Multimedia datasets for anomaly detection: a review

Kumari, Pratibha; Bedi, Anterpreet Kaur; Saini, Mukesh

doi:10.1007/s11042-023-17425-z

Cited by 2 publications

(1 citation statement)

References 233 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, along with the explosive interest in artificial intelligence technology, machine learning-based anomaly detection techniques are being studied in vari-ous approaches [56][57][58][59][60]. Various industries are studying by applying anomaly detection techniques [61][62][63][64][65][66][67][68][69][70]. In marine engineering, several studies have been conducted to detect anomalies related to ship path movements.…”

Section: Machine Learning-based Anomaly Detectionmentioning

confidence: 99%

Machine Learning-Based Anomaly Detection on Seawater Temperature Data with Oversampling

Kang,

Kim,

Lim

2024

JMSE

View full text Add to dashboard Cite

This study deals with a method for anomaly detection in seawater temperature data using machine learning methods with oversampling techniques. Data were acquired from 2017 to 2023 using a Conductivity–Temperature–Depth (CTD) system in the Pacific Ocean, Indian Ocean, and Sea of Korea. The seawater temperature data consist of 1414 profiles including 1218 normal and 196 abnormal profiles. This dataset has an imbalance problem in which the amount of abnormal data is insufficient compared to that of normal data. Therefore, we generated abnormal data with oversampling techniques using duplication, uniform random variable, Synthetic Minority Oversampling Technique (SMOTE), and autoencoder (AE) techniques for the balance of data class, and trained Interquartile Range (IQR)-based, one-class support vector machine (OCSVM), and Multi-Layer Perceptron (MLP) models with a balanced dataset for anomaly detection. In the experimental results, the F1 score of the MLP showed the best performance at 0.882 in the combination of learning data, consisting of 30% of the minor data generated by SMOTE. This result is a 71.4%-point improvement over the F1 score of the IQR-based model, which is the baseline of this study, and is 1.3%-point better than the best-performing model among the models without oversampling data.

show abstract