Zhang Xiaojie

Prof. Zhang Xiaojie

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
13 July 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
ZXZhang Xiaojie
Zhang Xiaojie
SDSaptarshi Debroy
Saptarshi Debroy
With the evolution of 5G and Internet of Things technologies, Mobile Edge Computing (MEC) has emerged as a major computing paradigm. Compared to cloud computing, MEC integrates network control, computing, and storage to customizable, fast, reliable, and secure distributed services that are closer to the user and data site. Although a popular research topic, MEC resource management comes in many forms due to its emerging nature and there exists little consensus in the community. In this survey, we present a comprehensive review of existing research problems and relevant solutions within MEC resource management. We first describe the major problems in MEC resource allocation when the user applications have diverse performance requirements. We discuss the unique challenges caused by the dynamic nature of the environments and use cases where MEC is adopted. We also explore and categorize existing solutions that address such challenges. We particularly explore traditional optimization-based methods and deep learning-based approaches. In addition, we take a deeper dive into the most popular applications and use cases that adopt MEC paradigm and how MEC provides customized solutions for each use cases, in particular, video analytics applications. Finally, we outline the open research challenges and future directions. 1

6 December 2023
Verified
Conference Paper
Open access
ZXZhang Xiaojie
Zhang Xiaojie
HGHouchao Gan
Houchao Gan
APAMITANGSHU PAL
AMITANGSHU PAL
SDSoumyabrata Dey
Soumyabrata Dey
SDSaptarshi Debroy
Saptarshi Debroy
Multi-view 3D reconstruction driven augmented, virtual, and mixed reality applications are becoming increasingly edge-native, due to factors such as, rapid reconstruction needs, security/privacy concerns, and lack of connectivity to cloud platforms. Managing edge-native 3D reconstruction, due to edge resource constraints and inherent dynamism of 'in the wild' 3D environments, involves striking a balance between conflicting objectives of achieving rapid reconstruction and satisfying minimum quality requirements. In this paper, we take a deeper dive into multi-view 3D reconstruction latency-quality trade-off, with an emphasis on reconstruction of dynamic 3D scenes. We propose data-level and task-level parallelization of 3D reconstruction pipelines, holistic edge system optimizations to reduce reconstruction latency, and long-term minimum reconstruction quality satisfaction. The proposed solutions are validated through collection of real-world 3D scenes with varying degree of dynamism that are used to perform experiments on hardware edge testbed. The results show that our solutions can achieve between 50% to 75% latency reduction without violating long term minimum quality requirements.

18 October 2025 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
ZXZhang Xiaojie
Zhang Xiaojie
PWPeng Wang
Peng Wang
SYShima Yousefi
Shima Yousefi
SDSaptarshi Debroy
Saptarshi Debroy
Keqin LiKeqin Li
Keqin Li
Recent research highlights a critical gap between the computing capabilities of modern IoT devices and the computational demands of Artificial Intelligent (AI) applications. The edge computing paradigm offers a promising solution by providing reliable and fast computing services close to the data source. Due to their inherent resource constraints, a single edge server often cannot handle the heavy computational load from nearby IoT devices, requiring multi-server collaboration. However, achieving efficient cooperation is challenging due to dynamic workload fluctuations and uneven data distribution. To address these issues, this paper presents a novel solution that involves optimizing task execution paths and resource management to enhance the performance of edge servers, particularly in scenarios with unbalanced data or uneven distribution of IoT devices. Our approach not only deploys multiple edge servers, but also focuses on the intelligent allocation and management of computing tasks. Specifically, we propose c2mec , a cooperative multi-split and multi-hop edge computing framework. The proposed c2mec framework uses problem decomposition to efficiently decouple the variables that need to be optimized. In addition, c2mec employs a multi-agent Deep Reinforcement Learning (DRL) based algorithm to mitigate the negative impact of decoupling and provides a flexible data splitting strategy. Finally, c2mec designs an energy-aware training method for IoT devices to reduce their long-term training cost. Through our comprehensive experimental results, we demonstrate how c2mec achieves notable improvement in energy saving across different scenarios compared to existing solutions, such as full and partial task offloading.

15 April 2025 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
ZXZhang Xiaojie
Zhang Xiaojie
SDSaptarshi Debroy
Saptarshi Debroy
PWPeng Wang
Peng Wang
Keqin LiKeqin Li
Keqin Li
Edge computing plays a crucial role in large-scale and real-time video analytics for smart cities, particularly in environments with massive machine-type communications (mMTC) among IoT devices. Due to the dynamic nature of mMTC, one of the main challenges is to achieve energy-efficient resource allocation and service placement in resource-constrained edge computing environments. In this paper, we introduce DeepRB, a deep learning-based resource broker framework designed for real-time video analytics in edge-native environments. DeepRB develops a two-stage algorithm to address both resource allocation and service placement efficiently. First, it uses a Residual Multilayer Perceptron ( ResMLP) network to approximate traditional iterative resource allocation policies for IoT devices that frequently transition between active and idle states. Second, for service placement, DeepRB leverages a multi-agent federated deep reinforcement learning (DRL) approach that incorporates clustering and knowledge-aware model aggregation. Through extensive simulations, we demonstrate the effectiveness of DeepRB in improving schedulability and scalability compared to baseline edge resource management algorithms. Our results highlight the potential of DeepRB for optimizing resource allocation and service placement for real-time video analytics in dynamic and resource-constrained edge computing environments.

12 November 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
PWPeng Wang
Peng Wang
YWYucheng Wu
Yucheng Wu
YLYin Lan
Yin Lan
LHLina Han
Lina Han
ZXZhang Xiaojie
Zhang Xiaojie
XWXiaohui Wei
Xiaohui Wei
Band selection (BS) is an important and fundamental preprocessing in terms of accelerating the efficiency of subsequent analysis of hyperspectral images (HSIs). This technology is also indispensable in relevant applications within the consumer electronics field. In unsupervised scenarios, the structural information encoded by the sample similarity matrix is essential for identifying key bands. However, existing BS methods are unable to address the situation where HSIs are stored in a distributed manner and cannot be shared—traditional methods rely on centralized data, making it impossible to calculate global sample similarity, which limits their application in such scenarios. Motivated by the federated learning, where a global model is learned collaboratively while keeping data on local devices, we propose a novel unsupervised federated BS framework to address these challenges in this paper. Specifically, each device iteratively updates the sample similarity matrix encoding the manifold structure information, and transfers secure summarized local band information to a central server, and then the server aggregates these information to generate the optimal band subset. Besides, our proposed framework can be adopted to other feature selection scenarios with slight modifications. This paper presents the first practical attempt to apply federated learning to the BS task Experimental results on HSIs demonstrate the effectiveness of our method when compared with other well-known methods.

Verified
Journal Article
Open access
PDF file
WLWen Li
Wen Li
ZXZhiyu Xu
Zhiyu Xu
XWXiangqiong Wu
Xiangqiong Wu
JXJu Xiang
Ju Xiang
ZXZhang Xiaojie
Zhang Xiaojie
Adverse drug reaction (ADR) prioritization and ordinal-frequency estimation are related but distinct prediction objectives, while aggregate ranking performance in sparse annotation matrices can be strongly influenced by frequently annotated side effects. Within CAFNet-DG, CAFNet-D uses task-specific association and ordinal-frequency functions built on shared molecular–relational representations, while annotation prevalence is evaluated explicitly within each training fold. On a SIDER-derived dataset comprising 750 drugs and 994 side effects, replacing a shared output with task-specific functions produced the largest joint change in staged drug-disjoint ablation, increasing mAP from 0.340 to 0.382 and reducing RMSE from 1.754 to 1.142. A prevalence-only ranking achieved an mAP of 0.410, close to the CAFNet-DG value of 0.413, indicating that aggregate ADR ranking is strongly associated with the benchmark annotation distribution. Prevalence-matched, prevalence-stratified, frequently annotated side-effect removal, and per-drug analyses were therefore used to distinguish drug-conditioned ranking variation from global annotation-prevalence effects. An equal-weight same-architecture ensemble control yielded no significant differences from CAFNet-DG across seven ranking metrics after Holm correction; generic variance reduction therefore could not be excluded as an explanation for the modest score-integration gain. Scaffold-disjoint and independent-data evaluations showed modest transfer, while ordinal-frequency agreement on CT-ADE remained limited. The results support the CAFNet-D task-specific formulation and prevalence-aware evaluation, while CAFNet-DG provides the score-integration setting examined under matched ensemble controls.