Fig 5 - uploaded by Asım Balbay
Content may be subject to copyright.
Source publication
Artificial neural networks (ANNs) have been widely used in modeling of various systems. Training of ANNs is commonly performed by backpropagation based on a gradient-based learning rule. However, it is well-known that such learning rule has several shortcomings such as slow convergence and training failures. This paper proposes a modeling technique...
Context in source publication
Context 1
... ELM randomly chooses and fixes the weights between input and hidden neurons based on continuous probability density function which is is a uniform distribution function in the range -1 to +1. Then, it determines analytically the weights between hidden neurons and output neurons of the SLFN. The block diagram of proposed method is given in Fig. 5. As shown in figure, air temperature, air velocity, and drying time are chosen as the inputs to ELM whereas moisture content is designated as the output of ELM. The performance of ELM depends on type of activation function and the number of hidden neurons to be used. Therefore, these parameters of ELM are determined through several ...
Similar publications
The consumption of peanuts and other oilseeds (nuts) as walnuts, almonds, chestnuts, hazelnuts and pistachios promote weight loss. Mice, male (20 g - 35 g) were treated on a standard diet (SD, n = 08) and a test diet (high calorie) (HD, n = 08). The HD standardized in this experiment was composed of a mixture of commercial feed Labina® flour and pr...
Pistachio (Pistacia vera L.) is an important crop in arid and semi-arid regions. Although this plant can tolerate drought stress, this type of environmental stress decreases the yield and the quality of nuts. In this study, differential response of some organic metabolites and antioxidant defense systems to drought stress was investigated in five v...
The wild pistachio (Pistacia Atlantica Mutika) exists in 2.4 million ha of Iranian forest. In this way the pistachio of Syrjan was chosen as a case study. The objective of this study was to determine physical and mechanical properties of wild pistachio nut of Syrjan rejoin as a function of moisture content. The physical properties including thousan...
In Iran, the Indian meal moth, Plodia interpunctella (Hübner), is one of the most important pests of such stored products as date fruits and pistachio nuts. Ozone was applied as a gas at four concentrations (0, 2, 3, and 5 ppm) for four different periods (30, 60, 90, and 120 min) on the immature stages of P. interpunctella. The results indicated th...
Citations
... A secagem é uma das técnicas de conservação mais antigas, e baseia-se na retirada de água de um produto por evaporação ou sublimação, através da aplicação de calor em condições controladas. BALBAY et al., 2012). Dentre os diversos métodos empregados para secagem de frutas, destacam-se secagem natural, em leito fixo, em camada de espuma, por atomização e em Nesse contexto, esse trabalho teve por objetivo realizar uma revisão bibliográfica sobre as principais técnicas de secagem aplicada à frutas, abordando os fundamentos, vantagens e desvantagens de cada técnica, bem como seus principais parâmetros e resultados na secagem de diversas frutas. ...
... A secagem é uma das técnicas de conservação mais antigas, e baseia-se na retirada de água de um produto por evaporação ou sublimação, através da aplicação de calor em condições controladas. BALBAY et al., 2012). Dentre os diversos métodos empregados para secagem de frutas, destacam-se secagem natural, em leito fixo, em camada de espuma, por atomização e em Nesse contexto, esse trabalho teve por objetivo realizar uma revisão bibliográfica sobre as principais técnicas de secagem aplicada à frutas, abordando os fundamentos, vantagens e desvantagens de cada técnica, bem como seus principais parâmetros e resultados na secagem de diversas frutas. ...
... For example, ELM has been used in troubleshooting, soft measurements, speech recognition, image processing, face recognition, etc. Kumar used ELM to minimize the effect of machine parameter variations in servo motor trajectory control [19]. Balbay et al. [20] proposed a modeling technique based on ELM and demonstrated the effectiveness of the LEM in modeling the process of drying bittim nuts. ...
... The syrup, hot water and seeds are stored in the material tank (18). The syrup regulating valve (17), the hot water regulating valve (19) and the seed regulating valve (20) control their output, respectively. There are three temperature sensors (14)(15)(16) for measuring the input temperatures on-line, respectively. ...
The process of sugar evaporative crystallization is a nonlinear process with large time lag and strong coupling. It is difficult to establish a reasonable mechanism model. In this paper, we use the data driving modeling method to establish an Adaptive Control model for batch boiling sugar crystallization process. First, by analyzing the main influencing factors of the evaporative crystallization process of intermittent boiling sugar, the most important two parameters, brix and liquid level, are selected as the control object. The self-adaptive differential evolution Extreme Learning Machine (SaDE-ELM) is used to construct the control model. A least squares support vector machine (LSSVM) is established and connected in the control loop to control the opening of the feed valve so that to control the feed flowrate according to the objective values of syrup Brix and liquid level. Experiments are conducted and the obtained data are used to train and verify the learning machines. Experiments indicate that the learning machines are able to realize adaptive control to key parameters of the crystallization process. Comparison of different neural networks indicates that the LSSVM performs better than BP, RBF and ELM and SaDE-ELM with prediction error of below 0.01, and training time of below 0.05 s.
... [26] However, only a few studies about applying ELM for modeling the drying process of agricultural products can be found in the literature. [27,28] Furthermore, no reports have been found detailing the effects of HHAIB and drying temperature as well as air velocity on hot air impingement drying (AID) characteristics and quality of broccoli florets. ...
In current work, the influences of high-humidity hot air impingement blanching (HHAIB) time (60, 90, 120, and 150 s), drying temperature (60, 65, 70, and 75 °C), and air velocity (6, 9, and 12 m/s) on drying characteristics and quality attributes of broccoli florets were explored. Extreme learning machine (ELM) was employed to describe the drying behavior of broccoli florets. Results showed that proper HHAIB pretreatment can extensively increase drying rate compared to the control group (unblanched samples). The entire drying process of broccoli florets occurred in the falling period. Besides, proper HHAIB pretreatment can enhance vitamin C preservation, the color quality, and the rehydration capacity of dried broccoli florets. Based on error analysis results, the prediction accuracy of the optimal ELM model with 4-50-1 topology is found to be satisfied for the moisture ratio prediction of broccoli florets during air impingement drying process, with the R², χ2, and MSE reached to 0.9993, 8.04e⁻⁵, and 2.01e⁻⁴, respectively.
... ELM produces high generalization performance at very high speed (Huang et al. 2011). There are different applications of ELM in the literature (Balbay et al. 2012;Du et al. 2014;Yu et al. 2013). In this study, a new version of ELM, called Bayesian ELM (BELM), which learns the output weights of basic ELM based on parametric Bayesian methods. ...
This article adopts four high-accuracy machine learning-based approaches for the prediction of discharge coefficient of a Piano Key Weir (PK-weir) under subcritical condition located on the straight open-channel flume. These approaches consist of least-square support vector machine (LS-SVM), extreme learning machine (ELM), Bayesian ELM (BELM), and logistic regression (LR). For this purpose, 70 laboratory test results are used for determining discharge coefficient of PK-weir for a wide range of discharge values. Root-mean-squared error (RMSE), Nash–Sutcliffe model efficiency coefficient (NSE), the coefficient of correlation (R), threshold statistics (TS), and scatter index (SI) are used for comparing the performance of the models. The simulation results indicate that an improvement in predictive accuracy could be achieved by the ELM approach in comparison with LS-SVM and LR (RMSE of 0.016 and NSE of 0.986), while the BELM model’s generalization capacity enhanced, with RMSE of 0.011 and NSE of 0.989 in validation dataset. The results show that BELM is a simple and efficient algorithm which exhibits good performance; hence, it can be recommended for estimating discharge coefficient.
... The Extreme Learning Machine as an evolving learning technique gives efficient unified solutions to generalize feed-forward networks including but not limited to (each supports single-and multi-hidden-layer) neural networks, Radial Basis Function (RBF) networks and kernel learning. Single hidden layer feed forward networks (SLFNs), is one of the most accepted feed forward neural networks, have been greatly studied from each theoretical and application aspect for their learning capabilities and fault-tolerant dependability [1][2][3][4][5][6]. However, most accepted learning algorithms for training SLFNs are still relatively not quick since all the parameters of SFLNs need to be tuned through repetitive procedures and these algorithms may also stuck in a local minimum. ...
Extreme Learning Machine (ELM) is a high effective learning algorithm for the single hidden layer feed forward neural networks. Compared with the existing neural network learning algorithm it solves the slow training speed and over-fitting problems. It has been used in different fields and applications such as biomedical engineering, computer vision, remote sensing, chemical process and control and robotics. It has better generalization stability, sparsity, accuracy, robustness, optimal control and fast learning rate This paper introduces a brief review about ELM and MLELM, describing the principles and latest research progress about the algorithms, theories and applications. Next, Multilayer Extreme Learning Machine (MLELM) and other state-of-the-art classifiers are trained on this suitable training feature vector for classification of data. Deep learning has the advantage of approximating the complicated function and mitigating the optimization difficulty associated with deep models. Multilayer extreme learning machine is a learning algorithm of an Artificial Neural Network (ANN) which takes to be good for deep learning and extreme learning machine. This review presents a comprehensive view of these advances in ELM and MLELM which may be worthy of exploring in the future.
... ELM produces high generalization performance at very high speed (Huang et al., , 2011. There are lots of applications of ELM in the literature (Balbay et al., 2012;Yu et al., 2013;Du et al., 2014). GPR is probabilistic and non-parametric method that has been successful applied to modern different problems in engineering (Zhao et al., 2012;Nearing et al., 2013;Chen et al., 2014). ...
This article adopts three artificial intelligence techniques (Gaussian Process Regression (GPR), Least Square Support Vector Machine (LSSVM) and Extreme Learning Machine (ELM)) for prediction of rock depth (d) at any point in Chennai. GPR, ELM and LSSVM have been used as regression techniques. Latitude and longitude have been adopted as inputs of the GPR, ELM and LSSVM models. The performance of the ELM, GPR and LSSVM models has been compared. The developed ELM, GPR and LSSVM models produce spatial variability of rock depth at Chennai. The results show that the proposed ELM, LSSVM and GPR are robust models for the prediction of rock depth at any point in Chennai.
... Mokhtarian et al. [55] reported that an MLP ANN model was slightly better than the Newton thin-layer drying model in estimating the convec-335 tive drying kinetics of pumpkin cubes. Balbay et al. [42] found that the generalization capability of ANN architecture with ELM algorithm dominated conventional algorithms such as LM and SCG algorithms to predict the hot air drying kinetics of peeled bittim nuts. 340 A hybrid ANN model, through integrating a pure ANN model and simple thin-layer drying model (Newton model), was developed by Saraceno et al. [43] The model was successfully tested with experimental data compared to the simple ANN and thin-layer drying models. ...
Inspired by the functional behavior of the biological nervous system of the human brain, artificial neural network (ANN) has found many applications as a superior tool to model complex, dynamic, highly nonlinear, and ill-defined scientific and engineering problems. For this reason, ANNs are employed extensively in drying applications because of their favorable characteristics such as efficiency, generalization, and simplicity. This paper presents a comprehensive review of numerous significant applications of the ANN technique to solve problems of nonlinear function approximation, pattern detection, data interpretation, optimization, simulation, diagnosis, control, data sorting, clustering, and noise reduction in drying technology. We summarize the use of the ANN approach in modeling various dehydration methods, e.g., batch convective thin-layer drying, fluidized bed drying, osmotic dehydration, osmotic-convective drying, infrared, microwave, infrared- and microwave-assisted drying processes, spray drying, freeze drying, rotary drying, renewable drying, deep bed drying, spout bed drying, industrial drying, and several miscellaneous applications. Generally, ANNs have been used in drying technology for modeling, predicting, and optimization of heat and mass transfer, thermodynamic performance parameters, and quality indicators as well as physiochemical properties of dried products. Moreover, a limited number of researchers have focused on control of drying systems to achieve desired product quality by on-line manipulating of the drying conditions using previously trained ANNs. Opportunities and limitations of the ANN technique for drying process simulation, optimization, and control are attained to guide future R&D in this area.
... ,Pan et al. (2012),Suresh et al. (2009),Wang, Huang, et al. (2011),Zhou et al. (2013), Text classification and understandingCambria et al. (in press),Poria et al. (2014),Yang and Mao (2013),Zhao et al. (2011, System modeling and predictionBalbay, Kaya, et al. (2012),Balbay, Avci, et al. (2012),Chen, Dong, et al. (2012), Chen and Ou (2011), Feng, Wang, et al. (2012), Lin et al. (2013), Li, Niu, et al. (2012), Minhas, Mohammed, et al. (2010), Saavedra-Moreno et al. (2013), Tan et al. (2012), Tian and Mao (2010), Wang and Do (2012), Wang, Qian, et al. (2013), Wefky et al. (2012), Wong and Guo (2010), Wong et al. (2013), Xia et al. (2012), Xu et al. (2013), Xu, Dong, Zhao, et al. (2012), Yan and Wang (2014), Yang et al. (2012), Yu et al. (2011), Zhang et al. (2013), Zhao et al. (2013), Zhao, Qi, et al. (2012), Control and robotics Decherchi et al. (2011), Kosmatopoulos and Kouvelas (2009a, 2009b), Rong et al. (2011), Yu et al. (2012), Zhang and Slaughter (2011), Chemical process Liu, Jiang, et al. (2012), Wang, Xu, et al. (2012), Wang, Jin, et al. (2013), Zhang and Zhang (2011), Fault detection and diagnosis Chen, Ding, et al. (2012), Cheng et al. (2012), Creech and Jiang (2012), Kong et al. (2013), Martínez-Rego et al. (2010), Muhammad et al. (2013), Yang et al. (2011), Time series analysis Butcher et al. (2013), Sovilj et al. (2010), Wang and Han (2012), Zhang and Wang (2011a, 2011b), Remote sensing Pal et al. (2013), Pal (2009), ...
Extreme learning machine (ELM) has gained increasing interest from various research fields recently. In this review, we aim to report the current state of the theoretical research and practical advances on this subject. We first give an overview of ELM from the theoretical perspective, including the interpolation theory, universal approximation capability, and generalization ability. Then we focus on the various improvements made to ELM which further improve its stability, sparsity and accuracy under general or specific conditions. Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks. These newly emerging algorithms greatly expand the applications of ELM. From implementation aspect, hardware implementation and parallel computation techniques have substantially sped up the training of ELM, making it feasible for big data processing and real-time reasoning. Due to its remarkable efficiency, simplicity, and impressive generalization performance, ELM have been applied in a variety of domains, such as biomedical engineering, computer vision, system identification, control and robotics, etc. In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.
Drying is one of the most effective methods to preserve foods and guarantee their supply for more people. Mathematical modeling is an important tool that aids the design, development , optimization and control of food drying systems. Driven by the increasing needs to dry more foods with higher efficiency, sustainability, better food quality and safety, various novel drying technologies have been developed, and food drying modeling approaches have also evolved significantly. In this review, progresses and advancements in empirical, mechanistic, and machine learning (ML) modeling approaches in food drying processes toward Multiphysics, multiphase, multidimensional, and intelligent directions are over-viewed. Several challenges, needs, and future trends are identified and discussed, which includes multiscale modeling, shape change and structure deformation, coupling of food reaction kinetics, intelligent control and digitalization, translation, and dissemination of mod-eling results. The materials presented here aim to emphasize the importance of food drying modeling for addressing the key food challenges and attract more food scientists and engineers to contribute to improve food drying models and a more sustainable food production system. ARTICLE HISTORY
