Using pre &amp; post-processing methods to improve binding site predictions

Sun, Yi; Castellano, Cristina González; Robinson, Mark; Adams, Rod; Rust, Alistair G.; Davey, Neil

doi:10.1016/j.patcog.2009.01.027

Cited by 14 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that these results rely critically on the use of sampling for the imbalanced data. Without sampling, as shown in Table 5, we obtained very poor results (see [28] for a further exposition).…”

Section: Discussionmentioning

confidence: 90%

Integrating genomic binding site predictions using real-valued meta classifiers

Sun

Robinson

Adams

et al. 2008

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 90%

Integrating genomic binding site predictions using real-valued meta classifiers

Sun

Robinson

Adams

et al. 2008

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

“…Hochmann also realizing the significance of data preparation used Main Component Evaluation to prepare the data set [7]. Finally, Mizuno proposes a data equalization method to enhance the functionality of an Artificial Neural System in specialized evaluation of-the market exchange [10].…”

Section: Data Preprocessignand Machine Learningmentioning

confidence: 99%

“…A kernel function can be employed to implicitly chart the data points into a higher dimensional feature room, and to consider the innerproduct in therefore as to attribute gap [10]. The advantages of utilizing a kernel function is the fact that the data is prone to become linearly detachable in the higher attribute difference.…”

Section: The Support Vector Machinementioning

confidence: 99%

“…Additional studies have discovered it helpful when used to sensory networks in the fiscal forecasting domain [10].The quantity of function completed in this region remains restricted to several studies. It appears legitimate to suppose this strategy might be similarly useful when used to some other domains, along with other machine learners.…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

A Hierarchical Feature Set optimization for effective code change based Defect Forecasting

Reddy¹

2013

IOSR-JCE

View full text Add to dashboard Cite

“…This data cleaning technique has been used in several experiments. For example, Sun et al [8] applied Tomek links technique to remove noisy data for improving binding site predictions on sequences of DNA. They concluded that by removing Tomek links from the training data, the classifier can improve the classification accuracy especially on the imbalanced data set.…”

Section: P(ν) = P(µ)p(γ)mentioning

confidence: 99%

Data Cleaning for Classification Using Misclassification Analysis

Jeatrakul¹,

Wong²,

Fung

2010

J. Adv. Comput. Intell. Intell. Inform.

View full text Add to dashboard Cite

In most classification problems, sometimes in order to achieve better results, data cleaning is used as a preprocessing technique. The purpose of data cleaning is to remove noise, inconsistent data and errors in the training data. This should enable the use of a better and representative data set to develop a reliable classification model. In most classification models, unclean data could sometime affect the classification accuracies of a model. In this paper, we investigate the use of misclassification analysis for data cleaning. In order to demonstrate our concept, we have used Artificial Neural Network (ANN) as the core computational intelligence technique. We use four benchmark data sets obtained from the University of California Irvine (UCI) machine learning repository to investigate the results from our proposed data cleaning technique. The experimental data sets used in our experiment are binary classification problems, which are German credit data, BUPA liver disorders, Johns Hopkins Ionosphere and Pima Indians Diabetes. The results show that the proposed cleaning technique could be a good alternative to provide some confidence when constructing a classification model.

show abstract

Using pre & post-processing methods to improve binding site predictions

Cited by 14 publications

References 10 publications

Integrating genomic binding site predictions using real-valued meta classifiers

Integrating genomic binding site predictions using real-valued meta classifiers

A Hierarchical Feature Set optimization for effective code change based Defect Forecasting

Data Cleaning for Classification Using Misclassification Analysis

Contact Info

Product

Resources

About