Filters








23,472 Hits in 7.3 sec

Improved Gini-Index Algorithm to Correct Feature-Selection Bias in Text Classification

Heum PARK, Hyuk-Chul KWON
2011 IEICE transactions on information and systems  
Therefore, to correct that bias and improve feature selection in text classification using Gini-Index, we propose an improved Gini-Index (I-GI) algorithm with three reformulated Gini-Index expressions.  ...  Heum PARK †a) , Nonmember and Hyuk-Chul KWON †b) , Member SUMMARY This paper presents an improved Gini-Index algorithm to correct feature-selection bias in text classification.  ...  On the other hand, 'Trading', 'Stock' and 'Statement' look to be irrelevant features.  ... 
doi:10.1587/transinf.e94.d.855 fatcat:iosruove2radfm4bk3v6idv26a

On Error Correction Neural Networks for Economic Forecasting [article]

Mhlasakululeka Mvubu, Emmanuel Kabuga, Christian Plitz, Bubacarr Bah, Ronnie Becker, Hans Georg Zimmermann
2020 arXiv   pre-print
A class of RNNs called Error Correction Neural Networks (ECNNs) was designed to compensate for missing input variables.  ...  As expected it out performed the simple RNN and LSTM and other hybrid models which involve a de-noising pre-processing step.  ...  It enhances the accuracy of a correct prediction for short-term forecasting like it is shown in [10] .  ... 
arXiv:2004.05277v2 fatcat:zfmjgsspkzb25fc6kmsrnry3xi

A Framework for Collocation Error Correction in Web Pages and Text Documents

Alan Varghese, Aparna S. Varde, Jing Peng, Eileen Fitzpatrick
2015 SIGKDD Explorations  
This framework integrates machine learning approaches with natural language processing techniques, proposing suitable heuristics to provide responses to collocation errors, ranked in the order of correctness  ...  It would also help in providing automated error correction in machine translated documents and offering assistance to people using ESL tools.  ...  Similarly in machine translation such errors can occur and should be corrected to enhance performance. There has been work on incorporating temporal changes in Web and text data, e.g., [6, 7] .  ... 
doi:10.1145/2830544.2830548 fatcat:z4cvlt56kbgetd4tdvuu2injue

Exemplar-based Underwater Image Enhancement Augmented by Wavelet Corrected Transforms

Adarsh Jamadandi, Uma Mudenagudi
2019 Computer Vision and Pattern Recognition  
In this paper we propose a novel deep learning framework to enhance underwater images by augmenting our network with wavelet corrected transformations.  ...  We propose an encoder-decoder module with wavelet pooling and unpooling as one of the network components to perform progressive whitening and coloring transforms to enhance underwater images via realistic  ...  data for their twostage network that performs color correction.  ... 
dblp:conf/cvpr/JamadandiM19 fatcat:ptgxgt26lzclnjc6ao5c4nmudu

Forecasting of financial data: a novel fuzzy logic neural network based on error-correction concept and statistics

Dusan Marcek
2017 Complex & Intelligent Systems  
These proposed modelling approaches and SVM models are applied to predict the high-frequency time series of the BUX stock index.  ...  Then, the accuracy of forecasting models based on statistical (stochastic), machine learning methods, and soft/granular RBF network is investigated.  ...  of the BUX stocks index.  ... 
doi:10.1007/s40747-017-0056-6 fatcat:yavmdcywuvb3zj5flpvu32hule

Hybridization of Machine Learning Techniques to Optimize Portfolio of Stock Market: Review of Literature from the Period 2005 to 2018

Keerti. Mahajan, Ulka Toro, R.V Kulkarni
2021 International journal of recent technology and engineering  
But as stock market is uncertain and complicated the selection of good scripts are considered as one of the challenge in stock market field.  ...  In finance there has always been the problem of how to combine investments to form a portfolio.  ...  These clusters are applied to Rough Set classification model to select correct stock by applying set of rules.  ... 
doi:10.35940/ijrte.e5107.019521 fatcat:5gjhq3dqefcjjf4j6lmarhbno4

Efficacy of Error for the Correction of Initially Incorrect Assumptions and of Feedback for the Affirmation of Correct Responding: Learning in the Classroom

Gary M. Brosvic, Michael L. Epstein, Michael J. Cook, Roberta E. Dihoff
2005 The Psychological Record  
Neither the source of feedback nor the number of responses permitted influenced performance on classroom examinations but both factors interacted significantly to enhance the final examination performance  ...  The correction of initially inaccurate strategies by combining immediate feedback with iterative responding was not differentially effective as a function of information source: educator or the Immediate  ...  resources that learners could use to evaluate their understanding of test materials and to correct their initially inaccurate assumptions (e.g., Kluger & DeNisi, 1996; Kulhavy & Stock, 1989) .  ... 
doi:10.1007/bf03395518 fatcat:banoafvsmbgn7k3cikgyr4j7w4

Corrections and Clarifications

1996 Science  
You will also learn and apply new computer technology to support the research, discovery and development efforts of our pharmaceutical R&D.  ...  In addition, she liked the fact that "there was a lot to learn."  ...  Not to mention a customer service line that lets you speak to a person, not just a machine.  ... 
doi:10.1126/science.272.5264.935f fatcat:vjmmfp623jc23fykpzivnszkiu

Correction Workers' Burnout and Outcomes: A Bayesian Network Approach

Jin Lee, Robert Henning, Martin Cherniack
2019 International Journal of Environmental Research and Public Health  
The present study seeks to demonstrate how Bayesian Network analysis can be used to support Total Worker Health® research on correction workers by (1) revealing the most probable scenario of how psychosocial  ...  The data from 353 correction workers from a state department of corrections in the United States were utilized.  ...  Conflicts of Interest: The authors the present study have no involvement in or affiliations with any organization or entity with any financial interest, such as employment, consultancies, stock ownership  ... 
doi:10.3390/ijerph16020282 pmid:30669527 pmcid:PMC6352158 fatcat:muv6usetnrhwxpvt7hdtquhpoi

Short-Term Wind Speed Hybrid Forecasting Model Based on Bias Correcting Study and Its Application

Mingfei Niu, Shaolong Sun, Jie Wu, Yuanlei Zhang
2015 Mathematical Problems in Engineering  
This paper proposes a novel combination bias correcting forecasting method, which includes the combination forecasting method and forecasting bias correcting model.  ...  The accuracy of wind speed forecasting is becoming increasingly important to improve and optimize renewable wind power generation.  ...  The authors are grateful to the editors and reviewers for their valuable suggestions.  ... 
doi:10.1155/2015/351354 fatcat:ks6tk6xvubh3dkxpldhagczm54

Harvesting social media sentiment analysis to enhance stock market prediction using deep learning

Pooja Mehta, Sharnil Pandya, Ketan Kotecha
2021 PeerJ Computer Science  
Our experiments were performed using machine-learning and deep-learning methods including Support Vector Machine, MNB classifier, linear regression, Naïve Bayes and Long Short-Term Memory.  ...  Machine learning can provide a more accurate and robust approach to handle SM-related predictions.  ...  The performance of the SA is fed to stock-market prediction to any machine learning models.  ... 
doi:10.7717/peerj-cs.476 pmid:33954250 pmcid:PMC8053016 fatcat:3urgqds64bgy3f22cpkpafzh2q

Deep Learning for Stock Market Index Price Movement Forecasting Using Improved Technical Analysis

Chinthakunta Manjunath, CHRIST (Deemed to be University), Balamurugan Marimuthu, Bikramaditya Ghosh, CHRIST (Deemed to be University), RV Institute of Management
2021 International Journal of Intelligent Engineering and Systems  
In this research, deep learning methods are evaluated on the India NIFTY 50 index, a benchmark Indian equity market, by performing a technical data augmentation approach.  ...  Hence, TA1 can be used to construct a robust predictive model in forecasting the stock index movements.  ...  Acknowledgments We are grateful for the technological infrastructure help CHRIST (Deemed to be University) Bangalore, India, to do our research work.  ... 
doi:10.22266/ijies2021.1031.13 fatcat:jen5725nmvfuvhg6tkndvqjoj4

A Novel Operational Partition between Neural Network Classifiers on Vulnerability to Data Mining Bias

Charles Wong
2014 Journal of Software Engineering and Applications  
It is difficult if not impossible to appropriately and effectively select from among the vast pool of existing neural network machine learning predictive models for industrial incorporation or academic  ...  research exploration and enhancement.  ...  Kim [16] uses a PDL model with a genetic algorithm-enhanced learning rule on seven years of daily Korean Stock index prices.  ... 
doi:10.4236/jsea.2014.74027 fatcat:nyma6fa4wrcdnk7x6cb23fexmi

A Modeling Approach on the Correction Model of the Chromatic Aberration of Scanned Wood Grain Images

Jingjing Mao, Zhihui Wu, Xinhao Feng
2022 Coatings  
Quality Enhancement).  ...  Therefore, we described a novel method of correcting the chromatic aberration of scanned wood grain to maximally restore the objective color information of the real wood grain.  ...  [18] used the * * * color measuring system to develop a machine learning model for predicting the mechanical properties of artificially weathered fir, alder, oak, and poplar wood.  ... 
doi:10.3390/coatings12010079 fatcat:r6op27pxdjafrhyxrpojfhlzeu

Integrating High Volume Financial Datasets to Achieve Profitable and Interpretable Short Term Trading with the FTSE100 Index [chapter]

Thomas Amorgianiotis, Konstantinos Theofilatos, Sovan Mitra, Efstratios F. Georgopoulos, Spiros Likothanassis
2014 IFIP Advances in Information and Communication Technology  
Lately, several machine learning methods have been proposed to solve these problems [1] . Despite the encouraging results of new hybrid methodologies their performance could be further enhanced.  ...  dataset (training dataset) the past three years. 3 Method description GAMLP methodology The first machine learning methodology which was applied in the present study is a hybrid combination of Genetic  ... 
doi:10.1007/978-3-662-44722-2_36 fatcat:oh7vpywm5zdztmaowtfad4umqu
« Previous Showing results 1 — 15 out of 23,472 results