A label noise filtering and label missing supplement framework based on game theory

Liu, Yuwen; Yao, Rongju; Wang, Fan; Wang, Ruili; Ma, Rui; Qi, Lianyong

doi:10.1016/j.dcan.2021.12.008

Cited by 5 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data mining techniques have provided outstanding performance in many applications, e.g., data security and privacy 20 , game theory 21 , blockchain systems 22 , healthcare 23 , etc. Due to the recent development of phishing detection methods, various machine learning-based techniques have also been employed 6 , 9 , 10 , 13 to investigate the legality of websites.…”

Section: Related Workmentioning

confidence: 99%

An effective detection approach for phishing websites using URL and HTML features

Aljofey

Jiang

Rasool

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Today's growing phishing websites pose significant threats due to their extremely undetectable risk. They anticipate internet users to mistake them as genuine ones in order to reveal user information and privacy, such as login ids, pass-words, credit card numbers, etc. without notice. This paper proposes a new approach to solve the anti-phishing problem. The new features of this approach can be represented by URL character sequence without phishing prior knowledge, various hyperlink information, and textual content of the webpage, which are combined and fed to train the XGBoost classifier. One of the major contributions of this paper is the selection of different new features, which are capable enough to detect 0-h attacks, and these features do not depend on any third-party services. In particular, we extract character level Term Frequency-Inverse Document Frequency (TF-IDF) features from noisy parts of HTML and plaintext of the given webpage. Moreover, our proposed hyperlink features determine the relationship between the content and the URL of a webpage. Due to the absence of publicly available large phishing data sets, we needed to create our own data set with 60,252 webpages to validate the proposed solution. This data contains 32,972 benign webpages and 27,280 phishing webpages. For evaluations, the performance of each category of the proposed feature set is evaluated, and various classification algorithms are employed. From the empirical results, it was observed that the proposed individual features are valuable for phishing detection. However, the integration of all the features improves the detection of phishing sites with significant accuracy. The proposed approach achieved an accuracy of 96.76% with only 1.39% false-positive rate on our dataset, and an accuracy of 98.48% with 2.09% false-positive rate on benchmark dataset, which outperforms the existing baseline approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

An effective detection approach for phishing websites using URL and HTML features

Aljofey

Jiang

Rasool

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The unreliability of label data has been studied across borders. Liu, Qi et al 14 , 15 proposed a framework for tag noise filtering and missing Tag Supplement (LNFS). They take location tags in location-based social networks (LBSN) as an example to implement our framework.…”

Section: Related Workmentioning

confidence: 99%

A pavement distresses identification method optimized for YOLOv5s

Guo

Yang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Automatic detection and recognition of pavement distresses is the key to timely repair of pavement. Repairing the pavement distresses in time can prevent the destruction of road structure and the occurrence of traffic accidents. However, some other factors, such as a single object category, shading and occlusion, make detection of pavement distresses very challenging. In order to solve these problems, we use the improved YOLOv5 model to detect various pavement distresses. We optimize the YOLOv5 model and introduce attention mechanism to enhance the robustness of the model. The improved model is more suitable for deployment in embedded devices. The optimized model is transplanted to the self-built intelligent mobile platform. Experimental results show that the improved network model proposed in this paper can effectively identify pavement distresses on the self-built intelligent mobile platform and datasets. The precision, recall and mAP are 95.5%, 94.3% and 95%. Compared with YOLOv5s and YOLOv4 models, the mAP of the improved YOLOv5s model is increased by 4.3% and 25.8%. This method can provide technical reference for pavement distresses detection robot.

show abstract

“…Moreover, studies have been conducted to improve the performance of algorithms by improving the data quality. Liu [ 21 ] vectorized restaurant names and user comments in social networks and improved the low-quality data and data without location labels based on cosine similarity. The performance of the labeling model was improved using game theory [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Kim

Lee

2022

Sensors

View full text Add to dashboard Cite

This paper proposes a data valuation algorithm for inertial measurement unit-based human activity recognition (IMU-based HAR) data based on meta reinforcement learning. Unlike previous studies that received feature-level input, the algorithm in this study added a feature extraction structure to the data valuation algorithm, and it can receive raw-level inputs and achieve excellent performance. As IMU-based HAR data are multivariate time-series data, the proposed algorithm incorporates an architecture capable of extracting both local and global features by inserting a transformer encoder after the one-dimensional convolutional neural network (1D-CNN) backbone in the data value estimator. In addition, the 1D-CNN-based stacking ensemble structure, which exhibits excellent efficiency and performance on IMU-based HAR data, is used as a predictor to supervise model training. The Berg balance scale (BBS) IMU-based HAR dataset and the public datasets, UCI-HAR, WISDM, and PAMAP2, are used for performance evaluation in this study. The valuation performance of the proposed algorithm is observed to be excellent on IMU-based HAR data. The rate of discovering corrupted data is higher than 96% on all datasets. In addition, classification performance is confirmed to be improved by the suppression of discovery of low-value data.

show abstract

A label noise filtering and label missing supplement framework based on game theory

Cited by 5 publications

References 41 publications

An effective detection approach for phishing websites using URL and HTML features

An effective detection approach for phishing websites using URL and HTML features

A pavement distresses identification method optimized for YOLOv5s

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Contact Info

Product

Resources

About