20,069 Hits in 4.3 sec

2D Gaze Estimation Based on Pupil-Glint Vector Using an Artificial Neural Network

Jianzhong Wang, Guangyue Zhang, Jiadong Shi
2016 Applied Sciences  
In order to solve the mapping function, an improved artificial neural network (DLSR-ANN) based on direct least squares regression is proposed.  ...  artificial neural network).  ...  Figure 2 . 2 Scheme framework of improved artificial neural network based on direct least squares regression.  ... 
doi:10.3390/app6060174 fatcat:b6rbjezxhrd5zm4rbyikdt7m2y

Mixed transfer function neural networks for knowledge acquisition

M. Imad Khan, Yakov Frayman, Saeid Nahavandi
2009 2009 IEEE International Conference on Industrial Technology  
However inductive models, like Artificial Neural Networks (ANNs), may suffer from a few drawbacks involving over-fitting and the difficulty to easily understand the model itself.  ...  In this paper, we propose a novel type of ANN, a Mixed Transfer Function Artificial Neural Network (MTFANN), which aims to improve the complexity fitting and comprehensibility of the most popular type  ...  Zurada, "Extraction of Rules from Artificial Neural Networks for Nonlinear Regression," IEEE Transactions on Neural Networks, Vol. 13, No. 3, 2002.  ... 
doi:10.1109/icit.2009.4939662 fatcat:x3amrwlsq5hv5fdlth2y7upnri

Application of Data Mining Using Artificial Neural Network: Survey

Muhammad Arif, Khubaib Amjad Alam, Mehdi Hussain
2015 International Journal of Database Theory and Application  
ANN can also be used for the purpose of extracting rules from trained neural networks. 246 Copyright ⓒ 2015 SERSC experience rather than on the knowledge masked in the database.  ...  Minimum support and minimum confidence are the two factors of an association rule which determine the strength of a rule [5] .The combine tactic of Artificial neural network based network inference and  ...  Ensemble recursive rule extraction is basically mining of rules from the ensemble neural network.  ... 
doi:10.14257/ijdta.2015.8.1.25 fatcat:sbcxvdwebnf3ro7e3zxhun3esi

Quantile Regression Neural Networks Based Prediction of Drug Activities

Mohammed E. El-Telbany
2014 IAES International Journal of Artificial Intelligence (IJ-AI)  
The quantile estimation via neural network structure technique introduced in this paper is used to predict activity of pyrimidines based on the structure–activity relationship of these compounds which  ...  In comparison with statistical quantile regression, the qrnn significantly reduce the prediction error.</p>  ...  Figure 2 . 2 The quantile regression loss function. Figure 3 . 3 Structure of the neural network. Quantile Regression Neural Networks Based Prediction of Drug Activities (Mohammed E.  ... 
doi:10.11591/ijai.v3.i4.pp150-155 fatcat:mtszblws5zgxbktdxqx7nxvpty

Software Effort Estimation Using Adaptive Fuzzy-Neural Approach

Riyadh A.K. Mehdi
2017 International Journal of Computer Applications Technology and Research  
Results obtained based on the China dataset indicates that a hybrid model that combine fuzzy inferencing with neural networks ability to learn from examples provided more accurate results than using neural  ...  Index Terms -Software effort estimation; fuzzy inference; datasets; neural networks; and fuzzy-neural systems.  ...  The neural network uses either a pure back propagation gradient descent learning rule, or a hybrid learning rule that uses back propagation and a least squares method [21] .  ... 
doi:10.7753/ijcatr0607.1011 fatcat:s7p7jbjqdjegbnufvmozccxuma

Software Effort Prediction Using Regression Rule Extraction from Neural Networks

Rudy Setiono, Karel Dejaeger, Wouter Verbeke, David Martens, Bart Baesens
2010 2010 22nd IEEE International Conference on Tools with Artificial Intelligence  
This paper describes a rule extraction technique that derives a set of comprehensible IF-THEN rules from a trained neural network applied to the domain of software effort prediction.  ...  The suitability of this technique is tested on the ISBSG R11 data set by a comparison with linear regression, radial basis function networks, and CART.  ...  Regression rule extraction A set of regression rules can be induced from the trained NN by applying REFANN (Rule Extraction from Function Approximating Neural Networks) [31, 32] .  ... 
doi:10.1109/ictai.2010.82 dblp:conf/ictai/SetionoDVMB10 fatcat:hkpiuzs3tbgm3dpd3u53pm62di

Using artificial neural networks for forecasting per share earnings

Mohammad Sarchami
2012 African Journal of Business Management  
The hypotheses are based on the idea that: 1) an artificial neural network with an error backward propagation algorithm is able to forecast the earnings of per share; 2) a neural network with a genetic  ...  In order to forecast per share earnings using an "artificial neural network with an error backward propagation algorithm" and an "artificial neural network with a genetic algorithm", 61 firms in 7 financial  ...  other hand, the ability of models based on artificial neural networks, is it possible to use artificial neural networks for forecasting and what is the ability of the artificial neural network with an  ... 
doi:10.5897/ajbm11.2811 fatcat:qswqqgpsbjdctj6fdjykfy6vhi

Finding hidden-feature depending laws inside a data set and classifying it using Neural Network [article]

Thilo Moshagen, Nihal Acharya Adde, Ajay Navilarekal Rajgopal
2021 arXiv   pre-print
It is clear, and one experiences it soon, that in the case of clustered data, an artificial neural network with logcosh loss learns the bigger cluster rather than the mean of the two.  ...  Even more so, the ANN, when used for regression of a set-valued function, will learn a value close to one of the choices, in other words, one branch of the set-valued function, while a mean-square-error  ...  Mean Square Error (MSE) or L2 loss This function originates from the theory of regression, least-squares method. Mean Square Error (MSE) is the most commonly used regression loss function.  ... 
arXiv:2101.10427v1 fatcat:hq5zxv3uejgl7fulgtb6trgswi


Jarosław Smoczek
2015 Journal of KONES Powertrain and Transport  
The artificial intelligence is frequently addressed to the predictive problem by utilizing the learning capability of artificial neural network (ANN), and possibility of nonlinear mapping using fuzzy rules-based  ...  This problem has been extensively studied in many scientific works, where the predictive models are based on the data-driven approaches that can be generally divided into statistical techniques (regression  ...  The knowledge bases consisting of rules type of if-then is extracted from multiple pre-processed data.  ... 
doi:10.5604/12314005.1138154 fatcat:rpenk3etgbc2dgsza6ula6otwq

Credit scoring in banks and financial institutions via data mining techniques: A literature review

Seyed Mahdi sadatrasoul, Mohammadreza gholamian, Mohammad Siami, Zeynab Hajimohammadi
2013 Journal of Artificial Intelligence and Data Mining  
Also ensemble methods, support vector machines and neural network methods are the most favorite techniques used recently.  ...  The findings of the review reveals that data mining techniques are mostly applied to individual credit score and there are a few researches on enterprise and SME credit scoring.  ...  network - [11] Bagging, Boosting (adaboost), staking ensembles based on Logistic Regression, Decision Tree, Artificial Neural Network and Support Vector Machine compared with each other - [12]  ... 
doi:10.22044/jadm.2013.124 doaj:8e8e42083d7c4db9a5eef786a0f2eaa9 fatcat:rlic3qipxvdubh5stt6xokdczy

Estimating spatial variations in soil organic carbon using satellite hyperspectral data and map algebra

Salahuddin M. Jaber, Christopher L. Lant, Mohammed I. Al-Qinna
2011 International Journal of Remote Sensing  
Acknowledgements This material is based upon work supported by the National Science Foundation under Grant No. 0410187.  ...  Finally, Gomez et al. (2008) applied just one regression modelling technique (i.e. partial least squares), which was also based on a small sample size (only 72).  ...  stepwise regression followed by three nodes artificial neural network, (f) stepwise regression followed by five nodes artificial neural network, (g) principal components followed by stepwise regression  ... 
doi:10.1080/01431161.2010.494637 fatcat:gpxsorbxgbdljevfj36qknlxra

Comparative Analysis of Neural Network Models for Premises Valuation Using SAS Enterprise Miner [chapter]

Tadeusz Lasota, Michał Makos, Bogdan Trawiński
2009 Studies in Computational Intelligence  
Eight different algorithms were used including artificial neural networks, statistical regression and decision trees.  ...  All models were applied to actual data sets derived from the cadastral system and the registry of real estate transactions. A dozen of predictive accuracy measures were employed.  ...  AVMs are currently based on methodologies from multiple regression analysis to neural networks and expert systems [11] .  ... 
doi:10.1007/978-3-642-03958-4_29 fatcat:o6s4wqjrv5gsvgsmni53j2573y

Study of Time Series Data Mining for the Real Time Hydrological Forecasting: A Review

Satanand Mishra, C. Saravanan, V. K. Dwivedi
2015 International Journal of Computer Applications  
Researchers are developed models for runoff forecasting using the data mining tools and techniques like regression analysis, clustering, artificial neural network (ANN), and support vector machine (SVM  ...  This paper presents a review of runoff forecasting method based on hydrological time series data mining.  ...  Neural network based on Back Propagation Approach Back propagation is a common method to train an Artificial Neural Network.  ... 
doi:10.5120/20692-3581 fatcat:v3vfg7a4wfgwxfdgxdgvlhvrfq

Decision tree based control chart pattern recognition

Chih-Hsuan Wang, Ruey-Shan Guo, Ming-Huang Chiang, Jehn-Yih Wong
2008 International Journal of Production Research  
Acknowledgements The authors are grateful to many helpful comments from two anonymous referees. The research is supported by National Science Council of Taiwan under Grant NSC-95-2416-H-130-019.  ...  on least-square and mean regressions.  ...  Decision tree based control chart pattern recognition Rapid developments in artificial intelligence have motivated researchers to explore the artificial neural network (ANN) based control chart pattern  ... 
doi:10.1080/00207540701294619 fatcat:icyckenyhnhrfdmkrw7j34fc2a

Survey of Data Mining Techniques Used for Real Time Churn Prediction

Jean Claude Turiho, Wilson Cheruiyot, Anne Kibe, Irénée Mungwarakarama
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
Data mining is one of the techniques which provide different methods and application to find out those customers who are going to churn and how to prevent them.  ...  The first one called AntMiner+ uses Ant Colony Optimization gather rules from data and second one named Active Learning Based Approach for support vector machine rule extraction and experiment were conducted  ...  -F.Tsai et al., [9] used association rules to extract feature from original one to improve the prediction performance.  ... 
doi:10.23956/ijarcsse/v7i3/01319 fatcat:pcdrlao7aza4hgmzvmuj7dvasm
« Previous Showing results 1 — 15 out of 20,069 results