A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023
Almost 85% of companies polled said they were looking into anomaly detection (AD) technologies for their industrial image anomalies. The present problem concerns detecting anomalies often occupied by redundant data. It can be either in images or in videos. Finding a correct pattern is a challenging...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Information Security |
| Online Access: | http://dx.doi.org/10.1049/2024/8821891 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825199952017489920 |
|---|---|
| author | Shalini Kumari Chander Prabha Asif Karim Md. Mehedi Hassan Sami Azam |
| author_facet | Shalini Kumari Chander Prabha Asif Karim Md. Mehedi Hassan Sami Azam |
| author_sort | Shalini Kumari |
| collection | DOAJ |
| description | Almost 85% of companies polled said they were looking into anomaly detection (AD) technologies for their industrial image anomalies. The present problem concerns detecting anomalies often occupied by redundant data. It can be either in images or in videos. Finding a correct pattern is a challenging task. AD is crucial for various applications, including network security, fraud detection, predictive maintenance, fault diagnosis, and industrial and healthcare monitoring. Many researchers have proposed numerous methods and worked in the area of AD. Multiple anomalies and considerable intraclass variation make industrial datasets tough. Further, research is needed to create robust, efficient techniques that generalize datasets and detect anomalies in complex industrial images. The outcome of this study focuses on various AD methods from 2019 to 2023. These techniques are categorized further into machine learning (ML), deep learning (DL), and federated learning (FL). It explores AD approaches, datasets, technologies, complexities, and obstacles, emphasizing the requirement for effective detection across domains. It explores the results achieved in various ML, DL, and FL AD methods, which helps researchers explore these techniques further. Future research directions include improving model performance, leveraging multiple validation techniques, optimizing resource utilization, generating high-quality datasets, and focusing on real-world applications. The paper addresses the changing environment of AD methods and emphasizes the importance of continuing research and innovation. Each ML and DL AD model has strengths and shortcomings, concentrating on accuracy and performance while applying quality parameters for evaluation. FL provides a collaborative way to improve AD using distributed data sources and data privacy. |
| format | Article |
| id | doaj-art-62e4060359a3455cac4e1c1b4f934701 |
| institution | Kabale University |
| issn | 1751-8717 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Information Security |
| spelling | doaj-art-62e4060359a3455cac4e1c1b4f9347012025-02-08T00:00:08ZengWileyIET Information Security1751-87172024-01-01202410.1049/2024/8821891A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023Shalini Kumari0Chander Prabha1Asif Karim2Md. Mehedi Hassan3Sami Azam4Chitkara University Institute of Engineering and TechnologyChitkara University Institute of Engineering and TechnologyFaculty of Science and TechnologyComputer Science and Engineering DisciplineFaculty of Science and TechnologyAlmost 85% of companies polled said they were looking into anomaly detection (AD) technologies for their industrial image anomalies. The present problem concerns detecting anomalies often occupied by redundant data. It can be either in images or in videos. Finding a correct pattern is a challenging task. AD is crucial for various applications, including network security, fraud detection, predictive maintenance, fault diagnosis, and industrial and healthcare monitoring. Many researchers have proposed numerous methods and worked in the area of AD. Multiple anomalies and considerable intraclass variation make industrial datasets tough. Further, research is needed to create robust, efficient techniques that generalize datasets and detect anomalies in complex industrial images. The outcome of this study focuses on various AD methods from 2019 to 2023. These techniques are categorized further into machine learning (ML), deep learning (DL), and federated learning (FL). It explores AD approaches, datasets, technologies, complexities, and obstacles, emphasizing the requirement for effective detection across domains. It explores the results achieved in various ML, DL, and FL AD methods, which helps researchers explore these techniques further. Future research directions include improving model performance, leveraging multiple validation techniques, optimizing resource utilization, generating high-quality datasets, and focusing on real-world applications. The paper addresses the changing environment of AD methods and emphasizes the importance of continuing research and innovation. Each ML and DL AD model has strengths and shortcomings, concentrating on accuracy and performance while applying quality parameters for evaluation. FL provides a collaborative way to improve AD using distributed data sources and data privacy.http://dx.doi.org/10.1049/2024/8821891 |
| spellingShingle | Shalini Kumari Chander Prabha Asif Karim Md. Mehedi Hassan Sami Azam A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 IET Information Security |
| title | A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 |
| title_full | A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 |
| title_fullStr | A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 |
| title_full_unstemmed | A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 |
| title_short | A Comprehensive Investigation of Anomaly Detection Methods in Deep Learning and Machine Learning: 2019–2023 |
| title_sort | comprehensive investigation of anomaly detection methods in deep learning and machine learning 2019 2023 |
| url | http://dx.doi.org/10.1049/2024/8821891 |
| work_keys_str_mv | AT shalinikumari acomprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT chanderprabha acomprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT asifkarim acomprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT mdmehedihassan acomprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT samiazam acomprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT shalinikumari comprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT chanderprabha comprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT asifkarim comprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT mdmehedihassan comprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 AT samiazam comprehensiveinvestigationofanomalydetectionmethodsindeeplearningandmachinelearning20192023 |