Application of Particle Swarm Optimization Algorithm for Optimizing ANN Model in Recognizing Ripeness of Citrus

Rosli, Anis Diyana; Adenan, Nur Sabrina; Hashim, Hadzli; Abdullah, Noor Ezan; Sulaiman, Saiful Aman; Baharudin, Rohaiza

doi:10.1088/1757-899x/340/1/012015

Cited by 9 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PSO algorithm is one of the most particularly popular, which shows good performance in terms of global search ability and convergence speed [21]. It has been successfully used to solve problems in various areas such as healthcare [22], finance [23]- [24], telecommunications [25]- [26], energy [27]- [28], image thresholding [29] and others [30]- [31]. Despite its good results, the PSO method encounter a premature convergence when solving a complex optimization problem, this is due to the improper balance between the local and global searches.…”

Section: Research and Application Of Transient Electromagnetic Methods Inversion Technique Based On Particle Swarm Optimization Algorithmmentioning

confidence: 99%

Research and Application of the Transient Electromagnetic Method Inversion Technique Based on Particle Swarm Optimization Algorithm

Zhang³

2020

IEEE Access

View full text Add to dashboard Cite

The transient electromagnetic (TEM) method is widely used in shallow surface engineering geological surveys due to its advantages such as light weight, high efficiency, and strong resolution. However, interpretation and inversion of TEM data is a complicated process. The traditional algorithm of TEM inversion employs the "smoke ring" fast imaging method, which can only reflect the approximate morphology of the stratigraphic model, and the inversion accuracy is low. Therefore, this method cannot meet the requirements of high-precision inversion. In this paper, we present the particle swarm optimization (PSO) algorithm for TEM inversion. First of all, the response of the rectangular loop source TEM based on electric dipole integration was calculated and compared with the analytical solution results of the rectangular loop source and the accuracy of the algorithm was verified. Then, we introduced the solution process of the particle swarm optimization algorithm and analyzed the influence of particle swarm optimization algorithm parameter selection on the accuracy of the inversion result and the convergence speed. Next, a layered medium model was established. The particle swarm optimization algorithm and "smoke ring" fast imaging method were used to perform inversion calculation. The results show that the PSO algorithm has the advantages of high efficiency and accuracy. Finally, we examined the effectiveness of the particle swarm optimization algorithm for TEM data processing by inverting survey data from an Air-raid shelter on the campus of Chongqing University in China and comparing the results with those from the "smoke ring" fast imaging. The research works in this paper provide new methods and techniques for TEM data processing.INDEX TERMS Transient electromagnetic method; particle swarm optimization algorithm; fast imaging; inversion;

show abstract

Section: Research and Application Of Transient Electromagnetic Methods Inversion Technique Based On Particle Swarm Optimization Algorithmmentioning

confidence: 99%

Research and Application of the Transient Electromagnetic Method Inversion Technique Based on Particle Swarm Optimization Algorithm

Zhang³

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In addition, their interactions lead to a constant enhancement in the quality of their interactions, which is quantified as the fitness value [62]. PSO is used to create an ANN technique for each neuron that improves synaptic mass, architecture, transfer function [63], [64].…”

Section: 3mentioning

confidence: 99%

“…In addition, for the purpose of developing computational intelligence or heuristic optimization, new Nature-inspired optimization methodologies must be regularly developed because speeding up the convergence of an algorithm remains a challenging task. [64], [84]- [86], there are other optimization methods that are used to select the suitable hyperparameters for ANN models researchers in [87] suggest utilizing variance Matrix Adaptation Evolution Strategy (CMA-ES), which is well-known for its cutting-edge efficiency in derivative-free optimization, while in [88] adapted a simpler coordinate-search and Nelder-Mead methods for the optimization of the hyper-parameters. In [25] the researchers applied RBFs as error surrogates and use an integer algorithm called (HORD) for hyper-parameter optimization that is both deterministic and efficient.…”

Section: Another Techniquementioning

confidence: 99%

Artificial Neural Network Hyperparameters Optimization: A Survey

Kadhim¹,

Abdullah²,

Ghathwan³

2022

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Machine-learning (ML) methods often utilized in applications like computer vision, recommendation systems, natural language processing (NLP), as well as user behavior analytics. Neural Networks (NNs) are one of the most es-sential ways to ML; the most challenging element of designing a NN is de-termining which hyperparameters to employ to generate the optimal model, in which hyperparameter optimization improves NN performance. This study includes a brief explanation regarding a few types of NN as well as some methods for hyperparameter optimization, as well as previous work results in enhancing ANN performance using optimization methods that aid research-ers and data analysts in developing better ML models via identifying the ap-propriate hyperparameter configurations.

show abstract

“…The research could categorize between the ripe and unripe levels of Citrus Suhuensis. The algorithm would adjust the network connections weights and adapt its values during training for the best output results [7].…”

Section: Introductionmentioning

confidence: 99%

Ripeness Level Classification of Banana Fruit Based on Hue Saturate Value (HSV) Color Space Using K-Nearest Neighbor Algorithm

2021

IJATCSE

View full text Add to dashboard Cite

Many types of bananas are cultivated locally in Indonesia, including the Muli Banana or Musa Acuminata Linn. During the post-harvest period of banana fruit, there is a problem in the sorting process of bananas based on their level of maturity. The fruit sorting process manually uses the human eye, but it is ineffective due to decreased vision and the large quantity of fruit. Therefore, we need a system that can quickly classify the ripeness of the banana fruit. This study aims to create a system that can organize the maturity level of the banana fruit. The classification system designed using the HSV color feature extraction method and the K-Nearest Neighbor classification algorithm. After going through the testing phase, the system can classify bananas into three classes: unripe, ripe, and rotten. System testing used 30 test data images, and the results show 2 test images whose classification results are wrong and 28 other test images whose classification results are correct. Based on calculations, the accuracy achieved by the system is 93.333%.

show abstract

Application of Particle Swarm Optimization Algorithm for Optimizing ANN Model in Recognizing Ripeness of Citrus

Cited by 9 publications

References 11 publications

Research and Application of the Transient Electromagnetic Method Inversion Technique Based on Particle Swarm Optimization Algorithm

Research and Application of the Transient Electromagnetic Method Inversion Technique Based on Particle Swarm Optimization Algorithm

Artificial Neural Network Hyperparameters Optimization: A Survey

Ripeness Level Classification of Banana Fruit Based on Hue Saturate Value (HSV) Color Space Using K-Nearest Neighbor Algorithm

Contact Info

Product

Resources

About