A New Breakpoint in Hybrid Particle Swarm-Neural Network Architecture: Individual Boundary Adjustment

2016 ◽  
Vol 15 (06) ◽  
pp. 1313-1343 ◽  
Author(s):  
Rahime Ceylan ◽  
Hasan Koyuncu
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Processing Time ◽  
Particle Swarm ◽  
Hybrid Structure ◽  
Classification Performance ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Stochastic Optimization Algorithms ◽  
Accuracy Rates

Neural Network (NN) is an effective classifier, but it generally uses the Backpropagation type algorithms which are insufficient because of trapping to local minimum of error rate. For elimination of this handicap, stochastic optimization algorithms are used to update the parameters of NN. Particle Swarm Optimization (PSO) is one of these providing a robust coherence with NN. In realized studies about Hybrid PSO-NN, position and velocity boundaries of weight and bias are chosen equal or set free in space which leave the performance of PSO-NN in suspense. In this paper, the limitations of weight velocity (wv), weight position (wp), bias velocity (bv) and bias position (bp) are diversely changed and their effects on the output of hybrid structure are examined. Concerning this, the formed structure is called as Bounded PSO-NN on account of adjusting the optimum operating conditions (intervals). On performance evaluation, proposed method is tested on binary and multiclass pattern classification by using six medical datasets: Wisconsin Breast Cancer (WBC), Pima Indian Diabetes (PID), Bupa Liver Disorders (BLD), Heart Statlog (HS), Breast Tissue (BT) and Dermatology Data (DD). Upon analyzing the results, it was revealed that Bounded PSO-NN has a faster processing time than general PSO-NNs in which set-free and wpi[Formula: see text]bpi and wvi[Formula: see text]bvi conditions are settled. The superiority in terms of processing time is about 199[Formula: see text]s (set-free) and 307[Formula: see text]s (wpi[Formula: see text]bpi and wvi[Formula: see text]bvi) for training, about 16[Formula: see text]ms (set-free) and 9[Formula: see text]ms (wpi[Formula: see text]bpi and wvi[Formula: see text]bvi) for test. In terms of classification performance, PSO-NN (set-free condition), PSO-NN (wpi[Formula: see text]bpi & wvi[Formula: see text]bvi) and PSO-NN with individual boundary adjustment (bounded PSO-NN) respectively achieves to accuracy rates as 69.84%, 95.31% and 97.22% on WBC, 47.01%, 76.69% and 77.73% on PID, 55.36%, 67.54% and 73.91% on BLD, 64.82%, 81.48% and 85.56% on HS, 75%, 92.31% and 100% on BT, 27.47%, 92.31% and 100% on DD. In the light of experiments, it is seen that Bounded PSO-NN is better than general PSO-NNs for obtaining the optimum results. Consequently, the importance of limitations is clarified and it is proven that each limitation must be adjusted individually, not be set free or not be chosen equal.

Search for Optimum Operating Conditions for a Water Purification Process Integrated to a Heat Transformer with Energy Recycling using Artificial Neural Network Inverse Solved by Genetic and Particle Swarm Algorithms

2012 ◽  
Vol 7 (1) ◽  
Author(s):  
Youness El Hamzaoui ◽  
Bassam Ali ◽  
J. Alfredo Hernandez ◽  
Obed Cortez Aburto ◽  
Outmane Oubram
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Purification ◽  
Particle Swarm ◽  
Optimization Methods ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Purification Process ◽  
Artificial Neural ◽  
Heat Transformer

The coefficient of performance (COP) for a water purification process integrated to an absorption heat transformer with energy recycling was optimized using the artificial intelligence. The objective of this paper is to develop an integrated approach using artificial neural network inverse (ANNi) coupling with optimization methods: genetic algorithms (GAs) and particle swarm algorithm (PSA). Therefore, ANNi was solved by these optimization methods to estimate the optimal input variables when a COP is required. The paper adopts two cases studies to accomplish the comparative study. The results illustrate that the GAs outperforms the PSA. Finally, the study shows that the GAs based on ANNi is a better optimization method for control on-line the performance of the system, and constitutes a very promising framework for finding a set of “good solutions”.

Predictive Emission Monitoring Model for LM1600 Gas Turbines Based on Neural Network Architecture Trained on Field Measurements and CFD Data

2001 ◽  
Author(s):  
K. K. Botros ◽  
G. R. Price ◽  
G. Kibrya
Keyword(s):  
Neural Network ◽  
Ambient Temperature ◽  
Gas Turbines ◽  
Network Architecture ◽  
Absolute Error ◽  
Operating Conditions ◽  
Maximum Absolute Error ◽  
Flamelet Model ◽  
Emission Monitoring ◽  
One Year

A Predictive Emission Monitoring (PEM) model has been developed based on an optimized Neural Network (NN) architecture which takes 8 fundamental parameters as input variables. The model predicts both NO and NOx as output variables. The NN is initially trained using a combination of two sets of data: a) measured data at various loads from an LM1600 gas turbine installed at one of the compressor stations on TransCanada Transmission system in Alberta, Canada, b) data generated by a Computational Fluid Dynamics (CFD) at different operating conditions covering the range of the engine operating parameters spanned over one year. The predictions of NOx by CFD employed the ‘flamelet’ model and a set of 8 reactions including the Zeldovich mechanism for thermal NOx along with an empirical correlation for prompt NOx formation. It was found that a Multi Layer Perceptron type Neural Network with two hidden layers was the optimum architecture for predicting NO levels with a maximum absolute error of around 7%, mean absolute error of 2.3% and standard deviation of 1.97%. The model is easy to implement on the station PLC. A set of one year data consisting of 2804 cases was submitted to the above optimized NN architecture with varying ambient temperature from –29.9 °C to 35.7 °C and output power from 570 kW to 16.955 MW. This gave consistent contours of NO levels. As expected, NN architecture shows that NO increases with increasing power or ambient temperature.

scholarly journals Fixed bed utilization for the isolation of xylene vapor: Kinetics and optimization using response surface methodology and artificial neural network

2020 ◽  
Vol 26 (2) ◽  
pp. 200105-0
Author(s):  
Kaushal Naresh Gupta ◽  
Rahul Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface Methodology ◽  
Response Surface ◽  
Flow Rate ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Operating Parameters ◽  
Bed Height ◽  
Artificial Neural

This paper discusses the isolation of xylene vapor through adsorption using granular activated carbon as an adsorbent. The operating parameters investigated were bed height, inlet xylene concentration and flow rate, their influence on the percentage utilization of the adsorbent bed up to the breakthrough was found out. Mathematical modeling of experimental data was then performed by employing a response surface methodology (RSM) technique to obtain a set of optimum operating conditions to achieve maximum percentage utilization of bed till breakthrough. A fairly high value of R2 (0.993) asserted the proposed polynomial equation’s validity. ANOVA results indicated the model to be highly significant with respect to operating parameters studied. A maximum of 76.1% utilization of adsorbent bed was found out at a bed height of 0.025 m, inlet xylene concentration of 6,200 ppm and a gas flow rate of 25 mL.min-1. Furthermore, the artificial neural network (ANN) was also employed to compute the percentage utilization of the adsorbent bed. A comparison between RSM and ANN divulged the performance of the latter (R2 = 0.99907) to be slightly better. Out of various kinetic models studied, the Yoon-Nelson model established its appropriateness in anticipating the breakthrough curves.

scholarly journals Xbee-Based WSN Architecture for Monitoring of Banana Ripening Process Using Knowledge-Level Artificial Intelligent Technique

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4033 ◽  
Author(s):  
Saud Altaf ◽  
Shafiq Ahmad ◽  
Mazen Zaindin ◽  
Muhammad Waseem Soomro
Keyword(s):  
Neural Network ◽  
Fruit Ripening ◽  
Network Architecture ◽  
Architectural Design ◽  
Back Propagation ◽  
Classification Performance ◽  
Sensor Nodes ◽  
Present Condition ◽  
Wireless Sensor ◽  
Intelligent Technique

Real-time monitoring of fruit ripeness in storage and during logistics allows traders to minimize the chances of financial losses and maximize the quality of the fruit during storage through accurate prediction of the present condition of fruits. In Pakistan, banana production faces different difficulties from production, post-harvest management, and trade marketing due to atmosphere and mismanagement in storage containers. In recent research development, Wireless Sensor Networks (WSNs) are progressively under investigation in the field of fruit ripening due to their remote monitoring capability. Focused on fruit ripening monitoring, this paper demonstrates an Xbee-based wireless sensor nodes network. The role of the network architecture of the Xbee sensor node and sink end-node is discussed in detail regarding their ability to monitor the condition of all the required diagnosis parameters and stages of banana ripening. Furthermore, different features are extracted using the gas sensor, which is based on diverse values. These features are utilized for training in the Artificial Neural Network (ANN) through the Back Propagation (BP) algorithm for further data validation. The experimental results demonstrate that the projected WSN architecture can identify the banana condition in the storage area. The proposed Neural Network (NN) architectural design works well with selecting the feature data sets. It seems that the experimental and simulation outcomes and accuracy in banana ripening condition monitoring in the given feature vectors is attained and acceptable, through the classification performance, to make a better decision for effective monitoring of current fruit condition.

scholarly journals Neural Model with Particle Swarm Optimization Kalman Learning for Forecasting in Smart Grids

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Alma Y. Alanis ◽  
Luis J. Ricalde ◽  
Chiara Simetti ◽  
Francesca Odone
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Particle Swarm Optimization ◽  
Smart Grids ◽  
Network Architecture ◽  
Particle Swarm ◽  
Design Parameters ◽  
Complex Nature ◽  
Training Algorithm ◽  
Swarm Optimization

This paper discusses a novel training algorithm for a neural network architecture applied to time series prediction with smart grids applications. The proposed training algorithm is based on an extended Kalman filter (EKF) improved using particle swarm optimization (PSO) to compute the design parameters. The EKF-PSO-based algorithm is employed to update the synaptic weights of the neural network. The size of the regression vector is determined by means of the Cao methodology. The proposed structure captures more efficiently the complex nature of the wind speed, energy generation, and electrical load demand time series that are constantly monitorated in a smart grid benchmark. The proposed model is trained and tested using real data values in order to show the applicability of the proposed scheme.

scholarly journals Particle Swarm Optimization to Obtain Weights in Neural Network

MATEMATIKA ◽  
2019 ◽  
Vol 35 (3) ◽  
Author(s):  
Budi Warsito ◽  
Hasbi Yasin ◽  
Alan Prahutama
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Network Model ◽  
Neural Network Model ◽  
Network Architecture ◽  
Optimization Technique ◽  
Particle Swarm ◽  
Feed Forward Neural Network ◽  
Swarm Optimization ◽  
Hidden Layer

This research discusses the use of a class of heuristic optimization to obtain the weights in neural network model for time series prediction. In this case, Feed Forward Neural Network (FFNN) was chosen as the class of network architecture. The heuristic algorithm determined to obtain the weights in network was Particle Swarm Optimization (PSO). It is a non-gradient optimization technique. This method was used for optimizing the connection weights of network. The lags used as the input were selected based on the strong relationship with the current. The eight architectures were conducted to improve the accuracy of the neural network model. In each architecture, we repeated the running thirty times to get the statistics of mean and variance. The comparison of the performance of various architectures based on the minimum MSE and the stability of the results is presented in this paper. The optimal number of neurons in hidden layer was determined by these criteria. The proposed procedure was applied in air pollution data, i.e. Solid Particulate Matter (SPM). The results showed that the proposed procedure gave promising results in terms of prediction accuracy. A few neurons in hidden layer are strongly recommended in choosing the optimal architecture.

scholarly journals A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5672
Author(s):  
Vahid Tavakkoli ◽  
Kabeh Mohsenzadegan ◽  
Kyandoghere Kyamakya
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Classification Performance ◽  
Suitable Model ◽  
Classification Models ◽  
Visual Sensing ◽  
Previous State ◽  
Low Performance ◽  
Complex Features

The core objective of this paper is to develop and validate a comprehensive visual sensing concept for robustly classifying house types. Previous studies regarding this type of classification show that this type of classification is not simple (i.e., tough) and most classifier models from the related literature have shown a relatively low performance. For finding a suitable model, several similar classification models based on convolutional neural network have been explored. We have found out that adding/involving/extracting better and more complex features result in a significant accuracy related performance improvement. Therefore, a new model taking this finding into consideration has been developed, tested and validated. The model developed is benchmarked with selected state-of-art classification models of relevance for the “house classification” endeavor. The test results obtained in this comprehensive benchmarking clearly demonstrate and validate the effectiveness and the superiority of our here developed deep-learning model. Overall, one notices that our model reaches classification performance figures (accuracy, precision, etc.) which are at least 8% higher (which is extremely significant in the ranges above 90%) than those reached by the previous state-of-the-art methods involved in the conducted comprehensive benchmarking.

Sign in / Sign up

Export Citation Format

Share Document