Author name cluster

Wang Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

JBHI Journal 2024 Journal Article

DEBCM: Deep Learning-Based Enhanced Breast Invasive Ductal Carcinoma Classification Model in IoMT Healthcare Systems

Amin Ul Haq
Jian Ping Li
Inayat Khan
Bless Lord Y. Agbley
Sultan Ahmad
M. Irfan Uddin
Wang Zhou
Shakir Khan

Accurate breast cancer (BC) diagnosis is a difficult task that is critical for the proper treatment of BC in IoMT (Internet of Medical Things) healthcare systems. This paper proposes a convolutional neural network (CNN)-based diagnosis method for detecting early-stage breast cancer. In developing the proposed method, we incorporated the CNN model for the invasive ductal carcinoma (IDC) classification using breast histology image data. We have incorporated transfer learning (TL) and data augmentation (DA) mechanisms to improve the CNN model's predictive outcomes. For the fine-tuning process, the CNN model was trained with breast histology image data. Furthermore, the held-out cross-validation method for best model selection and hyper-parameter tuning was incorporated. In addition, various performance evaluation metrics for model performance assessment were computed. The experimental results confirmed that the proposed model outperformed the baseline models across all evaluation metrics, achieving 99. 04% accuracy. We recommend the proposed method for early recognition of BC in IoMT healthcare systems due to its high performance.

Details DOI

AAAI Conference 2022 Conference Paper

An Adversarial Framework for Generating Unseen Images by Activation Maximization

Yang Zhang
Wang Zhou
Gaoyuan Zhang
David Cox
Shiyu Chang

Activation maximization (AM) refers to the task of generating input examples that maximize the activation of a target class of a classifier, which can be used for class-conditional image generation and model interpretation. A popular class of AM method, GAN-based AM, introduces a GAN pre-trained on a large image set, and performs AM over its input random seed or style embeddings, so that the generated images are natural and adversarial attacks are prevented. Most of these methods would require the image set to contain some images of the target class to be visualized. Otherwise they tend to generate other seen class images that most maximizes the target class activation. In this paper, we aim to tackle the case where information about the target class is completely removed from the image set. This would ensure that the generated images truly reflect the target class information residing in the classifier, not the target class information in the image set, which contributes to a more faithful interpretation technique. To this end, we propose PROBE- GAN, a GAN-based AM algorithm capable of generating image classes unseen in the image set. Rather than using a pre-trained GAN, PROBEGAN trains a new GAN with AM explicitly included in its training objective. PROBEGAN consists of a class-conditional generator, a seen-class discriminator, and an all-class unconditional discriminator. It can be shown that such a framework can generate images with the features of the unseen target class, while retaining the naturalness as depicted in the image set. Experiments have shown that PROBEGAN can generate unseen-class images with much higher quality than the baselines. We also explore using PROBEGAN as a model interpretation tool. Our code is at https: //github. com/csmiler/ProbeGAN/.

PDF Details

AAAI Conference 2020 Conference Paper

Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning

Xiang Ni
Jing Li
Mo Yu
Wang Zhou
Kun-Lung Wu

This paper considers the problem of resource allocation in stream processing, where continuous data ﬂows must be processed in real time in a large distributed system. To maximize system throughput, the resource allocation strategy that partitions the computation tasks of a stream processing graph onto computing devices must simultaneously balance workload distribution and minimize communication. Since this problem of graph partitioning is known to be NP-complete yet crucial to practical streaming systems, many heuristic-based algorithms have been developed to ﬁnd reasonably good solutions. In this paper, we present a graph-aware encoderdecoder framework to learn a generalizable resource allocation strategy that can properly distribute computation tasks of stream processing graphs unobserved from training data. We, for the ﬁrst time, propose to leverage graph embedding to learn the structural information of the stream processing graphs. Jointly trained with the graph-aware decoder using deep reinforcement learning, our approach can effectively ﬁnd optimized solutions for unseen graphs. Our experiments show that the proposed model outperforms both METIS, a state-of-the-art graph partitioning algorithm, and an LSTMbased encoder-decoder model, in about 70% of the test cases.

PDF Details