检索结果-内蒙古大学图书馆

Prediction and optimization of medium-chain carboxylic acids production from food waste using machine learning models

引用

BIORESOURCE TECHNOLOGY 2023年第1期370卷 128533页

作者： Long, Fei Fan, Joshua Liu, Hong Oregon State Univ Dept Biol & Ecol Engn Corvallis OR 97331 USA Crescent Valley High Sch Corvallis OR 97330 USA Oregon State Univ 116 Gilmore Hall Corvallis OR 97331 USA

Machine learning models were developed in this study to predict and optimize the medium-chain carbolic acids (MCCAs) production from food waste. All three selected prediction algorithms achieved decent performance (accuracy > 0.85, R2 > 0.707). Three optimization algorithms were applied for MCCA production optimization based on the prediction algorithms. The maximum MCCA production rate (0.68 g chemical oxygen demand per liter per day) was achieved by simulated annealing coupled with random forest under the optimal conditions of pH 8.3, temperature 50 degrees C, retention time 4 days, loading rate 15.8 g volatile solid per liter per day, and inoculum to food waste ratio 70:30 with semi-continuous mode. Further experiments validated (18 % error) that the MCCA production rate was 113 % higher than the highest production rate of current lab experiments and 60 % higher than the statistical optimization using response surface methodology. This study demonstrates the potential of using machine learning for MCCA production prediction and optimization.

关键词： Carboxylate platform Prediction models optimization models Response surface methodology

来源：评论

学校读者我要写书评

暂无评论

Decision-making models in the optimization of electric vehicle charging station locations: a review

Decision-making models in the optimization of electric vehic...

引用

Mediterranean Electrotechnical Conference (MELECON)

作者： João Pinto Vítor Filipe José Baptista Antonio Oliveira Tiago Pinto University of Trás-os-Montes and Alto Douro Vila Real Portugal EDS - Energy Drawing Systems Bragança Portugal

ISBN: (数字)9798350387025

ISBN: (纸本)9798350387032

The number of electric vehicles is increasing progressively for various reasons, including economic and environmental factors. There has also been a technological development regarding both the operation and charging of these vehicles. Therefore, it is very important to reinforce the charging infrastructure, which can be optimised through the application of computational tools. There are several approaches that should be considered when trying to find the best location for electric vehicles charging stations. In the literature, different methods are described that can be applied to address this specific issue, including optimisation methods and decision-making techniques such as multicriteria analysis. One of the possible limitations of these methods is that they may not consider all perspectives of the various entities involved, potentially resulting in solutions that do not fully represent the optimal outcome; nevertheless, they provide invaluable information that can be applied in the development of integrative models and potentially more comprehensive ones. This article presents a research and discussion on the most commonly used decision models for this issue, considering optimisation models and multi-criteria decision-making strategies for the adequate planning of EV charging station installation, taking into account the different perspectives of the involved entities.

关键词： Economics Reviews Biological system modeling optimization models Computational modeling Charging stations Electric vehicle charging

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning optimization on Machine Learning models to Predict Software Defects

Hyperparameter Tuning Optimization on Machine Learning Model...

引用

Advanced Information Scientific Development (ICAISD), International Conference on

作者： Oky Kurniawan Yuris Alkhalifi Lady Agustin Fitriana Muhammad Rifqi Firdaus Amin Nur Rais Sofian Wira Hadi Information Technology Universitas Bina Sarana Informatika Jakarta Indonesia Computer Technology Universitas Bina Sarana Informatika Jakarta Indonesia Information System Universitas Bina Sarana Informatika Jakarta Indonesia

ISBN: (数字)9798350392036

ISBN: (纸本)9798350392043

Accessing and obtaining information has become seamless in the realm of software development. However, ensuring the software quality before deployment is crucial. This study focuses on evaluating software quality by identifying defects using predictive classification models. The study employs Ensemble Gradient Boosting techniques combined with hyperparameter optimization methods to enhance performance. Four optimization models were tested: Grid Search, Random Search, Bayesian optimization (Hyperopt), and Optuna. The primary goal is to improve the prediction accuracy of software defects using various hyperparameter tuning approaches. The results demonstrated that Ensemble Gradient Boosting achieved a notable accuracy of 77.87% with an AUC of 0.777. In comparison, Grid Search achieved an accuracy of 68.79% and an AUC of 0.688, whereas Random Search recorded 67.80% accuracy and an AUC of 0.678. Hyperopt performed the best, yielding an accuracy of 79.36% and an AUC of 0.792. Optuna showed an accuracy of 68.54% with an AUC of 0.685. Among the models, Hyperopt emerged as the most effective, significantly improving accuracy and overall performance. This study highlights the impact of hyperparameter tuning in optimizing machine learning models for software defect prediction.

关键词： Accuracy optimization models Software quality Predictive models Boosting Hyperparameter optimization Bayes methods Tuning optimization Software development management

来源：评论

学校读者我要写书评

暂无评论

Calibration of Compartmental Epidemiological models via Graybox Bayesian optimization

Calibration of Compartmental Epidemiological Models via Gray...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Puhua Niu Byung-Jun Yoon Xiaoning Qian Electrical & Computer Engineering Texas A&M University College Station TX USA Computational Science Initiative Brookhaven National Laboratory Upton NY USA Computer Science & Engineering Texas A&M University College Station TX USA

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

In this study, we focus on developing efficient calibration methods via Bayesian decision-making for the family of compartmental epidemiological models. The existing calibration methods usually assume the compartmental model is cheap in terms of its output and gradient evaluation, which may not hold in practice when extending them to more general settings. Therefore, we introduce model calibration methods based on a “graybox” Bayesian optimization (BO) scheme, more efficient calibration for general epidemiological models. This approach uses Gaussian processes as a surrogate to the expensive model, and leverages the functional structure of the compartmental model to enhance calibration performance. Additionally, we develop model calibration methods via a decoupled decision-making strategy for BO, which further exploits the decomposable nature of the functional structure. The calibration efficiencies of the multiple proposed schemes are evaluated based on various data generated by a compartmental model mimicking real-world epidemic processes. Experimental results demonstrate that our proposed graybox variants of BO schemes can further improve the calibration performance measured by the logarithm of mean square errors and achieve faster performance convergence in terms of BO iterations. We anticipate that the proposed calibration methods can be extended to enable fast calibration of more complex epidemiological models, such as the agent-based models.

关键词： Epidemics Biological system modeling optimization models Decision making Measurement uncertainty Gaussian processes Mean square error methods Calibration Bayes methods optimization

来源：评论

学校读者我要写书评

暂无评论

Supply Chain optimization: Bibliometric Analysis of Mathematical models Emphasizing Sustainability and Global Trends

Supply Chain Optimization: Bibliometric Analysis of Mathemat...

引用

Agrosystem Engineering, Technology & Applications (AGRETA), IEEE International Conference on

作者： Najihan Awang Ali Adibah Shuib Ismail Rakibe School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Perak Malaysia College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Malaysia Faculty of Plantation and Agro technology Universiti Teknologi MARA Melaka Malaysia

ISBN: (数字)9798350373660

ISBN: (纸本)9798350373677

Understanding the need for lean supply chains to reduce costs, improve efficiency, and address carbon emissions, climate change, and sustainability concerns has developed over recent years. Advanced quantitative supply chain optimization models and novel solution methods are needed to meet these challenges. This study provides comprehensive insights into supply chain optimization via mathematical models, focusing on agricultural supply chains, sustainability, and global trends. The bibliometric analysis used data from Scopus, covering the period from 1988 to August 23, 2023, totaling 1,778 papers. Microsoft Excel was used for frequency analysis due to its robust data handling capabilities, VOSviewer for data visualization, and Harzing's Publish or Perish for comprehensive citation metrics and analysis. The study examines trends and impacts of publications, identifies the most productive and influential countries, institutions, and authors, and highlights highly cited articles and prevalent themes in supply chain optimization. Findings demonstrate high average citations, indicating active scholarly debate on major supply chain optimization mathematical model issues. The top three nations demonstrating the most robust crossnational collaboration are China, the United States, and Iran, highlighting significant global engagement. VOSviewer visualizations identify areas for further research, including sustainable agriculture supply chain models integrating environmental considerations, resilient global supply chain networks, and real-time adaptive optimization models enabled by big data and AI technologies. These areas are crucial for achieving economic efficiency, food security, waste management and environmental sustainability, echoing the themes of innovation, sustainability, and global collaboration. This research contributes to the rapidly emerging literature on worldwide trends in supply chain optimization using mathematical modeling. It investigates growing issues

关键词： Adaptation models optimization models Biological system modeling Supply chains Bibliometrics Data visualization Market research Real-time systems Sustainable development optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Fidelity Hyperparameter optimization in Large Language models

Adaptive Multi-Fidelity Hyperparameter Optimization in Large...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Benarji Mulakala Madan Lal Saini Ashirvad Singh Vamsi Bhukya Arnod Mukhopadhyay Department of CSE AIT Chandigarh University Punjab India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

Fine-tuning of any machine learning models especially large language models is a difficult task because of the large hyper parameter space and high training cost. This paper tries to overcome this by proposing a technique called Adaptive Multi-Fidelity Hyper parameter optimization (AMF-HPO) which combines multiple advanced techniques like multi-fidelity evaluations, reinforcement learning, Bayesian optimization, and transfer learning. This technique first uses low-fidelity evaluations to eliminate unnecessary hyper parameter space. It then uses a RL agent to identify the next configuration. It then uses Bayesian optimization and Transfer learning to select the optimal hyper parameter configuration.

关键词： Training optimization models Large language models Computational modeling Transfer learning Reinforcement learning Probabilistic logic Bayes methods optimization Tuning

来源：评论

学校读者我要写书评

暂无评论

Alpine Wetlands Information Extraction Using Optimized Multifeatures and Random Forest Algorithm

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 7347-7363页

作者： Wang, Dongchuan Yang, Fei Jia, Shijie Wang, Zhiheng Dong, Chunhua Lang, Mingwei Ye, Kai Liu, Haotian Li, Tingrong Tianjin Chengjian Univ Sch Geol & Geomat Tianjin 300384 Peoples R China

Alpine wetlands are a special ecosystem that is extremely sensitive to global climate change. The unique geographical location and climatic conditions of the Yellow-River-Source National Park give rise to diverse wetland types at the land-water interface, which exhibit phenomena such as "same object with different spectra" and "different objects with the same spectrum." These complexities pose significant challenges in accurately extracting information from alpine wetlands in the study area. To address these challenges, this study proposes a novel integrated multialgorithm feature optimization model that combines three filtering algorithms with a random forest (RF) algorithm for classifying alpine wetland information. First, the rich feature information in the image is initially filtered using a fusion of the three algorithms. Then, the RF algorithm is applied to optimize the filtered features. Finally, the RF classification model is used to refine wetland extraction based on this optimized feature set. The results show that 1) the fused filtering algorithm demonstrates higher stability than each individual algorithm and takes into consideration the strengths and weaknesses of each individual algorithm;2) the classification accuracy of the RF algorithm reaches its highest value when the number of feature variables is 21;3) the optimal classification of alpine wetlands is achieved using the RF classification model based on the best set of feature variables, resulting in an overall accuracy of 93.32% and a Kappa coefficient of 91.65% . Compared to existing land cover datasets, the proposed method provides a more detailed classification of alpine wetlands.

关键词： Climate change Random forests Wetlands Ecosystems Classification algorithms Radio frequency Filtering algorithms Information filters Stability analysis optimization models Land surface Alpine wetlands feature selection filter algorithms random forest (RF)

来源：评论

学校读者我要写书评

暂无评论

Parameter optimization Method for AC Filters in HVDC Considering Reactive Power Compensation Effectiveness

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2025年第1期40卷 365-375页

作者： Lin, Sheng Mu, Dalin Xu, Lijuan He, Zhengyou Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China

In high-voltage direct current (HVDC) systems, the parameters of the AC filter (ACF) have a significant impact on the performance of reactive power (RP) compensation and filtering, as well as the capital cost. However, the RP compensation effectiveness and economy of ACFs under different HVDC operation modes are difficult to be satisfied comprehensively. Therefore, a parameter optimization method for ACFs is proposed to balance the technical performance and economy in this paper. First, considering the variety of actual HVDC operation modes, the parameters of ACFs are analyzed in relation to the performance and capital cost, which leads to the key impact factors of parameter design. Then, considering both the RP exchange quantity and the capital cost of investment and land occupation, the objective function is defined. By considering the sub-bank numbers and filtering performance of ACFs, the constraints are proposed. Finally, genetic algorithm with the elitist strategy is used to obtain the optimized ACF parameters. The comparative results show that the performance of RP compensation and filtering of the optimized ACFs is effectively improved and guaranteed, and meanwhile the capital cost is reduced.

关键词： Costs HVDC transmission Investment Filters Power harmonic filters Harmonic analysis Capacitors Reactive power optimization models Linear programming HVDC AC filter reactive power compensation parameter optimization genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Three-Stage Dynamic Game Strategy Incorporating Wind Generation Uncertainty Against FDI Attack of Wind Farm Reactive Power Compensation

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2025年第2期40卷 1504-1517页

作者： Liu, Xuecheng Wang, Haoxin Shi, Libao Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China

The integration of large-scale wind generation further accentuates the issues of system voltage fluctuations and the increase of line loss. In addition, the uncertainty of wind generation could potentially undermine the efficacy of traditional bad data detection techniques, posing challenges for power gird defenders in accurately assessing the data quality of compensation equipment, thereby increasing the risk of cyber attacks on system. In this paper, based on a proposed day-ahead attack and defense funding allocation strategy, a novel three-stage defender-attacker-operator dynamic game model incorporating wind generation uncertainty is established, aiming to minimize the energy loss caused by false data injection attacks against reactive power compensation equipment of wind farm. In order to effectively address the proposed three-stage dynamic game framework, an equivalent reformulation of a tri-level mixed integer nonlinear mathematical programming model is established. To tackle the middle-lower-level optimization model, a fast self-adaptive piecewise-linear approximation algorithm is proposed associated with the semi-definite relaxation technique. Additionally, a hybrid heuristic search algorithm is devised to solve the upper-level problem. Finally, the validity of the proposed optimization model and solution method is then demonstrated by conducting simulation analysis on the modified IEEE 14-node test system and a real-sized power grid in China.

关键词： Reactive power Wind farms Cyberattack Wind power generation Games Uncertainty optimization models False data injection attack game theory reactive power compensation semi-definite relaxation wind generation uncertainty

来源：评论

学校读者我要写书评

暂无评论

Unconstrained Fuzzy C-Means Based on Entropy Regularization: An Equivalent Model

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第2期37卷 979-990页

作者： Nie, Feiping Zhang, Runxin Duan, Yu Wang, Rong Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect iOPEN Key Lab Intelligent Interact & Applicat Sch Comp SciMinist Ind & Informat Technol Xian 710072 Shaanxi Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence OPt & Elect iOPEN Minist Ind & Informat Technol Key Lab Intelligent Interact & Applicat Xian 710072 Shaanxi Peoples R China

Fuzzy c-means based on entropy regularization (FCER) is a commonly used machine learning algorithm that uses maximum entropy as the regularization term to realize fuzzy clustering. However, this model has many constraints and is challenging to optimize directly. During the solution process, the membership matrix and cluster centers are alternately optimized, easily converging to poor local solutions, limiting the clustering performance. In this paper, we start with the optimization model and propose an unconstrained fuzzy clustering model (UFCER) equivalent to FCER, which reduces the size of optimization variables from (n+d)xc to dxc. More importantly, there is no need to calculate the membership matrix during the optimization process iteratively. The time complexity is only linear, and the convergence speed is fast. We conduct extensive experiments on real datasets. The comparison of objective function value and clustering performance fully demonstrates that under the same initialization, our proposed algorithm can converge to smaller local minimums and get better clustering performance.

关键词： Clustering algorithms optimization Entropy Linear programming Time complexity optimization models Machine learning algorithms Convergence Complexity theory Vectors Fuzzy c-means gradient descent local minimum maximum entropy

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：