检索结果-内蒙古大学图书馆

Comprehensive assessment of 12 soft computing approaches for modelling reference evapotranspiration in humid locations

引用

METEOROLOGICAL APPLICATIONS 2020年第1期27卷

作者： Shiri, Jalal Zounemat-Kermani, Mohammad Kisi, Ozgur Karimi, Sahar Mohsenzadeh Univ Tabriz Fac Agr Water Engn Dept Tabriz Iran Shahid Bahonar Univ Kerman Water Engn Dept Kerman Iran Ilia State Univ Fac Nat Sci & Engn Tbilisi Georgia

Owing to the lack of lysimetric data in many regions, the standard Penman-Monteith equation-adopted by Food and Agriculture Organization of the United Nations (FAO56-PM model) is usually used to calculate the reference evapotranspiration (ETo). However, as this model needs many meteorological parameters that cannot be easily obtained in many regions, other simple models along with the soft computing models are used to obtain ETo values. The paper presents a comprehensive comparison of 12 soft computing models: gene expression programming (GEP), neuro-fuzzy with grid partitioning (NF-GP), neuro-fuzzy with sub-clustering (NF-SC), multivariate adaptive regression spline (MARS), boosted regression tree (BT), random forest (RF), model tree (MT), support vector machine (SVM), SVM-firefly algorithm (SVM-FA), extreme learning machine (ELM), neural network-particle swarm optimization (NN-PSO) and neural network-differential evolution (NN-DE), to estimate daily ETo values in humid regions. Therefore, daily meteorological data from two weather stations (during a 12 year period) were used to assess the models. The obtained results revealed that very good efficiency was obtained from all the applied methods. The temperature-based SVM-FA (root mean square error (RMSE) = 0.324 mm, Nash-Sutcliffe co-efficient (NS) = 0.960) and NF-GP (RMSE = 0.272 mm, NS = 0.974) models generally provided the best accuracy when estimating the ETo of Sari and Bablosar, two humid stations in northern Iran, respectively. The accuracy ranks of the other models (from best to worst) were found to be: NN-PSO, NF-SC, ELM, NN-DE, MARS, GEP, RF, SVM, BT and MT. Among the radiation-based models, the NF-GP provided the best accuracy at estimating the ETo of both stations. The other models were ranked as: ELM, SVM-FA, NN-DE, NN-PSO, MARS, RF, BT, NF-SC, SVM and MT, respectively.

关键词： evapotranspiration modelling optimization algorithms soft computing

来源：评论

学校读者我要写书评

暂无评论

Circulating Current Control for Modular Multilevel Converters With (N+1) Selective Harmonic Elimination-PWM

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2020年第8期35卷 8712-8725页

作者： Perez-Basante, Angel Ceballos, Salvador Konstantinou, Georgios Pou, Josep Sanchez-Ruiz, Alain Lopez, Iraide de Alegria, Inigo Martinez Tecnalia Res & Innovat Energy & Environm Div Derio 48160 Spain Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Ingeteam R&D Europe SL Zamudio 48710 Spain Univ Basque Country Elect Technol Dept Bilbao 48013 Spain

Modular multilevel converters (MMCs) require control of the circulating current, $i_{\text{circ}}$, to improve their operation and efficiency. This is particularly important when low switching frequency modulation techniques, such as selective harmonic elimination pulsewidth modulation (SHE-PWM) are applied. This article provides a novel method to control the circulating current along with (N+1) SHE-PWM. Unlike the case of (2N+1) SHE-PWM, explicit redundant levels are not available and, therefore, different modulation indexes, $m_{1}$ and $m_{2}$, are employed in the upper and lower arms to obtain the desired modulation index $m_{a}$. Unlike previous (N+1) circulating current methods, the distances between $m_{a}$, $m_{1}$, and $m_{2}$ remain constant to not disturb the phase output voltage, with an interchange of $m_{1}$ and $m_{2}$ between the arms used to follow the desired $i_{\text{circ}}$. The control adjusts the dc component of the circulating current and the energy stored in the SMs to their references, while maintaining the energy balance between the upper and lower arms. Simulation tests and experimental results, obtained from a single-phase laboratory prototype MMC, validate the proposed control technique.

关键词： Selective harmonic elimination (SHE) modular multilevel converter (MMC) optimization algorithms circulating current

来源：评论

学校读者我要写书评

暂无评论

Novel DTN Mobility-Driven Routing in Autonomous Drone Logistics Networks

引用

IEEE ACCESS 2020年 8卷 13661-13673页

作者： Iranmanesh, Saeid Raad, Raad Raheel, Muhammad Salman Tubbal, Faisel Jan, Tony Melbourne Inst Technol Sch Informat Technol & Engn Sydney NSW 2000 Australia Univ Wollongong Sch Elect Comp & Telecommun Engn Wollongong NSW 2522 Australia

Drones have become prevalent for the delivery of goods by many retail companies such as Amazon and Dominos. Amazon has an issued patent that describes how drones scan and collect data on their fly-overs while dropping off packages. In this context, we propose a path optimization algorithm for a drone multi-hop communications network that can carry and forward data in addition to its primary function of parcel deliveries. We argue that traditional Delay Tolerant Networking (DTN) based protocols may not be efficient for this purpose. Therefore, this paper proposes a new DTN-based algorithm that optimizes drone flight paths in conjunction with optimized routing to deliver both parcels and data in a power efficient way and within the shortest possible time. We propose a heuristic algorithm called Weighted Flight Path Planning (WFPP) that priorities the data packets in an exchange pool in order to create an optimized path for the drones. Our approach is to determine a weight for each packet based on the packet & x2019;s remaining time to live, priority, size, and location of the packet & x2019;s destination. When two drones meet each other, they exchange the high weighted packets. Simulation studies show that WFPP delivers up to 25 & x0025;more packets compared with EBR, EPIDEMIC, and a similar path planning method. Also, WFPP reduces the data delivery delays by up to 66 & x0025;while the overhead ratio is low.

关键词： Delay tolerant network drones intelligent transportation systems forwarding strategy dynamic mobility models EBR EPIDEMIC smart cities routing optimization algorithms unmanned aerial vehicles vehicular networks

来源：评论

学校读者我要写书评

暂无评论

Estimation of pile settlement applying hybrid ALO-MLP and GOA-MLP approaches

引用

淡江理工学刊 2022年第6期25卷 1239-1255页

作者： Jin-kou Hu

Pile settlement (SP) socketed to rock has taken vital regard. Despite introducing some design methods to measure SP, applying the novel and efficient prediction model with satisfactory performance is pivotal. The main goal of this study is to find out the applicability of applying two hybrid multi-layer perceptron neural network (MLP) models in predicting the SP in the Klang Valley Mass Rapid Transit (KVMRT) project constructed operated in Kuala Lumpur, Malaysia. Various hidden layers of models were examined to have comprehensive, accurate and reliable outputs. Ant lion optimizer (ALO) and grasshopper optimization algorithm (GOA) was applied to identify each hidden layer's optimal number of neurons. In this case, five parameters were considered as input variables and SP as output. Regarding ALO-MLP models, ALO-MLP1 has the lowest score (48), with R^2 stood at 0.9382 and 0.93, and PI at 0.0416 and 0.0494 for the training and testing phases, respectively. In the training phase, best values of R^2, RMSE and PI were belonged to MLP1, while MLP2 has the smallest value of MAE. However, in the testing phase, MLP model with two hidden layer has best values for all indices, which makes it the proposed MLP model with two hidden layers. The results show that ALO is more capable than GOA for determining the optimal neuron numbers of MLP. By summation of the ranking scores obtained from performance evaluation indices, although GOA-MLP models have acceptable performance, two layers of MLP optimized with ALO could be recognized as the proposed model.

关键词： Pile Settlement Prediction Multi-layer perceptron neural network optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Accuracy enhancement for monthly evaporation predicting model utilizing evolutionary machine learning methods

引用

INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY 2020年第7期17卷 3373-3396页

作者： Mohamadi, S. Ehteram, M. El-Shafie, A. Grad Univ Adv Technol Inst Sci & High Technol & Environm Sci Dept Ecol Kerman Iran Semnan Univ Fac Civil Engn Dept Water Engn & Hydraul Struct Semnan Iran Univ Malaya Fac Engn Civil Engn Dept Kuala Lumpur Malaysia

Evaporation is an important parameter for water resource management. In this article, two case studies with different climates were considered in the prediction of monthly evaporation. The optimization algorithms, namely shark algorithm (SA) and firefly algorithms (FFAs), were used to train the adaptive neuro-fuzzy interface system (ANFIS), multilayer perceptron (MLP) model and radial basis function (RBF) model for the prediction of monthly evaporation. The monthly weather data from two stations, Mianeh station and Yazd station, operated by the Iran Meteorological Service were used to examine the proposed models. In the quantitative analysis, the hybrid ANFIS-SA improved the MAE index over the ANFIS, RBF, MLP, RBF-SA, MLP-SA, RBF-FFA, MLP-FFA and ANFIS-SA up to 47% during training and to 51% during testing while examining Yazd station. It should be mentioned that the higher RSR and MAE were attained by the hybrid soft computing (ANN-FFA, RBF-FFA and ANFIS-FFA) models in two stations. The results proved that the developed ANFIS models that have been integrated with shark algorithms could be considered as a powerful tool for predicting evaporation.

关键词： Soft computing models optimization algorithms Water resource management Evaporation

来源：评论

学校读者我要写书评

暂无评论

Improving exploration and exploitation via a Hyperbolic Gravitational Search Algorithm

引用

KNOWLEDGE-BASED SYSTEMS 2020年 193卷

作者： Pelusi, Danilo Mascella, Raffaele Tallini, Luca Nayak, Janmenjoy Naik, Bighnaraj Deng, Yong Univ Teramo Fac Commun Sci Teramo Italy Aditya Inst Technol & Management Dept Comp Sci & Engn Tekkali K Kotturu India Veer Surendra Sai Univ Technol Dept Comp Applicat Burla Odisha India Univ Elect Sci & Technol China Inst Fundamental & Frontier Sci Chengdu Peoples R China

Finding the best compromise between exploration and exploitation phases of a search algorithm is a hard task. The Gravitational Search Algorithm (GSA) is an evolutionary algorithm based on the Newton's universal law of gravitation. Many studies show that GSA suffers from slow exploitation which generates premature convergence. This paper proposes a Hyperbolic Gravitational Search Algorithm (HGSA) able to find an optimal balance between exploration and exploitation. The main contributions of this work are: the definition of suitable hyperbolic acceleration coefficients, the dynamic regulation of the gravitational constant coefficient through hyperbolic function and the definition of a decreasing hyperbolic function for the best agents which attract the other agents. The proposed algorithm is compared with well-known search algorithms on classical benchmark functions, CEC-06 2019 benchmark functions and three-bar truss design problem. The results show that HGSA is better than other algorithms in terms of optimization and convergence performances. (c) 2019 Elsevier B.V. All rights reserved.

关键词： Evolutionary algorithms Gravitational search algorithm optimization algorithms Exploration and exploitation Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

Push-Sum on Random Graphs: Almost Sure Convergence and Convergence Rate

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2020年第3期65卷 1295-1302页

作者： Rezaienia, Pouya Gharesifard, Bahman Linder, Tamas Touri, Behrouz Univ British Columbia Sauder Sch Business Vancouver BC V6T 1Z4 Canada Queens Univ Dept Math & Stat Kingston ON K7L 3N6 Canada Univ Calif San Diego Dept Elect & Comp Engn La Jolla CA 92093 USA

In this paper, we study the problem of achieving average consensus over a random time-varying sequence of directed graphs by extending the class of so-called push-sum algorithms to such random scenarios. Provided that an ergodicity notion, which we term the directed infinite flow property, holds and the auxiliary states of agents are uniformly bounded away from zero infinitely often, we prove the almost sure convergence of the evolutions of this class of algorithms to the average of initial states. Moreover, for a random sequence of graphs generated using a so-called time-varying -irreducible probability matrix, we establish convergence rates for the proposed push-sum algorithm.

关键词： Convergence Heuristic algorithms Random sequences Protocols optimization Machine learning algorithms Communication networks Distributed optimization optimization algorithms random networks

来源：评论

学校读者我要写书评

暂无评论

Combinatorial test list generation based on Harmony Search Algorithm

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2020年第7期13卷 3361-3377页

作者： Alsewari, AbdulRahman A. Poston, Robin Zamli, Kamal Z. Balfaqih, Mohammed Aloufi, Khalid S. Univ Malaysia Pahang Coll Comp & Appl Sci Fac Comp Pahang 26300 Gambang Malaysia Univ Malaysia Pahang IBM Ctr Excellence Pahang 26300 Gambang Malaysia Univ Memphis Business Informat & Technol Memphis TN 38152 USA Jeddah Univ Comp & Networks Engn Dept Jeddah 23218 Saudi Arabia South Ural State Univ Automobile Transportat Dept Chelyabinsk 454080 Russia Taibah Univ Coll Comp Sci & Engn Medina 41477 Saudi Arabia

Combinatorial test case generation faces a problem on how to reduce the test cases by uncover the unnecessary test cases. So, there is a need for expert applications or strategies that generate the most optimum test cases keeping in mind the most important combinations. Complementing existing work on combinatorial test case generation strategies, also known as t-way testing strategies (i.e., where t represents interaction degree), this paper presents the design and the implementation of a new combinatorial test list generation strategy based on Harmony Search (HS) algorithm, called General T-way Harmony Search-based Strategy (GTHS). HS has been chosen to be the main engine of test generation because it could balance between intensification and diversification. Benchmarking experimental results show that GTHS produces competitive results as compared to other existing well-known optimization-based strategies and provides the support for high combination degrees (i.e., t <= 12).

关键词： Computational ontelligence Intelligent test list generators optimization algorithms Combinatorial optimization problems

来源：评论

学校读者我要写书评

暂无评论

Designing Robotically-Constructed Metal Frame Structures

引用

COMPUTER GRAPHICS FORUM 2020年第2期39卷 411-422页

作者： Ma, Z. Walzer, A. Schumacher, C. Rust, R. Gramazio, F. Kohler, M. Bacher, M. Swiss Fed Inst Technol Zurich Switzerland Disney Res Zurich Switzerland

We present a computational technique that aids with the design of structurally-sound metal frames, tailored for robotic fabrication using an existing process that integrate automated bar bending, welding, and cutting. Aligning frames with structurally-favorable orientations, and decomposing models into fabricable units, we make the fabrication process scale-invariant, and frames globally align in an aesthetically-pleasing and structurally-informed manner. Relying on standard analysis of frames, we then co-optimize the shape and topology of bars at the local unit level. At this level, we minimize combinations of functional and aesthetic objectives under strict fabrication constraints that model the assembly of discrete sets of bent bars. We demonstrate the capabilities of our global-to-local approach on four robotically-constructed examples.

关键词： CCS Concepts . Applied computing -> Computer-aided design . Computing methodologies -> Shape modeling optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Simulation, optimization and visualization of transportation data: Simulation, optimisation et visualisation de données de transport

Simulation, optimization and visualization of transportation...

引用

作者： Panovski, Dancho Institut polytechnique de Paris

学位级别：博士

Aujourd'hui, toutes les grandes métropoles de France, d'Europe et du reste du monde souffrent de graves problèmes de congestion et de saturation des infrastructures routières, qui concernent à la fois les transports individuels et publics. Les systèmes de transport actuels atteignent leurs limites de capacité et semblent incapables d'absorber l'augmentation des flux de passagers à l'*** ce contexte, l'un des principaux défis à relever concerne la création de méthodologies dédiées pour l'analyse des données de transport géo-localisées pour le stockage instantané, l'analyse, la gestion et la diffusion de flux de données massives. Les algorithmes associés doivent être capables de gérer des listes d'événements de plusieurs dizaines de minutes pour calculer des trajectoires réelles, des occupations instantanées, des cycles de changement de feux de circulation ainsi que des prévisions de flux de circulation de vé*** cette thèse, nous abordons deux différentes problématiques liées à ce *** première contribution concerne l'optimisation des systèmes de feux tricolores. L'objectif est de minimiser le temps de trajet total des véhicules présents dans une certaine partie d'une ville. Dans ce but, nous proposons une technique d’optimization de type PSO (Particle Swarm optimization). Les résultats expérimentaux obtenus montrent qu'une telle approche permet d'obtenir des gains importants (5.37% - 21.53%) en termes de temps de parcours moyen global des vé*** deuxième partie de la thèse est consacrée à la problématique de la prédiction des flux de trafic. En particulier, nous nous concentrons sur la prédiction de l'heure d'arrivée des bus dans les différentes stations présentes sur un itinéraire donné. Ici, nos contributions concernent tout d'abord l'introduction d'un nouveau modèle de données, appelé TDM (Traffic Density Matrix), qui capture dynamiquement la situation du trafic tout au long d'un itinéraire de bus donné. Ensuite, nous montrons comment d

关键词： Transports publics Algorithmes d'optimisation Apprentissage en profondeur Apprentissage automatique Simulation du trafic Machine learning Traffic simulation Deep learning Public transport optimization algorithms

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：