Dan Zhao

Dan Zhao

Auto-generated profile, based on publicly available information

Dan Zhao

Pengcheng Laboratory, Shenzhen, China

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
10 January 2022 in IEEE Transactions on Education
Verified
Journal Article
Open access
DZDan Zhao
Dan Zhao
CMCristina Hava Muntean
Cristina Hava Muntean
ACAdriana E. Chis
Adriana E. Chis
GRGregor Rozinaj
Gregor Rozinaj
GMGabriel-Miro Muntean
Gabriel-Miro Muntean
Contributions: This article presents a large-scale study which investigates students' reaction to game-based learning as part of programming courses. The study focuses on knowledge acquisition, learner experience, and game usability. Background: Despite the rapid growth of the information and communication technologies (ICTs) sector, the lack of engagement with science, technology, engineering, and mathematics (STEM) subjects and high dropout rates in computer science and engineering majors is linked directly to the large number of unfilled vacancies in the ICT employment market. To tackle one of the underlying causes for this crisis, (i.e., traditional teaching paradigms struggle to attract students to rather abstract and difficult STEM subjects such as programming), innovative technology-enhanced learning solutions are sought. Intended Outcomes: A set of serious games were proposed and designed to promote students' understanding of programming concepts, improve their confidence, stimulate their interest in STEM and increase engagement with the courses through vivid and appealing scenarios. Application Design: Targeting undergraduate and postgraduate students, the games focused on several key programming topics. They were designed to visualize the programming concepts in illustrative and entertaining scenarios. A comprehensive assessment methodology which includes surveys, observations, and interviews was employed to investigate the impact of the games. Findings: The results show that by using the games in the teaching and learning process all the students have benefited, although differently based on their location, educational backgrounds, and game played. The impact of detailed demographic aspects, such as participants' use of technology, their initial attitude toward school, and learning STEM on the results needs further study.

11 July 2024 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
RLRuoyu Li
Ruoyu Li
QLQing Li
Qing Li
QZQingsong Zou
Qingsong Zou
DZDan Zhao
Dan Zhao
XZXiangyi Zeng
Xiangyi Zeng
HSHenning Schulzrinne
Henning Schulzrinne
Synthetic traffic generation can produce sufficient data for model training of various traffic analysis tasks for IoT networks with few costs and ethical concerns. However, with the increasing functionalities of the latest smart devices, existing approaches can neither customize the traffic generation of various device functions nor generate traffic that preserves the sequentiality among packets as the real traffic. To address these limitations, this paper proposes IoTGemini, a novel framework for high-quality IoT traffic generation, which consists of a Device Modeling Module and a Traffic Generation Module. In the Device Modeling Module, we propose a method to obtain the profiles of the device functions and network behaviors, enabling IoTGemini to customize the traffic generation like using a real IoT device. In the Traffic Generation Module, we design a Packet Sequence Generative Adversarial Network (PS-GAN), which can generate synthetic traffic with high fidelity of both per-packet fields and sequential relationships. We set up a real-world IoT testbed to evaluate IoTGemini. The experiment result shows that IoTGemini can achieve great effectiveness in device modeling, high fidelity of synthetic traffic generation, and remarkable usability to downstream tasks on different traffic datasets and downstream traffic analysis tasks.

12 January 2021 in IEEE Transactions on Education
Verified
Journal Article
Closed access
DZDan Zhao
Dan Zhao
CMCristina Hava Muntean
Cristina Hava Muntean
ACAdriana E. Chis
Adriana E. Chis
GMGabriel-Miro Muntean
Gabriel-Miro Muntean
Contribution: This research study deploys three serious games with various topics in an entry-level C Programming module and investigates students' learning outcomes. The study also explores whether learners belonging to different subgroups benefit more from the use of serious games than their peers. The subgroups are formed based on learner demographics that capture learners' attitude toward school or STEM subjects, their previous educational performance and gender. Background: Despite the latest rapid economy growth in the ICT sector, many European countries are facing the challenge of retaining students in STEM-related subjects, which could lead to unfilled vacancies in the ICT job markets in the near future. Serious games have been utilized in the classrooms of many STEM subjects to improve students' learning experience and learning outcomes, and potentially encourage their engagement with STEM-related industries. While some prior works had assessed the effectiveness of serious games in improving students' learning outcomes, little research has been done to investigate the impacts among students with different previous educational background and performance, attitude, and gender. Research Questions: 1) Do the proposed serious games improve students' learning outcomes? and 2) Do students with certain previous educational performance, learning attitude, and/or gender benefit more than others from the use of serious games? Methodology: To thoroughly study students' learning outcome, a large-scale pilot was deployed as part of the first-year undergraduate C Programming module at Dublin City University, Ireland. A multidimensional pedagogical assessment toolkit was utilized. In particular, a demographic questionnaire was carried out before the pilot began, based on which students were divided into different subgroups in terms of educational ability, initial attitude to school, attitude toward learning STEM subjects, and gender. Pre- and post-tests were conducted right before and after playing each game. For students belonging to each subgroup and for all students, the average pre- and post-test marks related to each game were compared, while paired-sample t-tests were also conducted to assess the statistical significance of knowledge gain. Findings: Statistically significant knowledge gains were observed in all three games for all students. The students with good previous educational performance or strong attitude toward attending school and learning STEM subjects, tend to gain more by using serious games, as they obtained statistically significant improved learning outcomes in all three games. The students with average starting points, although performed better in the post-test than in the pretest in all games, they achieved statistically significant improvements in some cases only.


15 July 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RLRuoyu Li
Ruoyu Li
QLQing Li
Qing Li
YHYucheng Huang
Yucheng Huang
QZQingsong Zou
Qingsong Zou
DZDan Zhao
Dan Zhao
Athanasios V. VasilakosAthanasios V. Vasilakos
Athanasios V. Vasilakos
Existing IoT Network Anomaly Detection Systems (NADSes) typically treat IoT devices as independent entities and model them by Euclidean space features. These approaches suffer from low accuracies on new attacks (e.g., platform-based attacks and evasion attacks), since they do not fully consider the semantic information including traffic periodicity and device/environment interactions. In this paper, we propose SeIoT, a knowledge graph-based bimodal anomaly detection framework for smart homes. We propose a knowledge graph structure to represent the semantic information of a smart home. First, we propose the Action Fingerprint module, an efficient and effective traffic classification approach to extract the device actions and features required by the knowledge graph. Then, we propose a bimodal anomaly detection framework including interaction-related and time-related detectors to detect the knowledge graph. We propose a feature separation-based heterogeneous graph attention network that can accurately model the interactions among devices and environments, and a method to represent traffic periodicity for the time-related detector. For evaluation, we set up a real-world testbed and evaluate the detection performance of both device-targeted attacks and platform-based attacks. Experiment results show that SeIoT can achieve better detection capability than prior work on both of the attacks.

24 August 2024
Verified
Conference Paper
Open access
JXJingyu Xiao
Jingyu Xiao
ZXZhiyao Xu
Zhiyao Xu
QZQingsong Zou
Qingsong Zou
QLQing Li
Qing Li
DZDan Zhao
Dan Zhao
MLMichael R. Lyu
Michael R. Lyu
Smart homes, powered by the Internet of Things, offer great convenience but also pose security concerns due to abnormal behaviors, such as improper operations of users and potential attacks from malicious attackers. Several behavior modeling methods have been proposed to identify abnormal behaviors and mitigate potential risks. However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors. In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors, which are often overlooked during learning. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference. Comprehensive experiments demonstrate that SmartGuard consistently outperforms state-of-the-art baselines and also offers highly interpretable results.