res Ctr Wuhan 430068 Peoples R China

The development of reliable predictive models for soil behavior represents a crucial advancement in geotechnical engineering, particularly for optimizing material compositions and reducing experimental uncertainties. Traditional experimental approaches for determining the optimal rubber particle size and content are often resource-intensive, time-consuming, and subject to significant variability. In this study, the shear strength of clay mixed with rubber particles solidified by the Enzyme-Induced Calcium Carbonate Precipitation (EICP) technique was investigated and predictively modeled using a machine learning algorithm. The effects of different rubber contents and particle sizes on the shear strength of the clay were analyzed experimentally, and a hybrid model of a convolutional neural network (CNN) and long short-term memory (LSTM) network optimized based on the crown porcupine optimization (CPO) algorithm was proposed to predict the shear strength of the EICP-treated clay mixed with rubber particles. The superiority of the CPO-CNN-LSTM model in predicting shear strength was verified by comparing multiple machine learning algorithms. The results show that the addition of rubber particles significantly improves the shear strength of the clay, especially at a 5% rubber content. The coefficient of determination (R2) of the CPO-CNN-LSTM model on the training and test datasets reaches 0.98 and 0.97, respectively, which exhibit high prediction accuracy and generalization ability.

关键词： shear strength soil solidification enzyme-induced carbonate precipitation rubber rubber-clay mixtures machine learning predictive modeling

来源：评论

学校读者我要写书评

暂无评论

predictive modeling for Identifying Undervalued Stocks Using Machine Learning

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2025年第0期

作者： Sukma, Narongsak Namahoot, Chakkrit Snae Naresuan Univ Fac Sci Phitsanulok Thailand Naresuan Univ Fac Sci Ctr Excellence Nonlinear Anal & Optimizat Phitsanulok Thailand

This study investigates the application of Machine Learning (ML) techniques to identify undervalued stocks, addressing the limitations of traditional investment strategies that rely heavily on fundamental analysis. As financial markets become more complex, characterized by volatility and information asymmetry, conventional valuation methods often struggle to capture these dynamics. In contrast, ML offers the ability to analyze large datasets and uncover intricate patterns, presenting a data-driven alternative for stock selection and portfolio optimization. A comprehensive predictive framework was developed, integrating traditional financial ratios with novel features derived from value investing principles and technical analysis. Several ML models - Random Forest, Long Short-Term Memory (LSTM), and Support Vector Machines - were assessed for their ability to predict high-return stocks. Performance metrics, including accuracy, precision, and recall, were used to evaluate model effectiveness. Among the models tested, the LSTM demonstrated the highest accuracy at 0.81, proving its robustness in identifying undervalued stocks. This research contributes to the growing body of literature on ML in finance by offering a practical framework that bridges theoretical concepts with real-world applications. The study also emphasizes the importance of refining ML algorithms to improve model interpretability and transparency, crucial for fostering trust in these systems. Future research should explore the use of ensemble methods and alternative data sources to further enhance prediction accuracy, while addressing challenges related to accountability in ML-driven investment strategies. This work advances the conversation around algorithmic trading and the future of data-driven finance.

关键词： Undervalued stocks algorithmic approaches machine learning predictive modeling financial markets

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of Surface Integrity and Material Removal Rate in Computer Numerical Control Machining: Effects of Thermal Conductivity and Hardness

引用

MATERIALS 2025年第7期18卷 1557-1557页

作者： Alsoufi, Mohammad S. Bawazeer, Saleh A. Umm Al Qura Univ Coll Engn & Architecture Dept Mech Engn Mecca 21955 Saudi Arabia

This study investigates the influence of thermal conductivity and hardness on computer numerical control (CNC) turning performance, focusing on key machining metrics-material removal rate (MRR), surface roughness (R-a), and surface waviness (W-a)-across five engineering materials: aluminum 6061, brass C26000, bronze C51000, carbon steel 1020, and stainless steel 304. Experimental results reveal a strong correlation between material properties and machining efficiency. Materials with high thermal conductivity (>100 W/m.K) exhibited up to 38% higher MRR and improved surface integrity compared to low-conductivity counterparts. Aluminum 6061 achieved the highest MRR (7.5 mm(3)/min at a 0.25 mm/rev feed rate), with the lowest R-a (similar to 0.58 mu m) and W-a (similar to 0.4576 mu m), confirming its excellent machinability and heat dissipation. Conversely, stainless steel 304, characterized by low thermal conductivity (16 W/m.K) and high hardness (210 HBW), recorded the lowest MRR (1.125 mm(3)/min), elevated R-a (>1.0 mu m), and substantial waviness (W-a similar to 0.9442 mu m), indicating severe tool wear and thermal deformation. A multivariable regression model incorporating cutting speed, feed rate, thermal conductivity, and hardness was developed to predict MRR, achieving high predictive accuracy (R-2 > 0.92) for high-conductivity materials. Deviations of +/- 0.5 mm(3)/min were observed in harder, low-conductivity materials due to nonlinear effects such as strain hardening and thermal expansion. Measurement uncertainty analysis, with an estimated expanded uncertainty of +/- 2.5% for MRR and +/- 0.02 mu m for surface metrics, ensures the reliability of these findings. These results underscore the importance of material-specific machining parameter optimization to enhance productivity, surface quality, and tool longevity in high-precision industries, including aerospace, automotive, and biomedical manufacturing.

关键词： CNC turning thermal conductivity material removal rate (MRR) predictive modeling surface roughness (R-a) surface waviness (W-a) hardness

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of the potentially hazardous psychrotolerant Bacillus cereus group in fried rice

引用

FOOD RESEARCH INTERNATIONAL 2025年 202卷 115698页

作者： Kang, Miseon Park, Jin Hwa Kim, Hyun Jung Korea Food Res Inst Food Safety & Distribut Res Grp Wanju 55365 South Korea Univ Sci & Technol Dept Food Biotechnol Daejeon 34113 South Korea

Bacillus cereus group (BCG) includes closely related bacterial species with different phenotypic characteristics, such as pathogenic potential, enzymatic capacity, and thermotypes. Psychrotolerant BCG (pBCG) strains can grow and produce toxins at low temperatures, creating concerns for the food industry. However, many current routine food diagnosis methods do not consider pBCG, and predictive modeling, which is an essential tool for food safety and public health, has not been developed using pBCG, but rather using mesophilic strains (mBCG). Given the limited information on predictive modeling and accurate strain identification of pBCG, we developed a predictive model for fried rice, a known causative food for BCG foodborne disease, using pBCG food isolates and whole-genome sequencing for accurate taxonomic classification. In predictive modeling, four pBCG food isolates selected through phenotypic screening grew at temperatures above 5 degrees C, whereas mBCG reference strains did not grow below 13 degrees C. The primary and secondary models for pBCG (covering 5-37 degrees C) and mBCG (covering 13-37 degrees C) fit well, with R-2 > 0.98. By validating the dynamic model under three time-varying temperature profiles, we observed root mean square error values < 0.42 log CFU/g and acceptable simulation zone values > 82%. The four pBCG isolates used in the predictive model were identified using whole-genome sequencing as B. cereus sensu stricto, B. toyonensis, and B. mycoides, which carried enterotoxin genes. Psychrotolerant signatures of the 16S rRNA and cspA were detected in the BCG9 isolate. The predictive model and genomic characterization of pBCG strains can be applied to manage and control pBCG, ensuring the food quality and safety of fried rice products in the cold chains.

关键词： Bacillus cereus group Psychrotolerance predictive modeling Fried rice Whole genome sequencing

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of PFAS behavior and degradation in novel treatment scenarios: A review

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2025年 196卷

作者： Olawade, David B. Ijiwade, James O. Fapohunda, Oluwaseun Ige, Abimbola O. Olajoyetan, David O. Wada, Ojima Zechariah Univ East London Sch Hlth Sport & Biosci Dept Allied & Publ Hlth London England Medway NHS Fdn Trust Dept Res & Innovat Gillingham ME7 5NY England York St John Univ Dept Publ Hlth London England Arden Univ Sch Hlth & Care Management Arden HouseMiddlemarch Pk Coventry CV3 4FJ England Univ Ibadan Fac Sci Dept Chem Ibadan Nigeria Univ Arizona Dept Chem & Biochem Tucson AZ USA Adekunle Ajasin Univ Dept Chem Sci Akungba Akoko Ondo Nigeria Hamad Bin Khalifa Univ Qatar Fdn Coll Sci & Engn Div Sustainable Dev Doha Qatar

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental contaminants that resist conventional water treatment methods, raising concerns about their impact on human health and ecosystems. As PFAS contamination becomes increasingly widespread, the need for novel, effective treatment solutions have grown. predictive modeling offers a promising approach to evaluate PFAS behavior, removal efficiency, and transformation pathways in emerging treatment technologies. This narrative review explores current advancements in predictive models for PFAS remediation, focusing on methods that incorporate PFAS structural characteristics, environmental factors, and treatment type. Three main modeling approaches are discussed: empirical, mechanistic, and machine learning models, each with unique strengths and limitations depending on data availability and treatment conditions. The review also addresses recent developments in advanced treatment systems such as advanced oxidation processes (AOPs), electrochemical treatment, and adsorption, as well as the role of machine learning in optimizing treatment predictions. Key challenges, including data limitations, transformation product toxicity, and model validation, are examined, with recommendations for future research emphasizing data expansion, integration of toxicity predictions, and enhanced model interpretability. By tailoring predictive models to PFAS-specific variables and diverse treatment conditions, researchers can advance sustainable PFAS management practices and guide effective remediation strategies for contaminated sites.

关键词： PFAS predictive modeling Advanced oxidation processes Machine learning Treatment systems

来源：评论

学校读者我要写书评

暂无评论

predictive modeling and Analysis of Photocatalytic Degradation Performance of Biochar-ZnO Nanocomposites on Different Agrochemicals

引用

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH 2025年第3期19卷 1-27页

作者： Patel, Jinal Gaur, Rama Shahabuddin, Syed Padia, Nandan Vakharia, Vinay Suhas, Prof. Tyagi, Inderjeet Pandit Deendayal Energy Univ Sch Energy Technol Dept Chem Gandhinagar 382426 Gujarat India Pandit Deendayal Energy Univ Sch Technol Dept Comp Sci & Engn Gandhinagar 382007 Gujarat India Pandit Deendayal Energy Univ Sch Technol Dept Mech Engn Gandhinagar 382007 Gujarat India Gurukul Kangri Dept Chem Hardwar 249404 Uttrakhand India Minist Environm Forests & Climate Change Ctr DNA Taxon Mol Systemat Div Zool Survey India Kolkata 700053 West Bengal India

To accommodate rising food demand, the agricultural industry has expanded significantly. The widespread use of agrochemicals has generated concerns about their environmental effect, notably on water quality and aquatic biodiversity. The buildup of pesticide residues in water bodies has long-term consequences for marine life and general ecosystem health. The present work describes the synthesis of biochar-ZnO nanocomposites with varying ZnO concentrations using a solid thermal decomposition technique. The produced biochar-ZnO nanocomposites were thoroughly characterized to validate their composition, structure, and characteristics. Diffraction techniques were used to establish crystal structure, spectroscopy for molecular and electronic analysis, electron microscopy for detailed imaging of particle dispersion, and thermal analysis to check stability and composition. These nanocomposites' potential as photocatalysts for degrading atrazine (ATZ) and 2,4-dichlorophenoxyacetic acid (2,4-D) in aqueous solutions was studied, with 93% and 90% degradation efficiency at 1 mg/mL dosage in 90 min. pH, loading experiments, catalyst dosage, and recycling studies were investigated. In addition, mineralization tests, scavenger investigations, and a comprehensive degradation process have been investigated. Furthermore, the prediction ability of machine learning (ML) models such as Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN) was assessed to predict the percentage removal of contaminants. The SVM model outperformed the RF and ANN models, with RMSE of 4.93, MAE of 4.38, and R2 of 0.95, respectively. This work emphasizes the potential of biochar-ZnO nanocomposites as efficient photocatalysts and the efficacy of machine learning algorithms in improving photocatalytic treatment techniques for agrochemical degradation.

关键词： Biochar-ZnO Photocatalytic degradation Agrochemical Wastewater treatment predictive modeling

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of crumb rubber-modified mortar: insights from ANN, LR, RF, and M5P methods

引用

Asian Journal of Civil Engineering 2025年第4期26卷 1621-1633页

作者： Hurukadli, Parikshit Parashar, Bhupender Shukla, Bishnu Kant Sharma, Pushpendra Kumar Sihag, Parveen Department of Civil Engineering JSS Academy of Technical Education Noida 201301 India Department of Mathematics JSS Academy of Technical Education Noida 201301 India School of Civil Engineering Lovely Professional University Phagwara 144411 India Department of Civil Engineering Chandigarh University Mohali 140413 India

This study investigates the feasibility of using crumb rubber as a partial sand replacement in cement mortar, aiming to address environmental challenges associated with tire waste while contributing to sustainable construction practices. The experimental phase involved preparing cement mortar samples with varying percentages of crumb rubber and analyzing the resulting compressive strength. Crumb rubber substitution at levels of up to 7.5% in a 1:5 to 1:6 mix proportion resulted in practical compressive strengths between 2–6 MPa, suitable for certain applications in construction. The compressive strength reduction associated with increased crumb rubber was offset by improved durability characteristics, including enhanced ductility and energy absorption. To model and predict compressive strength effectively, four machine learning approaches—Artificial Neural Network (ANN), Random Forest (RF), Linear Regression (LR), and M5P tree—were implemented. The ANN model emerged as the most effective with respect to testing data, with performance metrics including Coefficient of Correlation (CC) values of 0.9998, Nash–Sutcliffe Efficiency (NSE) values 0.9959, least Root Mean Squared Error (RMSE) of 0.2125, least Scattering Index (SI) of 0.041 and least Mean Absolute Error (MAE) of 0.1693. Sensitivity analysis further highlighted crumb rubber percentage as a critical factor influencing compressive strength, underscoring the potential for targeted optimization. The findings suggest that incorporating crumb rubber in mortar can balance sustainability goals with material performance, especially when paired with advanced predictive modeling. Future work is recommended to optimize formulations by varying water-cement ratios or introducing plasticizers to enhance the strength of rubber-modified mortar. This research highlights a promising pathway for reusing waste materials in construction, contributing to both environmental and structural engineering fields. © The Author(s), under exc

关键词： Artificial neural networks (ANN) Compressive strength Crumb rubber Plastering predictive modeling Sustainable construction Waste management

来源：评论

学校读者我要写书评

暂无评论

predictive modeling of Cedrus atlantica natural regeneration: grazing intensity and bioclimatic extremes as the primary drivers in the Ain Leuh Forest, Middle Atlas of Morocco

引用

modeling EARTH SYSTEMS AND ENVIRONMENT 2025年第1期11卷 1-25页

作者： Boussalim, Youssef Dallahi, Youssef Mohammed V Univ Rabat Fac Sci Ctr Plant & Microbial Biotechnol Lab Plant Biotechnol & Physiol Rabat 10000 Morocco

North African forests are experiencing a significant lack of woody species' natural regeneration as a result of global change factors like climate change and human pressure. Natural regeneration is a crucial process in forest ecosystem dynamics, providing valuable information on the future of forest stands. A lack of recruitment can jeopardize the sustainability of forests and impair the many ecosystem services they supply. The Atlas cedar (Cedrus atlantica (Endl.) Manetti ex Carri & egrave;re) is a major woody species in North Africa and the Mediterranean region in general. modeling this species' natural regeneration occurrence and determining the underlying causes of its variability at the forest scale is critical for ecological, management, and restoration objectives. In this study, two predictive models were used to investigate the natural regeneration occurrence of Atlas cedar in mixed stands of the Ain Leuh Forest, which is located in the central Moroccan Middle Atlas. Data from 1885 plots was used to create a standard Binary Logistic Regression model (BLR) and a Random Forest machine learning model (RF), with predictors chosen from a consistent dataset of 55 explanatory variables such as bioclimatic, edaphic, topographical, stand and anthropogenic factors, and vegetation indices. Exploratory data analysis, feature selection, and multicollinearity analysis were carried out utilizing point biserial correlation, polychoric correlation, and Spearman's rank correlation. To train models and avoid overfitting, a tenfold cross validation was utilized. The models were then assessed during the testing phase using the area under the curve metric (AUC). According to the findings, grazing intensity and bioclimatic extremes, such as precipitation and temperature, have the greatest impact on natural regeneration occurrence. The BLR model outperformed the RF model (AUC = 0.659) with an AUC of 0.704. Spatial prediction using BLR shows that extremely appropriate locations for

关键词： Natural regeneration predictive modeling Atlas cedar Middle Atlas of Morocco Ain Leuh Forest

来源：评论

学校读者我要写书评

暂无评论

predictive modeling and risk assessment strategies for enhancing dairy product safety: A comprehensive review

Food Safety and Health

引用

Food Safety and Health 2025年第2期3卷 172-187页

作者： Pahariya, Prachi Shrivastav, Awani Goswami, Tridib Kumar Choudhary, Ruplal Southern Illinois University Carbondale Carbondale IL United States Agricultural and Food Engineering Department IIT Kharagpur West Bengal Kharagpur India

The dairy industry is a crucial part of the food sector, encompassing a wide range of raw, pre-processed, and post-processed dairy products. The concern about delivering safe dairy products is increasing due to the rise in pathogenic outbreaks associated with the dairy industry. To mitigate the risks associated with dairy products, risk assessment (RA) and predictive modeling play vital roles. This review article provides a comprehensive analysis of RA and predictive modeling in managing these risks. Risk assessment offers a structured approach to evaluate public health risks through hazard identification, hazard characterization, exposure assessment, and risk characterization. predictive modeling complements RA by using scientific and mathematical methods to anticipate microbial behavior under various conditions, aiding in the prevention of contamination throughout the dairy supply chain. This article emphasizes the application of these tools in real-world scenarios to improve the accuracy of food safety predictions. In conclusion, integrating risk assessment with predictive modeling is essential for mitigating contamination risks and ensuring the safety and quality of dairy products. While significant advancements have been made, future research should focus on enhancing model precision through robust data sets and advanced machine learning, leading to more effective strategies that protect public health. © 2025 The Author(s). Food Safety and Health published by John Wiley & Sons Australia, Ltd on behalf of International Association of Dietetic Nutrition and Safety.

关键词： dairy products hazards predictive modeling risk analysis risk assessment

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：