IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization
The evolution of artificial intelligence has thrust the Online Judge (OJ) systems into the forefront of research, particularly within programming education, with a focus on enhancing performance and efficiency. Addressing the shortcomings of the current OJ systems in coarse defect localization granu...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | High-Confidence Computing |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667295224000710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839648296932474880 |
|---|---|
| author | Lihua Song Ying Han Yufei Guo Chenying Cai |
| author_facet | Lihua Song Ying Han Yufei Guo Chenying Cai |
| author_sort | Lihua Song |
| collection | DOAJ |
| description | The evolution of artificial intelligence has thrust the Online Judge (OJ) systems into the forefront of research, particularly within programming education, with a focus on enhancing performance and efficiency. Addressing the shortcomings of the current OJ systems in coarse defect localization granularity and heavy task scheduling architecture, this paper introduces an innovative Integrated Intelligent Defect Localization and Lightweight Task Scheduling Online Judge (IDL-LTSOJ) system. Firstly, to achieve token-level fine-grained defect localization, a Deep Fine-Grained Defect Localization (Deep-FGDL) deep neural network model is developed. By integrating Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU), this model extracts fine-grained information from the abstract syntax tree (AST) of code, enabling more accurate defect localization. Subsequently, we propose a lightweight task scheduling architecture to tackle issues, such as limited concurrency in task evaluation and high equipment costs. This architecture integrates a Kafka messaging system with an optimized task distribution strategy to enable concurrent execution of evaluation tasks, substantially enhancing system evaluation efficiency. The experimental results demonstrate that the Deep-FGDL model improves the accuracy by 35.9% in the Top-20 rank compared to traditional machine learning benchmark methods for fine-grained defect localization tasks. Moreover, the lightweight task scheduling strategy notably reduces response time by nearly 6000ms when handling 120 task volumes, which represents a significant improvement in evaluation efficiency over centralized evaluation methods. |
| format | Article |
| id | doaj-art-218cbd662bd74581a15e55be8889c0cb |
| institution | Matheson Library |
| issn | 2667-2952 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | High-Confidence Computing |
| spelling | doaj-art-218cbd662bd74581a15e55be8889c0cb2025-06-29T04:53:08ZengElsevierHigh-Confidence Computing2667-29522025-06-0152100268IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localizationLihua Song0Ying Han1Yufei Guo2Chenying Cai3Department of Computer Science, North China University of Technology, Beijing 100144, ChinaDepartment of Computer Science, North China University of Technology, Beijing 100144, China; Corresponding author.Department of Statistics, George Washington University, DC 20052, USADepartment of Computer Science, North China University of Technology, Beijing 100144, ChinaThe evolution of artificial intelligence has thrust the Online Judge (OJ) systems into the forefront of research, particularly within programming education, with a focus on enhancing performance and efficiency. Addressing the shortcomings of the current OJ systems in coarse defect localization granularity and heavy task scheduling architecture, this paper introduces an innovative Integrated Intelligent Defect Localization and Lightweight Task Scheduling Online Judge (IDL-LTSOJ) system. Firstly, to achieve token-level fine-grained defect localization, a Deep Fine-Grained Defect Localization (Deep-FGDL) deep neural network model is developed. By integrating Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU), this model extracts fine-grained information from the abstract syntax tree (AST) of code, enabling more accurate defect localization. Subsequently, we propose a lightweight task scheduling architecture to tackle issues, such as limited concurrency in task evaluation and high equipment costs. This architecture integrates a Kafka messaging system with an optimized task distribution strategy to enable concurrent execution of evaluation tasks, substantially enhancing system evaluation efficiency. The experimental results demonstrate that the Deep-FGDL model improves the accuracy by 35.9% in the Top-20 rank compared to traditional machine learning benchmark methods for fine-grained defect localization tasks. Moreover, the lightweight task scheduling strategy notably reduces response time by nearly 6000ms when handling 120 task volumes, which represents a significant improvement in evaluation efficiency over centralized evaluation methods.http://www.sciencedirect.com/science/article/pii/S2667295224000710Online Judge (OJ) systemFine-grained defect localizationDeep neural networkTask scheduling |
| spellingShingle | Lihua Song Ying Han Yufei Guo Chenying Cai IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization High-Confidence Computing Online Judge (OJ) system Fine-grained defect localization Deep neural network Task scheduling |
| title | IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization |
| title_full | IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization |
| title_fullStr | IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization |
| title_full_unstemmed | IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization |
| title_short | IDL-LTSOJ: Research and implementation of an intelligent online judge system utilizing DNN for defect localization |
| title_sort | idl ltsoj research and implementation of an intelligent online judge system utilizing dnn for defect localization |
| topic | Online Judge (OJ) system Fine-grained defect localization Deep neural network Task scheduling |
| url | http://www.sciencedirect.com/science/article/pii/S2667295224000710 |
| work_keys_str_mv | AT lihuasong idlltsojresearchandimplementationofanintelligentonlinejudgesystemutilizingdnnfordefectlocalization AT yinghan idlltsojresearchandimplementationofanintelligentonlinejudgesystemutilizingdnnfordefectlocalization AT yufeiguo idlltsojresearchandimplementationofanintelligentonlinejudgesystemutilizingdnnfordefectlocalization AT chenyingcai idlltsojresearchandimplementationofanintelligentonlinejudgesystemutilizingdnnfordefectlocalization |