检索结果-内蒙古大学图书馆

Extracting Classification Rules from Artificial Neural Network Trained with Discretized Inputs

NEURAL PROCESSING LETTERS 2020年第3期52卷 2469-2491页

作者： Yedjour, Dounia USTO MB Fac Math & Comp Sci Dept Comp Sci BP 1505 El Mnaouer 31000 Oran Algeria

Rule extraction from artificial neural networks remains important task in complex diseases such as diabetes and breast cancer where the rules should be accurate and comprehensible. The quality of rules is improved by the improvement of the network classification accuracy which is done by the discretization of input attributes. In this paper, we developed a rule extraction algorithm based on multiobjective genetic algorithms and association rules mining to extract highly accurate and comprehensible classification rules from ANN's that have been trained using the discretization of the continuous attributes. The data pre-processing provides very good improvement of the ANN accuracy and consequently leads to improve the performance of the classification rules in terms of fidelity and coverage. The results show that our algorithm is very suitable for medical decision making, so an excellent average accuracy of 94.73 has been achieved for the Pima dataset and 99.36 for the breast cancer dataset.

关键词： Neural network Rule extraction multiobjective genetic algorithm Discretized attributes

来源：评论

学校读者我要写书评

暂无评论

Functional optimization of a Persian lime packing using TRIZ and multi-objective genetic algorithms

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2020年 139卷 105558-000页

作者： Alfonso Aguilar-Lasserre, Alberto Eduardo Torres-Sanchez, Victor Fernandez-Lambert, Gregorio Azzaro-Pantel, Catherine Cortes-Robles, Guillermo Alberto Roman-del Valle, Missael Tecnol Nacl Mexico Inst Tecnol Nacl Mexico Inst Tecnol Orizaba Div Estudios Posgrad & Invest Av Oriente 9852 Orizaba 94320 Veracruz Mexico Inst Tecnol Super Misantla Div Estudios Posgrad & Invest Km 1-8Carretera Loma del Cojolite S-N Misantla 93821 Veracruz Mexico Univ Toulouse Lab Genie Chim UMR 5503 CNRSINPENSIAGET 4 Allee Emile MonsoBP 84234 F-3143 Toulouse France

This article proposes a novel approach that uses a mathematical model optimized by genetic algorithms harmonized with the Russian theory of problem solving and invention (TRIZ) to design an export packing of Persian Lime. The mathematical model (with functional elements of non-spatial type) optimizes the spaces of the Persian Lime Packing, maximizes the Resistance to Vertical Compression and minimizes the Amount of Material Used, according to the operation restrictions of the packing during the transport of the merchandise. This approach is developed in four phases: the identification of the solution space;the optimization of the conceptual design;the application of TRIZ;and the generation of the final proposal solution. The results show the proposed packing (with 28% less cardboard) supports at least the same vertical load with respect to the nearest competitor packing. However, with the same number of packings per pallet and pallets per container, the space used by the packing assembled and deployed in the container is greater by 10% and 38% respectively. Besides, TRIZ includes innovative non-spatial elements such as the airflow and the friction of the product inside the packing. The contribution of this approach can be replicable for the packing design of other horticultural products of the agri-food chain.

关键词： multiobjective genetic algorithm TRIZ Contradiction matrix Packing and packaging Fresh fruit exportation Packaging innovation

来源：评论

学校读者我要写书评

暂无评论

Analytical Optimal Design of a Two-Phase Axial-Gap Transverse Flux Motor

引用

ENERGIES 2021年第12期14卷 3666-3666页

作者： Ballestin-Bernad, Victor Sergio Artal-Sevil, Jesus Antonio Dominguez-Navarro, Jose Univ Zaragoza Sch Engn & Architecture Dept Elect Engn Zaragoza 50018 Spain

Transverse flux motors (TFMs) are being investigated to be used in vehicle traction applications due to their high torque density. In this paper, a two-phase axial-gap transverse flux motor is designed for an electric scooter, proposing a novel analytical design method. First, the dimensioning equations of the motor are obtained based on the vehicle requirements, and the stationary dq model is calculated. Then, the motor is optimized using a multiobjective genetic algorithm, and finally a 3D-FEM verification is made. Both the motor structure and the design method aim to have a low complexity, in order to favor the sizing and manufacturing processes through a low computation time and simple core shapes. This approach has not yet been explored in axial-gap TFMs.

关键词： transverse flux motor vehicle traction analytical design multiobjective genetic algorithm finite element method

来源：评论

学校读者我要写书评

暂无评论

Analysis of Supercritical CO₂ Cycle Using Zigzag Channel Pre-Cooler: A Design Optimization Study Based on Deep Neural Network

引用

ENERGIES 2021年第19期14卷 6227-6227页

作者： Saeed, Muhammed Berrouk, Abdallah S. Singh, Munendra Pal Alawadhi, Khaled Siddiqui, Muhammad Salman Khalifa Univ Sci & Technol Dept Mech Engn P Box 127788 Abu Dhabi U Arab Emirates Khalifa Univ Sci & Technol Ctr Catalysis Separat CeCas POB 127788 Abu Dhabi U Arab Emirates Coll Technol Stud Dept Automot & Marine Engn Technol Publ Author Appl Educ & Training Kuwait 70654 Kuwait Norwegian Univ Life Sci Fac Sci & Technol N-1430 As Norway

The role of a pre-cooler is critical to the sCO(2)-BC as it not only acts as a sink but also controls the conditions at the main compressor's inlet that are vital to the cycle's overall performance. Despite their prime importance, studies on the pre-cooler's design are hard to find in the literature. This is partly due to the unavailability of data around the complex thermohydraulic characteristics linked with their operation close to the critical point. Henceforth, the current work deals with designing and optimizing pre-cooler by utilizing machine learning (ML), an in-house recuperator and pre-cooler design, an analysis code (RPDAC), and a cycle design point code (CDPC). Initially, data computed using 3D Reynolds averaged Navier-Stokes (RANS) equation is used to train the machine learning (ML) model based on the deep neural network (DNN) to predict Nusselt number (Nu) and friction factor (f). The trained ML model is then used in the pre-cooler design and optimization code (RPDAC) to generate various designs of the pre-cooler. Later, RPDAC was linked with the cycle design point code (CDPC) to understand the impact of various designs of the pre-cooler on the cycle's performance. Finally, a multi-objective genetic algorithm was used to optimize the pre-cooler geometry in the environment of the power cycle. Results suggest that the trained ML model can approximate 99% of the data with 90% certainty in the pre-cooler's operating regime. Cycle simulation results suggest that the cycle's performance calculation can be misleading without considering the pre-cooler's pumping power. Moreover, the optimization study indicates that the compressor's inlet temperature ranging from 307.5 to 308.5 and pre-cooler channel's Reynolds number ranging from 28,000 to 30,000 would be a good compromise between the cycle's efficiency and the pre-cooler's size.

关键词： pre-cooler design 1 PCHEs 2 sCO(2)-BC deep learning neural network machine learning optimization multiobjective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

From E-budgeting to smart budgeting: Exploring the potential of artificial intelligence in government decision-making for resource allocation

引用

GOVERNMENT INFORMATION QUARTERLY 2022年第2期39卷 101644-101644页

作者： Valle-Cruz, David Fernandez-Cortez, Vanessa Ramon Gil-Garcia, J. Univ Autonoma Estado Mexico Unidad Acad Profes Tianguistenco San Pedro Tlaltizapan Santiago Tiangu Mexico Univ Autonoma Estado Mexico Fac Contaduria & Adm Cerro De Coatepec S-NCiudad Univ Toluca De Lerdo Mexico SUNY Albany Ctr Technol Govt Albany NY 12222 USA SUNY Albany Rockefeller Coll Publ Affairs & Policy Albany NY 12222 USA Univ Americas Puebla Cholula Mexico

Artificial intelligence has become an important tool for governments around the world. However, it is not clear to what extent artificial intelligence can improve decision-making, and some policy domains have not been the focus of most recent studies, including the public budget process. More specifically, budget allocation is one of the areas in which AI may have greatest potential. Therefore, this study attempts to contribute to this gap in our existing knowledge by answering the following research question: To what extent can artificial intelligence techniques help distribute public spending to increase GDP, decrease inflation and reduce the Gini index? In order to respond to this question, this article proposes an algorithmic approach on how budget inputs (specific expenditures) are processed to generate certain outputs (economic, political, and social outcomes). The authors use the multilayer perceptron and a multiobjective genetic algorithm to analyze World Bank Open Data from 1960 to 2019, including 217 countries. The advantages of implementing this type of decision support system in public expenditures allocation arise from the ability to process large amounts of data and to find patterns that are not easy to detect, which include multiple non-linear relationships. Some technical aspects of the expenditure allocation process could be improved with the help of these kinds of techniques. In addition, the results of the AIbased approach are consistent with the findings of the scientific literature on public budgets, using traditional statistical techniques.

关键词： Artificial intelligence Public budgeting E-budgeting Smart budgeting Multilayer perceptron multiobjective genetic algorithm Smartness Budget intelligent machine

来源：评论

学校读者我要写书评

暂无评论

Hybrid Artificial Neural Network and genetic algorithm Model for Multi-Objective Strength Optimization of Concrete with Surkhi and Buntal Fiber 2020

Hybrid Artificial Neural Network and Genetic Algorithm Model...

引用

12th International Conference on Computer and Automation Engineering (ICCAE)

作者： Silva, Dante L. de Jesus, Kevin Lawrence M. Villaverde, Bernard S. Adina, Edgar M. Mapua Univ 658 Muralla St Manila 1002 Philippines

ISBN: (纸本)9781450376785

Fiber-reinforced concrete (FRC) is one of the efficient innovation in concrete industry that has the ability to enhance the mechanical properties significantly. To cope up with the increase in infrastructural activities which resulted in greater demand in production of different construction materials have a negative impact on the environment, this study aims to determine the mechanical performance of the optimum compressive and flexural strength of buntal fiber-reinforced concrete with surkhi as partial replacement for sand (BFRC-SS). Using 28th-day compressive and flexural strength, several mixtures were experimentally tested to derive a mix proportion that gave the best mechanical properties of BFRC-SS. From the results, best hybrid models of compressive and flexural strength were formulated using Artificial Neural Network (ANN). Results showed that ANN was able to establish the effects of surkhi and buntal (Corypha utan Lam) fiber to the mechanical properties of BFRC-SS. Furthermore, the multi-objective genetic algorithm (GA) model generated the optimum proportion for the best compressive and flexural strength. Fuzzy Inference System (FIS) and Multi-Linear Regression Analysis (MLRA) were also utilized to assess and validate the hybrid model through surface imaging Utilizing least percent error, ANN hybrid model showed the most significant predictive model compared to other models generated by MLRA and FIS. This study adoptied the fusion of 4.0 Industrial Revolution and favoring creativity and integrity through artificial intelligence.

关键词： Surkhi Buntal Fiber Artificial Neural Network multiobjective genetic algorithm Fuzzy-Inference System MultiLinear Regression Analysis

来源：评论

学校读者我要写书评

暂无评论

Fuzzy logic-based adaptive equaliser for non-linear perpendicular magnetic recording channels

引用

IET COMMUNICATIONS 2019年第9期13卷 1304-1310页

作者： Wongsathan, Rati Supnithi, Pornchai King Mongkuts Inst Technol Ladkrabang Fac Engn Bangkok 10520 Thailand

This paper proposes the fuzzy logic equaliser (FLE) for the detection of non-linear perpendicular magnetic recording (PMR) channels. The multi-objective genetic algorithm (MOGA) is utilised to optimise all of the fuzzy parameters and reduce the complexity while maintaining the accuracy. By means of this optimisation, the total number of fuzzy rules is significantly reduced about 44%. The bit error rate (BER) performance of the proposed FLEs are compared with those of the conventional detector and traditional non-linear equalisers for Volterra channel, in presence of non-linear amplitude distortions in high-density PMR channels. The proposed FLE outperforms existing detectors by 1 to 12 dB SNR gains. Furthermore, the complexity in terms of multiplication counts per execution and reliability of detectors with regard to the number of system parameters through the Akaike's information criterion (AIC) are assessed to verify the effectiveness of the proposed FLEs. An extension to PMR channel with jitter noise proves the robustness of the proposed FLEs.

关键词： genetic algorithms fuzzy logic perpendicular magnetic recording adaptive equalisers error statistics jitter fuzzy set theory reliability fuzzy logic-based adaptive equaliser FLE multiobjective genetic algorithm bit error rate performance nonlinear equalisers Volterra channel nonlinear amplitude distortions nonlinear PMR channel detection nonlinear perpendicular magnetic recording channel detection MOGA complexity reduction optimisation BER SNR reliability Akaike information criterion AIC jitter noise noise figure 1.0 dB to 12.0 dB

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimisation algorithm for routability and timing driven circuit clustering on FPGAs

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2019年第4期13卷 273-281页

作者： Wang, Yuan Trefzer, Martin A. Bale, Simon J. Walker, James A. Tyrrell, Andy M. Univ Hertfordshire Sch Engn & Technol Hatfield Herts England Univ York Dept Elect Engn York N Yorkshire England

Circuit clustering algorithms fit synthesised circuits into field programmable gate array (FPGA) configurable logic blocks (CLBs) efficiently. This fundamental process in FPGA CAD flow directly impacts both effort required and performance achievable in subsequent place-and-route processes. Circuit clustering is limited by hardware constraints of specific target architectures. Hence, better circuit clustering approaches are essential for improving device utilisation whilst at the same time optimising circuit performance parameters such as, e.g. power and delay. In this study, the authors present a method based on multi-objective genetic algorithm (MOGA) to facilitate circuit clustering. They address a number of challenges including CLB input bandwidth constraints, improvement of CLB utilisation, minimisation of interconnects between CLBs. The authors' new approach has been validated using the 'Golden 20' MCNC benchmark circuits that are regularly used in FPGA-related literature. The results show that the method proposed in this study achieves improvements of up to 50% in clustering, routability and timing when compared to state-of-the-art approaches including VPack, T-VPack, RPack, DPack, HDPack, MOPack and iRAC. The key contribution of this work is a flexible EDA flow that can incorporate numerous objectives required to successfully tackle real-world circuit design on FPGA, providing device utilisation at increased design performance.

关键词： field programmable gate arrays logic design genetic algorithms network routing integrated circuit design timing circuits electronic design automation flexible EDA flow interconnect minimisation place-and-route process configurable logic blocks field programmable gate array timing driven circuit clustering multiobjective optimisation algorithm real-world circuit design FPGA-related literature Golden 20 MCNC benchmark circuits CLB utilisation CLB input bandwidth constraints multiobjective genetic algorithm time optimising circuit performance parameters FPGA CAD flow

来源：评论

学校读者我要写书评

暂无评论

Prediction of irrigation event occurrence at farm level using optimal decision trees

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2019年 157卷 173-180页

作者： Gonzalez Perea, R. Camacho Poyato, E. Montesinos, P. Rodriguez Diaz, J. A. Univ Cordoba Dept Agron Campus RabanalesEdif da Vinci E-14071 Cordoba Spain

Irrigation water demand is highly variable and depends on farmers' decision about when to irrigate. Their decision affects the performance of the irrigation networks. An accurate daily prediction of irrigation events occurrence at farm scale is a key factor to improve the management of the irrigation districts and consequently the sustainability of the irrigated agriculture. In this work, a hybrid heuristic methodology that combines Decision Trees and genetic algorithm has been developed to find the optimal decision tree to model farmer's behaviour, predicting the occurrence of irrigation events. The methodology has been tested in a real irrigation district and results showed that the optimal models developed have been able to predict between 68% and 100% of the positive irrigation events and between 93% and 100% of the negative irrigation events.

关键词： Artificial intelligence multiobjective genetic algorithm Irrigation scheduling Expert systems

来源：评论

学校读者我要写书评

暂无评论

ANN-Based STATCOM Tuning for Performance Enhancement of Combined Wind Farms

引用

ELECTRIC POWER COMPONENTS AND SYSTEMS 2019年第1-2期47卷 10-26页

作者： Rashad, Ahmed Kamel, Salah Jurado, Francisco Abdel-Nasser, Mohamed Mahmoud, Karar Aswan Univ Fac Engn Dept Elect Engn Aswan Egypt Univ Jaen Dept Elect Engn Jaen Spain Chongqing Univ Coll Elect Engn State Key Lab Power Transmiss Equipment & Syst Se Chongqing Peoples R China

Although the wind farms based on squirrel cage induction generators (SCIG) is cheaper than the wind farms based on doubly fed induction generators (DFIG), it is always in desperate need for reactive power compensation. Nevertheless, the wind farms based on DFIG are expensive compared with the SCIG wind farm, it features by its ability to control the active power independent of reactive power. However, combined wind farm (CWF) has been developed to collect the benefits of SCIG and DFIG wind turbines in the same wind farm. In this article, artificial neural network (ANN) is used to evaluate gain parameters of static synchronous compensator (STATCOM) in order to improve the stability performance of CWF. The impact of tuned STATCOM on the performance of CWF during gust wind speed and during three-phase fault is comprehensively investigated. The performance of CWF with STATCOM tuned by ANN is compared with its performance when the STATCOM tuned by the multiobjective genetic algorithm (MOGA) and whale optimization algorithm (WOA). The results show that the performance of CWF can be enhanced using STATCOM tuned by ANN more than MOGA and WOA.

关键词： squirrel cage induction generators doubly fed induction generators combined wind farm STATCOM artificial neural network multiobjective genetic algorithm whale optimization algorithm

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：