Jinzhi Ouyang

Jinzhi Ouyang

Auto-generated profile, based on publicly available information

Jinzhi Ouyang

School of Computer Science, Xiangtan University, Xiangtan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
28 October 2022 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
SLSaiqin Long
Saiqin Long
YZYing Zhang
Ying Zhang
QDQingyong Deng
Qingyong Deng
TPTingrui Pei
Tingrui Pei
JOJinzhi Ouyang
Jinzhi Ouyang
ZXZhihua Xia
Zhihua Xia
Cloud-edge collaboration can overcome the shortcomings of high latency of the centralized model of cloud computing and insufficient computing power of edge computing, and better meet the needs of various application scenarios, which has become a research hotspot in recent years. The 6 G network is driven by the deep integration of network and computing, which will further accelerate the collaborative and integrated development of the cloud datacenter, edge servers, end devices, and application. This paper considers the combination of edge computing and cloud computing, and studies the problem of task offloading with the optimization objectives of energy consumption, delay, and multi-node load balancing under an “End-Edge-Cloud” collaborative architecture for 6G network. We regard the problem of task offloading as a multi-objective optimization problem. By improving AR-MOEA, a task offloading algorithm based on the “End-Edge-Cloud” architecture (TO-EEC) is proposed. It is verified through experiments that TO-EEC has a fast convergence speed. Compared with other similar offloading algorithms, TO-EEC has significant optimization effects on energy consumption, delay and multi-node load variance under multiple constraints.

7 January 2025 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
FWFuyi Wang
Fuyi Wang
JOJinzhi Ouyang
Jinzhi Ouyang
XLXiaoning Liu
Xiaoning Liu
LPLei Pan
Lei Pan
LZLeo Yu Zhang
Leo Yu Zhang
RDRobin Doss
Robin Doss
The substantial progress in privacy-preserving machine learning (PPML) facilitates outsourced medical computer-aided diagnosis (MedCADx) services. However, existing PPML frameworks primarily concentrate on enhancing the efficiency of prediction services, without exploration into diverse medical services such as medical segmentation. In this paper, we propose MedShield , a pioneering cryptographic framework for diverse MedCADx services (i.e., multi-service, including medical imaging prediction and segmentation). Based on a client-server (two-party) setting, MedShield efficiently protects medical records and neural network models without fully outsourcing. To execute multi-service securely and efficiently, our technical contributions include: 1) optimizing computational complexity of matrix multiplications for linear layers at the expense of free additions/subtractions; 2) introducing a secure most significant bit protocol with crypto-friendly activations to enhance the efficiency of non-linear layers; 3) presenting a novel layer for upscaling low-resolution feature maps to support multi-service scenarios in practical MedCADx. We conduct a rigorous security analysis and extensive evaluations on benchmarks (MNIST and CIFAR-10) and real medical records (breast cancer, liver disease, COVID-19, and bladder cancer) for various services. Experimental results demonstrate that MedShield achieves up to $2.4\times$ , $4.3\times$ , and $2\times$ speed up for MNIST, CIFAR-10, and medical datasets, respectively, compared with prior work when conducting prediction services. For segmentation services, MedShield preserves the precision of the unprotected version, showing a $1.23\%$ accuracy improvement.