Works (20)
Updated: September 23rd, 2024 08:17
2024 article
Detecting ChatGPT-Generated Code Submissions in a CS1 Course Using Machine Learning Models
PROCEEDINGS OF THE 55TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, SIGCSE 2024, VOL. 1, pp. 526–532.
author keywords: ChatGPT; large language model; artificial intelligence; introductory programming course; CS1; cheat detection; plagiarism detection
TL;DR:
This work evaluated the performance of both traditional machine learning models and Abstract Syntax Tree-based (AST-based) deep learning models in detecting ChatGPT code from student code submissions, and suggested that both traditional machine learning models and AST-based deep learning models are effective in identifying ChatGPT-generated code with accuracy above 90%.
(via Semantic Scholar)
open access via dl.acm.org (publisher PDF)
UN Sustainable Development Goal Categories
4. Quality Education
(Web of Science; OpenAlex)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: March 8, 2024
2024 conference paper
Enhancing Code Tracing Question Generation with Refined Prompts in Large Language Models
Fan, A. X., Hendrawan, R. A., Shi, Y., & Ma, Q. (2024, March 14).
UN Sustainable Development Goal Categories
4. Quality Education
(OpenAlex)
Source: ORCID
Added: March 22, 2024
2024 conference paper
Novices' Perceptions of Web-Search and AI for Programming
Skripchuk, J., Bacher, J., Shi, Y., Tran, K., & Price, T. (2024, March 14).
Source: ORCID
Added: March 22, 2024
2023 article
Investigating the Impact of On-Demand Code Examples on Novices' Open-Ended Programming Projects
PROCEEDINGS OF THE 2023 ACM CONFERENCE ON INTERNATIONAL COMPUTING EDUCATION RESEARCH V.1, ICER 2023 V1, pp. 464–475.
author keywords: open-ended programming; code examples; block-based programming; novice programming
TL;DR:
It was found that students who had access to all 37 code examples used a significantly larger variety of code APIs, perceived the programming as relatively more creative, but also experienced a higher task load.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education
(Web of Science)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: September 11, 2023
2022 article
Code-DKT: A Code-based Knowledge Tracing Model for Programming Tasks
ArXiv.
TL;DR:
This work proposes Code-based Deep Knowledge Tracing (Code-DKT), a model that uses an attention mechanism to automatically extract and select domain-specific code features to extend DKT, and shows that Code-D KT consistently outperforms DKT.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education
(OpenAlex)
Source: ORCID
Added: December 10, 2022
2022 article
Developing Comic-based Learning Toolkits for Teaching Computing to Elementary School Learners
PROCEEDINGS OF THE 54TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, VOL 2, SIGCSE 2023, pp. 1325–1325.
TL;DR:
The use of comics to teach computing by having learners create, design, and arrange comic panels to support the informal learning of computing concepts for elementary school learners through a physical comic-based learning toolkit.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education
(Web of Science)
Sources: ORCID, Web Of Science
Added: March 7, 2023
2022 article
Identifying Common Errors in Open-Ended Machine Learning Projects
PROCEEDINGS OF THE 53RD ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION (SIGCSE 2022), VOL 1, Vol. 1, pp. 216–222.
Contributors: J. Skripchuk n, n & T. Price n
author keywords: Computer science education; Machine learning education; Data science
TL;DR:
This work qualitatively coded over 2,500 cells of code from 19 final team projects in an upper-division machine learning course to identify what ML errors students struggle with, and found that library usage, hyperparameter tuning, and misusing test data were among the most common errors.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education
(Web of Science)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: July 23, 2022
2021 conference paper
Investigate Effectiveness of Code Features in Knowledge Tracing Task on Novice Programming Course
CEUR Workshop Proceedings, 3051. http://www.scopus.com/inward/record.url?eid=2-s2.0-85122896934&partnerID=MN8TOARS
Source: ORCID
Added: December 10, 2022
2021 conference paper
Just a Few Expert Constraints Can Help: Humanizing Data-Driven Subgoal Detection for Novice Programming
Educational Data Mining 2021. https://eric.ed.gov/?id=ED615599
Source: ORCID
Added: January 7, 2022
2021 conference paper
Knowing both when and where: Temporal-ASTNN for Early Prediction of Student Success in Novice Programming Tasks
Educational Data Mining 2021. https://eric.ed.gov/?id=ED615543
Source: ORCID
Added: January 7, 2022
2021 conference paper
More With Less: Exploring How to Use Deep Learning Effectively through Semi-supervised Learning for Automatic Bug Detection in Student Code
Educational Data Mining 2021. https://eric.ed.gov/?id=ED615586
Source: ORCID
Added: January 7, 2022
2021 article
Toward Semi-Automatic Misconception Discovery Using Code Embeddings
LAK21 CONFERENCE PROCEEDINGS: THE ELEVENTH INTERNATIONAL CONFERENCE ON LEARNING ANALYTICS & KNOWLEDGE, pp. 606–612.
author keywords: Neural Network; Code Analysis; Automatic Assessment; Learning Representation
TL;DR:
This work presents a novel method for the semi-automated discovery of problem-specific misconceptions from students’ program code in computing courses, using a state-of-the-art code classification model.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education
(Web of Science)
Sources: ORCID, Web Of Science, NC State University Libraries
Added: October 21, 2021
2021 article
Toward semi-automatic misconception discovery using code embeddings
ArXiv. http://www.scopus.com/inward/record.url?eid=2-s2.0-85102809405&partnerID=MN8TOARS
Source: ORCID
Added: December 10, 2022
2020 conference paper
Comparing feature engineering approaches to predict complex programming behaviors
CEUR Workshop Proceedings, 2734. http://www.scopus.com/inward/record.url?eid=2-s2.0-85096164837&partnerID=MN8TOARS
Source: ORCID
Added: December 10, 2022
2020 article
Test_positive at W-nut 2020 shared task-3: Joint event multi-task learning for slot filling in noisy text
ArXiv. http://www.scopus.com/inward/record.url?eid=2-s2.0-85098406978&partnerID=MN8TOARS
Source: ORCID
Added: December 10, 2022
2019 conference paper
Energy audition based cyber-physical attack detection system in IoT
Proceedings of the ACM Turing Celebration Conference - China.
Contributors: * , F. Li, W. Song, X. Li * & J. Ye
TL;DR:
The framework applies a data-centric method to process the energy consumption data and classify the attack status of the monitored device, and is more secure in cases the kernel of the device is already compromised.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
7. Affordable and Clean Energy
(OpenAlex)
Source: ORCID
Added: October 21, 2021
2019 journal article
Enhanced Cyber-Physical Security in Internet of Things Through Energy Auditing
IEEE Internet of Things Journal, 6(3), 5224–5231.
Contributors: F. Li *, * , A. Shinde *, J. Ye * & W. Song *
author keywords: Cyber and physical attack detection; deep learning (DL); energy audit; Internet of Things (IoT)
TL;DR:
This is the first attempt to detect and identify IoT cyber and physical attacks based on energy auditing and analytics-based IoT monitoring mechanism using the energy meter readings and proposes a disaggregation-aggregation architecture.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
7. Affordable and Clean Energy
(OpenAlex)
Source: ORCID
Added: September 4, 2019
2019 journal article
System Statistics Learning-Based IoT Security: Feasibility and Suitability
IEEE Internet of Things Journal, 6(4), 6396–6403.
Contributors: F. Li *, A. Shinde *, * , J. Ye *, X. Li * & W. Song *
author keywords: Anomaly detection; deep learning; failure and intrusion detection; Internet of Things (IoT); machine learning
TL;DR:
It is concluded that relatively simple machine learning models are more suitable for IoT security, and a data-driven anomaly detection method is preferred.
(via Semantic Scholar)
Source: ORCID
Added: September 4, 2019
2018 conference paper
Dynamic Time-frequency Feature Extraction for Brain Activity Recognition
2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018-July, 3104–3107.
Contributors: * , F. Li *, T. Liu *, F. Beyette * & W. Song *
MeSH headings : Algorithms; Brain; Electroencephalography; Imagery, Psychotherapy; Signal Processing, Computer-Assisted
TL;DR:
This paper proposes an improved dynamic feature extraction approach based on a time-frequency representation and an optimal sequence similarity measurement that demonstrates the importance of the advanced feature extraction in time series data analysis, e.g. biomedical signal.
(via Semantic Scholar)
Source: ORCID
Added: September 4, 2019
2018 article
PoTrojan: powerful neural-level trojan designs in deep learning models
(2018, February 8).
Source: ORCID
Added: September 4, 2019
Employment
Updated: June 7th, 2024 14:14
2024 - present
Utah State University Logan, US
Assistant Professor
Department of Computer Science
2019 - 2024
North Carolina State University Raleigh, North Carolina, US
Graduate Assistant
Department of Computer Science
2019 - 2019
Stratifyd Inc Charlotte, NC, US
Research Scientist Intern
2015 - 2019
University of Georgia Athens, GA, US
Graduate Assistant
Computer Science
Education
Updated: June 7th, 2024 14:14
2019 - 2024
NC State University Raleigh, NC, US
Doctor of Philosophy
Department of Computer Science
2015 - 2017
University of Georgia Athens, Georgia, US
Master of Science
Department of Computer Science
2011 - 2015
Central South University Changsha, Hunan, CN
Bachelor of Engineering
Department of Automation
Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.
Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.