Journal of King Saud University-Computer and Information Sciences最新文献_第6页

Dual-stream dynamic graph structure network for document-level relation extraction 用于文档级关系提取的双流动态图结构网络

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-03 DOI: 10.1016/j.jksuci.2024.102202

Yu Zhong, Bo Shen

Extracting structured information from unstructured text is crucial for knowledge management and utilization, which is the goal of document-level relation extraction. Existing graph-based methods face issues with information confusion and integration, limiting the reasoning capabilities of the model. To tackle this problem, a dual-stream dynamic graph structural network is proposed to model documents from various perspectives. Leveraging the richness of document information, a static document heterogeneous graph is constructed. A dynamic heterogeneous document graph is then induced based on this foundation to facilitate global information aggregation for entity representation learning. Additionally, the static document graph is decomposed into multi-level static semantic graphs, and multi-layer dynamic semantic graphs are further induced, explicitly segregating information from different levels. Information from different streams is effectively integrated via an information integrator. To mitigate the interference of noise during the reasoning process, a noise regularization mechanism is also designed. The experimental results on three extensively utilized publicly accessible datasets for document-level relation extraction demonstrate that our model achieves F1 scores of 62.56%, 71.1%, and 86.9% on the DocRED, CDR, and GDA datasets, respectively, significantly outperforming the baselines. Further analysis also demonstrates the effectiveness of the model in multi-entity scenarios.

从非结构化文本中提取结构化信息对于知识管理和利用至关重要，这也是文档级关系提取的目标。现有的基于图的方法面临着信息混淆和整合的问题，限制了模型的推理能力。为解决这一问题，我们提出了一种双流动态图结构网络，从不同角度对文档进行建模。利用丰富的文档信息，构建静态文档异构图。然后在此基础上诱导出动态异构文档图，以促进实体表征学习的全局信息聚合。此外，静态文档图被分解成多层次的静态语义图，并进一步诱导出多层次的动态语义图，明确分离来自不同层次的信息。来自不同信息流的信息通过信息集成器进行有效集成。为了减少推理过程中的噪声干扰，还设计了噪声正则化机制。在三个广泛使用的公开文档级关系提取数据集上的实验结果表明，我们的模型在 DocRED、CDR 和 GDA 数据集上的 F1 分数分别达到了 62.56%、71.1% 和 86.9%，明显优于基线模型。进一步的分析还证明了该模型在多实体场景中的有效性。

{"title":"Dual-stream dynamic graph structure network for document-level relation extraction","authors":"Yu Zhong, Bo Shen","doi":"10.1016/j.jksuci.2024.102202","DOIUrl":"10.1016/j.jksuci.2024.102202","url":null,"abstract":"<div><div>Extracting structured information from unstructured text is crucial for knowledge management and utilization, which is the goal of document-level relation extraction. Existing graph-based methods face issues with information confusion and integration, limiting the reasoning capabilities of the model. To tackle this problem, a dual-stream dynamic graph structural network is proposed to model documents from various perspectives. Leveraging the richness of document information, a static document heterogeneous graph is constructed. A dynamic heterogeneous document graph is then induced based on this foundation to facilitate global information aggregation for entity representation learning. Additionally, the static document graph is decomposed into multi-level static semantic graphs, and multi-layer dynamic semantic graphs are further induced, explicitly segregating information from different levels. Information from different streams is effectively integrated via an information integrator. To mitigate the interference of noise during the reasoning process, a noise regularization mechanism is also designed. The experimental results on three extensively utilized publicly accessible datasets for document-level relation extraction demonstrate that our model achieves F1 scores of 62.56%, 71.1%, and 86.9% on the DocRED, CDR, and GDA datasets, respectively, significantly outperforming the baselines. Further analysis also demonstrates the effectiveness of the model in multi-entity scenarios.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 9","pages":"Article 102202"},"PeriodicalIF":5.2,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ParaU-Net: An improved UNet parallel coding network for lung nodule segmentation ParaU-Net：用于肺结节分割的改进型 UNet 并行编码网络

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-01 DOI: 10.1016/j.jksuci.2024.102203

Yingqi Lu , Xiangsuo Fan , Jinfeng Wang , Shaojun Chen , Jie Meng

Accurate segmentation of lung nodules is crucial for the early detection of lung cancer and other pulmonary diseases. Traditional segmentation methods face several challenges, such as the overlap between nodules and surrounding anatomical structures like blood vessels and bronchi, as well as the variability in nodule size and shape, which complicates the segmentation algorithms. Existing methods often inadequately address these issues, highlighting the need for a more effective solution. To address these challenges, this paper proposes an improved multi-scale parallel fusion encoding network, ParaU-Net. ParaU-Net enhances the segmentation accuracy and model performance by optimizing the encoding process, improving feature extraction, preserving down-sampling information, and expanding the receptive field. Specifically, the multi-scale parallel fusion mechanism introduced in ParaU-Net better captures the fine features of nodules and reduces interference from other structures. Experiments conducted on the LIDC (The Lung Image Database Consortium) public dataset demonstrate the excellent performance of ParaU-Net in segmentation tasks, with results showing an IoU of 87.15%, Dice of 92.16%, F1-score of 92.24%, F2-score of 92.33%, and F0.5-score of 92.69%. These results significantly outperform other advanced segmentation methods, validating the effectiveness and accuracy of the proposed model in lung nodule CT image analysis. The code is available at https://github.com/XiaoBai-Lyq/ParaU-Net.

准确分割肺结节对于早期检测肺癌和其他肺部疾病至关重要。传统的分割方法面临着一些挑战，例如结节与周围解剖结构（如血管和支气管）之间的重叠，以及结节大小和形状的可变性，这些都使分割算法变得复杂。现有方法往往无法充分解决这些问题，因此需要更有效的解决方案。为了应对这些挑战，本文提出了一种改进的多尺度并行融合编码网络 ParaU-Net。ParaU-Net 通过优化编码过程、改进特征提取、保留向下采样信息和扩大感受野来提高分割精度和模型性能。具体来说，ParaU-Net 引入的多尺度并行融合机制能更好地捕捉结节的精细特征，并减少其他结构的干扰。在 LIDC（肺部图像数据库联盟）公共数据集上进行的实验证明了 ParaU-Net 在分割任务中的卓越性能，结果显示 IoU 为 87.15%，Dice 为 92.16%，F1-score 为 92.24%，F2-score 为 92.33%，F0.5-score 为 92.69%。这些结果明显优于其他先进的分割方法，验证了所提模型在肺结节 CT 图像分析中的有效性和准确性。代码见 https://github.com/XiaoBai-Lyq/ParaU-Net。

{"title":"ParaU-Net: An improved UNet parallel coding network for lung nodule segmentation","authors":"Yingqi Lu , Xiangsuo Fan , Jinfeng Wang , Shaojun Chen , Jie Meng","doi":"10.1016/j.jksuci.2024.102203","DOIUrl":"10.1016/j.jksuci.2024.102203","url":null,"abstract":"<div><div>Accurate segmentation of lung nodules is crucial for the early detection of lung cancer and other pulmonary diseases. Traditional segmentation methods face several challenges, such as the overlap between nodules and surrounding anatomical structures like blood vessels and bronchi, as well as the variability in nodule size and shape, which complicates the segmentation algorithms. Existing methods often inadequately address these issues, highlighting the need for a more effective solution. To address these challenges, this paper proposes an improved multi-scale parallel fusion encoding network, ParaU-Net. ParaU-Net enhances the segmentation accuracy and model performance by optimizing the encoding process, improving feature extraction, preserving down-sampling information, and expanding the receptive field. Specifically, the multi-scale parallel fusion mechanism introduced in ParaU-Net better captures the fine features of nodules and reduces interference from other structures. Experiments conducted on the LIDC (The Lung Image Database Consortium) public dataset demonstrate the excellent performance of ParaU-Net in segmentation tasks, with results showing an IoU of 87.15%, Dice of 92.16%, F1-score of 92.24%, F2-score of 92.33%, and F0.5-score of 92.69%. These results significantly outperform other advanced segmentation methods, validating the effectiveness and accuracy of the proposed model in lung nodule CT image analysis. The code is available at <span><span>https://github.com/XiaoBai-Lyq/ParaU-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 9","pages":"Article 102203"},"PeriodicalIF":5.2,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LungNeXt: A novel lightweight network utilizing enhanced mel-spectrogram for lung sound classification LungNeXt：利用增强型 Mel 光谱图进行肺音分类的新型轻量级网络

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-01 DOI: 10.1016/j.jksuci.2024.102200

Fan Wang , Xiaochen Yuan , Yue Liu , Chan-Tong Lam

Lung auscultation is essential for early lung condition detection. Categorizing adventitious lung sounds requires expert discrimination by medical specialists. This paper details the features of LungNeXt, a novel classification model specifically designed for lung sound analysis. Furthermore, we propose two auxiliary methods: RandClipMix (RCM) for data augmentation and Enhanced Mel-Spectrogram for Feature Extraction (EMFE). RCM addresses the issue of data imbalance by randomly mixing clips within the same category to create new adventitious lung sounds. EMFE augments specific frequency bands in spectrograms to highlight adventitious features. These contributions enable LungNeXt to achieve outstanding performance. LungNeXt optimally integrates an appropriate number of NeXtblocks, ensuring superior performance and a lightweight model architecture. The proposed RCM and EMFE methods, along with the LungNeXt classification network, have been evaluated on the SPRSound dataset. Experimental results revealed a commendable score of 0.5699 for the lung sound five-category task on SPRSound. Specifically, the LungNeXt model is characterized by its efficiency, with only 3.804M parameters and a computational complexity of 0.659G FLOPS. This lightweight and efficient model is particularly well-suited for applications in electronic stethoscope back-end processing equipment, providing efficient diagnostic advice to physicians and patients.

肺部听诊对于早期发现肺部疾病至关重要。对肺部杂音进行分类需要医学专家的专业辨别。本文详细介绍了 LungNeXt 的特点，这是一种专为肺部声音分析而设计的新型分类模型。此外，我们还提出了两种辅助方法：用于数据增强的 RandClipMix（RCM）和用于特征提取的增强型 Mel-Spectrogram （EMFE）。RCM 通过随机混合同一类别中的片段来创建新的偶然肺音，从而解决了数据不平衡的问题。EMFE 增强了频谱图中的特定频段，以突出偶然特征。这些贡献使 LungNeXt 实现了出色的性能。LungNeXt 优化整合了适当数量的 NeXt 块，确保了卓越的性能和轻量级的模型架构。我们在 SPRSound 数据集上对所提出的 RCM 和 EMFE 方法以及 LungNeXt 分类网络进行了评估。实验结果表明，在 SPRSound 的肺部声音五类任务中取得了 0.5699 的高分。具体来说，LungNeXt 模型的特点是效率高，只有 3.804M 个参数，计算复杂度为 0.659G FLOPS。这种轻便高效的模型尤其适合应用于电子听诊器后端处理设备，为医生和患者提供高效的诊断建议。

{"title":"LungNeXt: A novel lightweight network utilizing enhanced mel-spectrogram for lung sound classification","authors":"Fan Wang , Xiaochen Yuan , Yue Liu , Chan-Tong Lam","doi":"10.1016/j.jksuci.2024.102200","DOIUrl":"10.1016/j.jksuci.2024.102200","url":null,"abstract":"<div><div>Lung auscultation is essential for early lung condition detection. Categorizing adventitious lung sounds requires expert discrimination by medical specialists. This paper details the features of LungNeXt, a novel classification model specifically designed for lung sound analysis. Furthermore, we propose two auxiliary methods: RandClipMix (RCM) for data augmentation and Enhanced Mel-Spectrogram for Feature Extraction (EMFE). RCM addresses the issue of data imbalance by randomly mixing clips within the same category to create new adventitious lung sounds. EMFE augments specific frequency bands in spectrograms to highlight adventitious features. These contributions enable LungNeXt to achieve outstanding performance. LungNeXt optimally integrates an appropriate number of NeXtblocks, ensuring superior performance and a lightweight model architecture. The proposed RCM and EMFE methods, along with the LungNeXt classification network, have been evaluated on the SPRSound dataset. Experimental results revealed a commendable score of 0.5699 for the lung sound five-category task on SPRSound. Specifically, the LungNeXt model is characterized by its efficiency, with only 3.804M parameters and a computational complexity of 0.659G FLOPS. This lightweight and efficient model is particularly well-suited for applications in electronic stethoscope back-end processing equipment, providing efficient diagnostic advice to physicians and patients.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 8","pages":"Article 102200"},"PeriodicalIF":5.2,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-throughput systolic array-based accelerator for hybrid transformer-CNN networks 基于高通量收缩阵列的混合变压器-网络加速器

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-01 DOI: 10.1016/j.jksuci.2024.102194

Qingzeng Song , Yao Dai , Hao Lu , Guanghao Jin

In this era of Transformers enjoying remarkable success, Convolutional Neural Networks (CNNs) remain highly relevant and useful. Indeed, hybrid Transformer-CNN network architectures, which combine the benefits of both approaches, have achieved impressive results. Vision Transformer (ViT) is a significant neural network architecture that features a convolutional layer as its first layer, primarily built on the transformer framework. However, owing to the distinct computation patterns inherent in attention and convolution, existing hardware accelerators for these two models are typically designed separately and lack a unified approach toward accelerating both models efficiently. In this paper, we present a dedicated accelerator on a field-programmable gate array (FPGA) platform. The accelerator, which integrates a configurable three-dimensional systolic array, is specifically designed to accelerate the inferential capabilities of hybrid Transformer-CNN networks. The Convolution and Transformer computations can be mapped to a systolic array by unifying these operations for matrix multiplication. Softmax and LayerNorm which are frequently used in hybrid Transformer-CNN networks were also implemented on FPGA boards. The accelerator achieved high performance with a peak throughput of 722 GOP/s at an average energy efficiency of 53 GOPS/W. Its respective computation latencies were 51.3 ms, 18.1 ms, and 6.8 ms for ViT-Base, ViT-Small, and ViT-Tiny. The accelerator provided a

12 \times

improvement in energy efficiency compared to the CPU, a

2.3 \times

improvement compared to the GPU, and a

1.5 \times

to

2 \times

improvement compared to existing accelerators regarding speed and energy efficiency.

在变压器取得巨大成功的今天，卷积神经网络（CNN）仍然非常重要和有用。事实上，结合了变形器和 CNN 两种方法优点的混合变形器-CNN 网络架构已经取得了令人瞩目的成果。视觉变换器（ViT）是一种重要的神经网络架构，其第一层为卷积层，主要建立在变换器框架之上。然而，由于注意力和卷积的固有计算模式不同，这两种模型的现有硬件加速器通常是分开设计的，缺乏一种统一的方法来高效地加速这两种模型。在本文中，我们在现场可编程门阵列（FPGA）平台上提出了一种专用加速器。该加速器集成了一个可配置的三维收缩阵列，专门用于加速混合变换器-CNN 网络的推理能力。通过统一矩阵乘法运算，卷积和变换器计算可以映射到合成阵列中。在混合变换器-CNN 网络中经常使用的 Softmax 和 LayerNorm 也在 FPGA 板上实现。加速器实现了高性能，峰值吞吐量为 722 GOP/s，平均能效为 53 GOPS/W。ViT-Base、ViT-Small 和 ViT-Tiny 的计算延迟分别为 51.3 毫秒、18.1 毫秒和 6.8 毫秒。与 CPU 相比，该加速器的能效提高了 12 倍；与 GPU 相比，提高了 2.3 倍；与现有加速器相比，在速度和能效方面提高了 1.5 倍至 2 倍。

{"title":"High-throughput systolic array-based accelerator for hybrid transformer-CNN networks","authors":"Qingzeng Song , Yao Dai , Hao Lu , Guanghao Jin","doi":"10.1016/j.jksuci.2024.102194","DOIUrl":"10.1016/j.jksuci.2024.102194","url":null,"abstract":"<div><div>In this era of Transformers enjoying remarkable success, Convolutional Neural Networks (CNNs) remain highly relevant and useful. Indeed, hybrid Transformer-CNN network architectures, which combine the benefits of both approaches, have achieved impressive results. Vision Transformer (ViT) is a significant neural network architecture that features a convolutional layer as its first layer, primarily built on the transformer framework. However, owing to the distinct computation patterns inherent in attention and convolution, existing hardware accelerators for these two models are typically designed separately and lack a unified approach toward accelerating both models efficiently. In this paper, we present a dedicated accelerator on a field-programmable gate array (FPGA) platform. The accelerator, which integrates a configurable three-dimensional systolic array, is specifically designed to accelerate the inferential capabilities of hybrid Transformer-CNN networks. The Convolution and Transformer computations can be mapped to a systolic array by unifying these operations for matrix multiplication. Softmax and LayerNorm which are frequently used in hybrid Transformer-CNN networks were also implemented on FPGA boards. The accelerator achieved high performance with a peak throughput of 722 GOP/s at an average energy efficiency of 53 GOPS/W. Its respective computation latencies were 51.3 ms, 18.1 ms, and 6.8 ms for ViT-Base, ViT-Small, and ViT-Tiny. The accelerator provided a <span><math><mrow><mn>12</mn><mo>×</mo></mrow></math></span> improvement in energy efficiency compared to the CPU, a <span><math><mrow><mn>2</mn><mo>.</mo><mn>3</mn><mo>×</mo></mrow></math></span> improvement compared to the GPU, and a <span><math><mrow><mn>1</mn><mo>.</mo><mn>5</mn><mo>×</mo></mrow></math></span> to <span><math><mrow><mn>2</mn><mo>×</mo></mrow></math></span> improvement compared to existing accelerators regarding speed and energy efficiency.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 8","pages":"Article 102194"},"PeriodicalIF":5.2,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A scalable attention network for lightweight image super-resolution 用于轻量级图像超分辨率的可扩展注意力网络

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-01 DOI: 10.1016/j.jksuci.2024.102185

Jinsheng Fang , Xinyu Chen , Jianglong Zhao , Kun Zeng

Modeling long-range dependencies among features has become a consensus to improve the results of single image super-resolution (SISR), which stimulates interest in enlarging the kernel sizes in convolutional neural networks (CNNs). Although larger kernels definitely improve the network performance, network parameters and computational complexities are raised sharply as well. Hence, an optimization of setting the kernel sizes is required to improve the efficiency of the network. In this work, we study the influence of the positions of larger kernels on the network performance, and propose a scalable attention network (SCAN). In SCAN, we propose a depth-related attention block (DRAB) that consists of several multi-scale information enhancement blocks (MIEBs) and resizable-kernel attention blocks (RKABs). The RKAB dynamically adjusts the kernel size concerning the locations of the DRABs in the network. The resizable mechanism allows the network to extract more informative features in shallower layers with larger kernels and focus on useful information in deeper layers with smaller ones, which effectively improves the SR results. Extensive experiments demonstrate that the proposed SCAN outperforms other state-of-the-art lightweight SR methods. Our codes are available at https://github.com/ginsengf/SCAN.

建立特征之间的长程依赖关系模型已成为改善单图像超分辨率（SISR）结果的共识，这激发了人们对扩大卷积神经网络（CNN）内核大小的兴趣。虽然增大内核肯定会提高网络性能，但网络参数和计算复杂度也会大幅提高。因此，需要对内核大小的设置进行优化，以提高网络的效率。在这项工作中，我们研究了较大内核的位置对网络性能的影响，并提出了一种可扩展的注意力网络（SCAN）。在 SCAN 中，我们提出了一种深度相关注意力块（DRAB），它由多个多尺度信息增强块（MIEB）和可调整大小的内核注意力块（RKAB）组成。RKAB 可根据 DRAB 在网络中的位置动态调整内核大小。这种可调整大小的机制允许网络在较浅的层中用较大的内核提取更多的信息特征，而在较深的层中用较小的内核关注有用的信息，从而有效地改善了 SR 结果。大量实验证明，所提出的 SCAN 优于其他最先进的轻量级 SR 方法。我们的代码见 https://github.com/ginsengf/SCAN。

{"title":"A scalable attention network for lightweight image super-resolution","authors":"Jinsheng Fang , Xinyu Chen , Jianglong Zhao , Kun Zeng","doi":"10.1016/j.jksuci.2024.102185","DOIUrl":"10.1016/j.jksuci.2024.102185","url":null,"abstract":"<div><div>Modeling long-range dependencies among features has become a consensus to improve the results of single image super-resolution (SISR), which stimulates interest in enlarging the kernel sizes in convolutional neural networks (CNNs). Although larger kernels definitely improve the network performance, network parameters and computational complexities are raised sharply as well. Hence, an optimization of setting the kernel sizes is required to improve the efficiency of the network. In this work, we study the influence of the positions of larger kernels on the network performance, and propose a scalable attention network (SCAN). In SCAN, we propose a depth-related attention block (DRAB) that consists of several multi-scale information enhancement blocks (MIEBs) and resizable-kernel attention blocks (RKABs). The RKAB dynamically adjusts the kernel size concerning the locations of the DRABs in the network. The resizable mechanism allows the network to extract more informative features in shallower layers with larger kernels and focus on useful information in deeper layers with smaller ones, which effectively improves the SR results. Extensive experiments demonstrate that the proposed SCAN outperforms other state-of-the-art lightweight SR methods. Our codes are available at <span><span>https://github.com/ginsengf/SCAN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 8","pages":"Article 102185"},"PeriodicalIF":5.2,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing requirements-to-code traceability with GA-XWCoDe: Integrating XGBoost, Node2Vec, and genetic algorithms for improving model performance and stability 利用 GA-XWCoDe 增强从需求到代码的可追溯性：集成 XGBoost、Node2Vec 和遗传算法，提高模型性能和稳定性

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-10-01 DOI: 10.1016/j.jksuci.2024.102197

Zhiyuan Zou , Bangchao Wang , Xinrong Hu , Yang Deng , Hongyan Wan , Huan Jin

This study addresses the challenge of requirements-to-code traceability by proposing a novel model, Genetic Algorithm-XGBoost With Code Dependency (GA-XWCoDe), which integrates eXtreme Gradient Boosting (XGBoost) with a Node2Vec model-weighted code dependency strategy and genetic algorithms for parameter optimisation. XGBoost mitigates overfitting and enhances model stability, while Node2Vec improves prediction accuracy for low-confidence links. Genetic algorithms are employed to optimise model parameters efficiently, reducing the resource intensity of traditional methods. Experimental results show that GA-XWCoDe outperforms the state-of-the-art method TRAceability lInk cLassifier (TRAIL) by 17.44% and Deep Forest for Requirement traceability (DF4RT) by 33.36% in terms of average F1 performance across four datasets. It is significantly superior to all baseline methods at a confidence level of

α

¡0.01 and demonstrates exceptional performance and stability across various training data scales.

本研究针对需求到代码的可追溯性所面临的挑战，提出了一种新的模型--代码依赖性遗传算法-XGBoost（GA-XWCoDe），该模型集成了 eXtreme Gradient Boosting（XGBoost）、Node2Vec 模型加权代码依赖性策略和参数优化遗传算法。XGBoost 可减轻过度拟合并增强模型稳定性，而 Node2Vec 则可提高低置信度链接的预测准确性。遗传算法用于有效优化模型参数，降低了传统方法的资源强度。实验结果表明，就四个数据集的平均 F1 性能而言，GA-XWCoDe 比最先进的 TRAceability lInk cLassifier（TRAIL）方法高出 17.44%，比需求可追溯性深林（DF4RT）方法高出 33.36%。在置信度为 α¡0.01 时，它明显优于所有基线方法，并在各种训练数据规模下表现出卓越的性能和稳定性。

{"title":"Enhancing requirements-to-code traceability with GA-XWCoDe: Integrating XGBoost, Node2Vec, and genetic algorithms for improving model performance and stability","authors":"Zhiyuan Zou , Bangchao Wang , Xinrong Hu , Yang Deng , Hongyan Wan , Huan Jin","doi":"10.1016/j.jksuci.2024.102197","DOIUrl":"10.1016/j.jksuci.2024.102197","url":null,"abstract":"<div><div>This study addresses the challenge of requirements-to-code traceability by proposing a novel model, Genetic Algorithm-XGBoost With Code Dependency (GA-XWCoDe), which integrates eXtreme Gradient Boosting (XGBoost) with a Node2Vec model-weighted code dependency strategy and genetic algorithms for parameter optimisation. XGBoost mitigates overfitting and enhances model stability, while Node2Vec improves prediction accuracy for low-confidence links. Genetic algorithms are employed to optimise model parameters efficiently, reducing the resource intensity of traditional methods. Experimental results show that GA-XWCoDe outperforms the state-of-the-art method TRAceability lInk cLassifier (TRAIL) by 17.44% and Deep Forest for Requirement traceability (DF4RT) by 33.36% in terms of average F1 performance across four datasets. It is significantly superior to all baseline methods at a confidence level of <span><math><mi>α</mi></math></span>¡0.01 and demonstrates exceptional performance and stability across various training data scales.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 8","pages":"Article 102197"},"PeriodicalIF":5.2,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast and robust JND-guided video watermarking scheme in spatial domain 空间域快速稳健的 JND 引导视频水印方案

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-09-30 DOI: 10.1016/j.jksuci.2024.102199

Antonio Cedillo-Hernandez , Lydia Velazquez-Garcia , Manuel Cedillo-Hernandez , David Conchouso-Gonzalez

Generally speaking, those watermarking studies using the spatial domain tend to be fast but with limited robustness and imperceptibility while those performed in other transform domains are robust but have high computational cost. Watermarking applied to digital video has as one of the main challenges the large amount of computational power required due to the huge amount of information to be processed. In this paper we propose a watermarking algorithm for digital video that addresses this problem. To increase the speed, the watermark is embedded using a technique to modify the DCT coefficients directly in the spatial domain, in addition to carrying out this process considering the video scene as the basic unit and not the video frame. In terms of robustness, the watermark is modulated by a Just Noticeable Distortion (JND) scheme computed directly in the spatial domain guided by visual attention to increase the strength of the watermark to the maximum level but without this operation being perceivable by human eyes. Experimental results confirm that the proposed method achieves remarkable performance in terms of processing time, robustness and imperceptibility compared to previous studies.

一般来说，使用空间域进行的水印研究往往速度快，但鲁棒性和不可感知性有限，而使用其他变换域进行的水印研究鲁棒性强，但计算成本高。数字视频水印技术面临的主要挑战之一是，由于需要处理的信息量巨大，因此需要大量的计算能力。本文针对这一问题提出了一种数字视频水印算法。为了提高速度，我们采用了一种在空间域直接修改 DCT 系数的技术来嵌入水印，此外，我们还将视频场景而不是视频帧作为基本单位来执行这一过程。在鲁棒性方面，水印是通过直接在空间域计算的 "刚注意到的失真"（JND）方案调制的，该方案以视觉注意力为导向，将水印强度提高到最大水平，但人眼无法感知这一操作。实验结果证实，与之前的研究相比，所提出的方法在处理时间、鲁棒性和不可感知性方面都取得了显著的性能。

{"title":"Fast and robust JND-guided video watermarking scheme in spatial domain","authors":"Antonio Cedillo-Hernandez , Lydia Velazquez-Garcia , Manuel Cedillo-Hernandez , David Conchouso-Gonzalez","doi":"10.1016/j.jksuci.2024.102199","DOIUrl":"10.1016/j.jksuci.2024.102199","url":null,"abstract":"<div><div>Generally speaking, those watermarking studies using the spatial domain tend to be fast but with limited robustness and imperceptibility while those performed in other transform domains are robust but have high computational cost. Watermarking applied to digital video has as one of the main challenges the large amount of computational power required due to the huge amount of information to be processed. In this paper we propose a watermarking algorithm for digital video that addresses this problem. To increase the speed, the watermark is embedded using a technique to modify the DCT coefficients directly in the spatial domain, in addition to carrying out this process considering the video scene as the basic unit and not the video frame. In terms of robustness, the watermark is modulated by a Just Noticeable Distortion (JND) scheme computed directly in the spatial domain guided by visual attention to increase the strength of the watermark to the maximum level but without this operation being perceivable by human eyes. Experimental results confirm that the proposed method achieves remarkable performance in terms of processing time, robustness and imperceptibility compared to previous studies.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 9","pages":"Article 102199"},"PeriodicalIF":5.2,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Software requirement engineering over the federated environment in distributed software development process 分布式软件开发过程中联合环境下的软件需求工程

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-09-28 DOI: 10.1016/j.jksuci.2024.102201

Abdulaziz Alhumam, Shakeel Ahmed

In the recent past, the distributed software development (DSD) process has become increasingly prevalent with the rapid evolution of the software development process. This transformation would necessitate a robust framework for software requirement engineering (SRE) to work in federated environments. Using the federated environment, multiple independent software entities would work together to develop software, often across organizations and geographical borders. The decentralized structure of the federated architecture makes requirement elicitation, analysis, specification, validation, and administration more effective. The proposed model emphasizes flexibility and agility, leveraging the collaboration of multiple localized models within a diversified development framework. This collaborative approach is designed to integrate the strengths of each local process, ultimately resulting in the creation of a robust software prototype. The performance of the proposed DSD model is evaluated using two case studies on the E-Commerce website and the Learning Management system. The proposed model is analyzed by considering divergent functional and non-functional requirements for each of the case studies and analyzing the performance using standardized metrics like mean square error (MSE), mean absolute error (MAE), and Pearson Correlation Coefficient (PCC). It is observed that the proposed model exhibited a reasonable performance with an MSE value of 0.12 and 0.153 for both functional and non-functional requirements, respectively, and an MAE value of 0.222 and 0.232 for both functional and non-functional requirements, respectively.

近年来，随着软件开发流程的快速发展，分布式软件开发（DSD）流程变得越来越普遍。这种转变需要一个强大的软件需求工程（SRE）框架，以便在联合环境中工作。利用联盟环境，多个独立的软件实体将共同开发软件，而且往往跨越组织和地理边界。联合架构的分散结构使需求激发、分析、规范、验证和管理更加有效。建议的模式强调灵活性和敏捷性，在一个多样化的开发框架内利用多个本地化模型的协作。这种协作方法旨在整合每个本地流程的优势，最终创建一个强大的软件原型。通过对电子商务网站和学习管理系统的两个案例研究，对所提出的 DSD 模型的性能进行了评估。通过考虑每个案例研究的不同功能和非功能需求，并使用均方误差 (MSE)、平均绝对误差 (MAE) 和皮尔逊相关系数 (PCC) 等标准化指标分析了所提出模型的性能。结果表明，所提出的模型表现出合理的性能，对功能性和非功能性需求的 MSE 值分别为 0.12 和 0.153，对功能性和非功能性需求的 MAE 值分别为 0.222 和 0.232。

{"title":"Software requirement engineering over the federated environment in distributed software development process","authors":"Abdulaziz Alhumam, Shakeel Ahmed","doi":"10.1016/j.jksuci.2024.102201","DOIUrl":"10.1016/j.jksuci.2024.102201","url":null,"abstract":"<div><div>In the recent past, the distributed software development (DSD) process has become increasingly prevalent with the rapid evolution of the software development process. This transformation would necessitate a robust framework for software requirement engineering (SRE) to work in federated environments. Using the federated environment, multiple independent softwareentities wouldwork together to develop software, often across organizationsand geographical borders. The decentralized structure of the federated architecture makes requirement elicitation, analysis, specification, validation, and administration more effective.The proposed model emphasizes flexibility and agility, leveraging the collaboration of multiple localized models within a diversified development framework. This collaborative approach is designed to integrate the strengths of each local process, ultimately resulting in the creation of a robust software prototype. The performance of the proposed DSD model is evaluated using two case studies on the E-Commerce website and the Learning Management system. The proposed model is analyzed by considering divergent functional and non-functional requirements for each of the case studies and analyzing the performance using standardized metrics like mean square error (MSE), mean absolute error (MAE), and Pearson Correlation Coefficient (PCC). It is observed that the proposed model exhibited a reasonable performance with an MSE value of 0.12 and 0.153 for both functional and non-functional requirements, respectively, and an MAE value of 0.222 and 0.232 for both functional and non-functional requirements, respectively.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 9","pages":"Article 102201"},"PeriodicalIF":5.2,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PFEL-Net: A lightweight network to enhance feature for multi-scale pedestrian detection PFEL-Net：用于增强多尺度行人检测特征的轻量级网络

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-09-26 DOI: 10.1016/j.jksuci.2024.102198

Jingwen Tang , Huicheng Lai , Guxue Gao , Tongguan Wang

In the context of intelligent community research, pedestrian detection is an important and challenging object detection task. The diversity in pedestrian target scales and the interference from the surrounding background can result in incorrect and missed detections by the detector, while a large algorithm model can pose challenges for deploying the detector. In response to these issues, this work presents a pedestrian feature enhancement lightweight network (PFEL-Net), which provides the possibility for edge computing and accurate detection of multi-scale pedestrian targets in complex scenes. Firstly, a parallel dilated residual module is designed to expand the receptive field for obtaining richer pedestrian features; then, the selective bidirectional diffusion pyramid network is devised to finely fuse features, and a detail feature layer captures multi-scale information; after that, the lightweight shared detection head is constructed to lightweight the model head; finally, the channel pruning algorithm is employed to further reduce the computational complexity and size of the improved model without compromising accuracy. On the CityPersons dataset, compared to YOLOv8, PFEL-Net increases the

m A P_{50}

and

m A P_{50 : 95}

by 6.3% and 4.9%, respectively, reduces the number of model parameters by 89% and compresses the model size by 85%, resulting in a mere 0.9 MB. Similarly, excellent performance is achieved on the TinyPerson dataset. The source code is available at https://github.com/1tangbao/PFEL.

在智能社区研究中，行人检测是一项重要而具有挑战性的目标检测任务。行人目标尺度的多样性和周围背景的干扰会导致检测器的错误检测和漏检，而庞大的算法模型又会给检测器的部署带来挑战。针对这些问题，本研究提出了行人特征增强轻量级网络（PFEL-Net），为边缘计算和复杂场景中多尺度行人目标的精确检测提供了可能。首先，设计了并行扩张残差模块来扩大感受野，以获得更丰富的行人特征；然后，设计了选择性双向扩散金字塔网络来精细融合特征，并通过细节特征层捕捉多尺度信息；之后，构建了轻量级共享检测头来轻量化模型头；最后，采用通道剪枝算法，在不影响精度的前提下进一步降低计算复杂度，减小改进模型的大小。在 CityPersons 数据集上，与 YOLOv8 相比，PFEL-Net 的 mAP50 和 mAP50:95 分别提高了 6.3% 和 4.9%，模型参数数量减少了 89%，模型大小压缩了 85%，结果仅为 0.9 MB。同样，在 TinyPerson 数据集上也取得了优异的性能。源代码见 https://github.com/1tangbao/PFEL。

{"title":"PFEL-Net: A lightweight network to enhance feature for multi-scale pedestrian detection","authors":"Jingwen Tang , Huicheng Lai , Guxue Gao , Tongguan Wang","doi":"10.1016/j.jksuci.2024.102198","DOIUrl":"10.1016/j.jksuci.2024.102198","url":null,"abstract":"<div><div>In the context of intelligent community research, pedestrian detection is an important and challenging object detection task. The diversity in pedestrian target scales and the interference from the surrounding background can result in incorrect and missed detections by the detector, while a large algorithm model can pose challenges for deploying the detector. In response to these issues, this work presents a pedestrian feature enhancement lightweight network (PFEL-Net), which provides the possibility for edge computing and accurate detection of multi-scale pedestrian targets in complex scenes. Firstly, a parallel dilated residual module is designed to expand the receptive field for obtaining richer pedestrian features; then, the selective bidirectional diffusion pyramid network is devised to finely fuse features, and a detail feature layer captures multi-scale information; after that, the lightweight shared detection head is constructed to lightweight the model head; finally, the channel pruning algorithm is employed to further reduce the computational complexity and size of the improved model without compromising accuracy. On the CityPersons dataset, compared to YOLOv8, PFEL-Net increases the <span><math><mrow><mi>m</mi><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></math></span> and <span><math><mrow><mi>m</mi><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn><mo>:</mo><mn>95</mn></mrow></msub></mrow></math></span> by 6.3% and 4.9%, respectively, reduces the number of model parameters by 89% and compresses the model size by 85%, resulting in a mere 0.9 MB. Similarly, excellent performance is achieved on the TinyPerson dataset. The source code is available at <span><span>https://github.com/1tangbao/PFEL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 8","pages":"Article 102198"},"PeriodicalIF":5.2,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142328201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A truthful randomized mechanism for task allocation with multi-attributes in mobile edge computing 移动边缘计算中多属性任务分配的真实随机机制

IF 5.2 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Journal of King Saud University-Computer and Information Sciences

Pub Date : 2024-09-26 DOI: 10.1016/j.jksuci.2024.102196

Xi Liu , Jun Liu

Mobile Edge Computing (MEC) aims at decreasing the response time and energy consumption of running mobile applications by offloading the tasks of mobile devices (MDs) to the MEC servers located at the edge of the network. The demands are multi-attribute, where the distances between MDs and access points lead to differences in required resources and transmission energy consumption. Unfortunately, the existing works have not considered both task allocation and energy consumption problems. Motivated by this, this paper considers the problem of task allocation with multi-attributes, where the problem consists of the winner determination and offloading decision problems. First, the problem is formulated as the auction-based model to provide flexible service. Then, a randomized mechanism is designed and is truthful in expectation. This drives the system into an equilibrium where no MD has incentives to increase the utility by declaring an untrue value. In addition, an approximation algorithm is proposed to minimize remote energy consumption and is a polynomial-time approximation scheme. Therefore, it achieves a tradeoff between optimality loss and time complexity. Simulation results reveal that the proposed mechanism gets the near-optimal allocation. Furthermore, compared with the baseline methods, the proposed mechanism can effectively increase social welfare and bring higher revenue to edge server providers.

移动边缘计算（MEC）旨在将移动设备（MD）的任务卸载到位于网络边缘的 MEC 服务器上，从而缩短移动应用程序的响应时间并降低能耗。需求是多属性的，移动设备和接入点之间的距离会导致所需资源和传输能耗的差异。遗憾的是，现有研究并未同时考虑任务分配和能耗问题。受此启发，本文考虑了多属性的任务分配问题，该问题包括获胜者确定和卸载决策问题。首先，将问题表述为基于拍卖的模型，以提供灵活的服务。然后，设计了一种随机机制，该机制在预期中是真实的。这就促使系统进入一个均衡状态，在此状态下，任何 MD 都没有动机通过宣布一个不真实的值来增加效用。此外，还提出了一种近似算法，以尽量减少远程能耗，这是一种多项式时间近似方案。因此，它实现了优化损失和时间复杂性之间的权衡。仿真结果表明，提出的机制获得了接近最优的分配。此外，与基线方法相比，建议的机制能有效提高社会福利，并为边缘服务器提供商带来更高的收益。

{"title":"A truthful randomized mechanism for task allocation with multi-attributes in mobile edge computing","authors":"Xi Liu , Jun Liu","doi":"10.1016/j.jksuci.2024.102196","DOIUrl":"10.1016/j.jksuci.2024.102196","url":null,"abstract":"<div><div>Mobile Edge Computing (MEC) aims at decreasing the response time and energy consumption of running mobile applications by offloading the tasks of mobile devices (MDs) to the MEC servers located at the edge of the network. The demands are multi-attribute, where the distances between MDs and access points lead to differences in required resources and transmission energy consumption. Unfortunately, the existing works have not considered both task allocation and energy consumption problems. Motivated by this, this paper considers the problem of task allocation with multi-attributes, where the problem consists of the winner determination and offloading decision problems. First, the problem is formulated as the auction-based model to provide flexible service. Then, a randomized mechanism is designed and is truthful in expectation. This drives the system into an equilibrium where no MD has incentives to increase the utility by declaring an untrue value. In addition, an approximation algorithm is proposed to minimize remote energy consumption and is a polynomial-time approximation scheme. Therefore, it achieves a tradeoff between optimality loss and time complexity. Simulation results reveal that the proposed mechanism gets the near-optimal allocation. Furthermore, compared with the baseline methods, the proposed mechanism can effectively increase social welfare and bring higher revenue to edge server providers.</div></div>","PeriodicalId":48547,"journal":{"name":"Journal of King Saud University-Computer and Information Sciences","volume":"36 9","pages":"Article 102196"},"PeriodicalIF":5.2,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0