检索结果-内蒙古大学图书馆

Prediction of building-scale solar energy potential in urban environment based on parametric modelling and machine learning algorithms

引用

SUSTAINABLE CITIES AND SOCIETY 2025年 119卷

作者： Tian, Jia Ooka, Ryozo Univ Tokyo Grad Sch Engn Dept Architecture 4-6-1 KomabaMeguro Ku Tokyo 1538505 Japan Univ Tokyo Inst Ind Sci 4-6-1 KomabaMeguro Ku Tokyo 1538505 Japan

Building integrated photovoltaics has received increasing attention due to its superior low-carbon characteristics. However, the surrounding environments influence the pattern of solar radiation distributed on building exteriors, posing a challenge to the installation of photovoltaic (PV) on buildings. Therefore, to optimize the use of solar resources for buildings in diverse block scenarios, a comprehensive assessment approach for building-scale solar energy potential is proposed in this research, using parametric modelling and machine learning algorithms. First, the building-scale solar energy potential is assessed under thousands of surrounding environments. Next, contributions of building factors to solar potential are analyzed. Finally, machine learning algorithms are employed to forecast the PV installation and generation for roofs and facades within different surrounding environments. Results show that for target buildings higher than 24 m, the PV installation ratio of roof, west and south fa & ccedil;ades are 98 %, 39 % and 46 %. Correspondingly, their average PV power potentials are 46kWh/m2.y, 75kWh/m2.y and 87kWh/m2.y. Based on the priority of contributions of building parameters to solar potential, the applicability of prediction is verified to provide optimal forecasting models and input combinations for predicting PV application on roofs and facades. The findings and workflows can provide references for predicting solar applications in buildings.

关键词： Building integrated photovoltaics Solar energy potential forecasting Photovoltaic power generation Solar radiation Parametric modelling machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Interpreting the relationship between properties of wood and pulping & paper via machine learning algorithms combined with SHAP analysis

引用

NORDIC PULP & PAPER RESEARCH JOURNAL 2025年第1期40卷 149-160页

作者： Liu, Xing Hong, Jie Zhang, Mingming Zhou, Liang Anhui Agr Univ Sch Mat & Chem Key Lab Natl Forestry & Grassland Adm Wood Qual I Hefei 230036 Peoples R China

The pulping ability and quality of paper high relay on the wood properties. However, the relationship between them are profound. Based on the extracting digital information from the anatomical, chemical, and physical properties of poplar wood, predictive models were developed for paper properties (tensile index, burst index and tear index) and pulping properties (Kappa number and pulp yield) using six algorithms, namely PLSR, ENR, RF, XGBoost, LightGBM, and CatBoost. The prediction results revealed that among the six algorithms, PLSR, ENR, and RF exhibited results of most prediction greater than 0.79. Notably, XGBoost, LightGBM, and CatBoost algorithms demonstrated superior predictive performance, with results greater than 0.9, except for the tear index. Furthermore, SHAP analysis suggested that the cellulose content is the primary factors to modulate pulping ability and the morphological features of cell wall shows apparent effects on mechanical properties of paper. It hopes the result will benefit to provide information to evaluate the value of poplar wood from different resources and then deliver instructions to genetic breeding program and forest management of poplar plantation.

关键词： poplar paper properties pulping properties machine learning algorithms shapley additive exPlanations

来源：评论

学校读者我要写书评

暂无评论

Predicting the Classification of Heart Failure Patients Using Optimized machine learning algorithms

引用

IEEE ACCESS 2025年 13卷 30555-30569页

作者： Ahmed, Marzia Sulaiman, Mohd Herwan Hassan, Md Maruf Bhuiyan, Touhid Daffodil Int Univ DIU Dept Software Engn Daffodil Smart City Dhaka 1216 Bangladesh Univ Malaysia Pahang Al Sultan Abdullah UMPSA Fac Elect & Elect Engn Technol Pekan 26600 Malaysia Southeast Univ Dept Comp Sci & Engn Dhaka Bangladesh Washington Univ Sci & Technol WUST Sch IT Alexandria VA 22314 USA

Heart failure is a critical condition with a high mortality rate, making accurate survival prediction essential for timely interventions. This study proposes an optimized machine learning approach using Gradient Boosting machine (GBM) and Adaptive Inertia Weight Particle Swarm Optimization (AIW-PSO) to predict heart failure survival. The dataset, sourced from Kaggle, includes clinical features such as age, ejection fraction, and serum creatinine levels for 299 heart failure patients. To address the imbalance in survival outcomes, Synthetic Minority Over-sampling Technique (SMOTE) was employed to balance the dataset, followed by SelectKBest and Chi-square feature selection methods to retain the most significant predictors. The optimized hyperparameters for the GBM model were identified using the AIW-PSO algorithm, which effectively balanced exploration and exploitation by adaptively adjusting inertia weights. Model selection was further refined using information criteria, including Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), ensuring that the best-performing model was chosen based on both predictive accuracy and model complexity. The optimized GBM model achieved a test accuracy of 94%, demonstrating superior performance compared to traditional machine learning models. The study underscores the importance of hyperparameter tuning through metaheuristic algorithms and highlights the potential of AIW-PSO in enhancing model performance for clinical prediction tasks. These findings have significant implications for clinical decision-making, offering a reliable and interpretable tool for predicting patient outcomes in heart failure management.

关键词： Cardiovascular diseases Predictive models Prediction algorithms machine learning algorithms Accuracy machine learning Computational modeling Mortality Adaptation models Particle swarm optimization Heart failure survival prediction machine learning algorithms hyperparameter optimization class imbalance handling AIW-PSO optimization

来源：评论

学校读者我要写书评

暂无评论

Forecasting of electricity consumption in Pakistan based on integrating machine learning algorithms and Monte Carlo simulation

引用

ELECTRICAL ENGINEERING 2025年 1-21页

作者： Nazir, Muhammad Umair Li, Jinchao North China Elect Power Univ Sch Econ & Management Beijing 102206 Peoples R China North China Elect Power Univ Beijing Key Lab New Energy & Low Carbon Dev Beijing 102206 Peoples R China

The quality of electricity consumption forecasting is crucial for the planning of Pakistan's power system. In order to improve the reliability of prediction results, this paper proposes a combined prediction model based on long short-term memory and Monte Carlo simulation. Firstly, the factors influencing Pakistan's electricity consumption were analyzed, such as economic growth rate, population size, and industrial development. Second, a deep-learning technique based on a long short-term memory (LSTM) neural network machine-learning model to forecast electricity consumption in Pakistan. Then, the probabilistic analysis of Monte Carlo with a 95% confidence interval forecasts the future consumption of electricity. At last, the historical data of Pakistan's GDP, Population, industry efficient and electricity consumption are used to testified the efficient, operative, consistent, and robust of the proposed model. The research of this paper is helpful to policymakers in Pakistan as it significantly contributes to more effective electricity management policies, energy supply industry behavioral changes, and reduced energy consumption.

关键词： Electricity consumption forecasting machine learning algorithms Monte Carlo simulation Pakistan

来源：评论

学校读者我要写书评

暂无评论

Distribution characteristics of volatile organic compounds and its multidimensional impact on ozone formation in arid regions based on machine learning algorithms

引用

ENVIRONMENTAL POLLUTION 2025年 373卷 126159页

作者： Shi, Guangyao Du, Huihui Du, Lingtong Ni, Xilu Hu, Yang Pang, Danbo Yao, Liangjin Ningxia Univ Sch Ecol & Environm Breeding Base State Key Lab Land Degradat & Ecol R Yinchuan 750021 Peoples R China Ningxia Yinchuan Urban Ecosyst Res Stn Yinchuan 750021 Peoples R China Yinchuan Ecol Environm Monitoring Stn Yinchuan 750001 Peoples R China Zhejiang Acad Forestry Hangzhou 310023 Peoples R China

Volatile Organic Compounds (VOCs) are key components of atmospheric pollution and play a critical role in ozone (O3) formation. Understanding their distribution and pollution sources is essential to grasping the multifaceted impact of VOCs on O3 production. This study, conducted at the Yinchuan Urban Ecosystem Research Station, carried out simultaneous field observations to collect data on VOCs, meteorological factors, and O3. machine learning algorithms were employed to analyze the sources of VOCs pollution and evaluate their impact on O3 formation. Results show that the monthly average volume fraction of total VOCs was 29.28 x 10-9, with alkanes dominating, accounting for 51.1 % of total VOCs during summer at high altitudes. Ethane (3.55 x 10-9), n-hexane (3.36 x 10-9), and propane (2.85 x 10-9) were identified as key components. Artificial source contributed 78.6 % of VOCs emissions in summer, with hydrocarbon volatile emission source (31.6 %) and vehicle emission source (30.1 %) being the major sources, while natural emissions accounted for only 21.4 %. VOCs exhibited a notable negative impact on O3 levels, reflected by a total effect value of -0.29. Among the VOCs components, aromatics, halocarbons, and alkanes were identified as the primary contributors to O3 dynamics, with respective effect values of 0.84, 0.75, and 0.71, and their contribution rates were quantified as 21.8 %, 19.4 %, and 18.4 %, respectively. Among meteorological factors, temperature was a key determinant of O3 levels, with a significant positive effect (effect value of 0.58). Temperature, wind speed, and relative humidity primarily influenced O3 through direct effects, while photosynthetically active radiation indirectly influenced O3 by affecting VOCs. The findings of this study link pollution sources, meteorological factors, and air quality management. Through systematic multidimensional analysis, it offers deeper insights into the complex relationships between meteorological factors, VOC

关键词： O3 VOCs Atmospheric pollution machine learning algorithms Structural equation model

来源：评论

学校读者我要写书评

暂无评论

Trace detection of antibiotics in wastewater using tunable core-shell nanoparticles SERS substrate combined with machine learning algorithms

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2025年 330卷 125700页

作者： Usman, Muhammad Ali, Wajid Alarfaji, Saleh S. Tamulevicius, S. Kaunas Univ Technol Inst Mat Sci K Barsausko St 59 LT-51423 Kaunas Lithuania Kaunas Univ Technol Dept Phys Studentu St 50 LT-51423 Kaunas Lithuania Hunan Univ Coll Mat Sci & Engn Key Lab Micronano Phys & Technol Changsha 410082 Hunan Peoples R China King Khalid Univ Fac Sci Dept Chem POB 9004 Abha 61413 Saudi Arabia

Surface-enhanced Raman scattering (SERS) show great potential for rapid and highly sensitive detection of trace amounts of contamination from the environment in the surface aquatic ecosystem. The widespread use of antibiotics has resulted in serious degradation of the water environment in the past few years, and their substantial residual contamination of wastewater has a harmful effect on ecosystems, which is associated with the development of antibiotic-resistant bacterial strains. However, in this study, a novel approach of core-shell nano- particles GNRs@1,4-BDT@Ag was used for the quantitative measurement of the concentration of antibiotics in wastewater solutions using the SERS technique coupled with computational methods. In our experiments, we selected commonly used antibiotics such as ciprofloxacin and levofloxacin in wastewater solutions. We then obtained SERS spectra for each antibiotic and its various combinations at varying concentrations. We combined it with machine learning algorithms to accurately identify and quantify the SERS spectra of the residual antibiotics in the system. Principal Component Analysis (PCA) and Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA) were subsequently employed for clustering analysis of the SERS spectral datasets. To evaluate the performance of machine learning algorithms five metrics were applied. The classification results demonstrate that while most algorithms achieved over 95 % accuracy in antibiotics status prediction, the Support Vector machine (SVM) model had the best performance, attaining a remarkable prediction accuracy of up to 99 %. This developed approach helps as a simple and expeditious tool for the analysis of antibiotics in wastewater and exhibits potential for broader applications in various domains.

关键词： Surface-enhanced Raman spectroscopy machine learning algorithms GNRs@Ag core-shell nanoparticles Antibiotics Detection sensitivity

来源：评论

学校读者我要写书评

暂无评论

Mechanical behavior of composite pipe structures under compressive force and its prediction using different machine learning algorithms

引用

MATERIALS TESTING 2025年第1期67卷 160-182页

作者： Bozkurt, Ilyas Mus Alparslan Univ Mech Engn TR-49250 Mus Turkiye

Thanks to machine learning algorithms, the performance of composites with high energy absorption capacity can be predicted with high accuracy rates with a small number of data. The aim of this study is to experimentally and numerically determine the crushing performances of glass/epoxy composite pipe structures under compressive force and to predict their compression behavior with the help of different machine learning algorithms. In the study, the crushing performances of composite pipes (peak force (PF), peak force displacement (PFD), mean crushing force (MCF), specific energy absorption (SEA), and total inner energy (TIE)) were determined for different specimen thicknesses, specimen lengths, mesh sizes, numbers of integration points, diameters (D), and compression directions (axial and radial). Additionally, the maximum strength values of composite pipes under force were estimated with the help of Linear Regression (LR), K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN) machine learning algorithms. The data taken from the ANN algorithm were found to be more reliable in estimating the PF and TIE values, with an accuracy rate of 92%. When determining the MCF value, it was found that the data obtained from the LR algorithm was more reliable than other algorithms, with an accuracy rate of 80%.

关键词： composite pipes compression test machine learning algorithms progressive damage analysis finite element method

来源：评论

学校读者我要写书评

暂无评论

Application of social entertainment robots based on machine learning algorithms and the Internet of Things in collaborative art performances

引用

ENTERTAINMENT COMPUTING 2025年 52卷

作者： Zhao, Zhenhua Guo, Feng Sangmyung Univ Dept Hightech Arts Convergence Seoul 03016 South Korea Taiyuan Univ Technol Dept Informat Engn Taiyuan 030024 Shanxi Peoples R China

In terms of control strategies for social entertainment robots, advanced control system design was adopted in the study, aiming to enable robots to achieve efficient collaborative art performances. The control system is based on machine learning algorithms and Internet of Things technology, combined with the application of sensing technology, providing accurate environmental perception and real-time feedback mechanisms for robots. Considering the collaboration and interaction between robots and human actors, control strategies adapted to different scenes were designed by analyzing and understanding the needs of artistic performances. These strategies not only consider the robot's own actions and performance, but also the interaction with human actors and the coordination with the entire performance scene. The control method in this article combines machine learning algorithms and sensing technology to enable robots to make intelligent decisions and action planning by learning and perceiving real-time environmental information. By modeling and simulating the structure and characteristics of the robot, precise planning and control of the robot's motion trajectory can be achieved. Through dynamic modeling, it is possible to better understand the motion characteristics and energy consumption of robots, and to adjust and optimize their actions during the performance process.

关键词： machine learning algorithms Internet of Things Social entertainment robots Collaborative performance Art performance

来源：评论

学校读者我要写书评

暂无评论

Determining the most accurate machine learning algorithms for medical diagnosis using the monk' problems database and statistical measurements

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2025年第2期37卷 357-376页

作者： Avuclu, Emre Aksaray Univ Dept Software Engn Fac Engn Aksaray Turkiye

Computer-aided diagnosis process in the field of health, especially cancer diagnosis, is of vital importance. Computer-aided diagnosis helps specialist physicians to make the most accurate diagnosis. According to research studies, it has been stated that the number of wrong or late diagnosis increases with each passing year and ultimately causes the death of people living in many parts of the world. For this reason, some calculations must be made to determine the most accurate one in the algorithm to be used to make the correct diagnosis. In this study, three different database Monk' problems were used to determine the most accurate algorithm for medical diagnosis. Monk' problems are used as one of the several classification problems used to create an important comparative study. Train and test operations were performed using five different machine learning algorithms (MLAs) (k Nearest Neighbor (k-NN), Decision Tree Algorithm (DT), Random Forest Algorithm (RF), Naive Bayes algorithm (NB), Support Vector Cases (SVM)). These machine learning algorithms are compared statistically in terms of performance. Two different databases in the medical field were used to test the results (Breast Cancer Coimbra Data Set, Diabetic Retinopathy Debrecen Data Set). In the test processes in the experimental studies, the highest accuracy rate was obtained from the k-NN, DT, RF, NB, SVM algorithms, respectively;0.9758, 1, 1, 0.9180, 0.9344. The best performance was obtained from RF MLA for 1. dataset, DT MLA for 2. dataset, highest accuracy rates from k-NN and RF MLAs in 3. dataset.

关键词： The most accurate diagnosis Monk' problems Cancer diagnosis statistical measurements machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic devices assisted by machine learning algorithms

引用

INTERNATIONAL JOURNAL OF EXTREME MANUFACTURING 2025年第4期7卷 042007-042007页

作者： Huo, Ziwei Sun, Qijun Yu, Jinran Wei, Yichen Wang, Yifei Cho, Jeong Ho Wang, Zhong Lin Chinese Acad Sci Beijing Inst Nanoenergy & Nanosyst Beijing 101400 Peoples R China Univ Chinese Acad Sci Sch Nanosci & Engn Beijing 100049 Peoples R China Guangxi Univ Ctr Nanoenergy Res Sch Phys Sci & Technol Nanning 530004 Peoples R China Shandong Zhongke Naneng Energy Technol Co Ltd Dongying Peoples R China Yonsei Univ Dept Chem & Biomol Engn Seoul 03722 South Korea Georgia Inst Technol Atlanta GA 30332 USA

Neuromorphic computing extends beyond sequential processing modalities and outperforms traditional von Neumann architectures in implementing more complicated tasks, e.g., pattern processing, image recognition, and decision making. It features parallel interconnected neural networks, high fault tolerance, robustness, autonomous learning capability, and ultralow energy dissipation. The algorithms of artificial neural network (ANN) have also been widely used because of their facile self-organization and self-learning capabilities, which mimic those of the human brain. To some extent, ANN reflects several basic functions of the human brain and can be efficiently integrated into neuromorphic devices to perform neuromorphic computations. This review highlights recent advances in neuromorphic devices assisted by machine learning algorithms. First, the basic structure of simple neuron models inspired by biological neurons and the information processing in simple neural networks are particularly discussed. Second, the fabrication and research progress of neuromorphic devices are presented regarding to materials and structures. Furthermore, the fabrication of neuromorphic devices, including stand-alone neuromorphic devices, neuromorphic device arrays, and integrated neuromorphic systems, is discussed and demonstrated with reference to some respective studies. The applications of neuromorphic devices assisted by machine learning algorithms in different fields are categorized and investigated. Finally, perspectives, suggestions, and potential solutions to the current challenges of neuromorphic devices are provided. The review discusses the basic structure of simple neuron models inspired by biological neurons and how they process information in simple neural networks, laying the foundation for neuromorphic device *** progress in the fabrication of neuromorphic devices is highlighted, focusing on advancements in materials, structures, and the development of st

关键词： neuromorphic devices machine learning algorithms artificial synapses memristors field-effect transistors

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：