LIVIVO - Search results -

Search results

Result 1 - 10 of total 23

Search options

Article ; Online: Population-Based Hyperparameter Tuning With Multitask Collaboration.

Li, Wendi / Wang, Ting / Ng, Wing W Y

IEEE transactions on neural networks and learning systems

2023 Volume 34, Issue 9, Page(s) 5719–5731

Abstract: Population-based optimization methods are widely used for hyperparameter (HP) tuning for a given specific task. In this work, we propose the population-based hyperparameter tuning with multitask collaboration (PHTMC), which is a general multitask ... ...

Abstract	Population-based optimization methods are widely used for hyperparameter (HP) tuning for a given specific task. In this work, we propose the population-based hyperparameter tuning with multitask collaboration (PHTMC), which is a general multitask collaborative framework with parallel and sequential phases for population-based HP tuning methods. In the parallel HP tuning phase, a shared population for all tasks is kept and the intertask relatedness is considered to both yield a better generalization ability and avoid data bias to a single task. In the sequential HP tuning phase, a surrogate model is built for each new-added task so that the metainformation from the existing tasks can be extracted and used to help the initialization for the new task. Experimental results show significant improvements in generalization abilities yielded by neural networks trained using the PHTMC and better performances achieved by multitask metalearning. Moreover, a visualization of the solution distribution and the autoencoder's reconstruction of both the PHTMC and a single-task population-based HP tuning method is compared to analyze the property with the multitask collaboration.
Language	English
Publishing date	2023-09-01
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2021.3130896
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: BASS: Broad Network Based on Localized Stochastic Sensitivity.

Wang, Ting / Zhang, Mingyang / Zhang, Jianjun / Ng, Wing W Y / Chen, C L Philip

IEEE transactions on neural networks and learning systems

2024 Volume 35, Issue 2, Page(s) 1681–1695

Abstract: The training of the standard broad learning system (BLS) concerns the optimization of its output weights via the minimization of both training mean square error (MSE) and a penalty term. However, it degrades the generalization capability and robustness ... ...

Abstract	The training of the standard broad learning system (BLS) concerns the optimization of its output weights via the minimization of both training mean square error (MSE) and a penalty term. However, it degrades the generalization capability and robustness of BLS when facing complex and noisy environments, especially when small perturbations or noise appear in input data. Therefore, this work proposes a broad network based on localized stochastic sensitivity (BASS) algorithm to tackle the issue of noise or input perturbations from a local perturbation perspective. The localized stochastic sensitivity (LSS) prompts an increase in the network's noise robustness by considering unseen samples located within a Q -neighborhood of training samples, which enhances the generalization capability of BASS with respect to noisy and perturbed data. Then, three incremental learning algorithms are derived to update BASS quickly when new samples arrive or the network is deemed to be expanded, without retraining the entire model. Due to the inherent superiorities of the LSS, extensive experimental results on 13 benchmark datasets show that BASS yields better accuracies on various regression and classification problems. For instance, BASS uses fewer parameters (12.6 million) to yield 1% higher Top-1 accuracy in comparison to AlexNet (60 million) on the large-scale ImageNet (ILSVRC2012) dataset.
Language	English
Publishing date	2024-02-05
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2022.3184846
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: KNNENS: A k-Nearest Neighbor Ensemble-Based Method for Incremental Learning Under Data Stream With Emerging New Classes.

Zhang, Jianjun / Wang, Ting / Ng, Wing W Y / Pedrycz, Witold

IEEE transactions on neural networks and learning systems

2023 Volume 34, Issue 11, Page(s) 9520–9527

Abstract: In this brief, we investigate the problem of incremental learning under data stream with emerging new classes (SENC). In the literature, existing approaches encounter the following problems: 1) yielding high false positive for the new class; i) having ... ...

Abstract	In this brief, we investigate the problem of incremental learning under data stream with emerging new classes (SENC). In the literature, existing approaches encounter the following problems: 1) yielding high false positive for the new class; i) having long prediction time; and 3) having access to true labels for all instances, which is unrealistic and unacceptable in real-life streaming tasks. Therefore, we propose the k -Nearest Neighbor ENSemble-based method (KNNENS) to handle these problems. The KNNENS is effective to detect the new class and maintains high classification performance for known classes. It is also efficient in terms of run time and does not require true labels of new class instances for model update, which is desired in real-life streaming classification tasks. Experimental results show that the KNNENS achieves the best performance on four benchmark datasets and three real-world data streams in terms of accuracy and F1-measure and has a relatively fast run time compared to four reference methods. Codes are available at https://github.com/Ntriver/KNNENS.
Language	English
Publishing date	2023-10-27
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2022.3149991
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Improving domain generalization by hybrid domain attention and localized maximum sensitivity.

Ng, Wing W Y / Zhang, Qin / Zhong, Cankun / Zhang, Jianjun

Neural networks : the official journal of the International Neural Network Society

2023 Volume 171, Page(s) 320–331

Abstract: Domain generalization has attracted much interest in recent years due to its practical application scenarios, in which the model is trained using data from various source domains but is tested using data from an unseen target domain. Existing domain ... ...

Abstract	Domain generalization has attracted much interest in recent years due to its practical application scenarios, in which the model is trained using data from various source domains but is tested using data from an unseen target domain. Existing domain generalization methods concern all visual features, including irrelevant ones with the same priority, which easily results in poor generalization performance of the trained model. In contrast, human beings have strong generalization capabilities to distinguish images from different domains by focusing on important features while suppressing irrelevant features with respect to labels. Motivated by this observation, we propose a channel-wise and spatial-wise hybrid domain attention mechanism to force the model to focus on more important features associated with labels in this work. In addition, models with higher robustness with respect to small perturbations of inputs are expected to have higher generalization capability, which is preferable in domain generalization. Therefore, we propose to reduce the localized maximum sensitivity of the small perturbations of inputs in order to improve the network's robustness and generalization capability. Extensive experiments on PACS, VLCS, and Office-Home datasets validate the effectiveness of the proposed method.
MeSH term(s)	Humans ; Generalization, Psychological ; Motivation
Language	English
Publishing date	2023-12-14
Publishing country	United States
Document type	Journal Article
ZDB-ID	740542-x
ISSN	1879-2782 ; 0893-6080
ISSN (online)	1879-2782
ISSN	0893-6080
DOI	10.1016/j.neunet.2023.12.014
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2365: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Concept Preserving Hashing for Semantic Image Retrieval With Concept Drift.

Tian, Xing / Ng, Wing W Y / Wang, Hui

IEEE transactions on cybernetics

2021 Volume 51, Issue 10, Page(s) 5184–5197

Abstract: Current hashing-based image retrieval methods mostly assume that the database of images is static. However, this assumption is not true in cases where the databases are constantly updated (e.g., on the Internet) and there exists the problem of concept ... ...

Abstract	Current hashing-based image retrieval methods mostly assume that the database of images is static. However, this assumption is not true in cases where the databases are constantly updated (e.g., on the Internet) and there exists the problem of concept drift. The online (also known as incremental) hashing methods have been proposed recently for image retrieval where the database is not static. However, they have not considered the concept drift problem. Moreover, they update hash functions dynamically by generating new hash codes for all accumulated data over time which is clearly uneconomical. In order to solve these two problems, concept preserving hashing (CPH) is proposed. In contrast to the existing methods, CPH preserves the original concept, that is, the set of hash codes representing a concept is preserved over time, by learning a new set of hash functions to yield the same set of hash codes for images (old and new) of a concept. The objective function of CPH learning consists of three components: 1) isomorphic similarity; 2) hash codes partition balancing; and 3) heterogeneous similarity fitness. The experimental results on 11 concept drift scenarios show that CPH yields better retrieval precisions than the existing methods and does not need to update hash codes of previously stored images.
Language	English
Publishing date	2021-10-12
Publishing country	United States
Document type	Journal Article
ISSN	2168-2275
ISSN (online)	2168-2275
DOI	10.1109/TCYB.2019.2955130
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Difference-Guided Representation Learning Network for Multivariate Time-Series Classification.

Ma, Qianli / Chen, Zipeng / Tian, Shuai / Ng, Wing W Y

IEEE transactions on cybernetics

2022 Volume 52, Issue 6, Page(s) 4717–4727

Abstract: Multivariate time series (MTSs) are widely found in many important application fields, for example, medicine, multimedia, manufacturing, action recognition, and speech recognition. The accurate classification of MTS has become an important research topic. ...

Abstract	Multivariate time series (MTSs) are widely found in many important application fields, for example, medicine, multimedia, manufacturing, action recognition, and speech recognition. The accurate classification of MTS has become an important research topic. Traditional MTS classification methods do not explicitly model the temporal difference information of time series, which is, in fact, important and reflects the dynamic evolution information. In this article, the difference-guided representation learning network (DGRL-Net) is proposed to guide the representation learning of time series by dynamic evolution information. The DGRL-Net consists of a difference-guided layer and a multiscale convolutional layer. First, in the difference-guided layer, we propose a difference gating LSTM to model the time dependency and dynamic evolution of the time series to obtain feature representations of both raw and difference series. Then, these two representations are used as two input channels of the multiscale convolutional layer to extract multiscale information. Extensive experiments demonstrate that the proposed model outperforms state-of-the-art methods on 18 MTS benchmark datasets and achieves competitive results on two skeleton-based action recognition datasets. Furthermore, the ablation study and visualized analysis are designed to verify the effectiveness of the proposed model.
MeSH term(s)	Learning ; Time Factors
Language	English
Publishing date	2022-06-16
Publishing country	United States
Document type	Journal Article
ISSN	2168-2275
ISSN (online)	2168-2275
DOI	10.1109/TCYB.2020.3034755
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: HRadNet: A Hierarchical Radiomics-Based Network for Multicenter Breast Cancer Molecular Subtypes Prediction.

Liang, Yinhao / Tang, Wenjie / Wang, Ting / Ng, Wing W Y / Chen, Siyi / Jiang, Kuiming / Wei, Xinhua / Jiang, Xinqing / Guo, Yuan

IEEE transactions on medical imaging

2024 Volume 43, Issue 3, Page(s) 1225–1236

Abstract: Breast cancer is a heterogeneous disease, where molecular subtypes of breast cancer are closely related to the treatment and prognosis. Therefore, the goal of this work is to differentiate between luminal and non-luminal subtypes of breast cancer. The ... ...

Abstract	Breast cancer is a heterogeneous disease, where molecular subtypes of breast cancer are closely related to the treatment and prognosis. Therefore, the goal of this work is to differentiate between luminal and non-luminal subtypes of breast cancer. The hierarchical radiomics network (HRadNet) is proposed for breast cancer molecular subtypes prediction based on dynamic contrast-enhanced magnetic resonance imaging. HRadNet fuses multilayer features with the metadata of images to take advantage of conventional radiomics methods and general convolutional neural networks. A two-stage training mechanism is adopted to improve the generalization capability of the network for multicenter breast cancer data. The ablation study shows the effectiveness of each component of HRadNet. Furthermore, the influence of features from different layers and metadata fusion are also analyzed. It reveals that selecting certain layers of features for a specified domain can make further performance improvements. Experimental results on three data sets from different devices demonstrate the effectiveness of the proposed network. HRadNet also has good performance when transferring to other domains without fine-tuning.
MeSH term(s)	Humans ; Female ; Breast Neoplasms/diagnostic imaging ; Breast Neoplasms/pathology ; Radiomics ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods ; Contrast Media ; Retrospective Studies
Chemical Substances	Contrast Media
Language	English
Publishing date	2024-03-05
Publishing country	United States
Document type	Multicenter Study ; Journal Article
ZDB-ID	622531-7
ISSN	1558-254X ; 0278-0062
ISSN (online)	1558-254X
ISSN	0278-0062
DOI	10.1109/TMI.2023.3331301
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2546: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: LiSSA: Localized Stochastic Sensitive Autoencoders.

Wang, Ting / Ng, Wing W Y / Pelillo, Marcello / Kwong, Sam

IEEE transactions on cybernetics

2021 Volume 51, Issue 5, Page(s) 2748–2760

Abstract: The training of autoencoder (AE) focuses on the selection of connection weights via a minimization of both the training error and a regularized term. However, the ultimate goal of AE training is to autoencode future unseen samples correctly (i.e., good ... ...

Abstract	The training of autoencoder (AE) focuses on the selection of connection weights via a minimization of both the training error and a regularized term. However, the ultimate goal of AE training is to autoencode future unseen samples correctly (i.e., good generalization). Minimizing the training error with different regularized terms only indirectly minimizes the generalization error. Moreover, the trained model may not be robust to small perturbations of inputs which may lead to a poor generalization capability. In this paper, we propose a localized stochastic sensitive AE (LiSSA) to enhance the robustness of AE with respect to input perturbations. With the local stochastic sensitivity regularization, LiSSA reduces sensitivity to unseen samples with small differences (perturbations) from training samples. Meanwhile, LiSSA preserves the local connectivity from the original input space to the representation space that learns a more robustness features (intermediate representation) for unseen samples. The classifier using these learned features yields a better generalization capability. Extensive experimental results on 36 benchmarking datasets indicate that LiSSA outperforms several classical and recent AE training methods significantly on classification tasks.
Language	English
Publishing date	2021-04-15
Publishing country	United States
Document type	Journal Article
ISSN	2168-2275
ISSN (online)	2168-2275
DOI	10.1109/TCYB.2019.2923756
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Hashing-Based Undersampling Ensemble for Imbalanced Pattern Classification Problems.

Ng, Wing W Y / Xu, Shichao / Zhang, Jianjun / Tian, Xing / Rong, Tongwen / Kwong, Sam

IEEE transactions on cybernetics

2022 Volume 52, Issue 2, Page(s) 1269–1279

Abstract: Undersampling is a popular method to solve imbalanced classification problems. However, sometimes it may remove too many majority samples which may lead to loss of informative samples. In this article, the hashing-based undersampling ensemble (HUE) is ... ...

Abstract	Undersampling is a popular method to solve imbalanced classification problems. However, sometimes it may remove too many majority samples which may lead to loss of informative samples. In this article, the hashing-based undersampling ensemble (HUE) is proposed to deal with this problem by constructing diversified training subspaces for undersampling. Samples in the majority class are divided into many subspaces by a hashing method. Each subspace corresponds to a training subset which consists of most of the samples from this subspace and a few samples from surrounding subspaces. These training subsets are used to train an ensemble of classification and regression tree classifiers with all minority class samples. The proposed method is tested on 25 UCI datasets against state-of-the-art methods. Experimental results show that the HUE outperforms other methods and yields good results on highly imbalanced datasets.
MeSH term(s)	Algorithms ; Research Design
Language	English
Publishing date	2022-02-16
Publishing country	United States
Document type	Journal Article
ISSN	2168-2275
ISSN (online)	2168-2275
DOI	10.1109/TCYB.2020.3000754
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Generative face inpainting hashing for occluded face retrieval.

Yang, Yuxiang / Tian, Xing / Ng, Wing W Y / Wang, Ran / Gao, Ying / Kwong, Sam

International journal of machine learning and cybernetics

2022 Volume 14, Issue 5, Page(s) 1725–1738

Abstract: COVID-19 has resulted in a significant impact on individual lives, bringing a unique challenge for face retrieval under occlusion. In this paper, an occluded face retrieval method which consists of generator, discriminator, and deep hashing retrieval ... ...

Abstract	COVID-19 has resulted in a significant impact on individual lives, bringing a unique challenge for face retrieval under occlusion. In this paper, an occluded face retrieval method which consists of generator, discriminator, and deep hashing retrieval network is proposed for face retrieval in a large-scale face image dataset under variety of occlusion situations. In the proposed method, occluded face images are firstly reconstructed using a face inpainting model, in which the adversarial loss, reconstruction loss and hash bits loss are combined for training. With the trained model, hash codes of real face images and corresponding reconstructed face images are aimed to be as similar as possible. Then, a deep hashing retrieval network is used to generate compact similarity-preserving hashing codes using reconstructed face images for a better retrieval performance. Experimental results show that the proposed method can successfully generate the reconstructed face images under occlusion. Meanwhile, the proposed deep hashing retrieval network achieves better retrieval performance for occluded face retrieval than existing state-of-the-art deep hashing retrieval methods.
Language	English
Publishing date	2022-12-02
Publishing country	Germany
Document type	Journal Article
ZDB-ID	2572473-3
ISSN	1868-808X ; 1868-8071
ISSN (online)	1868-808X
ISSN	1868-8071
DOI	10.1007/s13042-022-01723-3
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

Order via subito

Details ▾
- Full text online
- Order with fees

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Order via subito