Study of LED array fill light based on parallel particle swarm optimization in greenhouse planting
مطالعه نور پر کننده آرایه LED بر اساس بهینه سازی ازدحام ذرات موازی در کاشت گلخانه ای-2019
Agricultural productivity is crucial to the economy. The output and quality of crops have a direct impact on people’s daily lives and a country’s food and clothing. Therefore, harvesting high-quality crops efficiently and maximizing yield per unit area are the most important goals pursued by farmers. As an important parameter of plant growth, light intensity is one of the important factors that affects plant growth and development, morphological establishment and accumulation of functional chemical substances. When light intensity cannot meet the plant’s needs, the optimal light intensity or uneven light distribution will have a greater impact on plant growth and development. This paper aims to address the optimal plant light intensity problem. The paper presents an expert system technology database storing the empirical value of real-time light intensity values and compares it with a parallel particle swarm optimization algorithm to identify the optimal locations where LED lights need to be turned on and where drive circuit lit LED arrays need to be situated, to identify the number of LED fill lights and to solve light intensity optimization problems.
Keywords: Particle swarm optimization | Greenhouse | Fill light | Expert system | LED
An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction
یک مدل ماشین پیشرفته افراطی برای پیش بینی جریان رودخانه: پیشرفته ترین برنامه ها ، کاربردهای عملی در منطقه مهندسی منابع آب و جهت گیری تحقیقات آینده-2019
Despite the massive diversity in the modeling requirements for practical hydrological applications, there remains a need to develop more reliable and intelligent expert systems used for real-time prediction purposes. The challenge in meeting the standards of an expert system is primarily due to the influence and behavior of hydrological processes that is driven by natural fluctuations over the physical scale, and the resulting variance in the underlying model input datasets. River flow forecasting is an imperative task for water resources operation and management, water demand assessments, irrigation and agriculture, early flood warning and hydropower generations. This paper aims to investigate the viability of the enhanced version of extreme learning machine (EELM) model in river flow forecasting applied in a tropical environment. Herein, we apply the complete orthogonal decomposition (COD) learning tool to tune the output-hidden layer of the ELM model’s internal neuronal system, instead of the conventional multi-resolution tool (e.g., singular value decomposition). ToA-ELM, AdaBoost.RT-extreme learning machine; AI, artificial intelligence; ANFIS, adaptive neuro-fuzzy inference system; ANN, artificial neural network; ARIMA, autoregressive integrated moving average; AtmP, atmospheric pressure; B-ANN, bootstrap-artificial neural network; BCSO, binary-coded swarm optimization; B-ELM, bootstrap-extreme learning machine; C-ELM, complex-extreme learning machine; Cl−1, chloride; COD, complete orthogonal decomposition (COD); CRO-ELM, coral reefs optimization-extreme learning machine; DE-ELM, deferential evolution-extreme learning machine; DID, department of Irrigation and Drainage; DO, dissolved oxygen concentration; EC-SVR, evolutionary computation-based support vector machine; EDI, effective drought index; ELM, extreme learning machine; EELM, enhanced extreme learning machine; EEMD, ensemble empirical mode decomposition; EL-ANFIS, extreme learning adaptive neuro-fuzzy inference system; EMD, empirical mode decomposition; Ens, Nash-Sutcliffe coefficient; Ensemble-ELM, ensemble-extreme learning machine; EPR, evolutionary polynomial regression; ESNs, echo state networks; ETo, evapotranspiration; Fe, iron; Fr, Froude number; FS, factor of safety; GA-ELM, genetic algorithm-extreme learning machine; GCM, general circulation model; G-ELM, geomorphology extreme learning machine; GP, genetic programming; GRNN, generalized regression neural network; HCO3 -1, bicarbonate; HDSR, diffuse solar radiation; HRT, hydraulic retention time; I-ELM, integrated extreme learning machine; KELM, Kernelextreme learning machine; LST, land surface temperature; LASSO, least absolute shrinkage and selection operator; LSTM, long short-term memory network; LSSVM, least square support vector machine; MAE, mean absolute error; MARS, multivariate adaptive regression spline; MBFIPS, Multi-objective binary-coded fully informed particle swarm optimization; MC-OS-ELM, meta cognitive-online sequential-extreme learning machine; MLPNN, multi-linear perceptron neural network; MLR, multiple linear regression; MME, multi-model ensemble; NEMR, northeast monsoon rainfall; NO2 -1, nitrite; NO3 -1, nitrate; NO2, nitrogen dioxide; NT, total nitrogen; O3, ozone; OP-ELM, optimally pruned-extreme learning machine; OSELM, online sequential extreme learning machine; PCA, principal component analysis; pH, power of hydrogen; PM10, air pollution “suspended particulate matters”; PO4 -3, phosphorus; R-ELM, radial basis-extreme learning machine; r, determination coefficient; RE, relative error; RF, rainfall; RH, relative humidity; RHmax, maximum relative humidity; RHmean, mean relative humidity; RHmin, minimum relative humidity; RMSE, root mean square error; RVM, relevance vector machine; SaE-ELM, self-adaptive evolutionary-extreme learning machine; SC, specific conductance; S-ELM, sigmoid-extreme learning machine; SHr, sunshine hour; SR, solar radiation; SO4 -2, sulfate; SiO2, Silicon; SO2,
A new machine learning technique for an accurate diagnosis of coronary artery disease
یک روش جدید یادگیری ماشین برای تشخیص دقیق بیماری عروق کرونر-2019
Background and objective: Coronary artery disease (CAD) is one of the commonest diseases around the world. An early and accurate diagnosis of CAD allows a timely administration of appropriate treatment and helps to reduce the mortality. Herein, we describe an innovative machine learning methodology that enables an accurate detection of CAD and apply it to data collected from Iranian patients. Methods: We first tested ten traditional machine learning algorithms, and then the three-best perform- ing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features. Results: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field. Conclusions: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.
Keywords: Coronary artery disease (CAD) | Machine learning | Normalization | Genetic algorithm | Particle swarm optimization | Feature selection | Classification
Machine-learning assisted coarse-grained model for epoxies over wide ranges of temperatures and cross-linking degrees
یادگیری ماشین به کمک مدل دانه درشت برای epoxies در طیف گسترده ای از درجه حرارت و درجه اتصال متقابل-2019
We present a practical computational framework for the coarse-graining of cross-linked epoxies by developing a machine-learning technique, which integrates molecular dynamics simulations with artificial neural network (ANN) assisted particle swarm optimization (PSO) algorithm. Key features of the framework include two as- pects: (1) determining the bonded interactions via the iterative Boltzmann inversion method to emulate the local structures of the epoxies and, (2) optimizing the nonbonded interaction potentials through the machine- learning approach to reproduce the mechanical properties. Such machine-learning based technique is computa- tionally efficient in searching for the optimal solution of nonbonded potential parameters and enables the CG model to become transferable within a wide range of cross-linking degrees. This is mainly attributed to the fact that ANN can give good predictions based on training database obtained from CG simulations and thus greatly accelerates the PSO algorithm in achieving the optimal solution. On the basis of the DOC-transferable CG model, the cohesive interaction strength is phenomenologically adjusted to preserve the temperature-dependent prop- erties. The CG model allows the mechanical properties of cross-linked epoxies to be predicted with reasonable accuracy over wide ranges of cross-linking degrees and temperature. The proposed framework will become highly beneficial to the design of high performance epoxy-matrix nanocomposites.
Keywords: Machine-learning approach | Cross-linked epoxy | Coarse-grained model | Molecular dynamics
Screening and optimization of polymer flooding projects using artificial-neural-network (ANN) based proxies
غربالگری و بهینه سازی پروژه های سیلی پلیمری با استفاده از پروکسی مبتنی بر شبکه مصنوعی عصبی (ANN)-2019
Polymer flooding is one of the most broadly implemented chemical EOR processes due to its low injection cost and successes in oil production increments. This work develops artificial-neural-network based proxies by utilizing synthetic production histories generated from a high-fidelity numerical simulation model. Injectionpattern- based reservoir models are structured to establish the knowledgebase to train the proxies. A forward and an inverse-looking ANN models are structured in this study. The forward-looking expert system are employed as a forecasting and screening tool that is capable to predict time-based project responses. And the inverse-looking ANN predicts the project design schemes that fulfill the expected oil recoveries. The proxies are generalized considering reservoir rock and fluid properties and project design parameters. In this paper, we present results of extensive blind testing applications to confirm the validates of the proxy models. Afterwards, various applications of the expert systems are discussed. A project screening protocol that couples the expert system and particle swarm optimization (PSO) methodology is presented to maximize the polymer injection projects’ net present value (NPV). Moreover, we propose a robust computational workflow that coupled utilize the inverse and forward-looking proxies to find various polymer injection schemes to fulfill the expected oil production profile, which effectively addresses the issue associated with the existence of non-unique solutions in the inverse design problems. The expert ANN systems and the associated project design workflows provide versatile approaches for the field engineers to obtain quick techno-economical assessments of polymer injection projects.
Keywords: Artificial neural network | Polymer injection | Optimization | EOR screening | EOR project design
Swarm intelligence techniques in recommender systems - A review of recent research
تکنیک های هوش ازدحام در سیستم های توصیه کننده - مروری بر تحقیقات اخیر-2019
One of the main current applications of Intelligent Systems are Recommender systems (RS). RS can help users to find relevant items in huge information spaces in a personalized way. Several techniques have been investigated for the development of RS. One of them are Swarm Intelligence (SI) techniques, which are an emerging trend with various application areas. Although the interest in using Computational Intelligence in web personalization and information retrieval fostered the publication of some survey papers, these surveys so far focused on different application domains, e.g., clustering, or were too broadly focused and incorporated only a handful of SI approaches. This study provides a comprehensive review of 77 research publications applying SI in RS. The study focus on five aspects we consider relevant for such: the recommendation technique used, the datasets and the evaluation methods adopted in their experimental parts, the baselines employed in the experimental comparison of proposed approaches and the reproducibility of the reported results. At the end of this review, we discuss negative and positive aspects of these papers, as well as point out opportunities, challenges and possible future research directions. To the best of our knowledge, this survey is the most comprehensive review of approaches using SI in RS. Therefore, we believe this review will be a relevant material for researchers interested in either of the domains.
Keywords: Swarm intelligence | Particle swarm optimization | Ant colony optimization | Invasive weed optimization | Artificial bee colony | Recommender systems | Personalization
Clustering of multi-view relational data based on particle swarm optimization
خوشه بندی داده های رابطه ای چند منظوره بر اساس بهینه سازی ازدحام ذرات-2019
Clustering of multi-view data has received increasing attention since it explores multiple views of data sets aiming at improving clustering accuracy. Particle Swarm Optimization (PSO) is a well-known population-based meta-heuristic successfully used in cluster analysis. This paper introduces two hybrid clustering methods for multi-view relational data. These hybrid methods combine PSO and hard clus- tering algorithms based on multiple dissimilarity matrices. These methods take advantage of the global convergence ability of PSO and the local exploitation of hard clustering algorithms in the position up- date step, aiming to improve the balance between exploitation and exploration processes. Moreover, the paper provides adapted versions of 11 fitness functions suitable for vector data aiming at dealing with multi-view relational data. Two performance criteria were used to evaluate the clustering quality using the two proposed methods over eleven real-world data sets including image and document data sets. Among new findings, it was observed that the top three fitness functions are Silhouette index, Xu index and Intra-cluster homogeneity. The performance of the proposed algorithms was compared with previ- ous single and multi-view relational clustering algorithms. The results show that the proposed methods significantly outperformed the other algorithms in the majority of cases. The results reinforce the im- portance of the application of techniques such as PSO-based clustering algorithms in the field of expert systems and machine learning. Such application enhances classification accuracy and cluster compactness. Besides, the proposed algorithms can be useful tools in content-based image retrieval systems, providing good categorizations and automatically learning relevance weights for each cluster of images and sets of views.
Keywords: PSO | Cluster analysis | Multi-view clustering | Relational data
Hierarchical differential evolution algorithm combined with multi-cross operation
الگوریتم تکامل تفاضلی سلسله مراتبی همراه با عمل چند تقابلی-2019
In expert systems, complex optimization problems are always characterized by nonlinearity, nonconvex- ity, multi-modality, discontinuity, and high dimensionality. Although classical optimization algorithms are mature, they readily fall into a local optimum. The differential evolution (DE) algorithm has been suc- cessfully applied to solve numerous problems with expert systems. However, balancing the global and local search capabilities of the DE algorithm remains an open issue and has attracted significant research attention. Thus, a hierarchical heterogeneous DE algorithm that incorporates multi-cross operation (MCO) is proposed in this article. In the proposed algorithm, success-history-based adaptive DE (SHADE) is im- plemented in the bottom layer, while MCO is implemented in the top layer. The MCO search is based on the SHADE results, but its search results do not affect the bottom layer. First-order stability analyses con- ducted for the presented MCO showed that the individual positions are expected to converge at a fixed point in the search space. The accuracy and convergence speed of the proposed algorithm were also ex- perimentally compared with those of eight other advanced particle swarm optimization techniques and DE variants using benchmark functions from CEC2017. The proposed algorithm yielded better solution ac- curacy for 30- and 50-dimensional problems than the other variants, and although it did not provide the fastest convergence for all of the functions, it ranked among the top three for the unimodal and simple multimodal functions and achieved fast convergence for the other functions.
Keywords: Differential evolution | Particle swarm optimization | Hierarchical structure | Multi-cross operation
Dependence structure of Gabor wavelets based on copula for face recognition
ساختار وابستگی Gabor wavelets بر اساس کوپول برای تشخیص چهره-2019
Low resolution, difficult illumination and noise are the important factors that affect the performance of face recognition system. In order to counteract these adverse factors, in this paper we propose copula probability models based on Gabor wavelets for face recognition. Gabor wavelets have robust performance under lighting and noise conditions. The strong dependencies exist in the domain of Gabor wavelets due to their non-orthogonal property. In the light of the structure characteristic of Gabor wavelet sub- bands, the proposed methods use copula to capture the dependencies to represent the face image. Three probability-model-based methods CF-GW (Copula Function of Gabor Wavelets), LCM-GW (Lightweight Copula Model of Gabor Wavelets) and LCM-GW-PSO (Lightweight Copula Model of Gabor Wavelets with Particle Swarm Optimization) are proposed for face recognition. Experiments of face recognition show our proposed methods are more robust under the conditions of low resolution, lighting and noise than the popular methods such as the LBP-based methods and other Gabor-based methods. The face features extracted by our methods belong to the Riemannian manifold which is different to Euclidean space. In order to deal the issue of face recognition in complex environment, we can combine the face features in Riemannian manifold with the face features in Euclidean space to obtain the more robust face recognition system by using expert system technologies such as reasoning model and multi-classifier fusion.
Keywords: Face recognition | Gabor wavelets | Gaussian copula | Covariance matrix | Particle swarm optimization
الگوریتم بهینه سازی ازدحام ذرات با کنترل هوشمند تعداد ذرات برای طراحی بهینه ماشین های الکتریکی
سال انتشار: 2018 - تعداد صفحات فایل pdf انگلیسی: 8 - تعداد صفحات فایل doc فارسی: 23
در این مقاله، یک الگوریتم بهینه سازی ازدحام ذرات (PSO) اصلاح شده پیشنهاد می شود که نسخه ارتقاء یافته الگوریتم PSO معمولی است. برای بهبود دادن عملکرد الگوریتم PSO ، یک روش جدید برای کنترل کردن هوشمندانه تعداد ذرات به کار برده شده است. این روش جدید، مقدار هزینه بهترین جهانی (gbest) در تکرار فعلی نسبت به gbest در تکرار قبلی را با یکدیگر مقایسه می کند. اگر بین دو مقدار هزینه اختلافی وجود داشته باشد، آنگاه الگوریتم پیشنهادی در مرحله اکتشاف عمل می کند و تعداد ذرات را حفظ می کند. اما، وقتی که اختلاف در مقادیر هزینه نسبت به مقادیر تحمل تخصیص یافته توسط کاربر کوچکتر باشد، این الگوریتم پیشنهادی در مرحله استخراج عمل می کند و تعداد ذرات را کاهش می دهد. علاوه بر این، این الگوریتم ، نزدیکترین ذره به بهترین ذره را حذف می کند تا از تصادفی بودنش بر حسب فاصله ی اقلیدسی اطمینان حاصل کند. الگوریتم پیشنهادی با استفاده از پنج تابع آزمون عددی اعتبارسنجی می شود، که تعداد فراخوانی های تابع تا اندازه ای نسبت به PSO معمولی کاهش می یابد. بعد از اعتبار سنجی الگوریتم ، برای طراحی بهینه موتور سنکرون مغناطیس دائم درونی (IPMSM) به کار برده می شود تا اعوجاج هارمونیک کل (THD) نیروی ضد محرکه الکتریکی (back-EMF) کاهش یابد. با در نظر گرفتن شرط عملکرد، طراحی بهینه به دست می آید که back-EMF THD را کاهش داده و مقدار back-EMF را برآورده می کند. نهایتا، یک مدل آزمایشگاهی را ایجاد کرده و آزمایش می کنیم. برای اعتبارسنجی عملکرد طراحی بهینه و الگوریتم بهینه سازی ، یک آزمایش بدون بار انجام می شود. بر اساس نتایج آزمایشگاهی، اثربخشی الگوریتم پیشنهادی بر روی طراحی بهینه یک ماشین الکتریکی تایید می شود.
کلمات کلیدی: طراحی بهینه | الگوریتم بهینه سازی | بهینه سازی ذرات ذرات | ماشین الکتریکی | موتور همگام مگنت دائمی.
|مقاله ترجمه شده|