A Hybrid Learning Strategy for Real Hardware of Swing-Up Pendulum

2007 ◽  
Vol 11 (8) ◽  
pp. 972-978 ◽  
Author(s):  
Shingo Nakamura ◽  
◽  
Ryo Saegusa ◽  
Shuji Hashimoto
Keyword(s):  
Neural Network ◽  
Learning Strategy ◽  
Back Propagation ◽  
Optimal Controller ◽  
Learning Approaches ◽  
Learning Method ◽  
Data Sampling ◽  
Target Task ◽  
The Real ◽  
Real Hardware

Generally, the bottom-up learning approaches, such as neural-network, to obtain the optimal controller of target task for mechanical system face a problem including huge number of trials, which require much time and give stress against the hardware. To avoid such problems, a simulator is often built and performed with a learning method. However, there are also problems that how simulator is constructed and how accurate it performs. In this paper, we are considering a construction of simulator directly from the real hardware. Afterward a constructed simulator is used for learning target task and the obtained optimal controller is applied to the real hardware. As an example, we picked up the pendulum swing-up task which was a typical nonlinear control problem. The construction of a simulator is performed by back-propagation method with neural-network and the optimal controller is obtained by reinforcement learning method. Both processes are implemented without using the real hardware after the data sampling, therefore, load against the hardware gets sufficiently smaller, and the objective controller can be obtained faster than using only the hardware. And we consider that our proposed method can be a basic learning strategy to obtain the optimal controller of mechanical systems.

scholarly journals A Damage Detection Method Using Neural Network Optimized by Multiple Particle Collision Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Sergio V. Farias ◽  
Osamu Saotome ◽  
Haroldo F. Campos Velho ◽  
Elcio H. Shiguemori
Keyword(s):  
Neural Network ◽  
Damage Detection ◽  
Lamb Wave ◽  
Learning Strategy ◽  
Damage Identification ◽  
Particle Collision ◽  
Learning Approaches ◽  
Propagation Methods ◽  
Artificial Neural Network Ann ◽  
Multiple Particle

A critical task of structural health monitoring is damage detection and localization. Lamb wave propagation methods have been successfully applied for damage identification in plate-like structures. However, Lamb wave processing is still a challenging task due to its multimodal and dispersive characteristics. To address this issue, data-driven machine learning approaches as artificial neural network (ANN) have been proposed. However, the effectiveness of ANN can be improved based on its architecture and the learning strategy employed to train it. The present paper proposes a Multiple Particle Collision Algorithm (MPCA) to design an optimum ANN architecture to detect and locate damages in plate-like structures. For the first time in the literature, the MPCA is applied to find damages in plate-like structures. The present work uses one piezoelectric transducer to generate Lamb wave signals on an aluminum plate structure and a linear array of four transducers to capture the scattered signals. The continuous wavelet transform (CWT) processes the captured signals to estimate the time-of-flight (ToF) that is the ANN inputs. The ANN output is the damage spatial coordinates. In addition to MPCA optimization, this paper uses a quantitative entropy-based criterion to find the best mother wavelet and the scale values. The presented experimental results show that MPCA is capable of finding a simple ANN architecture with good generalization performance in the proposed damage localization application. The proposed method is compared with the 1-dimensional convolutional neural network (1D-CNN). A discussion about the advantages and limitations of the proposed method is presented.

scholarly journals Prediksi Pengoperasian Traktor di Lahan Kering Menggunakan Artificial Neural Network

2021 ◽  
Vol 12 (3) ◽  
pp. 127-133
Author(s):  
Taufik Nugraha Agassi ◽  
Yose Sebastian ◽  
Zainal Arifin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Content ◽  
Supervised Learning ◽  
Soil Water ◽  
Soil Water Content ◽  
Back Propagation ◽  
Learning Method ◽  
Ann Model ◽  
Dry Land

Soil water content is an important parameter in making a decision to use a tractor or not. The process of measuring soil water content and levels of field capacity in conventional which takes a long time and cannot be used in real-time to measure it is a major problem in the field. Determinants of soil water content such as ambient temperature, humidity, and rainfall can be obtained easily and quickly either by using a tool or retrieving data from the nearest BMKG station. The objective of this research is to obtain the most optimal prediction model in making decisions about tractor operation in dry land. This research uses an Artificial Neural Network (ANN) in modeling predictions of tractor operation. Prediction of tractor operation is a prediction of tractor use on a certain day using input data obtained before the day of tractor use. ANN modeling uses the back-propagation supervised learning method. The best ANN model used four hidden neurons with a learning coefficient of 0.2, a momentum of 0.8 and 20,000 iterations. This model has been able to provide optimal predictions with an accuracy value of 77%. The ANN model has been successful in predicting tractor operation on dry land using the back-propagation supervised learning method.

scholarly journals Antiphishing Model Based on Similarity Index and Neural Networks

2019 ◽  
Vol 9 (1) ◽  
pp. 4114-4119
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Similarity Index ◽  
Back Propagation Neural Network ◽  
Learning Method ◽  
Average Precision ◽  
Feed Forward Back Propagation ◽  
User Query ◽  
Work Model ◽  
The Web

Phishing is a negative technique that is used to steel private and confidential information over the web. In the present work author proposed a hybrid similarity of Cosine and Soft Cosine to calculate the similarity between the user query and repository as an anti-phishing approach. The proposed work model uses a multiclass learning method called Feed Forward Back Propagation Neural Network. The model evaluation results with 100 to 3000 test files shows that the hybrid model is able to detect the phishing attack with an average precision of 71% and is highly effective.

scholarly journals Defect identification method for poplar veneer based on progressive growing generated adversarial network and MASK R-CNN model

BioResources ◽  
2020 ◽  
Vol 15 (2) ◽  
pp. 3041-3052
Author(s):  
Kai Hu ◽  
Baojin Wang ◽  
Yi Shen ◽  
Jieru Guan ◽  
Yi Cai
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Surface Defects ◽  
Learning Strategy ◽  
Back Propagation ◽  
Self Organizing Map ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Main Production ◽  
Som Neural Network

As the main production unit of plywood, the surface defects of veneer seriously affect the quality and grade of plywood. Therefore, a new method for identifying wood defects based on progressive growing generative adversarial network (PGGAN) and the MASK R-CNN model is presented. Poplar veneer was mainly studied in this paper, and its dead knots, live knots, and insect holes were identified and classified. The PGGAN model was used to expand the dataset of wood defect images. A key ideal employed the transfer learning in the base of MASK R-CNN with a classifier layer. Lastly, the trained model was used to identify and classify the veneer defects compared with the back- propagation (BP) neural network, self-organizing map (SOM) neural network, and convolutional neural network (CNN). Experimental results showed that under the same conditions, the algorithm proposed in this paper based on PGGAN and MASK R-CNN and the model obtained through the transfer learning strategy accurately identified the defects of live knots, dead knots, and insect holes. The accuracy of identification was 99.05%, 97.05%, and 99.10%, respectively.

scholarly journals Sensitivity Analysis and 3D-displacement Inversion of Rock Parameters for High Steep Slope in Open-pit Mining

2016 ◽  
Vol 10 (1) ◽  
pp. 448-460 ◽  
Author(s):  
C.B. Zhou ◽  
R. He ◽  
N. Jiang ◽  
S.W. Lu
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Back Propagation ◽  
Back Analysis ◽  
Steep Slope ◽  
Open Pit ◽  
Open Pit Mining ◽  
Mechanical Parameters ◽  
The Real ◽  
Geological Conditions

Due to the complexity of multiple rocks and multiple parameters circumstance, various parameters are often reduced to only one parameter empirically to generalize geological conditions, ignoring the really influential parameters. A developed method was presented as a complement to 3D displacement inversion to obtain the relative important parameters under complex conditions with limited computational work. Furthermore, this method was applied to a high steep slope in open-pit mining to investigate field applicability of the developed system. Back analysis was conducted in the reality of the east open-pit working area of Daye Iron Mine and propositional steps were presented for parameters solving in complex circumstance. Firstly, multi-factor and single-factor sensitivity analysis were carried out to classify rock mass and mechanical parameters respectively according to the extent of their effects on deformations. Secondly, based on the results, main influence factors were selected as inversion parameters and taken into a 3D calculating model to get the displacement field and stress field, all of which would be the artificial network training samples together with inversion parameters. Thirdly, taking the real deformations as input for the trained back propagation (BP) neural network, the real material mechanical parameters could be obtained. Finally, the results of trained neural network have been confirmed by field monitoring data and provide a reference to obtain the matter parameters in complicated environment for other similar projects.

A New Back-Propagation Neural Network Algorithm for a Big Data Environment Based on Punishing Characterized Active Learning Strategy

2013 ◽  
Vol 4 (4) ◽  
pp. 32-45 ◽  
Author(s):  
Qiuhong Zhao ◽  
Feng Ye ◽  
Shouyang Wang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Active Learning ◽  
Learning Strategy ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Bp Algorithm ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Active Learning Strategy

This paper introduces the active learning strategy to the classical back-propagation neural network algorithm and proposes punishing-characterized active learning Back-Propagation (BP) Algorithm (PCAL-BP) to adapt to big data conditions. The PCAL-BP algorithm selects samples and punishments based on the absolute value of the prediction error to improve the efficiency of learning complex data. This approach involves reducing learning time and provides high precision. Numerical analysis shows that the PCAL-BP algorithm is superior to the classical BP neural network algorithm in both learning efficiency and precision. This advantage is more prominent in the case of extensive sample data. In addition, the PCAL-BP algorithm is compared with 16 types of classical classification algorithms. It performs better than 14 types of algorithms in the classification experiment used here. The experimental results also indicate that the prediction accuracy of the PCAL-BP algorithm can continue to increase with an increase in sample size.

scholarly journals Artificial Neural Networks and the Mass Appraisal of Real Estate

2018 ◽  
Vol 14 (03) ◽  
pp. 180 ◽  
Author(s):  
Gang Zhou ◽  
Yicheng Ji ◽  
Xiding Chen ◽  
Fangfang Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Real Estate ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Support Vector ◽  
The Real ◽  
The Real Estate ◽  
Artificial Neural

<p>With the rapid development of computer, artificial intelligence and big data technology, artificial neural networks have become one of the most powerful machine learning algorithms. In the practice, most of the applications of artificial neural networks use back propagation neural network and its variation. Besides the back propagation neural network, various neural networks have been developing in order to improve the performance of standard models. Though neural networks are well known method in the research of real estate, there is enormous space for future research in order to enhance their function. Some scholars combine genetic algorithm, geospatial information, support vector machine model, particle swarm optimization with artificial neural networks to appraise the real estate, which is helpful for the existing appraisal technology. The mass appraisal of real estate in this paper includes the real estate valuation in the transaction and the tax base valuation in the real estate holding. In this study we focus on the theoretical development of artificial neural networks and mass appraisal of real estate, artificial neural networks model evolution and algorithm improvement, artificial neural networks practice and application, and review the existing literature about artificial neural networks and mass appraisal of real estate. Finally, we provide some suggestions for the mass appraisal of China's real estate.</p>

scholarly journals Air Quality Modeling for Sustainable Clean Environment Using ANFIS and Machine Learning Approaches

Atmosphere ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 713
Author(s):  
Osman Taylan ◽  
Abdulaziz S. Alkabaa ◽  
Mohammed Alamoudi ◽  
Abdulrahman Basahel ◽  
Mohammed Balubaid ◽  
...  
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Urban Areas ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Nonlinear Least Squares ◽  
Optimization Method ◽  
Total Effect ◽  
Learning Approaches ◽  
Jeddah City

Air quality monitoring and assessment are essential issues for sustainable environmental protection. The monitoring process is composed of data collection, evaluation, and decision-making. Several important pollutants, such as SO2, CO, PM10, O3, NOx, H2S, location, and many others, have important effects on air quality. Air quality should be recorded and measured based on the total effect of pollutants that are collectively prescribed by a numerical value. In Canada, the Air Quality Health Index (AQHI) is used which is one numerical value based on the total effect of some concentrations. Therefore, evolution is required to consider the complex, ill-defined air pollutants, hence several naive and noble approaches are used to study AQHI. In this study, three approaches such as hybrid data-driven ANN, nonlinear autoregressive with external (exogenous) input (NARX) with a neural network, and adaptive neuro-fuzzy inference (ANFIS) approaches are used for estimating the air quality in an urban area (Jeddah city—industrial zone) for public health concerns. Over three years, 1771 data were collected for pollutants from 1 June 2016 until 30 September 2019. In this study, the Levenberg-Marquardt (LM) approach was employed as an optimization method for ANNs to solve the nonlinear least-squares problems. The NARX employed has a two-layer feed-forward ANN. On the other hand, the back-propagation multi-layer perceptron (BPMLP) algorithm was used with the steepest descent approach to reduce the root mean square error (RMSE). The RMSEs were 4.42, 0.0578, and 5.64 for ANN, NARX, and ANFIS, respectively. Essentially, all RMSEs are very small. The outcomes of approaches were evaluated by fuzzy quality charts and compared statistically with the US-EPA air quality standards. Due to the effectiveness and robustness of artificial intelligent techniques, the public’s early warning will be possible for avoiding the harmful effects of pollution inside the urban areas, which may reduce respiratory and cardiovascular mortalities. Consequently, the stability of air quality models was correlated with the absolute air quality index. The findings showed notable performance of NARX with a neural network, ANN, and ANFIS-based AQHI model for high dimensional data assessment.

Sign in / Sign up

Export Citation Format

Share Document