FPGA implementation of neuro-fuzzy system with improved PSO learning

Karakuzu, Cihan; Karakaya, Fuat; Çavuşlu, Mehmet Ali

doi:10.1016/j.neunet.2016.02.004

Cited by 29 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimization was carried out by putting a suitability function for all the birds known as particles. The PSO have a lot of advantages including (a) a quick and easy method to solve the problems, (b) PSO is an efficient optimization style to maintain and (c) needing tiny memory to calculate the best position and find the best solution (Chakraborty et al, , Karakuzu et al, ). The position and speed of a particle during the drying process are explained by the follwing algebraic equations (Koopialipoor, Fallah, Armaghani, Azizi, & Mohamad, ):

V_{new} = w * V + C_{1} r_{1} ((), P_{best} - X) + C_{2} r_{2} ((), g_{best} - X)

X_{new} = X + V_{new}

…”

Section: Methodsmentioning

confidence: 99%

“…The PSO technique as a standard optimization method is inspired by the interactive social behavior of some animal species, such as fish and birds to a food source (Chakraborty, Sarma, Bora, Faisal, & Hazarika, ; Karakuzu et al, ). In PSO, the bird is assumed as a feasible solution in the searching space.…”

Section: Methodsmentioning

confidence: 99%

“…The PSO algorithm shares many basic principles with genetic algorithm to compute quickly the problems. PSO with a stochastic global search feature, was initially developed for optimization of the constraint non‐convex problems as well as it was inspired using manner of animal swarms so that has been applied for neural and neuro‐fuzzy network training and solving of nonlinear problems (Chang, ; Karakuzu, Karakaya, & Cavuslu, ). The PSO is one of the most usually utilized evolutionary variants in hybrid techniques because of its capability of searching global optimum, convergence speed, and simplicity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Taghinezhad

Kaveh

Jahanbakhshi

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

In the study, drying process of quince fruit was accomplished in a microwave‐convective dryer (MCD). The experiments were carried out at microwave power levels of 100, 200, and 300 W, air temperatures of 40, 55, and 70°C, and air velocities of 0.5, 1, and 1.5 m/s. Nevertheless, three artificial intelligence techniques consisted of artificial neural networks (ANNs), particle swarm optimizer (PSO), and grey wolf optimizer (GWO) were evaluated to predict the parameters of Deff, SEC, ΔE, and Sb. In the evaluation the data by ANNs, input parameters of networks consisted the values of air temperature, microwave power, and air velocity. According to the results, the maximum values of effective moisture diffusivity ( Deff) and specific energy consumption (SEC) were 1.71 × 10−9 m2/s and 126.07 kWh/kg, respectively. In addition, minimum values of total change in color (ΔE) and shrinkage ( Sb) of quince achieved 10.85 and 33.85%, respectively. For predicting all parameters, three models used in the study represented good predictive capability with R2 > 0.97. The obtained results showed that the GWO model had better predictive performance than the ANN and PSO models. Practical Application Drying food and agricultural products by application of microwave‐hot air blend dryers can be a good alternative to hot air and microwave dryers. Microwave energy infiltrates the product and facilitates heat release from the product and thus reduces drying time compared to single dryers. The main aim of applying such different models, mathematical simulation or modeling in the drying technology of agricultural products is to transform physical qualities and their interactions into numerical quantities and mathematical relationships.

show abstract

V_{new} = w * V + C_{1} r_{1} ((), P_{best} - X) + C_{2} r_{2} ((), g_{best} - X)

X_{new} = X + V_{new}

…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Taghinezhad

Kaveh

Jahanbakhshi

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…These algorithms have recently emerged as a family of nature-inspired, population-based algorithms capable of producing low-cost, fast, and robust solutions to various complex problems [14]. Particle swarm optimization (PSO) was successfully applied to neuro-fuzzy or neural network training [15]. Zhao et al [16] proposed a selfadaptive harmony PSO search algorithm to solve global continuous optimization problems.…”

Section: Introductionmentioning

confidence: 99%

PSO-Based Fuzzy Markup Language for Student Learning Performance Evaluation and Educational Application

Lee

Wang

et al. 2018

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Fuzzy relationships exist between students' learning performance with various abilities and a test item. However, the challenges in implementing adaptive assessment agents are obtaining sufficient items, efficient and accurate computerized estimation, and a substantial feedback agent. Additionally, the agent must immediately estimate students' ability item by item, which places a considerable burden on the server, especially for a group test. Hence, the implementation of adaptive assessment agent is more difficult in practice. This paper proposes an agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for students' learning performance evaluation and educational applications, and the proposed agent is according to the response data from a conventional test and an item response theory (IRT)-based three-parameter logistic (3PL) model. First, we apply a Gauss-Seidel (GS)-based parameter estimation mechanism to estimate the items' parameters according to the response data, and then to compare its results with those of an IRTbased Bayesian parameter estimation mechanism. In addition, we propose a static-IRT test assembly mechanism to assemble a form for the conventional test. The presented FML-based dynamic assessment mechanism infers the probability of making a correct response to the item for a student with various abilities. Moreover, this paper also proposes a novel PSO-based FML (PFML) learning mechanism for optimizing the parameters between items and students. Finally, we adopt a K-fold cross validation mechanism to evaluate the performance of the proposed agent. Experimental results show that the novel PFML learning mechanism for the parameter estimation and learning optimization performs favorably. We believe the proposed PFML will be a reference for education research and pedagogy and an important co-learning mechanism for future human-machine educational applications. Index Terms-Dynamic assessment, Fuzzy Markup Language (FML), Genetic FML (GFML), item response theory (IRT), particle swarm optimization (PSO)The authors would like to thank the financial support sponsored by 1) Ministry

show abstract

“…In the PSO, social behavior of individuals of fish and bird swarms were mathematically modelled. Besides the PSO, many optimization algorithms such as artificial neural network [2,3], ant colony optimization (ACO) [4], moth-flame optimization (MFO) algorithm [5], artificial bee colony (ABC) algorithm [6] ,firefly algorithm [7], sine-cosine algorithm (SCA) [8], genetic algorithm (GA) [9], bat algorithm (BA) [10], differential evaluation (DE) [11], biogeography-based optimization (BBO) [12] , harmony search (HS) [13], gravitational search algorithm (GSA) [14], krill herd algorithm (KH) [15], etc were proposed in the literature. The main aim of these algorithms to find global optima value but some of them trapped local optima values.…”

Section: Introductionmentioning

confidence: 99%

SCSO: A novel sine-cosine based swarm optimization algorithm for numerical function optimization

Tuncer

2018

PEN

View full text Add to dashboard Cite

Many swarm optimization algorithms have been presented in the literature and these algorithms are generally nature-inspired algorithms. In this paper a novel sine-cosine based particle swarm optimization (SCSO) is presented. In SCSO, firstly particles are generated randomly in the search space. Personal best value and velocity of the particles are calculated and by using sine, cosine and difference valuee. Calculated velocity is used for updating particles. The proposed algorithm is basic algorithm and approximately 30 rows MATLAB codes are used to implement the proposed algorithm. This short code surprisingly has high optimization capability. In order to evaluate performance and prove success of this algorithm, 14 well known numerical functions was used and the results illustrate that the proposed algorithm is successful in numerical functions optimization.

show abstract

FPGA implementation of neuro-fuzzy system with improved PSO learning

Cited by 29 publications

References 21 publications

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

Use of artificial intelligence for the estimation of effective moisture diffusivity, specific energy consumption, color and shrinkage in quince drying

PSO-Based Fuzzy Markup Language for Student Learning Performance Evaluation and Educational Application

SCSO: A novel sine-cosine based swarm optimization algorithm for numerical function optimization

Contact Info

Product

Resources

About