Dan Meng

Dan Meng

Auto-generated profile, based on publicly available information

Dan Meng

Institute of Information Engineering, CAS, Beijing, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2017 in IEEE Access
Verified
Journal Article
Open access
DMDan Meng
Dan Meng
LZLibo Zhang
Libo Zhang
GCGuitao Cao
Guitao Cao
WCWenming Cao
Wenming Cao
GZGuixu Zhang
Guixu Zhang
BHBing Hu
Bing Hu
Diagnostic ultrasound offers great improvements in diagnostic accuracy and robustness. However, it is difficult to make subjective and uniform diagnoses, because the quality of ultrasound images can be easily influenced by machine settings, the characteristics of ultrasonic waves, the interactions between ultrasound and body tissues, and other uncontrollable factors. In this paper, we propose a novel liver fibrosis classification method based on transfer learning (TL) using VGGNet and a deep classifier called fully connected network (FCNet). In case of insufficient samples, deep features extracted using TL strategy can provide sufficient classification information. These deep features are then sent to FCNet for the classification of different liver fibrosis statuses. With this framework, tests show that our deep features combined with the FCNet can provide suitable information to enable the construction of the most accurate prediction model when compared with other methods.

1 January 2017 in Evidence-Based Complementary and Alternative Medicine
Verified
Journal Article
Open access
PDF file
DMDan Meng
Dan Meng
GCGuitao Cao
Guitao Cao
YDYe Duan
Ye Duan
MZMinghua ZHU
Minghua ZHU
LTLiping Tu
Liping Tu
JXJiatuo Xu
Jiatuo Xu
Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM). However, the majority of the existing tongue image analyses and classification methods are based on the low‐level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN), we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet) to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high‐level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

26 October 2023
Verified
Conference Paper
Open access
YLYuyuan Li
Yuyuan Li
Chaochao ChenChaochao Chen
Chaochao Chen
XZXiaolin Zheng
Xiaolin Zheng
YZYizhao Zhang
Yizhao Zhang
ZHZhongxuan Han
Zhongxuan Han
JWJun Wang
Jun Wang
With the growing privacy concerns in recommender systems, recommendation unlearning, i.e., forgetting the impact of specific learned targets, is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as the unlearning target. However, we find that attackers can extract private information, i.e., gender, race, and age, from a trained model even if it has not been explicitly encountered during training. We name this unseen information as attribute and treat it as the unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) aims to degrade attacking performance and make target attributes indistinguishable. In this paper, we focus on a strict but practical setting of AU, namely Post-Training Attribute Unlearning (PoT-AU), where unlearning can only be performed after the training of the recommendation model is completed. To address the PoT-AU problem in recommender systems, we design a two-component loss function that consists of i) distinguishability loss: making attribute labels indistinguishable from attackers, and ii) regularization loss: preventing drastic changes in the model that result in a negative impact on recommendation performance. Specifically, we investigate two types of distinguishability measurements, i.e., user-to-user and distribution-to-distribution. We use the stochastic gradient descent algorithm to optimize our proposed loss. Extensive experiments on three real-world datasets demonstrate the effectiveness of our proposed methods.

20 June 2025
Verified
Conference Paper
Open access
DJDian Jiao
Dian Jiao
XDXianglong Deng
Xianglong Deng
ZWZhiwei Wang
Zhiwei Wang
SFShengyu Fan
Shengyu Fan
YCYi Chen
Yi Chen
MZMingzhe Zhang
Mingzhe Zhang

24 July 2020 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
DMDan Meng
Dan Meng
RHRui Hou
Rui Hou
GSGang Shi
Gang Shi
BTBibo Tu
Bibo Tu
AYAimin Yu
Aimin Yu
YYYun Yang
Yun Yang
Continually disclosed vulnerabilities reveal that traditional computer architecture lacks the consideration of security. This paper proposes a security-first architecture, with the Active Security Processor (ASP) integrated to the conventional computer architectures. To reduce the attack surface of ASP and improve the security of the whole system, the ASP is physically isolated from the CPUs with an asymmetric address space. Both the ASP and CPU can run their own operating system and applications independently on their own memory space. Furthermore, the ASP has the highest privilege (Super Root) of the whole system with two features. Firstly, the ASP can access all CPU resources and collect multi-dimensional information efficiently to monitor and analyze malicious behaviors. However, the CPU cannot access the ASP resources in anyway. Secondly, instead of being scheduled by CPUs, the ASP can actively manage the security mechanisms employed in either CPUs or the ASP. Based on the security-first architecture, we introduce several typical security tasks running on ASP. With considerations of complexity and performance, we discuss four typical system-level implementation for integrating the ASP to the security-first architecture. We implemented an off-chip ASP as our first-generation security computer system design solution to evaluate the security and performance in real hardware.

4 September 2025 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
JKJunpeng Ke
Junpeng Ke
JZJunlong Zhou
Junlong Zhou
DMDan Meng
Dan Meng
Yue ZengYue Zeng
Yue Zeng
YSYizhou Shi
Yizhou Shi
SGSong Guo
Song Guo
Federated learning (FL) enables privacy-preserving distributed machine learning by training models on edge client devices using their local data without revealing their raw data. In edge environments, various applications require different neural network models, making it crucial to perform joint training of multiple models on edge devices, known as multi-task FL. While existing multi-task FL approaches enhance resource utilization on edge devices through adaptive resource configuration or client selection, optimizing either of these aspects alone may lead to suboptimality. Therefore, in this paper, we explore a joint client selection and resource configuration method called JCSRC for multi-task FL, aiming to maximize energy efficiency in environments with limited computation and communication resources and heterogeneous client devices. Firstly, we formalize this problem as a mixed-integer nonlinear programming problem considering all these characteristics and prove its NP-hardness. To address this problem, we first design a multi-agent reinforcement learning (MARL)-based client selection method that selects appropriate clients for each task to train their models. The MARL method makes client selection decisions based on the clients’ data quality, energy efficiency, communication, and computation capacity to ensure fast convergence and energy efficiency. Then, we design a particle swarm optimization (PSO)-based resource configuration scheme that configures appropriate computation and bandwidth resources for each task on each client. The PSO scheme makes resource configuration decisions based on theoretically derived optimal CPU frequency and bandwidth to achieve high energy efficiency. Finally, we carry out extensive simulations and testbed-based experiments to validate our proposed JCSRC. The results demonstrate that, in comparison to state-of-the-art solutions, JCSRC can save energy consumption by up to 59% to achieve the target accuracy.