TWTing Wang

Ting Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ting Wang has a total of 64 co-authors. Here are the top co-authors by number of shared publications:

  • Wing W. Y. Ng

    South China University of Technology

    11 shared publications
  • Jianjun Zhang

    College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China

    3 shared publications
  • Jintao Tang

    College of Computer, National University of Defense Technology, Changsha, China

    2 shared publications
  • Mingyang Zhang

    Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

    2 shared publications
  • Siyi Chen

    Department of Radiology, Guangzhou First Peoples Hospital, School of Medicine, South China University of Technology, Guangzhou, China

    2 shared publications
  • Wendi Li

    Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

    2 shared publications

Latest Publications

  • Localized Intra- and Inter-Tumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer

    by Yinhao Liang, Wenjie Tang, Qingcong Kong, Ting Wang, Jianjun Zhang, Wing W. Y. Ng, Siyi Chen, Ying Li, Yuan Guo

    This study proposes a novel method for extracting breast cancer tumor heterogeneity descriptors to non-invasively predict whether pathological complete response (pCR) can be achieved after neoadjuvant chemotherapy (NAC). These localized descriptors extract corresponding heterogeneity features for different radiomic features and are able to capture tumor characteristics at various localization levels. These descriptors also capture tumor heterogeneity both at the individual tumor level and across the whole dataset, providing decision-making models with features that are both more effective and interpretable. We validated the effectiveness of the proposed features with the Kolmogorov-Arnold network (KAN) across multiple centers, yielding an AUC of 0.92 when combined with pathological features and demonstrating good performance in external datasets (AUCs of 0.84 and 0.81). Additionally, we transform the best model into a symbolic formula to intuitively explain the machine learning model's prediction process, showing how factors such as age, HER2, Ki-67 and heterogeneity influence the prediction. The symbolized model is consistent with the experience of clinical experts, which enhances users' confidence in deep models. The experimental results show that our proposed features and method outperform classical heterogeneity features and end-to-end neural networks with a small additional computational cost.


  • HRadNet: A Hierarchical Radiomics-Based Network for Multicenter Breast Cancer Molecular Subtypes Prediction

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

    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.


  • GFFR-Net: Extraction of Forged General Features for Face Forgery Detection

    by Jin Dong, Pu Sun, Xinying Liu, Ting Wang, Yuhuan Feng, Yaning Shi

    Currently, advanced face forgery techniques are continuously evolving, and low-cost forgery methods are increasing in number. Faced with numerous novel and unknown forgery approaches, existing recognition models often struggle to achieve good generalization capabilities across different forgery domains. After conducting in-depth exploration and experiments on existing classification models and face forgery methods, we have improved the general process of face forgery recognition and proposed a generalized face forgery recognition method (GFFR-Net). This model features a designed extractor that solely extracts mid-level and deep semantic features from images and a domain alignment module capable of masking non-generalized forged features. The design of the feature extractor and domain alignment module aims to help the classifier extract all generalized forged features and address the distribution differences between data originating from various forgery methods. Additionally, we employ a fine-tuned VisionTransformer(ViT) as the classifier for face forgery recognition. During the training process of GFFR-Net, we created a new dataset from facial images generated by eleven different face editing methods, dividing it into two groups for training: ID-Replaced and ID-Remained. In the model comparison and ablation experiments, we used two forgery methods, FSGAN and StyleGAN2, which were not involved in the model training, to validate the generalization capabilities. The experimental results show that the domain generalization ability of this model is significantly superior to that of many powerful baseline models and state-of-the-art models.

  • Assessing Word Difficulty: A Mapping Method

    by Jingyi Tang, Ting Wang, Sicheng Zhu

    This paper presents a word difficulty mapping method that utilizes three indicators: Average Number of Times, Word Frequency Score, and Word Difficulty Score, to map the difficulty of words. The effectiveness of this method is demonstrated using the EERIE as a case study. To predict the Average Number of Times, a Refined Simulated Annealing Model, which combines K-Dimension Tree, is employed. Subsequently, word difficulty is mapped using K-Means cluster analysis. The results indicate a strong correlation between the Average Number of Times, Frequency Score of The Word, Difficulty Score of The Word and word difficulty, highlighting the efficacy of the proposed word difficulty mapping method.

  • SBHA: Sensitive Binary Hashing Autoencoder for Image Retrieval

    by Ting Wang, Su Lu, Jianjun Zhang, Xuyu Liu, Xing Tian, Wing W. Y. Ng, Wei-Neng Chen

    Binary hashing is an effective approach for content-based image retrieval, and learning binary codes with neural networks has attracted increasing attention in recent years. However, the training of hashing neural networks is difficult due to the binary constraint on hash codes. In addition, neural networks are easily affected by input data with small perturbations. Therefore, a sensitive binary hashing autoencoder (SBHA) is proposed to handle these challenges by introducing stochastic sensitivity for image retrieval. SBHA extracts meaningful features from original inputs and maps them onto a binary space to obtain binary hash codes directly. Different from ordinary autoencoders, SBHA is trained by minimizing the reconstruction error, the stochastic sensitive error, and the binary constraint error simultaneously. SBHA reduces output sensitivity to unseen samples with small perturbations from training samples by minimizing the stochastic sensitive error, which helps to learn more robust features. Moreover, SBHA is trained with a binary constraint and outputs binary codes directly. To tackle the difficulty of optimization with the binary constraint, we train the SBHA with alternating optimization. Experimental results on three benchmark datasets show that SBHA is competitive and significantly outperforms state-of-the-art methods for binary hashing.


  • BASS: Broad Network Based on Localized Stochastic Sensitivity

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

    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.


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

    by Jianjun Zhang, Ting Wang, Wing W. Y. Ng, Witold Pedrycz

    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.


  • Population-Based Hyperparameter Tuning With Multitask Collaboration

    by Wendi Li, Ting Wang, Wing W. Y. Ng

    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.


  • Multi-Localized Sensitive Autoencoder-Attention-LSTM For Skeleton-based Action Recognition

    by Wing Ng, Mingyang Zhang, Ting Wang

    One of key challenges of skeleton-based action recognition (SAR) tasks is the complex nature of human motion patterns. Variations such as performers and viewpoints may impose negative effects to the action recognition accuracy. In this work, we propose the Multi-Localized Sensitive Autoencoder-Attention-LSTM (Multi-LiSAAL) for SAR. The Localized Stochastic Sensitive Autoencoder (LiSSA) encodes both spatial and temporal information, and extracts meaningful features from different parts (four limbs and a trunk) from the skeleton. The LiSSA is trained by minimizing the localized generalization error to enhance the robustness of autoencoders via reducing its sensitivity with respect to small variations in inputs. We apply an attention mechanism to assign different weights to different skeleton parts and focus more on informative sections. Then, a backbone classifier network takes weighted features as inputs to differentiates actions. Experimental results on five public benchmarking datasets show that the Multi-LiSAAL outperforms state-of-the-art methods.