检索结果-内蒙古大学图书馆

Implementing a radial basis function model to anticipate the outcomes of the gasification

CHEMICAL PRODUCT AND PROCESS MODELING 2025年第1期20卷 57-78页

作者： Cui, Hongfang Su, Ning Cui, Hongyan Hebei Armed Police Corps Shijiazhuang 050000 Peoples R China Hengshui Univ Sch Math & Comp Sci Hengshui 053000 Peoples R China Hegang Digital Technol Co Ltd Shijiazhuang 050000 Peoples R China

Hydrogen (H-2) and nitrogen (N-2) are both critical components in gasification processes, making efficient conversion of carbonaceous feedstocks into valuable gases with reduced environmental impact indispensable. This study demonstrates a state-of-the-art approach to predictive modeling for these quantities at high accuracy while allowing cost-effective solutions under a variety of operational conditions, enhancing safety, and enabling data-driven optimization. This work develops a new framework that incorporates the radial basis function model with two state-of-the-art optimization algorithms, namely the Zebra Optimization algorithm (ZOA) and flow direction algorithm (FDA), to enhance the predictive accuracy of gasification processes. This is a new frontier in optimizing the sustainable conversion of carbonaceous feedstocks, demonstrating the potential of data-driven methodologies in process efficiency and environmental sustainability. The RBFD model resulted in outstanding anticipation capability for H2, reaching an exceptional R2 value of 0.997 during the whole period of testing. On the other hand, the RBZO framework proved to be the strongest predictor for N2 anticipation, presenting an outstanding R2 of 0.994 during the testing and validation phases. The RBFD and RBZO frameworks showed significantly higher productivity compared to the conventional RBF model, as evidenced by accuracy metrics like MSE, RMSE, and WAPE.

关键词： hydrogen nitrogen machine learning radial basis function Zebra Optimization algorithm flow direction algorithm

来源：评论

学校读者我要写书评

暂无评论

The determination of the strongest attributes of high-performance concrete featuring innovative admixtures via optimal regression-based methodologies

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第2期7卷 883-893页

作者： Zhang, Lianchao Guo, Shizhong Qi, Jianwei Tangshan Maritime Inst Tangshan 063000 Hebei Peoples R China

The acquisition of an optimal mix design for high-performance concrete (HPC) is known to present significant challenges due to its inherently intricate nature. Therefore, implementing machine learning techniques can effectively streamline the process, resulting in more efficient use of resources and a reduction in labor intensity. The present study has employed the support vector regression (SVR) methodology to forecast the compressive strength (CS) of HPC. In addition, the present investigation furnished two meta-heuristic techniques for attaining appropriate and suitable outcomes. Specifically, these techniques encompass the artificial hummingbird algorithm (AHA) and flow direction algorithm (FDA). The hybridized approach within the SVR-AHA and SVR-FDA frameworks was achieved by integrating algorithms with the model. Moreover, several criteria indicators have been employed to identify the optimal hybrid model. About 170 experimental data sets have been used to validate the performance of the developed method, which the samples split into two stages, including training and testing. Consequently, the utilization of the AHA algorithm in conjunction with the SVR model led to an enhanced association model, as evidenced by the following outcomes: RMSE = 2.00 (MPa), R2 = 98.59%, WAPE = 0.114 (MPa), MAPE = 1.22 (MPa), and. MAE = 0.717 (MPa).

关键词： High-performance concrete flow direction algorithm Artificial hummingbird algorithm Support vector regression Compressive strength

来源：评论

学校读者我要写书评

暂无评论

Prediction of California bearing ratio using multi-layer perceptron model based on multiple meta-heuristic optimizers

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第3期7卷 2489-2505页

作者： Chen, Jianhong Chengdu Polytech Coll Urban Construct Chengdu 610041 Sichuan Peoples R China

The California bearing ratio (CBR) is commonly employed within the field of geotechnical engineering and its associated applications, including but not limited to highway embankments, earth dams, and bridge abutments. This index can typically be ascertained through laboratory analyses or field test procedures. Nonetheless, the method of determining CBR is both time- and cost-intensive. Consequently, this research endeavors to present three hybrid models that integrate the multi-layer perceptron model (MLP) with three meta-heuristic algorithms, namely, the flow direction algorithm (FDA), Prairie dog optimization (PDO), and red deer algorithm (RDA). These models offer a cost-effective and efficient methodology for predicting CBR values while concurrently exhibiting enhanced precision in dealing with real-world complexities. The present study determined that 70% of the developed hybrid models were assigned to the training phase, while the 30% remaining were designated testing models. This study assessed the influence of eight distinct factors on the anticipated CBR values. To assess the precision of the models developed for two categories, an analysis is conducted that involves a comparative examination of projected outcomes versus observed results. This evaluation utilizes five distinct statistical measures, namely, the coefficient of determination (R2), root mean squared error (RMSE), mean squared error (MSE), mean absolute relative error (MARE), and uncertainty (U95%).

关键词： California bearing ratio Multi-layer perceptron model Prairie dog optimization flow direction algorithm Red deer algorithm

来源：评论

学校读者我要写书评

暂无评论

A FDA-based multi-robot cooperation algorithm for multi-target searching in unknown environments

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第6期10卷 7741-7764页

作者： Ye, Wenwen Cai, Jia Li, Shengping Zhaoqing Univ Sch Math & Stat Zhaoqing St Zhaoqing 526061 Guangdong Peoples R China Guangdong Univ Finance & Econ Sch Digital Econ Guangzhou 510320 Guangdong Peoples R China Shantou Univ Dept Mech Engn Tuojiang St Shantou 535063 Guangdong Peoples R China Shantou Univ MOE Key Lab Intelligent Mfg Tuojiang St Shantou 535063 Guangdong Peoples R China

Target search using a swarm of robots is a classic research topic that poses challenges, particularly in conducting multi-target searching in unknown environments. Key challenges include high communication cost among robots, unknown positions of obstacles, and the presence of multiple targets. To address these challenges, we propose a novel Robotic flow direction algorithm (RFDA), building upon the modified flow direction algorithm (FDA) to suit the characteristics of the robot's motion. RFDA efficiently reduces the communication cost and navigates around unknown obstacles. The algorithm also accounts for scenarios involving isolated robots. The pipeline of the proposed RFDA method is outlined as follows: (1). Learning strategy: a neighborhood information based learning strategy is adopted to enhance the FDA's position update formula. This allows swarm robots to systematically locate the target (the lowest height) in a stepwise manner. (2). Adaptive inertia weighting: An adaptive inertia weighting mechanism is employed to maintain diversity among robots during the search and avoid premature convergence. (3). Sink-filling process: The algorithm simulates the sink-filling process and moving to the aspect slope to escape from local optima. (4). Isolated robot scenario: The case of an isolated robot (a robot without neighbors) is considered. Global optimal information is only required when the robot is isolated or undergoing the sink-filling process, thereby reducing communication costs. We not only demonstrate the probabilistic completeness of RFDA but also validate its effectiveness by comparing it with six other competing algorithms in a simulated environment. Experiments cover various aspects such as target number, population size, and environment size. Our findings indicate that RFDA outperforms other methods in terms of the number of required iterations and the full success rate. The Friedman and Wilcoxon tests further demonstrate the superiority of RFDA.

关键词： flow direction algorithm Swarm robot Multi-target searching Neighborhood information based learning strategy

来源：评论

学校读者我要写书评

暂无评论

Predicting the settlement of pile based on a hybrid form of the model by considering Least Square Support Vector Regression

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第1期7卷 529-542页

作者： Chen, Qiang Chongqing Vocat Coll Transportat Sch Marxism Chongqing 402247 Peoples R China

Understanding the vertical settlement is crucial when designing the pile and foundation type used in real estate, specifically regarding the pile settlement (Sp). This issue is of utmost importance due to the numerous variables involved in designing piles that penetrate rock. Despite multiple efforts, clear and precise theoretical explanations regarding the interactions between soil and piles are currently unclear. As a result, many studies have opted to employ artificial intelligence techniques for determining the subsidence rate of piles over time under different loading conditions. This study presents a machine learning (ML) that effectively predicts the values of Sp, namely Least Square Support Vector Regression (LSSVR). In addition, the proposed model coupled with three meta-heuristic algorithms, including the flow direction algorithm (FDA), Chimp Optimization algorithm (ChOA), and Rider Optimization algorithm (ROA), to improve the performance and obtain the optimal results as a framework of hybrid. As a result, LSFD determined the most suitable effects with R2 and RMSE values equal to 0.2503 and 0.9952, respectively. Overall, using LSSVR with FDA, ChOA, and ROA can improve the accuracy and robustness of the model in predicting pile settlement, making it a valuable tool for geotechnical engineers designing foundation systems.

关键词： Pile settlement Least Square support vector regression flow direction algorithm Chimp optimization algorithm Rider optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An Efficient Mobile Edge Computing based Resource Allocation using Optimal Double Weighted Support Vector Transfer Regression

引用

JOURNAL OF GRID COMPUTING 2023年第3期21卷 1-20页

作者： Tripathi, Kuldeep Narayan Kaur, Gagandeep Arora, Nitin Agrawal, Rohit Madhav Inst Technol & Sci MITS Comp Sci & Engn Dept Gwalior 474005 Madhya Pradesh India Indian Inst Technol Elect & Comp Discipline Roorkee 247667 Uttarakhand India

Mobile edge computing (MEC) technology is gaining more attention in smart cities due to its powerful computation capability. However, there arise complications related to security and privacy while transmitting and processing raw data to other cloud or MEC servers. This makes the users unwilling to update their private information on the cloud servers. To tackle this issue, we proposed a novel approach for optimal task scheduling and resource allocation processes in this paper. The proposed 'double-weighted support vector transfer regression based flow direction (DSTR-FD) approach' resolves the issues of resource management of edge servers and makes optimal task offloading decisions with minimized energy consumption. Here, the model parameters such as weight functions, regularization parameters, and kernel parameters of the DSTR network are tuned using the flow direction (FD) algorithm. The proposed method thus provides better data privacy without sharing the original data with other servers along with minimizing the utilization of energy in the Internet of Things (IoT). The efficiency of the proposed DSTR-FD approach is evaluated by comparing its results with other states of art methods. The simulation experiments illustrate that the proposed DSTR-FD approach effectively minimizes the energy utilization of all IoT devices.

关键词： Mobile edge computing Resource allocation Task offloading Double weighted support vector transfer regression flow direction algorithm Smart city

来源：评论

学校读者我要写书评

暂无评论

Disturbance Observer-Based PID Control System Using DNA Strand Displacement and Its Application in Exponential Gate

引用

IEEE ACCESS 2023年 11卷 113160-113175页

作者： Zhang, Wujie Lv, Hui Dalian Univ Sch Software Engn Key Lab Adv Design & Intelligent Comp Minist Educ Dalian 116622 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110004 Liaoning Peoples R China

Synthetic control circuits have demonstrated their effectiveness in molecular process control. However, current synthetic control circuits counteract the impact of disturbances by error signals. A disturbance suppression strategy that combines a disturbance observer with a controller to achieve better disturbance suppression is presented in this paper. A disturbance observer-based PID control system (DOB-PID) is implemented for the first time using chemical reaction networks (CRNs). The controller parameters are obtained using the flow direction algorithm, which significantly reduces the parameter setting time. The DOB-PID based on CRNs achieves improved disturbance suppression without affecting the setpoint tracking characteristics. To overcome the limitation of the classic disturbance observer relying on the inverse nominal model, a modified disturbance observer-based control system (MDOB) is realized using CRNs. The MDOB-PID eliminates the need for the inverse nominal model in the modeling process. Furthermore, the MDOB-PID control system is combined with a feedforward controller, resulting in a modified disturbance observer-based feedforward control system (FDOB). This system effectively decouples the set value following and disturbance suppression characteristics, simplifying the parameter tuning process. Additionally, a FDOB-PID control system is established using DNA strand displacement. The FDOB-PID control system proposed in this paper exhibits lower overshoot and better disturbance suppression compared to existing control systems. Finally, a FDOB-PID exponential gate control system is developed to suppress leakage response in calculation process. This system ensures accurate calculation results even in the presence of a leaky response in the exponential gate.

关键词： Chemical reaction networks disturbance observation PID control DSD reaction networks flow direction algorithm feedforward control

来源：评论

学校读者我要写书评

暂无评论

Using the two optimization algorithms (BBO and FDA) coupling with radial basis neural network to estimate the compressive strength of high-ultra-performance concrete

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第1期44卷 827-837页

作者： Wu, Mengmeng Hubei Univ Technol Sch Civil Architecture & Environm Wuhan 430068 Hubei Peoples R China

Using Ultra-High Performance Concrete (UHPC) as the highly resistant material is widely advised in constructing sensitive structures to enhance safety. The utilization of eco-friendly contents such as fly-ash and silica-fume replacing cement can decrease the pollution rate in the production process of concrete and improve the compressive strength (CS) factor. There are many ways to appraise the CS of concretes as empirically and mathematically Artificial Neural Networks (ANN) as the high-accurate model is used in the present study. In this regard, Radial Basis Function (RBF) coupling with Biogeography-Based Optimization (BBO) and flow direction algorithm (FDA) created the two high-accurate frameworks: BBO-RBF and FDA-RBF. Enhancing the accuracy of RBF to predict the CS and decreasing the ANN net complexity leads to having better results evaluated by various metrics. Therefore, using the proposed frameworks, the correlation index of R2 to model the CS in the training phase for FDA-RBF was calculated at 0.9, although BBO-RBF could get 0.85, with a 0.5% difference. However, the RMSE of FDA-RBF was 9 MPa, and for BBO-RBF, this index was calculated at 10 MPa the former model has about three percent more accuracy than the latter.

关键词： Ultra-high-performance concrete radial basis function flow direction algorithm biogeography-based optimization compressive strength

来源：评论

学校读者我要写书评

暂无评论

A transfer learning coupled framework for distortion classification in laparoscopic videos

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第15期83卷 45947页

作者： Konduri, Praveen S. R. Rao, G. Siva Nageswara Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram Andhra Pradesh India

Capturing laparoscopic videos helps physicians to conduct minor surgeries and treatments effectively. But the problem is that these videos are easily affected by environmental conditions and various distortions that diminish the overall clarity. This reduces the possibility for physicians to complete the treatments successfully. To deal with this, video enhancement techniques are introduced, which require the help of effective distortion-type classification strategies. This work presents a compelling and accurate distortion classification technique based on transfer learning. The proposed work includes three main stages: feature extraction, fine-tuning and classification. The DenseNet-65 convolutional neural network (DDCNN) model has been chosen as the baseline, where the DenseNet-65 is pre-trained on the Imagenet dataset. The pre-trained model is used for feature extraction using the zero-shot transfer learning (ZSTL) technique, where only the first few layers of a model are engaged to extract the crucial spatial features. Then, the fine-tuning process was carried out using the flow direction algorithm (FDA) that tunes the parameters of the top layers. Finally, classification has been done using the softmax classifier, where the model classifies five different distortions in videos such as smoke, AWGN noise, motion blur, defocus blur and uneven illumination. The work has been implemented in Python, and the ICIP2020 challenge dataset is used for evaluations. The achieved accuracy outcomes of different distortion classes are smoke (97.8%), AWGN noise (100%), Motion blur (95.83%), Defocus blur (98.65%) and uneven illumination (99.01%). Moreover, the performance of a proposed scheme is examined in terms of different performance measures accuracy (98.8%), F1-score (96.9%), processing time (0.037 s), Spearman rank order correlation coefficient SROCC (0.995), Pearson linear correlation coefficient (PLCC) (0.995), and Kendall rank order correlation coefficient (KROCC) (0.8

关键词： Laparoscopic videos Distortions Zero-shot transfer learning Knowledge transfer DenseNet-65 flow direction algorithm Softmax classifier

来源：评论

学校读者我要写书评

暂无评论

Hydrological Object-Based flow direction Model for Constructing a Lake-Stream Topological System

引用

WATER RESOURCES RESEARCH 2023年第7期59卷 e2022WR033681-e2022WR033681页

作者： Zhao, Fei Xiong, Liyang Zhang, Chuzhi Wei, Hong Liu, Kai Tang, Guoan Nanjing Normal Univ Sch Geog Nanjing Peoples R China Nanjing Normal Univ Key Lab Virtual Geog Environm Minist Educ Nanjing Peoples R China Nanjing Normal Univ Jiangsu Ctr Collaborat Innovat Geog Informat Resou Nanjing Peoples R China Nanjing Normal Univ Sch Comp & Elect Informat Sch Artificial Intelligence Nanjing Peoples R China Chinese Acad Sci Nanjing Inst Geog & Limnol Key Lab Watershed Geog Sci Nanjing Peoples R China

The topological system of lakes and streams is the basis for deriving a multitude of patterns and processes in hydrology, geomorphology and ecology. flow direction is key to constructing a lake-stream topological system. However, lakes and streams are important hydrological objects that should be considered since they are linked during the process of material and energy transportation. Therefore, a flow direction algorithm that can clearly express the topological relationship of lakes and streams, was proposed here. Lakes and streams were taken as the hydrological objects in stream networks and coupled into a flow direction algorithm. A topological system was established based on the proposed algorithms. Six areas on the Tibetan Plateau were chosen as sample areas with the MERIT digital elevation model (DEM) as the DEM data source. Streams derived from flow direction data in the HydroSHEDS data set (HYDROSTREAMS) and MERIT hydro data set (MERITSTREAMS), as well as streams derived from flow direction results of the D-infinity algorithm and priority-flood algorithm were compared with streams derived from the proposed algorithm. The topological relationship between streams and lakes was clearly expressed by the proposed algorithm. In lake areas, the proposed algorithm showed better performance, and no parallel streams were found. In nonlake areas, the stream networks derived from these algorithms were stable. The proposed algorithm offers an opportunity to treat lakes and streams differently during simulation, thus adding to the authenticity of the simulation.

关键词： flow direction algorithm lake-stream topological system hydrological modeling

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：