scholarly journals Human Skeleton Detection and Extraction in Dance Video Based on PSO-Enabled LSTM Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Dingxin Li
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Data Sets ◽  
Market Demand ◽  
Human Skeleton ◽  
Data Set ◽  
Swarm Optimization ◽  
The Neural Network ◽  
Average Accuracy

With the significant increase of social informatization, the emerging information technology represented by machine vision has been applied to more and more scenes. Among them, the detection and extraction of human skeleton in a dance video based on this technology has a huge market demand in education and training. However, the existing detection and extraction technology has the problems of slow recognition speed and low extraction accuracy. Therefore, this paper proposes a neural network based on particle swarm optimization to detect and extract human skeletons in a dance video. Through the research and test on different data sets, it is found that the neural network based on particle swarm optimization algorithm has good detection and extraction ability and has high accuracy for the detection and recognition of human skeleton points. Among them, on all MPII data sets, the average accuracy of PSO-LSTM proposed in this paper is 3.9% higher than that of other optimal algorithms; on the PoseTrack data set, the average accuracy of detection and extraction is improved by 2.3%. The above results show that the neural network based on particle swarm optimization has fast detection speed and good extraction accuracy and can be used for the detection and extraction of human skeleton in a dance video.

scholarly journals SELEKSI FITUR ALGORITMA NEURAL NETWORK MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK MEMPREDIKSI KELAHIRAN PREMATUR

Kilat ◽  
2018 ◽  
Vol 6 (2) ◽  
pp. 106-111
Author(s):  
Redaksi Tim Jurnal
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Preterm Birth ◽  
Sensitivity And Specificity ◽  
Particle Swarm ◽  
Data Set ◽  
Swarm Optimization ◽  
Network Algorithm ◽  
The Neural Network ◽  
Neural Network Algorithm

Premature birth, defined as delivery in pregnant women with gestation age 20 - 36 weeks. Research related to preterm birth has been done by the researchers by using the neural network method. However such research only showcase about the results of the sensitivity and specificity. The results of research using the method of neural network in predicting preterm birth has a value of the resulting accuracy is still less accurate and only limited to presenting the results of the sensitivity and specificity. In this study produced a model of the neural network algorithm and model of neural network algorithm based on particle swarm optimization to get the architecture in predicting preterm birth and gives a more accurate value for accuracy on a data set of RSUPN Cipto Mangunkusumo , RS Sumber Waras and in its entirety. After you are done testing with two models of neural network algorithms and neural network algorithm based on particle swarm optimization and the results obtained are the neural network algorithm generates value accuracy of 94,60%, 96,40%, 91,33%, and AUC values of 0,973, 0,982, 0,953, however, after the addition of the neural network algorithm based on particle swarm optimization value accuracy of 95,20%, 96,80%, 92,40% and AUC values of 0,979 , 0,987, 0,965. So both of these methods has the distinction of accuracy which amounted to 0.60%, 0.40%, 1.07% and AUC value difference of 0.006, 0.005, 0.012.

scholarly journals Feature Selection Based on BP Neural Network and Adaptive Particle Swarm Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Bingsheng Chen ◽  
Huijie Chen ◽  
Mengshan Li
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Particle Swarm Optimization ◽  
Optimization Algorithm ◽  
Bp Neural Network ◽  
Particle Swarm Optimization Algorithm ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Data Sets ◽  
Swarm Optimization

Feature selection can classify the data with irrelevant features and improve the accuracy of data classification in pattern classification. At present, back propagation (BP) neural network and particle swarm optimization algorithm can be well combined with feature selection. On this basis, this paper adds interference factors to BP neural network and particle swarm optimization algorithm to improve the accuracy and practicability of feature selection. This paper summarizes the basic methods and requirements for feature selection and combines the benefits of global optimization with the feedback mechanism of BP neural networks to feature based on backpropagation and particle swarm optimization (BP-PSO). Firstly, a chaotic model is introduced to increase the diversity of particles in the initial process of particle swarm optimization, and an adaptive factor is introduced to enhance the global search ability of the algorithm. Then, the number of features is optimized to reduce the number of features on the basis of ensuring the accuracy of feature selection. Finally, different data sets are introduced to test the accuracy of feature selection, and the evaluation mechanisms of encapsulation mode and filtering mode are used to verify the practicability of the model. The results show that the average accuracy of BP-PSO is 8.65% higher than the suboptimal NDFs model in different data sets, and the performance of BP-PSO is 2.31% to 18.62% higher than the benchmark method in all data sets. It shows that BP-PSO can select more distinguishing feature subsets, which verifies the accuracy and practicability of this model.

Modeling and Optimisation of Xylose Production by Enzymatic Hydrolysis using Neural Network and Particle Swarm Optimization

2015 ◽  
Vol 10 (3) ◽  
pp. 173-178 ◽  
Author(s):  
Nur Atiqah Nurhalim ◽  
Mashitah Mat Don ◽  
Zainal Ahmad ◽  
Dipesh S. Patle
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Enzymatic Hydrolysis ◽  
Particle Swarm ◽  
Agitation Speed ◽  
Process Conditions ◽  
Optimum Conditions ◽  
Swarm Optimization ◽  
The Neural Network ◽  
Hydrolysis Process

Abstract Particle swarm optimization (PSO) method is used for the optimization of an enzymatic hydrolysis process for the production of xylose from rice straw. The enzymatic hydrolysis process conditions such as temperature, agitation speed and concentration of enzyme were optimized by using PSO to obtain the optimum yield of xylose. Data collected from an experimental design using response surface methodology were necessitated to develop the neural network modeling. The neural network model is used as a model in objective function of PSO to predict the optimum conditions, which involved in the enzymatic hydrolysis process. The optimum value is obtained from the performance of the best particle swarm among the optimum conditions in PSO. The predicted optimum values were validated through the experiment of the enzymatic hydrolysis process. The optimum temperature, agitation speed and xylanase concentration is observed to be 50.3°C, 132 rpm and 1.6474 mg/ml, respectively. The optimal yield of xylose is predicted as 0.1845 mg/ml using PSO.

scholarly journals Particle Swarm Optimization pada Analisa Review Software Antivirus Menggunakan Metode K-Nearest Neighbors

2020 ◽  
Vol 4 (2) ◽  
pp. 123
Author(s):  
Sucitra Sahara ◽  
Rizqi Agung Permana ◽  
Hariyanto Hariyanto
Keyword(s):  
Particle Swarm Optimization ◽  
Text Mining ◽  
Nearest Neighbor ◽  
Particle Swarm ◽  
Optimization Method ◽  
Data Sets ◽  
K Nearest Neighbor ◽  
Process Data ◽  
Data Set ◽  
Swarm Optimization

Abstrak: Virus pada komputer menjadi hal yang membahayakan bagi para pengguna komputer perorangan maupun perusahaan yang telah menerapkan sistem terkomputerisasi. Virus program yang didesain untuk tujuan jahat dapat merusak bagian tertentu dari komputer, bahkan yang paling merugikan adalah dapat merusak data penting pada perusahaan. Dalam hal ini maka diciptakanlah sebuah software anti virus, perkembangan anti virus selalu lebih lambat dari virus itu sendiri, sehingga peneliti akan mengadakan penyeleksian software anti virus pada suatu opini atau berdasarkan komentar masyarakat yang telah menggunakan software anti virus produk tertentu dan dituangkan ke media online seperti komentar pada suatu situs penjualan produk tersebut. Berdasarkan ribuan komentar akan diolah dan dikelompokkan pada jenis kata teks positif dan teks negatif, dan peneliti membuat klasifikasi data dengan menggunakan metode algoritma k-Nearest Neighbor (k-NN), algoritma k-NN adalah salah satu algoritma yang sesuai dalam penelitian kali ini. Peneliti menemukan bahwa algoritma k-NN mampu mengolah data set yang sudah dikelompokan pada teks positif dan negatif khususnya dalam pemilihan teks, dan penerapan metode optimasi Particle Swarm Optimization (PSO) yang dikombinasikan dengan k-NN diharapkan mampu meningkatkan nilai akurasi sehingga datanya lebih kuat dan valid. Sebelum data set diolah menggukanan optimasi PSO hanya menggunakan metode k-NN akurasi data yang diperoleh 70,50% sedangkan hasil akurasi setelah penggunaan metode k-nn dan optimasi PSO didapatkan nilai akurasi sebesar 83,50%. Dapat disimpulkan bahwa penggunaan optimasi PSO dan metode k-NN sangat sesuai pada konsep text mining dan  penyeksian pada data set berupa text. Kata kunci: Analisis Review, Optimasi Particle Swarm Optimization, Metode k-Nearest Neighbor.   Abstract: Viruses on computers become dangerous for individual computer users and companies that have implemented computerized systems. Virus programs that are designed for malicious purposes can damage certain parts of the computer, even the most detrimental is that it can damage important data on the company. In this case an anti-virus software is created, the development of anti-virus is always slower than the virus itself, so researchers will conduct an anti-virus software selection on an opinion or based on public comments that have used a particular product's anti-virus software and poured it into online media such as comment on a product sales site. Of the thousands of comments will be processed and grouped on the type of positive and negative text words, and researchers make data classification using the k-Nearest Neighbor (k-NN) algorithm method, the k-NN algorithm is one of the appropriate algorithms in this study. The researcher found that the k-NN algorithm is able to process data sets that have been grouped in positive and negative texts, especially in text selection, and the application of the Particle Swarm Optimization (PSO) optimization method combined with k-NN is expected to be able to increase the accuracy value so that the data is stronger and valid. Before the data set is processed using PSO optimization only using the k-NN method the accuracy of the data obtained is 70.50% while the accuracy results after the use of the k-nn method and PSO optimization obtained an accuracy value of 83.50%. It can be concluded that the use of PSO optimization and the k-NN method are very compatible with the concept of text mining and correction of text data sets. Keywords: Analysis Review, k-Nearest Neighbor Method, Particle Swarm Optimization optimization

A Unified Feature Selection Model for High Dimensional Clinical Data Using Mutated Binary Particle Swarm Optimization and Genetic Algorithm

2018 ◽  
Vol 13 (4) ◽  
pp. 1-14 ◽  
Author(s):  
Thendral Puyalnithi ◽  
Madhuviswanatham Vankadara
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Particle Swarm Optimization ◽  
Clinical Data ◽  
Particle Swarm ◽  
Binary Particle Swarm Optimization ◽  
Data Sets ◽  
Data Set ◽  
Swarm Optimization ◽  
Binary Genetic Algorithm

This article contends that feature selection is an important pre-processing step in case the data set is huge in size with many features. Once there are many features, then the probability of existence of noisy features is high which might bring down the efficiency of classifiers created out of that. Since the clinical data sets naturally having very large number of features, the necessity of reducing the features is imminent to get good classifier accuracy. Nowadays, there has been an increase in the use of evolutionary algorithms in optimization in feature selection methods due to the high success rate. A hybrid algorithm which uses a modified binary particle swarm optimization called mutated binary particle swarm optimization and binary genetic algorithm is proposed in this article which enhanced the exploration and exploitation capability and it has been a verified with proposed parameter called trade off factor through which the proposed method is compared with other methods and the result shows the improved efficiency of the proposed method over other methods.

Application of Artificial Neural Network–Particle Swarm Optimization Algorithm for Prediction of Gas Condensate Dew Point Pressure and Comparison With Gaussian Processes Regression–Particle Swarm Optimization Algorithm

2016 ◽  
Vol 138 (3) ◽  
Author(s):  
Abbas Khaksar Manshad ◽  
Habib Rostami ◽  
Seyed Moein Hosseini ◽  
Hojjat Rezaei
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Equations Of State ◽  
Particle Swarm ◽  
Gas Condensate ◽  
Dew Point ◽  
Data Sets ◽  
Swarm Optimization ◽  
Unseen Data ◽  
Point Pressure

For gas condensate reservoirs, as the reservoir pressure drops below the dew point pressure (DPP), a large amount of valuable condensate drops out and remains in the reservoir. Thus, prediction of accurate values for DPP is important and leads to successful development of gas condensate reservoirs. There are some experimental methods such as constant composition expansion (CCE) and constant volume depletion (CVD) for DPP measurement but difficulties in experimental measurement especially for lean retrograde gas condensate causes to develop of different empirical correlations and equations of state for DPP calculation. Equations of state and empirical correlations are developed for special and limited data sets and for unseen data sets they are not generalizable. To mitigate this problem, in this paper we developed new artificial neural network optimized by particle swarm optimization (ANN-PSO) for DPP prediction. Reservoir fluid composition, temperature and characteristics of the C7+ considered as input parameters to neural network and DPP as target parameter. Comparing results of the developed model in this research with Gaussian processes regression by particle swarm optimization (GPR-PSO), previous models and correlations shows that the predictive model is accurate and is generalizable to new unseen data sets.

scholarly journals Optimization of lapping process parameters of CP-Ti based on PSO with mutation and BPNN

2021 ◽  
Author(s):  
Kaiqiang Ye ◽  
Jianbin Wang ◽  
Hong Gao ◽  
Liu Yang ◽  
Ping Xiao
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Process Parameters ◽  
Particle Swarm ◽  
Process Parameter ◽  
Optimal Process ◽  
Swarm Optimization ◽  
The Neural Network ◽  
Cp Ti ◽  
Optimal Process Parameter

Abstract This work aims to improve the surface quality of commercially pure titanium (CP-Ti) with free alumina lapping fluid and establish the relationship between the main process parameters of lapping and roughness. On this basis, the optimal process parameters were searched by performing particle swarm optimization with mutation. First, free alumina lapping fluid was used to perform an L9(33) orthogonal experiment on CP-Ti to acquire data samples to train the neural network. At the same time, a BP neural network was created to fit the nonlinear functional relation among the lapping pressure P, spindle speed n, slurry flow Q and roughness Ra. Then, the range of the node numbers in the hidden layer of the neural network was determined by empirical formulas and the Kolmogorov theorem. On this basis, particle swarm optimization with mutation was used to search for the optimal process parameter configurations for lapping CP-Ti. The optimal process parameter configurations were used in the neural network to calculate the prediction value. Finally, the accuracy of the prediction was verified experimentally. The optimum process parameter configurations found by particle swarm optimization were as follows: the lapping pressure was 5 kPa, spindle speed was 60 r·min− 1 and slurry flow was 50 ml·min− 1. Then, the configurations were applied to a neural network to simulate prediction: the roughness was 0.1127 µm. The roughness obtained by experiments was 0.1134 µm. The error was 0.62%, which indicates that the well-trained neural network can achieve a good prediction when experimental data are missing. Applying the particle swarm optimization (PSO) algorithm with mutation to a neural network will obtain the optimal process parameter configurations, which can effectively improve the surface quality of CP-Ti lapped with free abrasive.

A Unified Feature Selection Model for High Dimensional Clinical Data Using Mutated Binary Particle Swarm Optimization and Genetic Algorithm

2021 ◽  
pp. 50-64
Author(s):  
Thendral Puyalnithi ◽  
Madhuviswanatham Vankadara
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Particle Swarm Optimization ◽  
Clinical Data ◽  
Particle Swarm ◽  
Binary Particle Swarm Optimization ◽  
Data Sets ◽  
Data Set ◽  
Swarm Optimization ◽  
Binary Genetic Algorithm

This article contends that feature selection is an important pre-processing step in case the data set is huge in size with many features. Once there are many features, then the probability of existence of noisy features is high which might bring down the efficiency of classifiers created out of that. Since the clinical data sets naturally having very large number of features, the necessity of reducing the features is imminent to get good classifier accuracy. Nowadays, there has been an increase in the use of evolutionary algorithms in optimization in feature selection methods due to the high success rate. A hybrid algorithm which uses a modified binary particle swarm optimization called mutated binary particle swarm optimization and binary genetic algorithm is proposed in this article which enhanced the exploration and exploitation capability and it has been a verified with proposed parameter called trade off factor through which the proposed method is compared with other methods and the result shows the improved efficiency of the proposed method over other methods.

Optimization Algorithms

2014 ◽  
pp. 182-199 ◽  
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Learning Enhancement ◽  
Swarm Optimization ◽  
Neural Network Learning ◽  
The Neural Network ◽  
Intelligent Behavior ◽  
Definition Of

In this chapter, the basic definition of Genetic Algorithm (GA) and some of the main operations applied in GA are explained. In addition, Swarm Intelligence (SI) is briefly explained as the new branch of intelligent behavior of nature phenomena. Although PSO has been explained in past chapters, this chapter explains PSO in detail and an example of the way PSO works is provided for better understanding. Some of the differences of Particle Swarm Optimization (PSO) and GA are provided and readers will learn how to use GA and PSO for training the neural network. The experiments and contents in this chapter are from the study by Nuzly (2006) in her thesis entitled “Particle Swarm Optimization for Neural Network Learning Enhancement”.

Sign in / Sign up

Export Citation Format

Share Document