FRIOD: A Deeply Integrated Feature-Rich Interactive System for Effective and Efficient Outlier Detection

Zhu, Xiaodong; Ji, Zhang; Li, Hongzhou; Fournier-Viger, Philippe; Lin, Jerry Chun‐Wei; Chang, Liang

doi:10.1109/access.2017.2771237

Cited by 12 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the above works, our hybrid approach focuses on the fiscal domain and provides an interactive network visualization environment through which tax officers can assess the results provided by machine learning and information diffusion methods. The importance of combining data mining and visualization methods has also been confirmed in [51] for the analysis of crime data and in [52] for the detection of outliers.…”

Section: Visualization Approachesmentioning

confidence: 95%

Combining Network Visualization and Data Mining for Tax Risk Assessment

et al. 2020

View full text Add to dashboard Cite

This paper presents a novel approach, called MALDIVE, to support tax administrations in the tax risk assessment for discovering tax evasion and tax avoidance. MALDIVE relies on a network model describing several kinds of relationships among taxpayers. Our approach suitably combines various data mining and visual analytics methods to support public officers in identifying risky taxpayers. MALDIVE consists of a 4-step pipeline: (i) A social network is built from the taxpayers data and several features of this network are extracted by computing both classical social network indexes and domain-specific indexes; (ii) an initial set of risky taxpayers is identified by applying machine learning algorithms; (iii) the set of risky taxpayers is possibly enlarged by means of an information diffusion strategy and the output is shown to the analyst through a network visualization system; (iv) a visual inspection of the network is performed by the analyst in order to validate and refine the set of risky taxpayers. We discuss the effectiveness of the MALDIVE approach through both quantitative analyses and case studies performed on real data in collaboration with the Italian Revenue Agency. INDEX TERMS Tax risk assessment, tax evasion discovery, network visualization, data mining, human-computer interaction.

show abstract

Section: Visualization Approachesmentioning

confidence: 95%

Combining Network Visualization and Data Mining for Tax Risk Assessment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In 2017, Zhu et al [19] developed FRIOD, an innovative interactive outlier detection method that incorporates deep human involvement to enhance detection performance and significantly simplify the detection process. The user-friendly interactive approach allows users to engage in the core outlier identification algorithm's primary stages, including locationaware distance thresholding, dense cell selection, and final top outlier validation.…”

Section: Literature Reviewmentioning

confidence: 99%

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

Govindaraj¹,

Kaliappan²,

Swaminathan³

2023

ISI

View full text Add to dashboard Cite

Outlier identification and elimination are essential preprocessing steps for data analysis tasks such as clustering, classification, and regression. The accuracy of data analysis outcomes may be compromised if outliers are not adequately addressed. Detecting outliers is particularly challenging when they are characterized by unusual combinations of multiple attributes. Furthermore, the presence of outliers can impact various data processing activities, necessitating either the reduction of outlier influence or their complete removal. Outlier detection in multivariate data presents a complex process that becomes increasingly difficult when dealing with high-dimensional datasets. Consequently, this study focuses on the identification of such outliers in multivariate datasets using intelligent techniques. In the proposed approach, outliers are detected using an Improved Neural Network (INN), where the hidden neurons are tuned by a novel Synergistic Firefly-Grey Wolf Optimization (SF-GWO) algorithm. This algorithm combines the strengths of the Firefly Optimization (SFO) and Grey Wolf Optimization (GWO) techniques to maximize accuracy. The unique method results in enhanced classification model performance, reduced computation time, and increased classification accuracy. The proposed model has been evaluated and compared with well-established traditional techniques, demonstrating its effectiveness in addressing the challenges of outlier detection in multidimensional datasets.

show abstract

“…In the literature, various feature extraction methods such as [ 35 , 41 , 64 , 66 ] have been used. In this study a new two-stage feature extraction approach has been presented.…”

Section: Proposed Systemmentioning

confidence: 99%

A hybrid LBP-DCNN based feature extraction method in YOLO: An application for masked face and social distance detection

Öztel

Akgün

2022

Multimed Tools Appl

View full text Add to dashboard Cite

COVID-19 is an ongoing pandemic and the WHO recommends at least one-meter social distance, and the use of medical face masks to slow the disease’s transmission. This paper proposes an automated approach for detecting social distance and face masks. Thus, it aims to help the reduction of diseases transferred by respiratory droplets such as COVID-19. For this system, a two-cascaded YOLO is used. The first cascade detects humans in the environment and computes the social distance between them. Then, the second cascade detects human faces with or without a mask. Finally, red bounding boxes encircle the people’s images that did not follow the rules. Also, in this paper, we propose a two-part feature extraction approach used with YOLO. The first part of the proposed feature extraction method extracts general features using the transfer learning approach. The second part extracts better features specific to the current task using the LBP layer and classification layers. The best average precision for the human detection task was obtained as 66% using Resnet50 in YOLO. The best average precision for the mask detection was obtained as 95% using Darknet19+LBP with YOLO. Also, another popular object detection network, Faster R-CNN, have been used for comparison purpose. The proposed system performed better than the literature in human and mask detection tasks.

show abstract

FRIOD: A Deeply Integrated Feature-Rich Interactive System for Effective and Efficient Outlier Detection

Cited by 12 publications

References 32 publications

Combining Network Visualization and Data Mining for Tax Risk Assessment

Combining Network Visualization and Data Mining for Tax Risk Assessment

An Enhanced Outlier Detection Approach for Multidimensional Datasets Using a Synergistic Firefly and Grey Wolf Optimization-Based Method

A hybrid LBP-DCNN based feature extraction method in YOLO: An application for masked face and social distance detection

Contact Info

Product

Resources

About