Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection

Shuo Liu; Damien Coyle

doi:10.1109/IJCNN55064.2022.9891877

Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection

Shuo Liu, Damien Coyle

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

101 Downloads (Pure)

Abstract

Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) algorithm can accurately estimate a boundary around normal data which is subsequently used to detect novelties. However, the computational complexity and the convergence time of the LSBD algorithms increases substantially when data dimensionality increases. To solve those challenges, we propose an Integrated Autoencoder-Level Set Method (AE-LSM) for ND in this paper. The AE structure is employed to reduce the feature space with high dimensionality to a 3-dimensional (3D) space. The LSM algorithm is trained based on the compressed 3D data to identify the boundary of normal data. The AE-LSM has advantages of boundary control and good generalization performance. Experiments on 5 benchmark UCI datasets and an Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed AE-LSM present a 3%~14% significant improvement based on the average AUC (p<0.05) over the AE and LSBD algorithms across the six datasets.

Original language	English
Title of host publication	2022 International Joint Conference on Neural Networks (IJCNN)
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	978-1-7281-8671-9, 978-1-6654-9526-4
DOIs	https://doi.org/10.1109/IJCNN55064.2022.9891877
Publication status	Published (in print/issue) - 30 Sept 2022
Event	IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - Italy, Padua, Italy Duration: 18 Jul 2022 → 23 Jul 2022 https://wcci2022.org/

Publication series

Name
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE
Abbreviated title	WCCI2022
Country/Territory	Italy
City	Padua
Period	18/07/22 → 23/07/22
Internet address	https://wcci2022.org/

Bibliographical note

Funding Information:
Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

Funding Information:
We are grateful for access to the Tier 2 High Performance Computing resources provided by the Northern Ireland High-Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant Nos. EP/T022175/ and EP/W03204X/1. DC is grateful for the UKRI Turing AI Fellowship 2021-2025 funded by the EPSRC (grant number EP/V025724/1). This project was supported by Vice Chancellor Research Scholarship, Ulster University, the Alzheimer's Research UK NI Networking, and the Global Challenges Research Fund Networking.

Publisher Copyright:
© 2022 IEEE.

Funding

Funding Information: Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. Funding Information: We are grateful for access to the Tier 2 High Performance Computing resources provided by the Northern Ireland High-Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant Nos. EP/T022175/ and EP/W03204X/1. DC is grateful for the UKRI Turing AI Fellowship 2021-2025 funded by the EPSRC (grant number EP/V025724/1). This project was supported by Vice Chancellor Research Scholarship, Ulster University, the Alzheimer's Research UK NI Networking, and the Global Challenges Research Fund Networking. Publisher Copyright: © 2022 IEEE.

Keywords

Novelty Detection
Level set method
autoencoder
Level set boundary description
novelty detection
level set boundary description
level set methods

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IJCNN55064.2022.9891877

Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty DetectionAuthor Accepted Manuscript -, 814 KB

Cite this

@inproceedings{f3d4d25d4b7140039f1dd255eed73255,

title = "Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection",

abstract = "Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) algorithm can accurately estimate a boundary around normal data which is subsequently used to detect novelties. However, the computational complexity and the convergence time of the LSBD algorithms increases substantially when data dimensionality increases. To solve those challenges, we propose an Integrated Autoencoder-Level Set Method (AE-LSM) for ND in this paper. The AE structure is employed to reduce the feature space with high dimensionality to a 3-dimensional (3D) space. The LSM algorithm is trained based on the compressed 3D data to identify the boundary of normal data. The AE-LSM has advantages of boundary control and good generalization performance. Experiments on 5 benchmark UCI datasets and an Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed AE-LSM present a 3\%\textasciitilde{}14\% significant improvement based on the average AUC (p<0.05) over the AE and LSBD algorithms across the six datasets.",

keywords = "Novelty Detection, Level set method, autoencoder, Level set boundary description, novelty detection, level set boundary description, level set methods",

author = "Shuo Liu and Damien Coyle",

note = "Funding Information: Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research \& Development, LLC.; Johnson \& Johnson Pharmaceutical Research \& Development LLC.; Lumosity; Lundbeck; Merck \& Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. Funding Information: We are grateful for access to the Tier 2 High Performance Computing resources provided by the Northern Ireland High-Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant Nos. EP/T022175/ and EP/W03204X/1. DC is grateful for the UKRI Turing AI Fellowship 2021-2025 funded by the EPSRC (grant number EP/V025724/1). This project was supported by Vice Chancellor Research Scholarship, Ulster University, the Alzheimer's Research UK NI Networking, and the Global Challenges Research Fund Networking. Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, WCCI2022 ; Conference date: 18-07-2022 Through 23-07-2022",

year = "2022",

month = sep,

day = "30",

doi = "10.1109/IJCNN55064.2022.9891877",

language = "English",

publisher = "IEEE",

booktitle = "2022 International Joint Conference on Neural Networks (IJCNN)",

address = "United States",

url = "https://wcci2022.org/",

}

TY - GEN

T1 - Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection

AU - Liu, Shuo

AU - Coyle, Damien

N1 - Funding Information: Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. Funding Information: We are grateful for access to the Tier 2 High Performance Computing resources provided by the Northern Ireland High-Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant Nos. EP/T022175/ and EP/W03204X/1. DC is grateful for the UKRI Turing AI Fellowship 2021-2025 funded by the EPSRC (grant number EP/V025724/1). This project was supported by Vice Chancellor Research Scholarship, Ulster University, the Alzheimer's Research UK NI Networking, and the Global Challenges Research Fund Networking. Publisher Copyright: © 2022 IEEE.

PY - 2022/9/30

Y1 - 2022/9/30

N2 - Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) algorithm can accurately estimate a boundary around normal data which is subsequently used to detect novelties. However, the computational complexity and the convergence time of the LSBD algorithms increases substantially when data dimensionality increases. To solve those challenges, we propose an Integrated Autoencoder-Level Set Method (AE-LSM) for ND in this paper. The AE structure is employed to reduce the feature space with high dimensionality to a 3-dimensional (3D) space. The LSM algorithm is trained based on the compressed 3D data to identify the boundary of normal data. The AE-LSM has advantages of boundary control and good generalization performance. Experiments on 5 benchmark UCI datasets and an Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed AE-LSM present a 3%~14% significant improvement based on the average AUC (p<0.05) over the AE and LSBD algorithms across the six datasets.

AB - Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) algorithm can accurately estimate a boundary around normal data which is subsequently used to detect novelties. However, the computational complexity and the convergence time of the LSBD algorithms increases substantially when data dimensionality increases. To solve those challenges, we propose an Integrated Autoencoder-Level Set Method (AE-LSM) for ND in this paper. The AE structure is employed to reduce the feature space with high dimensionality to a 3-dimensional (3D) space. The LSM algorithm is trained based on the compressed 3D data to identify the boundary of normal data. The AE-LSM has advantages of boundary control and good generalization performance. Experiments on 5 benchmark UCI datasets and an Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed AE-LSM present a 3%~14% significant improvement based on the average AUC (p<0.05) over the AE and LSBD algorithms across the six datasets.

KW - Novelty Detection

KW - Level set method

KW - autoencoder

KW - Level set boundary description

KW - novelty detection

KW - level set boundary description

KW - level set methods

UR - https://ieeexplore.ieee.org/xpl/conhome/1000500/all-proceedings

UR - https://www.scopus.com/pages/publications/85140783127

U2 - 10.1109/IJCNN55064.2022.9891877

DO - 10.1109/IJCNN55064.2022.9891877

M3 - Conference contribution

BT - 2022 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE

Y2 - 18 July 2022 through 23 July 2022

ER -

Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Efficient level set method for novelty detection

Cite this

Integrated Autoencoder-Level Set Method Outperforms Autoencoder for Novelty Detection

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Student theses

Efficient level set method for novelty detection

Cite this