检索结果-内蒙古大学图书馆

A review on the lignocellulosic derived biochar-based catalyst in wastewater remediation: Advanced treatment technologies and machine learning tools

引用

BIORESOURCE TECHNOLOGY 2023年第1期387卷 129587页

作者： Sharmila, V. Godvin Tyagi, Vinay Kumar Varjani, Sunita Banu, J. Rajesh Mar Ephraem Coll Engn & Technol Dept Civil Engn Marthandam 629171 Tamil Nadu India Natl Inst Hydrol Environm Hydrol Div Roorkee 247667 India City Univ Hong Kong Sch Energy & Environm Kowloon Tat Chee Ave Hong Kong Peoples R China Univ Petr & Energy Studies Sch Engn Sustainabil Cluster Dehra Dun 248007 Uttarakhand India Cent Univ Tamil Nadu Dept Biotechnol Thiruvarur 610005 Tamil Nadu India

Wastewater disposal in the ecosystem affects aquatic and human life, which necessitates the removal of the contaminants. Eliminating wastewater contaminants using biochar produced through the thermal decomposition of lignocellulosic biomass (LCB) is sustainable. Due to its high specific surface area, porous structure, oxygen functional groups, and low cost, biochar has emerged as an alternate contender in catalysis. Various innovative advanced technologies were combined with biochar for effective wastewater treatment. This review examines the use of LCB for the synthesis of biochar along with its activation methods. It also elaborates on using advanced biochar-based technologies in wastewater treatment and the mechanism for forming oxidizing species. The research also highlights the use of machine learning in pollutant removal and identifies the obstacles of biocharbased catalysts in both real-time and cutting-edge technologies. Probable and restrictions for further exploration are discussed.

关键词： Biochar-based catalyst Adsorption Advanced oxidation process Wastewater contamination machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes

引用

FOOD RESEARCH INTERNATIONAL 2023年第1期167卷 112679页

作者： Dong, Jian-E Li, Jieqing Liu, Honggao Wang, Yuan-Zhong Southwest Forestry Univ Coll Big Data & Intelligence Engn Kunming 650224 Peoples R China Yunnan Agr Univ Coll Agron & Biotechnol Kunming 650201 Peoples R China Zhaotong Univ Zhaotong 657000 Peoples R China Yunnan Acad Agr Sci Med Plants Res Inst Kunming 650200 Peoples R China Yunnan Acad Agr Sci Med Plants Res Inst 2238 Beijing Rd Kunming 650200 Peoples R China

This study proposed the necessity of identifying the sampling sites for Boletus tomentipes (***) in combination with cadmium content and environmental factors. Based on fourier transform mid-infrared spectroscopy (FT-MIR) preprocessing by 1st, 2nd, MSC, SNV and SG, five machine learning (ML) algorithms (NB, DT, KNN, RF, SVM) and three Gradient Boosting machine (GBM) algorithms (XGBoost, LightGBM, CatBoost) were built. To avoid complex preprocessing, we construct BoletusResnet model, propose the concepts of 3DCOS, 3DCOS projected images, index images in addition to 2DCOS, and combine them with deep learning (DL) for classification for the first time. It shows that GBM has higher accuracy than ML and DL has better accuracy than GBM. The four DL models presented in this paper achieve fine-grained sampling sites recognition based on small samples with 100 % accuracy, and a computer application system was developed on them. Therefore, spectral image processing combined with DL is a rapid and efficient classification method which can be widely used in food identification.

关键词： Cadmium Sampling site machine learning algorithm Gradient Boosting machine algorithm Image processing Deep learning

来源：评论

学校读者我要写书评

暂无评论

A novel framework for addressing uncertainties in machine learning-based geospatial approaches for flood prediction

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2023年第PartB期326卷 116813页

作者： Adnan, Mohammed Sarfaraz Gani Siam, Zakaria Shams Kabir, Irfat Kabir, Zobaidul Ahmed, M. Razu Hassan, Quazi K. Rahman, Rashedur M. Dewan, Ashraf Chittagong Univ Engn & Technol CUET Dept Urban & Reg Planning Chattogram 4349 Bangladesh North South Univ Dept Elect & Comp Engn Dhaka Bangladesh Curtin Univ Sch Earth & Planetary Sci Spatial Sci Discipline Perth 6102 Australia Presidency Univ Dept Elect & Comp Engn Dhaka Bangladesh Univ Newcastle Sch Environm & Life Sci Callaghan NSW 2258 Australia Univ Calgary Dept Geomat Engn 2500 Univ Drive NW Calgary AB T2N 1N4 Canada Univ Kebangsaan Malaysia Fac Engn & Built Environm Dept Elect Elect & Syst Engn Bangi 43600 Selangor Malaysia

Globally, many studies on machine learning (ML)-based flood susceptibility modeling have been carried out in recent years. While majority of those models produce reasonably accurate flood predictions, the outcomes are subject to uncertainty since flood susceptibility models (FSMs) may produce varying spatial predictions. How-ever, there have not been many attempts to address these uncertainties because identifying spatial agreement in flood projections is a complex process. This study presents a framework for reducing spatial disagreement among four standalone and hybridized ML-based FSMs: random forest (RF), k-nearest neighbor (KNN), multilayer perceptron (MLP), and hybridized genetic algorithm-gaussian radial basis function-support vector regression (GA-RBF-SVR). Besides, an optimized model was developed combining the outcomes of those four models. The southwest coastal region of Bangladesh was selected as the case area. A comparable percentage of flood potential area (approximately 60% of the total land areas) was produced by all ML-based models. Despite achieving high prediction accuracy, spatial discrepancy in the model outcomes was observed, with pixel-wise correlation co-efficients across different models ranging from 0.62 to 0.91. The optimized model exhibited high prediction accuracy and improved spatial agreement by reducing the number of classification errors. The framework pre-sented in this study might aid in the formulation of risk-based development plans and enhancement of current early warning systems.

关键词： Flood susceptibility machine learning algorithm Uncertainty analysis GIS Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A comparative study of traditional machine learning and hybrid fuzzy inference system machine learning models for air quality index forecasting

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2025年 1-22页

作者： Ordenshiya, K. M. Revathi, Gk Vellore Inst Technol Chennai Sch Adv Sci Dept Math Chennai Campus Chennai 600127 Tamil Nadu India

Air pollution from urban activities poses significant health risks, underscoring the need for effective monitoring of the air quality index (AQI). This paper presents a novel approach for AQI prediction by integrating a Takagi-Sugeno fuzzy inference system (TS-FIS) with machine learning (ML). Traditional ML techniques often encounter difficulties in converting regression datasets into classification formats, particularly when conventional labelling methods are inadequate. The TS-FIS model, developed using MATLAB, integrates both pollutant and meteorological data, simplifies input grouping and rule management, and converts regression data into classification levels such as healthy, moderate, and unhealthy using IF-THEN rules. The regression outputs are validated with metrics including RMSE (0.48), MSE (0.23), MAE (0.45), and MAPE (1.77). A random forest classifier (RFC) trained on the TS-FIS outputs achieves maximum 99.85% accuracy, with F1 score, precision, and recall, surpassing traditional methods, which achieve maximum 99.63% accuracy. The study also includes a comparative analysis of ML-based FIS models for AQI prediction with different parameters and membership functions, alongside a traditional ML model for AQI classification using RFC. The key novelty of this work lies in the fine-tuning of membership functions and parameters, which significantly enhances the performance of the ML-based FIS model, demonstrating its superiority. These results underscore the model's potential for practical applications in environmental monitoring and management.

关键词： Air quality index Artificial intelligence Fuzzy inference system machine learning algorithm Simulink

来源：评论

学校读者我要写书评

暂无评论

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

Power optimization of 1:2 and 1:4 photonic crystal based optical power splitters/combiners using machine learning algorithms

引用

Results in Optics 2025年 21卷

作者： Ghosh, Kalyan Kumar Mondal, Haraprasad Das, Himanshu Ranjan Soroosh, Mohammad Majumder, Sudipta Saikia, Bhargabjyoti Dibrugarh University Institute of Engineering and Technology Dibrugarh University Assam India Department of Electronics and Communication Engineering School of Engineering Central University of Karnataka Karnataka Kalaburagi 585367 India Department of Electrical Engineering Shahid Chamran University of Ahvaz Ahvaz Iraq

Optical power splitters play a vital role in signal distribution, network expansion, and both balanced and unbalanced power splitting in cost-efficient fiber optic systems. Similarly, optical power combiners are essential for signal aggregation, upstream transmission, and balanced network design. In this article, we propose the design of two power splitters—3 dB and 6 dB Y-shaped configurations—that also function as power combiners using two-dimensional photonic crystal waveguides. The performance of these devices has been analyzed using the finite difference time domain (FDTD) algorithm, and their operational parameters have been optimized through the K-means clustering and Particle Swarm Optimization algorithms. As a result of this optimization, the devices achieve precise 3 dB and 6 dB power splitting across all output ports with an efficiency of 99 %. Their fast response time (0.4 and 0.5 picoseconds for 3 dB and 6 dB respectively), high power delivery efficiency, precise power splitting/combining capabilities, and machine Learming (ML) – driven optimization make these splitters/combiners highly suitable for advanced fiber optic networks. © 2025 The Author(s)

关键词： Fiber optic networks Finite difference time domain machine learning algorithm Optical waveguides Power splitter

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

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

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

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：