4,638 Hits in 4.0 sec

Using neural networks in reliability prediction

N. Karunanithi, D. Whitley, Y.K. Malaiya
1992 IEEE Software  
Whitley, "Prediction of Software Reliability Using Neural Net-ReliabZiy Eng., May 1991, pp. 124- 130. works," P m t t ? Spp. SofFWure  ...  We also thank Scott This research was supported in part by NSFgrant IN-9010546, and in part by a project funded by the Fahhan for providing the code for his cascade-correlation algorithm.  ...  ACKNOWLEDGMENTS We thank IEEE Sofnuare reviewers for their useful comments and suggestions.  ... 
doi:10.1109/52.143107 fatcat:py4mu5pwqbhanfozef4eybovfe

A Review of Torque Ripple Control Strategies of Switched Reluctance Motor

Xudong Gao, Xudong Wang, Zhongyu Li, Yongqin Zhou
2015 International Journal of Control and Automation  
However, it also has obvious defects such as torque ripple and vibrating noise.  ...  Switched reluctance motor is a new type of AC speed-adjustable system with high application value; it has lots of advantages such as simple structure, consistence and durability, low cost, wide speed range  ...  Tzu-Shien Chuang is applied dc side current-feedback design approximate sliding mode power control (as the system inner), while sliding mode speed with feed forward control with integral compensation for  ... 
doi:10.14257/ijca.2015.8.4.13 fatcat:kjyqvwizfvbn3bgj7wmvzvlpka

Medical image analysis with artificial neural networks

J. Jiang, P. Trundle, J. Ren
2010 Computerized Medical Imaging and Graphics  
In the concluding section, a highlight of comparisons among all neural networks is included to provide a global view on computational intelligence with neural networks in medical imaging.  ...  of how neural networks can be applied to these areas and providing a foundation for further research and practical development.  ...  Feed-forward Network There are several different neural network architectures available for medical imaging applications, but one of the most common is the Feed-forward network.  ... 
doi:10.1016/j.compmedimag.2010.07.003 pmid:20713305 fatcat:iycrdoy4yfgjfof2ml4xk7iz6i

A Survey on Applications of Neural Networks and Genetic Algorithms in Fault Diagnostics for Antenna Arrays

Subhash Mishra
2013 IOSR Journal of Electrical and Electronics Engineering  
The traditional analytical methods find it tedious to handle fault finding problems related with antenna arrays. Neural networks are nonlinear in nature.  ...  In this review, the applications of neural networks and genetic algorithms in fault diagnosis of antenna arrays are summarized.  ...  Multi Layer Perceptron Neural Networks A multilayer perceptron (MLP) is a feed forward, non linear neural network which can have single or multiple hidden layers.  ... 
doi:10.9790/1676-0862732 fatcat:4e7ukujyxrb3pg53j7rsiybs3a

Machine tool positioning error compensation using artificial neural networks

John M. Fines, Arvin Agah
2008 Engineering applications of artificial intelligence  
This thesis is a study of the application of artificial neural networks to the problem of calculating error compensation values for axis positioning on a machine tool.  ...  A number of neural network architectures were examined for applicability to the problem and one was selected and implemented on the machine.  ...  In it is discussed the numerical results achieved by the artificial neural network positioning error compensation system and a comparison with the results achieved by traditional methods of compensation  ... 
doi:10.1016/j.engappai.2007.10.001 fatcat:7zxxjiigzvf5jnhe6s4ew34vt4

51951 Comparison of neural network and Markov random field1 image segmentation techniques

1994 NDT & E international  
Not • Oel""') • Defect Location Neural Network Architecture Fig. 5 . 5 Neural Network and Markov Random Field Comparison  ...  A straight-forward modification of the current algorithm would allow for an output for each defect c1ass (and one for "good"), rather than the current single network output.  ... 
doi:10.1016/0963-8695(94)90637-8 fatcat:uun4ip6gyvaqblax2n5tgbb3du

Comparison of Neural Network and Markov Random Field Image Segmentation Techniques* [chapter]

Fred G. Smith, Karen R. Jepsen, Peter F. Lichtenwalner
1992 Review of Progress in Quantitative Nondestructive Evaluation  
Not • Oel""') • Defect Location Neural Network Architecture Fig. 5 . 5 Neural Network and Markov Random Field Comparison  ...  A straight-forward modification of the current algorithm would allow for an output for each defect c1ass (and one for "good"), rather than the current single network output.  ... 
doi:10.1007/978-1-4615-3344-3_92 fatcat:ei6vkcrwordvvbwgzlq6ztivvu

Fault Tolerant Control Based on an Observer on PI Servo Design for a High-Speed Automation Machine

Prathan Chommuangpuck, Thanasak Wanglomklang, Suradet Tantrairatn, Jiraphon Srisertpol
2020 Machines  
The statistical mean value of the observer error signal is used to train the artificial neural network (ANN) model.  ...  The gain compensation was successful in reducing position error by more than 95% compared with the system without compensated gain.  ...  Acknowledgments: The authors are indebted to Suranaree University of Technology (SUT) and Western Digital (Thailand) Company Limited for their generosity and valuable comments.  ... 
doi:10.3390/machines8020022 fatcat:g2b63vjdubeozern7wp3rzesk4

Towards Intelligent Interpretation of Low Strain Pile Integrity Testing Results Using Machine Learning Techniques

De-Mi Cui, Weizhong Yan, Xiao-Quan Wang, Lie-Min Lu
2017 Sensors  
Low strain pile integrity testing (LSPIT), due to its simplicity and low cost, is one of the most popular NDE methods used in pile foundation construction.  ...  For foundation construction sites where the number of piles to be tested is large, it may take days before the expert can complete interpreting all of the piles and delivering the integrity assessment  ...  For comparison purpose, we also implement a conventional feed-forward neural network (FFNN) as the classification model, using the same data, the same extracted features and the same evaluation method.  ... 
doi:10.3390/s17112443 pmid:29068431 pmcid:PMC5713026 fatcat:7q65jpmibnbbvid6lgrefmpch4

Comparative Analysis of FeedforwardBackpropagation and Cascade Correlation Algorithm on BUPA Liver Disorder

Alpana Jijja, Dr.Dinesh Rai, Priyanka Mathur
2016 International Journal of Engineering and Technology  
In this paper we have made use of two classification algorithmsi.e. feedforwardbackpropagation neural network(FFBPNN) and Cascade Correlationfeedforward network (CCFFN) and compared the performance of  ...  Neural Network(NN) is widely used in medical research because of its cost effectiveness and easy-to-use systems. NN plays an important role in the decision support system.  ...  In this study, that we have undertaken, Multilayer Perceptron feed forward back propagation Neural Network is trained with Levenberg Marquardt (LM) algorithm for classification.  ... 
doi:10.21817/ijet/2016/v8i6/160806264 fatcat:nfe4wd5svncmrngqedu4iaria4

A Review on Machine Learning Models in Injection Molding Machines

Senthil Kumaran Selvaraj, Aditya Raj, R. Rishikesh Mahadevan, Utkarsh Chadha, Velmurugan Paramasivam, Fuat Kara
2022 Advances in Materials Science and Engineering  
Conventional methods relying on the operator's expertise and defect detection techniques are ineffective in reducing defects.  ...  One of the most suitable methods for the mass production of complicated shapes is injection molding due to its superior production rate and quality.  ...  When different weights are applied to the input nodes, the cumulative effect for each node is taken, and the output layer is formed. (2) Multilayer feed-forward network: the multilayer feed-forward network  ... 
doi:10.1155/2022/1949061 fatcat:lzi6kpqmdzcdrbr4tagwggdtp4

Machine Vision Based Inspection of Textile Fabrics

Chuanjun Wang, Chih-Ho Yu
1994 IAPR International Workshop on Machine Vision Applications  
In inspection algorithms, we use a hierarchy of improved BP neural networks which demonstrate a tree structure in the progress of defect detection and classification.  ...  To avoid the intense computation for real time inspection, we suggest a parallel pyramid hardware architecture consisting of several channels with CCD cameras in different resolutions working simultaneously  ...  The neural networks are of the model of feed forward multi-layered network with two hidden layers. We use an improved bac!c propagation algorithm for !earning [7] .  ... 
dblp:conf/mva/WangY94 fatcat:r2yio7n4lrajjne2hfywsa6rve

Intelligent control for handling motion nonlinearity in a retrofitted machining table

S.-J. Huang, C.-Y. Shy
1998 IEE Proceedings - Control Theory and Applications  
Hence intelligent model-free self-organising fuzzy control and neural network control strategies equipped with learning ability are employed to control this machining table, to improve both the adaptability  ...  For low cost automation, a traditional manually operated milling machine with a leadscrew transmission system was retrofitted with an AC servo-motor.  ...  Neural1 network control The multi-layer feed forward neural network is currently the most popular neural network application.  ... 
doi:10.1049/ip-cta:19982110 fatcat:q6mhdubdcvbtfivhg6ezyefmmm

Pricing 50ETF Option Based on Genetic Algorithm BP Model

Yulin Du, G. Lee
2018 MATEC Web of Conferences  
Comparing to the traditional parameter model pricing method, the neural network method has obvious advantages in solving this problem.  ...  The results show that the effect of neural network is better than that of B-S model, and the accuracy of GABP model is higher than that of BP neural network model and B-S model.  ...  network of genetic algorithm 2.1 BP neural network BP (Back Propagation) network is a multilayer feed forward neural network, the network training, adjust the training algorithm right threshold follows  ... 
doi:10.1051/matecconf/201822702010 fatcat:zloa5qcf2nfdbpypgwy6orpvma

Reduction of Elastomagnetic Sensor Errors by Using Neural Networks

J. Vojtko
2004 Radioengineering  
The using of exactly definedalgorithm of reducing sensor errors is not appropriate in this case.So, the unconventional solution is using of the neural networks.  ...  This article deals with possibilities of reduction of elastomagneticsensor errors. Elastomagnetic sensors are used for measuring of massivepressure force (of range about 200 kN).  ...  To summarize, feed-forward neural networks are able to compensate error of the elastomagnetic pressure force sensor EMS-200kN.  ... 
doaj:263691b2a9d0426fb64d17e80f2fa39e fatcat:v2bel3wohzhovjc3e2mqxhshea
« Previous Showing results 1 — 15 out of 4,638 results