Quansi Wen

Dr. Quansi Wen

South China University of Technology Guangzhou China
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
17 March 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CZChou-Jun Zhan
Chou-Jun Zhan
YZYufan Zheng
Yufan Zheng
HZHaijun Zhang
Haijun Zhang
Quansi WenQuansi Wen
Quansi Wen
The rapid geographic spread of COVID-19, to which various factors may have contributed, has caused a global health crisis. Recently, the analysis and forecast of the COVID-19 pandemic have attracted worldwide attention. In this work, a large COVID-19 data set consisting of COVID-19 pandemic, COVID-19 testing capacity, economic level, demographic information, and geographic location data in 184 countries and 1241 areas from December 18, 2019, to September 30, 2020, were developed from public reports released by national health authorities and bureau of statistics. We proposed a machine learning model for COVID-19 prediction based on the broad learning system (BLS). Here, we leveraged random forest (RF) to screen out the key features. Then, we combine the bagging strategy and BLS to develop a random-forest-bagging BLS (RF-Bagging-BLS) approach to forecast the trend of the COVID-19 pandemic. In addition, we compared the forecasting results with linear regression (LR) model, $K$ -nearest neighbors (KNN), decision tree (DT), adaptive boosting (Ada), RF, gradient boosting DT (GBDT), support vector regression (SVR), extra trees (ETs) regressor, CatBoost (CAT), LightGBM (LGB), XGBoost (XGB), and BLS.The RF-Bagging BLS model showed better forecasting performance in terms of relative mean-square error (RMSE), coefficient of determination ( $R^{2}$ ), adjusted coefficient of determination ( $R_{\mathrm{ adj}}^{2}$ ), median absolute error (MAD), and mean absolute percentage error (MAPE) than other models. Hence, the proposed model demonstrates superior predictive power over other benchmark models.

18 September 2020 in IEEE Network
Verified
Journal Article
Closed access
MAMohammad Iqbal Saryuddin Assaqty
Mohammad Iqbal Saryuddin Assaqty
YGYing Gao
Ying Gao
XHXiping Hu
Xiping Hu
ZNZhaolong Ning
Zhaolong Ning
VLVictor C. M. Leung
Victor C. M. Leung
YCYijian Chen
Yijian Chen
Automation in smart manufacturing depends on many parties in the supply chain and distribution networks. A smart manufacturer needs to track the location and state of materials from its suppliers and products to its customers/distributors to manage the corresponding production schedule. The need for such information can be fulfilled by the use of Industrial Internet of Things (IIoT) devices installed at each respective party. However, even though all parties may trust one another, they have confidential data produced by the IIoT devices that are not allowed to be shared with other parties, or only allowed to be exchanged with certain parties. Even though the data are not confidential, they may still be required to share partial data based on the needs of each party. On the other hand, all parties have their independent systems that differ from each other, which leads to complex integration. Regarding those situations, a private-blockchain-based IIoT is promising to bridge the need for product and material tracking information exchange between parties while maintaining the respective confidentiality.

1 May 2019
Verified
Conference Paper
Closed access
Quansi WenQuansi Wen
Quansi Wen
YGYing Gao
Ying Gao
ZCZhiling Chen
Zhiling Chen
DWDapeng Wu
Dapeng Wu
A supply chain is a system that includes multiple entities such as suppliers, manufacturers, carriers, retailers, and customers. How to encourage the willingness to cooperate and share information between these entities has always been one of the major challenges in the field of supply chain management. The Industrial Internet of Things (IIoT) can help entities get real-time data in the supply chain to share the key information and reduce costs. However, the supply chain not only needs to know how to gather the data but also ensures that the data processed is not leaked. Since Blockchain, as the main technology of Bitcoin, has the advantages of traceability and anti-counterfeiting, blockchain is the right tool to tackle the date sharing problem in supply chain. In this paper, we connect IIoT devices to the blockchain by combining the monitoring and recording of IIoT devices and storing real-time data in the network by smart contract. In addition, a blockchain-based supply chain structure is proposed. This structure provides collaboration solutions between different entities in the supply chain. In this structure, a fine-grained data sharing scheme for supply chain is proposed. By setting access policies to the smart contract, only the companies that satisfy the attributes of access policies can execute the smart contract and view the details of the transaction. The proposed scheme ensures reliability of data in the supply chain, and the privacy protection of the chain.

17 March 2021 in IEEE Access
Verified
Journal Article
Open access
Gao YingGao Ying
Gao Ying
QPQiaofeng Pan
Qiaofeng Pan
YLYangliang Liu
Yangliang Liu
HLHongliang Lin
Hongliang Lin
YCYijian Chen
Yijian Chen
Quansi WenQuansi Wen
Quansi Wen
The Notarial Office(NO), working on providing various essential certificates, still relies on manual handling and requires paper materials from other government departments. That brings lots of inconvenience. The Notarial Office rejects non-local paper materials for their lower credibility in the local place and then cannot provide cross-borders services. It also easily cause sensitive information leakage as copies of paper materials have been stored. In this case, a blockchain-based system is suitable to address challenges in this scenario because of its advantages (e.g, decentralized, immutability, transparency, auditability). We implemented this system on top of the Hyperledger Fabric. Moreover, we replace manual operations with smart contracts, set extra ledgers to off-load different types of transactions and provide encryption for private information when needed. In the end, we get an expected result. That is, the modification outperformed the unmodified network in experiments.

30 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Gao YingGao Ying
Gao Ying
YLYangliang Liu
Yangliang Liu
Quansi WenQuansi Wen
Quansi Wen
HLHongliang Lin
Hongliang Lin
YCYijian Chen
Yijian Chen
With the development of the Internet of Things (IoT), the number of drones, as a consumer-level IoT device, is rapidly increasing. The existence of a large number of drones increases the risk of misoperation during manual control. Therefore, it has become an inevitable trend to realize drone flying automation. Drone flying automation mainly relies on massive drone applications and services as well as third-party service providers, which not only complicate the drone network service environment but also raise some security and privacy issues. To address these challenges, this article proposes an innovative architecture called Secure Drone Network Edge Service (SDNES), which integrates edge computing and blockchain into the drone network to provide real-time and reliable network services for drones. To design a feasible and rational SDNES architecture, we first consider the real-time performance and apply edge computing technology in it to provide low-latency edge services for drones under 5G mobile network. We use DAG-based blockchain to guarantee the security and reliability of the drone network service environment and effectively avoid malicious behaviors. In order to illustrate the feasibility of this architecture, we design and implement a specific service case named Drone Collision Avoidance Navigation Service based on SDNES. Finally, a simulation experiment for the specific service case and a series of other performance-related experiments were carried out to verify the feasibility and rationality of our proposed architecture. The experimental results demonstrate that SDNES is a promising architecture to assist and accelerate drone flying automation.

19 April 2024 in IEEE Access
Verified
Journal Article
Open access
LGLe Gao
Le Gao
JYJiaxin Yu
Jiaxin Yu
JZJunzhe Zhang
Junzhe Zhang
YTYin Tang
Yin Tang
Quansi WenQuansi Wen
Quansi Wen
The concern and opposition to centralized management of user identities by third-party authorities have led to the emergence of Self-Sovereign Identity (SSI). With the help of blockchain, SSI effectively restore users’ control over their own identities, but privacy concerns due to blockchain transparency, coupled with the absence of accountability like Know Your Customer (KYC) and Anti-Money Laundering (AML), have cast uncertainties upon the viability of SSI. In this paper, we bridge this gap by introducing AASSI, a pioneering SSI protocol meticulously designed to balance the twin imperatives of privacy and accountability. Specifically, AASSI extends support for anonymity, self-derivation, fine-grained tracing and selective revocation. In the realm of anonymity and self-derivation, AASSI introduces redactable signatures, which empowers users to autonomously derive distinctive credentials for each user-service-provider interaction, effectively improving privacy protection and self-management capabilities. Pertaining to fine-grained tracing, the protocol employs a dual-tag system that facilitates tracing users’ real identities as well as a granular historical records of derived credentials. For selective revocation, AASSI leverages dynamic accumulators as a building block to enable the revocation of offending users. Ultimately, we provide functional comparison, which shows that AASSI has robust features, in particular, it supports novel self-derived features that further increase user control over their identity, and fine-grained tracking, which provides more flexibility for tracers. We demonstrate protocol efficiency through off-chain time-consuming comparison, which show that AASSI dramatically reduces the time overhead of credential verification. Moreover, We test the on-chain communication overhead and experimentally prove the feasibility of AASSI.