Qian Chen

Dr. Qian Chen

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
11 September 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
WLWentao Liu
Wentao Liu
ZNZhiwei Ni
Zhiwei Ni
QCQian Chen
Qian Chen
LNLiping Ni
Liping Ni
Deep neural networks (DNN) supported by multicenter large-scale Chest X-Ray (CXR) datasets can efficiently perform tasks such as disease identification, lesion segmentation, and report generation. However, the non-ignorable inter-domain heterogeneity caused by different equipment, ethnic groups, and scanning protocols may lead to dramatic degradation in model performance. Unsupervised domain adaptation (UDA) methods help alleviate the cross-domain discrepancy for subsequent analysis. Nevertheless, they may be prone to 1) spatial negative transfer: misaligning non-transferable regions which have inadequate knowledge, and 2) semantic negative transfer: failing to extend to scenarios where the label spaces of the source and target domain are partially shared. In this work, we propose a classification-based framework named attention-guided partial domain adaptation (AGPDA) network for overcoming these two negative transfer challenges. AGPDA is composed of two key modules: (1) a region attention discrimination block (RADB) to generate fine-grained attention value via lightweight region-wise multi-adversarial networks. (2) a residual feature recalibration block (RFRB) trained with class-weighted maximum mean discrepancy (MMD) loss for down-weighing the irrelevant source samples. Extensive experiments on two publicly available CXR datasets containing a total of 8598 pneumonia (viral, bacterial, and COVID-19) cases, 7163 non-pneumonia or healthy cases, demonstrate the superior performance of our AGPDA. Especially on three partial transfer tasks, AGPDA significantly increases the accuracy, sensitivity, and F1 score by 4.35%, 4.05%, and 1.78% compared to recently strong baselines.

14 February 2024 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
MLMoli Lyu
Moli Lyu
ZNZhiwei Ni
Zhiwei Ni
QCQian Chen
Qian Chen
FLFenggang Li
Fenggang Li
The edge computing paradigm has revolutionized the healthcare sector, providing more real-time medical data processing and analysis, which also poses more serious privacy and security risks that must be carefully considered and addressed. Based on differential privacy, we presented an innovative privacy-preserving model named Edge-DPSDG (Edge-Differentially Private Synthetic Data Generator) for smart healthcare under edge computing. It also develops and evolves a privacy budget allocation mechanism. In a distributed environment, the privacy budget for local medical data is personalized by computing the Shapley value and the information entropy value of each attribute in the dataset, which takes into account the trade-off between data privacy and utility. Extensive experiments on three public medical datasets are performed to evaluate the performance of Edge-DPSDG on two metrics. For utility evaluation, Edge-DPSDG shows a best 21.29% accuracy improvement compared to the state-of-the-art; our privacy budget allocation mechanism improved existing models’ accuracy by up to 6.05%. For privacy evaluation, Edge-DPSDG shows that can effectively ensure the privacy of the original datasets. In addition, Edge-DPSDG helps smooth the data, and results in a 3.99% accuracy loss decrease over the non-private model.

22 August 2024 in Electronics
Verified
Journal Article
Open access
PDF file
QCQian Chen
Qian Chen
ZNZhiwei Ni
Zhiwei Ni
XZXuhui Zhu
Xuhui Zhu
MLMoli Lyu
Moli Lyu
WLWentao Liu
Wentao Liu
PXPingfan XIA
Pingfan XIA
Edge computing enables efficient data aggregation for services like data sharing and analysis in distributed IoT applications. However, uploading dynamic high-dimensional data to an edge server for efficient aggregation is challenging. Additionally, there is the significant risk of privacy leakage associated with direct such data uploading. Therefore, we propose an edge-based differential privacy data aggregation method leveraging progressive UMAP with a dynamic time window based on LSTM (EDP-PUDL). Firstly, a model of the dynamic time window based on a long short-term memory (LSTM) network was developed to divide dynamic data. Then, progressive uniform manifold approximation and projection (UMAP) with differential privacy was performed to reduce the dimension of the window data while preserving privacy. The privacy budget was determined by the data volume and the attribute’s Shapley value, adding DP noise. Finally, the privacy analysis and experimental comparisons demonstrated that EDP-PUDL ensures user privacy while achieving superior aggregation efficiency and availability compared to other algorithms used for dynamic high-dimensional data aggregation.

31 August 2018 in IEEE Access
Verified
Journal Article
Open access
QCQian Chen
Qian Chen
XLXuejun Li
Xuejun Li
YWYanchun Wang
Yanchun Wang
Multi-tenant service-based systems (SBSs) have been widely used in recent years. In SBSs, Web services are composed of business processes that fulfill multiple tenants' functional and multi-dimensional quality-of-service (QoS) requirements, such as response time, throughput, and budget. QoS violations frequently occur, and the rate of service level agreement (SLA) breaches increases in a distributed and volatile operating environment. Service monitoring can be used to improve the reliability and availability of the systems by detecting runtime anomalies in a timely manner. However, this process consumes monitoring resources and incurs monitoring overhead in an SBS. In fact, different services in an SBS are not equally critical, and treating them as the same in monitoring wastes resources. Thus, it is a considerable challenge to monitor the services of a multi-tenant SBS in a cost-effective manner. In this paper, we propose SLA-driven Cost-Effective Monitoring for multi-Tenant SBSs (SCEMTS) based on criticality for formulating a monitoring strategy. In an SBS, the criticality of a service is evaluated based on two dimensions: QoS and tenants (including their priorities). To specify the different QoS requirements of tenants, tenant SLAs are used to rank tenants' priorities for weighting the criticality of a service in the monitoring resource distribution. Extensive experiments show that the SCEMTS outperforms the representative approaches in satisfying tenant SLAs, thus improving monitoring cost-effectiveness and ensuring the QoS of multi-tenant SBSs.

25 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JCJiale Cheng
Jiale Cheng
ZNZhiwei Ni
Zhiwei Ni
WLWentao Liu
Wentao Liu
QCQian Chen
Qian Chen
RYRui Yan
Rui Yan
The path-planning of unmanned delivery vehicles (UDVs) has garnered significant interest due to their extensive use in contactless delivery during severe epidemics and automated delivery of parcels in diverse scenarios. However, previous studies have focused on achieving the shortest path or time based on the comprehensive cost consumption in the transportation process and ignored the impact of different customers’ different delivery time requirements in the actual interactive system. Hence, a path-planning model is presented to tackle the routing dilemma of UDVs in logistics. This new dilemma, called the unmanned delivery vehicle routing problem (UDVRP), considers the comprehensive transportation cost consumption of distribution vehicles and the customer satisfaction of each distribution point. Customer satisfaction is defined based on the delivery time requirements of different customers. This novel deep neural network model incorporates an attention mechanism and applies a method called point-graph joint embedding and dual decoders (PGDD) to solve the problem. The network’s architecture, consisting of an encoder and two decoders, directly determines the path for unmanned delivery vehicles. In addition, the model is trained offline using a deep reinforcement-learning strategy in combination with pseudo-label learning. In this scenario, the output of one decoder serves as the label for another, overseeing its learning process to choose the most effective path. Experimental results demonstrate that PGDD reduces total costs by 8.73% on average compared to state-of-the-art algorithms in 100-node scenarios, with performance gains reaching 12.5% for larger-scale problems (400 nodes), validating its superiority in complex path-planning. Additionally, PGDD improves customer satisfaction by 15.2% and achieves a response time below 90ms in real-world deployment tests. The experimental results demonstrate that the proposed method is superior to several state-of-the-art algorithms in solving the path-planning problem of unmanned distribution vehicles.