An Integrated Method for Outlier Detection with Analytical Study of Distance Based and Angle Based Approaches

Mishra, Deepti; Soni, Devpriya

doi:10.1145/2905055.2905201

Cited by 4 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, a new approach is introduced and proposed [6] to find the outliers in the dataset called "Outlier Detection using Angle Based and Distance based Approach" (ODAD). It consists of four steps: density calculation, cluster identification, angle calculation, Euclidean distance calculation.…”

Section: Methodsmentioning

confidence: 99%

“…Equations to derive the co-ordinate values are given below In the algorithm as shown in figure 2, the analysis and value of coordinates of squares are calculated and put the entry in the square table. Now, the plane is divided into squares, the formula is given in equation ( 5) and equation (6).…”

Section: Number Of Squares On X Axismentioning

confidence: 99%

“…Local outliers are different from its neighbourhood only. This paper presents the algorithm for detecting outliers from the data named ODAD [6]. The algorithm combines the methodology of 'Angle based' approach and 'Distance based' approach to detect outliers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Outlier Detection for Improving Data Robust by ODAD Clustering Technique

Mishra¹,

Niu²

2019

IJATCSE

Self Cite

View full text Add to dashboard Cite

The paper presents the concept of outliers and its detection by applying an altogether a new approach. Outliers are the odd man out data points falling under the domain of data mining. Data Mining is the evolving heading, now a days because of its ability to deal large amount of data. This paper identifies the outliers in the dataset through an algorithm named outlier detection based on angle and distance based (ODAD) which is based on clustering techniques (which is combination of the angle based and distance based approaches). It encompasses basic five steps: density calculation, cluster identification, angle calculation, Euclidean distance calculation and finally outlier identification and detection. It first calculates the density between the data points to identify the "clusters". Further, to circle out the outliers, the distance-based method of clustering is applied collectively with angle based method to calculate the distance between the data points. The algorithm assigns the rank value to top most outlier data points. Data points having highest rank values considered as outliers. ODAD is implemented in both R and MSSQL.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Number Of Squares On X Axismentioning

confidence: 99%

See 1 more Smart Citation

Outlier Detection for Improving Data Robust by ODAD Clustering Technique

Mishra¹,

Niu²

2019

IJATCSE

Self Cite

View full text Add to dashboard Cite

show abstract

“…, where m is the attribute dimension of data object, V ik represents the value of the i th object in the k th attribute. q is a positive integer, and q = 1 and q = 2 denote the absolute distance and Euclidean distance, respectively (Mishra and Soni 2016). The first arrivals have only two attributes in the time-offset coordinates: the time and the offset, so the Euclidean distance between two first arrivals can be expressed as follows:…”

Section: Distance-based Outlier Detection Algorithmmentioning

confidence: 99%

First-arrival automatic picking based on improved energy ratio method and outlier detection theory

Qin

Pan

et al. 2021

Acta Geophys.

View full text Add to dashboard Cite

Based on the energy ratio method, an automatic picking method with strong noise resistance is proposed. It considers the influence of the current point's position on the first-arrival characteristic value. Specifically, an outlier detection technique is proposed to eliminate abnormal first arrivals for low signal-to-noise ratio (SNR) seismic data. First, the first arrivals of adjacent shots obtained by the new method are arranged according to the offsets. Then, combined with the distribution characteristics of the first arrivals, a symmetric window centered on the current point is established as the calculation range, and the distance-based outlier detection method is adopted for the abnormal first arrivals. The size of the calculation time window is determined by scanning the given value range. In order to optimize the processing results, we further propose an outlier detection method based on grid density. After this step, the abnormal first arrivals will be further eliminated. Following these steps, the abnormal first arrivals of all shots can be removed effectively. The actual data processing results show that the proposed program can accurately pick up the first arrivals and has a good performance in detecting the abnormal first arrivals. KeywordsFirst-arrival automatic picking • Abnormal first arrivals elimination • Distance-based outlier detection • Griddensity-based outlier detection Communicated by Prof. Sanyi Yuan (ASSOCIATE EDITOR), Prof. Michał Malinowski (CO-EDITOR-IN-CHIEF).

show abstract