Comparative Analysis of Outlier Detection Techniques

Malik, Kamal; Sadawarti, Harsh; S, Kalra G.

doi:10.5120/17026-7318

Cited by 19 publications

(28 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Outlier samples can be error-bound (for example, data entry point, measurement error, experimental error, sampling errors) or have no error, in which case they are called natural outlier. In other words, natural outliers are actually samples that do not make any errors, but their distance from the rest of the samples is considerably large [ 34 ]. There are different ways to identify outlier proteins.…”

Section: Resultsmentioning

confidence: 99%

Moonlighting protein prediction using physico-chemical and evolutional properties via machine learning methods

et al. 2021

View full text Add to dashboard Cite

Background Moonlighting proteins (MPs) are a subclass of multifunctional proteins in which more than one independent or usually distinct function occurs in a single polypeptide chain. Identification of unknown cellular processes, understanding novel protein mechanisms, improving the prediction of protein functions, and gaining information about protein evolution are the main reasons to study MPs. They also play an important role in disease pathways and drug-target discovery. Since detecting MPs experimentally is quite a challenge, most of them are detected randomly. Therefore, introducing an appropriate computational approach to predict MPs seems reasonable. Results In this study, we introduced a competent model for detecting moonlighting and non-MPs through extracted features from protein sequences. We attempted to set up a well-judged scheme for detecting outlier proteins. Consequently, 37 distinct feature vectors were utilized to study each protein’s impact on detecting MPs. Furthermore, 8 different classification methods were assessed to find the best performance. To detect outliers, each one of the classifications was executed 100 times by tenfold cross-validation on feature vectors; proteins which misclassified 90 times or more were grouped. This process was applied to every single feature vector and eventually the intersection of these groups was determined as the outlier proteins. The results of tenfold cross-validation on a dataset of 351 samples (containing 215 moonlighting and 136 non-moonlighting proteins) reveal that the SVM method on all feature vectors has the highest performance among all methods in this study and other available methods. Besides, the study of outliers showed that 57 of 351 proteins in the dataset could be an appropriate candidate for the outlier. Among the outlier proteins, there were non-MPs (such as P69797) that have been misclassified in 8 different classification methods with 16 different feature vectors. Because these proteins have been obtained by computational methods, the results of this study could reduce the likelihood of hypothesizing whether these proteins are non-moonlighting at all. Conclusions MPs are difficult to be identified through experimentation. Using distinct feature vectors, our method enabled identification of novel moonlighting proteins. The study also pinpointed that a number of non-MPs are likely to be moonlighting.

show abstract

Section: Resultsmentioning

confidence: 99%

Moonlighting protein prediction using physico-chemical and evolutional properties via machine learning methods

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For this reason, it has to be necessary to detect all outliers and to remove all of them from the data set. The methods used to determine the data that are outliers; are separated as statistical, parametric, non-parametric, distance-based, clustering-based and neural network [23]. In this study, the z-Score method which is one of the parametric methods was used.…”

Section: Outlier Rejectionmentioning

confidence: 99%

Classification of Dynamic Egg Weights Using Feature Extraction Methods

Seçil

Yumurtacı

Ergin

et al. 2020

Eskişehir Technical University Journal of Science and Technology a - Applied Sciences and Engineering

View full text Add to dashboard Cite

In this study, a feature vector is determined in order to classify chicken eggs into four different weight groups by using the dynamic weighing system, and then the success rates of different classifiers in the process of weight classification are analyzed. The class numbers and labels of the egg weight groups are determined as 1-extra large, 2-large, 3-middle, and 4small, respectively. The dynamic weighing system is made of three components; mechanic system, electronic control board, and software. Firstly, a data set is created on the basis of analogue egg weight data obtained from the dynamic weighing system. From the obtained data set, three different feature vectors are extracted by using Time-Domain (TD), Power Spectral Density (PSD) and Discrete Wavelet Transform (DWT) based methods. The extracted feature vectors are then applied to Linear Bayes Normal Classifier (LBNC), Fisher's Linear Discriminant Analysis (FLDA), Support Vector Machine (SVM), Decision Tree (DT), and K-Nearest Neighborhood (k-NN) classifiers respectively and egg weight classes are determined. A five-fold crossvalidation is carried out in order to confidentially test the performance of classification. As can be seen from the experimental results, both feature vectors and classifiers are highly successful in determining the weight classes of eggs. It is observed that the most successful features are the entropy values of DWT with a classification rate of 97.01% for the k-NN classifier.

show abstract

“…Fiducial cross sections as function of the jet multiplicity and eight differential variables test perturbative QCD under various conditions. Measuring W + and W − production separately, in addition allows to probe valence quark PDFs in a range of the momentum fraction x of the proton which is complementary to inclusive cross section measurements 13 .…”

Section: W Boson Production In Association With Jetsmentioning

confidence: 99%

Precision Measurements with an Electroweak Boson in the Final State with the ATLAS Detector

Lang

2018

Int. J. Mod. Phys. Conf. Ser.

View full text Add to dashboard Cite

Measurements of the Drell-Yan production of [Formula: see text] and [Formula: see text] bosons at the LHC provide a benchmark of our understanding of perturbative QCD and probe the proton structure in a unique way. The ATLAS collaboration has performed new measurements for [Formula: see text], [Formula: see text] and [Formula: see text] boson production, reaching unprecedented precision and strong constraints on parton distribution functions, in particular the strange quark density. Studying jet production in association with a vector boson, perturbative QCD predictions can be tested in a multi-scale environment. Once the QCD aspects of the vector boson production are understood, high precision measurements aim at the tests of the electroweak sector, such as measuring the [Formula: see text] boson mass. Here, a selection of recent ATLAS measurements, as presented at the 21st Particles and Nuclei International Conference, in September 2017 in Beijing, China, is discussed.

show abstract

Comparative Analysis of Outlier Detection Techniques

Cited by 19 publications

References 32 publications

Moonlighting protein prediction using physico-chemical and evolutional properties via machine learning methods

Moonlighting protein prediction using physico-chemical and evolutional properties via machine learning methods

Classification of Dynamic Egg Weights Using Feature Extraction Methods

Precision Measurements with an Electroweak Boson in the Final State with the ATLAS Detector

Contact Info

Product

Resources

About