检索结果-内蒙古大学图书馆

Graph-Based Feature Learning for Cross-Project software Defect Prediction

computers, Materials & Continua 2023年第10期77卷 161-180页

作者： Ahmed Abdu Zhengjun Zhai Hakim A.Abdo Redhwan Algabri Sungon Lee School of Software Northwestern Polytechnical UniversityXi’anChina School of Computer Science Northwestern Polytechnical UniversityXi’anChina Department of Computer Science Hodeidah UniversityPO Box 3114Al-HudaydahYemen Research Institute of Engineering and Technology Hanyang UniversityAnsanKorea Department of Robotics Hanyang UniversityAnsanKorea

Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for *** paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source *** proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive *** process involves graph construction,feature learning through graph embedding and LSTM,and defect *** evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.

关键词： Cross-project defect prediction graphs features deep learning graph embedding

来源：评论

学校读者我要写书评

暂无评论

Efficient adaptive rendering of planetary-scale terrains

Efficient adaptive rendering of planetary-scale terrains

引用

作者： Masood, Zafar Jiangbin, Zheng Irfan, Muhammad Ahmad, Idress School of Software Northwestern Polytechnical University Shaanxi Xi'an China Department of Computer Science and Software Engineering International Islamic University Islamabad Pakistan

Planetary-scale terrain requires adaptive simplification and tessellation for highperformance rendering. Real-world visualisation requires adaptive rendering of the world-scale geometric model, which is a challenging task especially on consumer-level notebooks. In this work, we propose a method for the adaptive rendering of the Earth's surface model using modern GPU features. The multi-resolution model is partitioned into patches and is submitted efficiently using the geometry-instancing feature for high-performance rendering. Patch-based algorithm culls worldscale model in graphics pipeline to reduce simplification and rendering load. The proposed method performs the adaptive simplification of patches with geometric-error control in image space for optimum triangulation. Simplified patches are tessellated using power-of-two tessellation factors to avoid boundary cracks. After tessellation, a three-dimensional surface is constructed by displacement mapping using a regular height data grid. Comparative evaluation of the proposed method with clipmaps and hardware-based tessellation methods is performed and results are presented. © 2023 Inderscience Enterprises Ltd.

关键词： Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

Explainable Story and Visualization for Learning Data Structure Concepts 5

Explainable Story and Visualization for Learning Data Struct...

引用

5th International Conference on computer science and Technologies in Education, CSTE 2023

作者： Wang, Bingshu Zhu, Xinyi Shi, Cheng Cheng, Yan School of Software Northwestern Polytechnical University Xi'an China School of Computer Science and Engineering Xi'An University of Technology Xi'an China

ISBN: (纸本)9798350325720

The 'Data Structure' course is a fundamental subject within the entire computer course system, and it plays a vital role in the field of computer and information disciplines. However, the abstraction and logic of data structures have made this course challenging for many underestimated students. It involves many concepts, which can be difficult to understand. To enhance teaching efficiency and facilitate students' comprehension of data structure concepts, we propose a method that combines storytelling and visualization. Our goal is to present these concepts clearly and promote a deeper understanding among students. We have developed new expressions that serve as a bridge between data structure concepts and their logical structures. Our teaching practice has shown that this approach is highly effective. It not only increases the teacher's confidence in their ability to teach, but also enhances students' subjective initiative when it comes to learning. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

High-quality Trajectory Generation for Autonomous Driving: A Lightweight Federated Learning-based Diffusion Model

High-quality Trajectory Generation for Autonomous Driving: A...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Gao, Runquan Kang, Jiawen Lai, Bingkun Xu, Minrui Sun, Geng Zhang, Tao Zhang, Weiting Yang, Dong Guangdong University of Technology School of Automation Guangzhou China Nanyang Technological University School of Computer Science and Engineering Singapore Jilin University College of Computer Science and Technology Changchun China Beijing Jiaotong University School of Software Engineering Beijing China Beijing Jiaotong University School of Electronic and Information Engineering Beijing China

ISBN: (纸本)9798350351255

Vehicle trajectory data plays a pivotal role in simulation testing for autonomous driving. Hence, there exist well-established trajectory generation methods employing deep generative models to generate trajectories mapping the distribution of the original dataset, thereby augmenting existing trajectory datasets. However, these methods typically rely on large datasets gathered by governmental or organizational entities for central training, which may pose data privacy, security, and accessibility issues. Therefore, it is challenging to generate high-quality traffic trajectory data while preserving privacy which involves a delicate balance between these two objectives. To deal with this challenge, we introduce Federated Learning into the diffusion model and propose a Federated Learning-based diffusion model (FedDifftraj) to generate traffic trajectory data. Unlike existing central training methods, FedDifftraj aggregates model parameters uploaded by different vehicles and then updates a global model. Additionally, there is a substantial communication overhead incurred during the training of the federated diffusion model. Therefore, we quantize the local diffusion model before uploading it to the parameter server. Through extensive simulations on real-world datasets, FedDifftraj can generate high-quality traffic trajectory data that is consistent with the results of the central training while preserving privacy and reducing communication overhead by 93.74% when utilizing 8-bit quantization. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A method of monitoring and locating eggs laid by breeding geese based on photoelectric sensing technology

引用

Information Processing in Agriculture 2022年第3期9卷 406-416页

作者： Yidan Xu Qiuju Xie Liwei Wang College of Mechanical and Automotive Engineering Zhaoqing UniversityZhaoqing526061China School of Computer Science and Software Zhaoqing UniversityZhaoqing 526061China

On the current breeding goose farm,the detection of individual egg laying mainly depends on some judgement experiences of farm *** present,there have been some egg laying detection systems developed with images and weighing sensors,which only signal the eggs being laid,but no egg position being ***,the detection rate of the system is not high due to environment limitations like dim light of the goose ***,to solve these problems mentioned above,an intelligent detection and positioning system is pro-posed by integrating technologies of the Radio Frequency(RF)and photoelectric sensors,together with the geometric calculation *** this research,individual egg laying information of breeding geese in a non-cage state was examined to improve the level of auto-matic detection and positioning in the field of breeder egg *** results showed that an accurate detection and positioning of an egg in a nest filled with the artificial turf could be achieved under some conditions:the height of sensor is 3.5 cm from the bottom plate of the egg laying nest,the spacing of the photoresistor module is 5 cm,and the external light intensity is less than 110 *** also shown that the error of the goose egg position recognition is 0.443 cm with a suitable level of straw in the ***,the monitoring system and positioningmethod that was developed in this research could provide a reference for the analysis of individual egg laying behavior,and could result in an improvement in the automatic egg collection for the breeding geese production.

关键词： Breeding geese Egg laying monitoring Goose egg location Photoelectric sensing technology RFID technology

来源：评论

学校读者我要写书评

暂无评论

FedHPM: Online Federated Learning via Heterogeneous Prediction Model 22

FedHPM: Online Federated Learning via Heterogeneous Predicti...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Zhang, Zhi Zhang, Shiwen Chen, Shuang Liang, Wei Hunan University of Science and Technology College of Computer Science and Technology Xiangtan China Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtan411201 China

ISBN: (纸本)9798331509712

In the era of big data and growing privacy concerns, Federated Learning (FL) has emerged as a promising solution for collaborative model training while preserving user data privacy. However, FL faces challenges such as inconsistent data quality and frequent client dropouts, which hinder its performance. To address these challenges, we propose FedHPM, a novel framework that leverages the predictive capabilities of Long Short-Term Memory (LSTM) networks. FedHPM incorporates an intelligent client selection mechanism that utilizes LSTM-based analysis of historical data to forecast clients' potential data quality and dropout likelihood. This mechanism enables efficient selection of the top best-performing clients for participation in each round of global model training. By mitigating the impact of dropouts and optimizing the composition of participating clients, FedHPM significantly improves both the convergence speed and final performance of the global model. Through extensive empirical evaluations, we demonstrate the superior performance of FedHPM in enhancing FL stability, accelerating the convergence rate, and maintaining model accuracy. The results highlight the effectiveness of our framework in addressing the challenges associated with data quality and dropouts, thereby advancing the field of federated learning. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Image Compression and Stable Reconstruction Based on Multi-Level Hybrid Feature Guidance 2

Image Compression and Stable Reconstruction Based on Multi-L...

引用

2nd International Conference on Machine Learning, Cloud Computing, and Intelligent Mining, MLCCIM 2023

作者： Zeng, Heng Gong, Nanxu College of Software Engineering Sichuan University Chengdu China School of Computer Science Sichuan University Chengdu China

ISBN: (纸本)9798350328530

Image compression is a technique that reduces storage space and transmission bandwidth requirements by reducing the amount of image data, aiming to improve storage and transmission efficiency while maintaining acceptable image quality. In recent years, learning-based image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression standards. Nevertheless, existing approaches often struggle to simultaneously achieve high compression rates and high-quality reconstruction. To tackle this issue, we present an image compression and stable reconstruction method based on multi-level hybrid feature guidance. Firstly, a hybrid attention module that combines spatial, channel, and shuffle attention is designed to improve the model's ability to capture local features of the image. Secondly, we utilize boundary prediction and frequency domain feature prediction auxiliary branches to guide the network for image compression and reconstruction. Moreover, we propose an image compression and reconstruction algorithm framework based on multi-level feature guidance. Based on experimental results, our method surpasses existing approaches in achieving superior rate-distortion performance. These research results are of great significance to the further development of image compression and reconstruction technology. © 2023 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy 23

Adaptive Evolutionary Reinforcement Learning Algorithm with ...

引用

23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024

作者： Wu, Xiaoqiang Zhu, Qingling Lin, Qiuzhen Chen, Weineng Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method. © 2024 International Foundation for Autonomous Agents and Multiagent Systems.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving Event Coreference Resolution Using Prompt Learning and U-shaped Module 4

Improving Event Coreference Resolution Using Prompt Learning...

引用

4th International Conference on computer science and Blockchain, CCSB 2024

作者： Zhang, Mengyao Long, Jun Huang, Wenti School of Software Xinjiang University Urumqi China Institute of Big Data Central South University Changsha China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China

ISBN: (纸本)9798350356502

Event Coreference Resolution (ECR) focuses on clustering event mentions that allude to identical actual events. Previous research primarily focuses on encoding event mentions without incorporating human interpretations, making it difficult to integrate human-summarized rules for guiding the ECR task. Furthermore, the semantic relations between event mentions have not been thoroughly explored, which impacts coreference judgment. To address these issues, we first utilize the powerful Longformer to acquire event representations at the document level. In addition, we introduce a prompt learning template to better emphasize event types and parameters, enhancing the interaction between event modeling and coreference judgment. Ultimately, we create matching vectors for event mentions using tensor matching and incorporate a U-shaped module to effectively identify the semantic relationships among these mentions, which enhances coreference discrimination. DPTU surpasses other ECR models on the KBP2017 dataset in cause of some experiments. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Autonomous Aspect-Image Instruction A2II: Q-Former Guided Multimodal Sentiment Classification 30

Autonomous Aspect-Image Instruction A2II: Q-Former Guided Mu...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Feng, Junjia Lin, Mingqian Shang, Lin Gao, Xiaoying State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Engineering and Computer Science Victoria University of Wellington New Zealand

ISBN: (纸本)9782493814104

Multimodal aspect-oriented sentiment classification (MABSC) task has garnered significant attention, which aims to identify the sentiment polarities of aspects by combining both language and vision information. However, the limited multimodal data in this task has become a big gap for the vision-language multimodal fusion. While large-scale vision-language pretrained models have been adapted to multiple tasks, their use for MABSC task is still in a nascent stage. In this work, we present an attempt to use the instruction tuning paradigm to MABSC task and leverage the ability of large vision-language models to alleviate the limitation in the fusion of textual and image modalities. To tackle the problem of potential irrelevance between aspects and images, we propose a plug-and-play selector to autonomously choose the most appropriate instruction from the instruction pool, thereby reducing the impact of irrelevant image noise on the final sentiment classification results. We conduct extensive experiments in various scenarios and our model achieves state-of-the-art performance on benchmark datasets, as well as in few-shot settings. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：