Computers & Electrical Engineering最新文献_第6页

Data driven approach for state-of-charge estimation of lithium-ion cell using stochastic variational Gaussian process 利用随机变异高斯过程估算锂离子电池充电状态的数据驱动方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-30 DOI: 10.1016/j.compeleceng.2024.109727

Modern electric vehicles rely on lithium-ion batteries. Electric vehicles (EVs) utilize intricate battery packs that require the oversight of a battery management system (BMS) to ensure safe, reliable, and efficient operation. The state estimation of the battery pack is an important responsibility carried out by the BMS. Accurately estimating the State-of-Charge (SOC) poses a considerable engineering challenge since it cannot be directly measured at the battery terminals. This study introduces a novel data-driven methodology for accurately estimating the SOC in Lithium-ion batteries, with a particular focus on its relevance in EV contexts. The framework is built upon the Stochastic Variational Gaussian Process (SVGP)—an improved version of the conventional Gaussian Process (GP). Unlike GP, It can scale up to very large datasets. Furthermore, SVGP uses variational inference to estimate the posterior instead of calculating, making it computationally efficient. The model training process involves using laboratory test data from an 18650 Lithium-ion Nickel Manganese Cobalt (NMC) cell that has gone through eight dynamic drive cycles. The findings showcase a remarkable level of precision in estimation, as indicated by an average R² value of 0.99 and a Mean Square Error (MSE) as low as 0.02.

现代电动汽车依赖于锂离子电池。电动汽车（EV）使用复杂的电池组，需要电池管理系统（BMS）的监督，以确保安全、可靠和高效的运行。电池组的状态估计是 BMS 的一项重要职责。由于无法在电池终端直接测量，因此准确估算充电状态（SOC）是一项相当大的工程挑战。本研究介绍了一种新颖的数据驱动方法，用于准确估算锂离子电池的 SOC，尤其关注其与电动汽车的相关性。该框架基于随机变异高斯过程（SVGP）--传统高斯过程（GP）的改进版本。与 GP 不同，它可以扩展到非常大的数据集。此外，SVGP 使用变异推理来估计后验而不是计算，因此计算效率很高。模型训练过程包括使用实验室测试数据，这些数据来自经过八个动态驱动循环的 18650 锂离子镍锰钴（NMC）电池。平均 R2 值为 0.99，平均平方误差 (MSE) 低至 0.02，这表明该模型的估算精度达到了很高的水平。

{"title":"Data driven approach for state-of-charge estimation of lithium-ion cell using stochastic variational Gaussian process","authors":"","doi":"10.1016/j.compeleceng.2024.109727","DOIUrl":"10.1016/j.compeleceng.2024.109727","url":null,"abstract":"<div><div>Modern electric vehicles rely on lithium-ion batteries. Electric vehicles (EVs) utilize intricate battery packs that require the oversight of a battery management system (BMS) to ensure safe, reliable, and efficient operation. The state estimation of the battery pack is an important responsibility carried out by the BMS. Accurately estimating the State-of-Charge (SOC) poses a considerable engineering challenge since it cannot be directly measured at the battery terminals. This study introduces a novel data-driven methodology for accurately estimating the SOC in Lithium-ion batteries, with a particular focus on its relevance in EV contexts. The framework is built upon the Stochastic Variational Gaussian Process (SVGP)—an improved version of the conventional Gaussian Process (GP). Unlike GP, It can scale up to very large datasets. Furthermore, SVGP uses variational inference to estimate the posterior instead of calculating, making it computationally efficient. The model training process involves using laboratory test data from an 18650 Lithium-ion Nickel Manganese Cobalt (NMC) cell that has gone through eight dynamic drive cycles. The findings showcase a remarkable level of precision in estimation, as indicated by an average R<sup>2</sup> value of 0.99 and a Mean Square Error (MSE) as low as 0.02.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A service-recommendation method for the Internet of Things leveraging implicit social relationships 利用隐式社会关系的物联网服务推荐方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-30 DOI: 10.1016/j.compeleceng.2024.109734

Integrating social-relationship information is widely considered an effective means to addressing the sparsity issue in Internet-of-Things (IoT) service recommendations. However, owing to platform variations and privacy concerns, acquiring explicit social-relationship information has become challenging. Therefore, researchers are gradually focusing on leveraging implicit social-relationship information to enhance recommendation effectiveness. Nevertheless, when using implicit social relationships, both user/service-implicit social-relationship and user-service interaction information rely on the same rating matrix, leading to nonindependence and coupling, which influence the recommendation model. To address this challenge, the present paper introduces a unique approach for IoT service recommendations, leveraging implicit social-relationship information (short for ISoc-IoTRec). First, we construct a user-service interaction graph, user-implicit social-relationship graph, and service-implicit social-relationship graph, learning their node embeddings through graph neural networks (GNNs). Subsequently, we introduce a cross information control module to achieve feature separation, ensuring that the user and service embeddings learned from different graphs remain independent in representation, thereby alleviating the nonindependence and coupling issues arising from the same data source. Following feature separation, the user and service embeddings are aggregated separately. Through an attention mechanism module, the model can selectively emphasize or attenuate the impact of each feature while considering the overall information, further addressing nonindependence and coupling issues. Extensive experiments conducted on three real-world datasets underscore the remarkable performance of ISoc-IoTRec, significantly outperforming existing recommendation algorithms.

整合社交关系信息被广泛认为是解决物联网（IoT）服务推荐中稀缺性问题的有效手段。然而，由于平台差异和隐私问题，获取显式社交关系信息变得具有挑战性。因此，研究人员逐渐将重点放在利用隐式社交关系信息来提高推荐效果上。然而，在使用隐式社交关系时，用户/服务隐式社交关系信息和用户-服务交互信息都依赖于同一个评级矩阵，这就导致了非独立性和耦合性，从而影响了推荐模型。为解决这一难题，本文提出了一种利用隐式社会关系信息（ISoc-IoTRec 的缩写）进行物联网服务推荐的独特方法。首先，我们构建了用户服务交互图、用户隐式社会关系图和服务隐式社会关系图，并通过图神经网络（GNN）学习它们的节点嵌入。随后，我们引入交叉信息控制模块来实现特征分离，确保从不同图中学习到的用户和服务嵌入在表示上保持独立，从而缓解同一数据源带来的非独立性和耦合性问题。特征分离后，用户嵌入和服务嵌入被分别聚合。通过注意力机制模块，该模型可以在考虑整体信息的同时，选择性地强调或削弱每个特征的影响，从而进一步解决非独立性和耦合性问题。在三个真实世界数据集上进行的广泛实验证明了 ISoc-IoTRec 的卓越性能，其表现明显优于现有的推荐算法。

{"title":"A service-recommendation method for the Internet of Things leveraging implicit social relationships","authors":"","doi":"10.1016/j.compeleceng.2024.109734","DOIUrl":"10.1016/j.compeleceng.2024.109734","url":null,"abstract":"<div><div>Integrating social-relationship information is widely considered an effective means to addressing the sparsity issue in Internet-of-Things (IoT) service recommendations. However, owing to platform variations and privacy concerns, acquiring explicit social-relationship information has become challenging. Therefore, researchers are gradually focusing on leveraging implicit social-relationship information to enhance recommendation effectiveness. Nevertheless, when using implicit social relationships, both user/service-implicit social-relationship and user-service interaction information rely on the same rating matrix, leading to nonindependence and coupling, which influence the recommendation model. To address this challenge, the present paper introduces a unique approach for IoT service recommendations, leveraging implicit social-relationship information (short for ISoc-IoTRec). First, we construct a user-service interaction graph, user-implicit social-relationship graph, and service-implicit social-relationship graph, learning their node embeddings through graph neural networks (GNNs). Subsequently, we introduce a cross information control module to achieve feature separation, ensuring that the user and service embeddings learned from different graphs remain independent in representation, thereby alleviating the nonindependence and coupling issues arising from the same data source. Following feature separation, the user and service embeddings are aggregated separately. Through an attention mechanism module, the model can selectively emphasize or attenuate the impact of each feature while considering the overall information, further addressing nonindependence and coupling issues. Extensive experiments conducted on three real-world datasets underscore the remarkable performance of ISoc-IoTRec, significantly outperforming existing recommendation algorithms.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A cross-chain-based approach for secure data sharing and interoperability in electronic health records using blockchain technology 利用区块链技术在电子健康记录中实现安全数据共享和互操作性的跨链方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-29 DOI: 10.1016/j.compeleceng.2024.109676

In most healthcare facilities, Electronic Health Records (EHRs) have changed paper-based medical records in the healthcare industry. Nevertheless, there are issues with credibility, management, and secure data storage with the existing EHR frameworks. In order to fill this, this work establishes a cross-chain approach for EHR record sharing that is based on the interoperability of EHRs. Different entities, like patients, healthcare providers, Government Agencies (GA), blockchain, and ledger are included in the proposed system. Several processes including initialization, registration process, agreement and verification process, bank fund transfer and certificate generation, health record exchange among two hospitals, and secret key generation, are used to implement the newly developed authentication approach. In addition, the key is obtained from the interior layers of Deep Residual SpinalNet (Deep RSNet), which is utilized to encrypt the EHR records. The Deep RSNet is the integration of Deep Residual Network (DRN) and SpinalNet. The investigation of the developed technique exposes the supremacy of the Deep RSNet model by achieving minimal values of response time, memory usage, and normalized variance of 53.677 sec, 2.682 MB, and 1.346 respectively.

在大多数医疗机构中，电子病历（EHR）已经改变了医疗行业的纸质医疗记录。然而，现有的电子病历框架在可信度、管理和安全数据存储方面存在问题。为了解决这些问题，这项工作建立了一种基于电子病历互操作性的跨链电子病历记录共享方法。拟议的系统包括不同的实体，如患者、医疗服务提供者、政府机构（GA）、区块链和分类账。初始化、注册过程、协议和验证过程、银行资金转账和证书生成、两家医院之间的健康记录交换以及密钥生成等几个过程用于实施新开发的身份验证方法。此外，密钥是从深度残余脊柱网（Deep RSNet）的内部层获得的，用于对电子病历记录进行加密。Deep RSNet 是 Deep Residual Network（DRN）和 SpinalNet 的集成。对所开发技术的调查显示，深度 RSNet 模型的响应时间、内存使用量和归一化方差的最小值分别为 53.677 秒、2.682 MB 和 1.346，从而显示了其优越性。

{"title":"A cross-chain-based approach for secure data sharing and interoperability in electronic health records using blockchain technology","authors":"","doi":"10.1016/j.compeleceng.2024.109676","DOIUrl":"10.1016/j.compeleceng.2024.109676","url":null,"abstract":"<div><div>In most healthcare facilities, Electronic Health Records (EHRs) have changed paper-based medical records in the healthcare industry. Nevertheless, there are issues with credibility, management, and secure data storage with the existing EHR frameworks. In order to fill this, this work establishes a cross-chain approach for EHR record sharing that is based on the interoperability of EHRs. Different entities, like patients, healthcare providers, Government Agencies (GA), blockchain, and ledger are included in the proposed system. Several processes including initialization, registration process, agreement and verification process, bank fund transfer and certificate generation, health record exchange among two hospitals, and secret key generation, are used to implement the newly developed authentication approach. In addition, the key is obtained from the interior layers of Deep Residual SpinalNet (Deep RSNet), which is utilized to encrypt the EHR records. The Deep RSNet is the integration of Deep Residual Network (DRN) and SpinalNet. The investigation of the developed technique exposes the supremacy of the Deep RSNet model by achieving minimal values of response time, memory usage, and normalized variance of 53.677 sec, 2.682 MB, and 1.346 respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accelerating QKD post-processing by secure offloading of information reconciliation 通过安全卸载信息调节加速 QKD 后处理

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-27 DOI: 10.1016/j.compeleceng.2024.109721

While quantum key distribution (QKD) offers unparalleled security in communication, its real-world application is hindered by inherent physical constraints. The challenge lies predominantly in the cumbersome, energy-intensive nature of current QKD systems, which stems largely from the time-intensive post-processing stage. This paper investigates the feasibility of offloading the computationally intensive post-processing tasks, specifically focusing on information reconciliation (IR), to potentially untrusted servers.

We present a novel scheme that leverages syndrome decoding techniques to efficiently transfer the IR step of QKD protocols to a single external server. Notably, this offloading is accomplished while maintaining the highest level of security, known as unconditional security. The proposed technique is bolstered by a comprehensive theoretical analysis and validated through experimental trials. These findings demonstrate the effectiveness of our approach in bridging the gap between the theoretical promise of QKD and its real-world deployment.

虽然量子密钥分发（QKD）为通信提供了无与伦比的安全性，但其在现实世界中的应用却受到固有物理限制的阻碍。挑战主要在于当前 QKD 系统的繁琐性和能源密集性，这主要源于时间密集型的后处理阶段。本文研究了将计算密集型后处理任务（特别是信息调节（IR））卸载到潜在的不可信任服务器上的可行性。我们提出了一种新方案，利用综合症解码技术将 QKD 协议的 IR 步骤高效地转移到单个外部服务器上。值得注意的是，这种卸载是在保持最高级别安全性（即无条件安全性）的前提下完成的。所提出的技术得到了全面理论分析的支持，并通过实验进行了验证。这些发现证明了我们的方法在缩小 QKD 理论前景与实际部署之间差距方面的有效性。

引用次数: 0

Computer vision based distributed denial of service attack detection for resource-limited devices 基于计算机视觉的资源有限设备分布式拒绝服务攻击检测

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-27 DOI: 10.1016/j.compeleceng.2024.109716

The growing adoption of Internet of Things (IoT) has rendered them a desirable target for cyber-attacks. One of the biggest threats to these systems is the distributed denial of service (DDoS) attack, which is a botnet-based attack. The reason for the increasing usage of machine learning and deep learning-based intrusion detection systems in IoT network security is their ability to recognize DDoS attack. Recent studies, however, shows how susceptible IoT networks are to these kinds of attacks and detection accuracy can be greatly lowered. While a majority of studies has concentrated on DDoS attack detection for deep learning, little attention has been paid to computer vision, especially image-based artificial intelligence technologies like convolutional neural network (CNN). In this study, we use an image-based dataset to evaluate the effectiveness of CNN, an effective computer vision approach, for DDoS attack detection in IoT contexts. Owing to the small size of the selected dataset and in order to improve the CNN model’s detection efficiency, we implement various data augmentation techniques prior to the model’s training, including scaling, rotation, and vertical and horizontal flipping. Next, we introduce an efficient CNN-based method for detection of DDoS attacks in IoT settings. Ultimately, we came to the conclusion that the statistical significance testing showed that there is a significance difference among the five models employed during the study, and the VGG19 which has higher accuracy (99.74%) and less computing cost (6020.80 s), which enables IoT devices to perform DDoS attack detection with cost-effectiveness.

物联网 (IoT) 的应用日益广泛，使其成为网络攻击的理想目标。这些系统面临的最大威胁之一是分布式拒绝服务（DDoS）攻击，这是一种基于僵尸网络的攻击。在物联网网络安全中，基于机器学习和深度学习的入侵检测系统的使用率越来越高，原因就在于它们能够识别 DDoS 攻击。然而，最近的研究表明，物联网网络很容易受到这类攻击的影响，而且检测精度会大大降低。虽然大多数研究都集中在深度学习的 DDoS 攻击检测上，但很少有人关注计算机视觉，尤其是基于图像的人工智能技术，如卷积神经网络（CNN）。在本研究中，我们使用基于图像的数据集来评估 CNN（一种有效的计算机视觉方法）在物联网环境下进行 DDoS 攻击检测的有效性。由于所选数据集规模较小，为了提高 CNN 模型的检测效率，我们在模型训练之前采用了各种数据增强技术，包括缩放、旋转、垂直和水平翻转。接下来，我们将介绍一种基于 CNN 的高效方法，用于检测物联网环境中的 DDoS 攻击。最终，我们得出的结论是，统计显著性测试表明，研究中采用的五个模型之间存在显著差异，而 VGG19 的准确率更高（99.74%），计算成本更低（6020.80 秒），这使得物联网设备能够以经济高效的方式进行 DDoS 攻击检测。

{"title":"Computer vision based distributed denial of service attack detection for resource-limited devices","authors":"","doi":"10.1016/j.compeleceng.2024.109716","DOIUrl":"10.1016/j.compeleceng.2024.109716","url":null,"abstract":"<div><div>The growing adoption of Internet of Things (IoT) has rendered them a desirable target for cyber-attacks. One of the biggest threats to these systems is the distributed denial of service (DDoS) attack, which is a botnet-based attack. The reason for the increasing usage of machine learning and deep learning-based intrusion detection systems in IoT network security is their ability to recognize DDoS attack. Recent studies, however, shows how susceptible IoT networks are to these kinds of attacks and detection accuracy can be greatly lowered. While a majority of studies has concentrated on DDoS attack detection for deep learning, little attention has been paid to computer vision, especially image-based artificial intelligence technologies like convolutional neural network (CNN). In this study, we use an image-based dataset to evaluate the effectiveness of CNN, an effective computer vision approach, for DDoS attack detection in IoT contexts. Owing to the small size of the selected dataset and in order to improve the CNN model’s detection efficiency, we implement various data augmentation techniques prior to the model’s training, including scaling, rotation, and vertical and horizontal flipping. Next, we introduce an efficient CNN-based method for detection of DDoS attacks in IoT settings. Ultimately, we came to the conclusion that the statistical significance testing showed that there is a significance difference among the five models employed during the study, and the VGG19 which has higher accuracy (99.74%) and less computing cost (6020.80 s), which enables IoT devices to perform DDoS attack detection with cost-effectiveness.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142326561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ResMT: A hybrid CNN-transformer framework for glioma grading with 3D MRI ResMT：利用三维核磁共振成像进行胶质瘤分级的混合 CNN 变换器框架

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-27 DOI: 10.1016/j.compeleceng.2024.109745

Accurate grading of gliomas is crucial for treatment strategies and prognosis. While convolutional neural networks (CNNs) have proven effective in classifying medical images, they struggle with capturing long-range dependencies among pixels. Transformer-based networks can address this issue, but CNN-based methods often perform better when trained on small datasets. Additionally, tumor segmentation is essential for classification models, but training an additional segmentation model significantly increases workload. To address these challenges, we propose ResMT, which combines CNN and transformer architectures for glioma grading, extracting both local and global features efficiently. Specifically, we designed a spatial residual module (SRM) where a 3D CNN captures glioma's volumetric complexity, and Swin UNETR, a pre-trained segmentation model, enhances the network without extra training. Our model also includes a multi-plane channel and spatial attention module (MCSA) to refine the analysis by focusing on critical features across multiple planes (axial, coronal, and sagittal). Transformer blocks establish long-range relationships among planes and slices. We evaluated ResMT on the BraTs19 dataset, comparing it with baselines and state-of-the-art models. Results demonstrate that ResMT achieves the highest prediction performance with an AUC of 0.9953, highlighting hybrid CNN-transformer models' potential for 3D MRI classification.

胶质瘤的准确分级对治疗策略和预后至关重要。虽然卷积神经网络（CNN）已被证明能有效地对医学影像进行分级，但它们在捕捉像素间的长距离依赖关系方面仍有困难。基于变压器的网络可以解决这一问题，但基于 CNN 的方法在小型数据集上训练时通常表现更好。此外，肿瘤分割对分类模型至关重要，但训练额外的分割模型会大大增加工作量。为了应对这些挑战，我们提出了 ResMT，它结合了用于胶质瘤分级的 CNN 和变换器架构，能有效提取局部和全局特征。具体来说，我们设计了一个空间残差模块（SRM），其中三维 CNN 可捕捉胶质瘤的体积复杂性，而 Swin UNETR 则是一个预先训练好的分割模型，无需额外训练即可增强网络。我们的模型还包括一个多平面通道和空间关注模块（MCSA），通过关注多个平面（轴向、冠状和矢状面）的关键特征来完善分析。变压器块建立了平面和切片之间的远距离关系。我们在 BraTs19 数据集上对 ResMT 进行了评估，并将其与基线和最先进的模型进行了比较。结果表明，ResMT 的预测性能最高，AUC 为 0.9953，凸显了混合 CNN 变换器模型在三维 MRI 分类中的潜力。

{"title":"ResMT: A hybrid CNN-transformer framework for glioma grading with 3D MRI","authors":"","doi":"10.1016/j.compeleceng.2024.109745","DOIUrl":"10.1016/j.compeleceng.2024.109745","url":null,"abstract":"<div><div>Accurate grading of gliomas is crucial for treatment strategies and prognosis. While convolutional neural networks (CNNs) have proven effective in classifying medical images, they struggle with capturing long-range dependencies among pixels. Transformer-based networks can address this issue, but CNN-based methods often perform better when trained on small datasets. Additionally, tumor segmentation is essential for classification models, but training an additional segmentation model significantly increases workload. To address these challenges, we propose ResMT, which combines CNN and transformer architectures for glioma grading, extracting both local and global features efficiently. Specifically, we designed a spatial residual module (SRM) where a 3D CNN captures glioma's volumetric complexity, and Swin UNETR, a pre-trained segmentation model, enhances the network without extra training. Our model also includes a multi-plane channel and spatial attention module (MCSA) to refine the analysis by focusing on critical features across multiple planes (axial, coronal, and sagittal). Transformer blocks establish long-range relationships among planes and slices. We evaluated ResMT on the BraTs19 dataset, comparing it with baselines and state-of-the-art models. Results demonstrate that ResMT achieves the highest prediction performance with an AUC of 0.9953, highlighting hybrid CNN-transformer models' potential for 3D MRI classification.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Radio frequency fingerprint recognition method based on prior information 基于先验信息的射频指纹识别方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-27 DOI: 10.1016/j.compeleceng.2024.109684

The open wireless communication environment is vulnerable to various malicious attacks. Wireless communication hardware devices have unique physical layer characteristics. As an inherent unique feature of wireless signals, radio frequency fingerprints provide a guarantee for the identification and verification of wireless signals. Most of the existing radio frequency fingerprint identification methods only extract fingerprints from one of the steady-state signals or transient signals. Neglecting the connection between the two wireless communication signals results in low identification accuracy of the radio frequency fingerprint identification method under the condition of a low signal-to-noise ratio. Aiming at the respective characteristics of these two signals, a radio frequency fingerprinting method combining transient and steady-state signals based on prior information of wireless signals is proposed. This method combines the characteristic stability of steady-state signals and the integrity characteristics of transient signals, which can effectively identify and classify wireless signals and achieve excellent recognition under low signal-to-noise ratio conditions. The effectiveness of the proposed method is verified by experimental comparison with the traditional radio frequency fingerprinting method on the LFM signal dataset.

开放的无线通信环境容易受到各种恶意攻击。无线通信硬件设备具有独特的物理层特征。射频指纹作为无线信号固有的独特特征，为无线信号的识别和验证提供了保障。现有的射频指纹识别方法大多只能从稳态信号或瞬态信号中提取指纹。由于忽略了两个无线通信信号之间的联系，在低信噪比条件下，射频指纹识别方法的识别精度较低。针对这两种信号各自的特点，提出了一种基于无线信号先验信息的瞬态和稳态信号相结合的射频指纹识别方法。该方法结合了稳态信号的稳定性特征和瞬态信号的完整性特征，能有效识别和分类无线信号，并在低信噪比条件下实现出色的识别效果。通过在 LFM 信号数据集上与传统射频指纹识别方法的实验对比，验证了所提方法的有效性。

{"title":"Radio frequency fingerprint recognition method based on prior information","authors":"","doi":"10.1016/j.compeleceng.2024.109684","DOIUrl":"10.1016/j.compeleceng.2024.109684","url":null,"abstract":"<div><div>The open wireless communication environment is vulnerable to various malicious attacks. Wireless communication hardware devices have unique physical layer characteristics. As an inherent unique feature of wireless signals, radio frequency fingerprints provide a guarantee for the identification and verification of wireless signals. Most of the existing radio frequency fingerprint identification methods only extract fingerprints from one of the steady-state signals or transient signals. Neglecting the connection between the two wireless communication signals results in low identification accuracy of the radio frequency fingerprint identification method under the condition of a low signal-to-noise ratio. Aiming at the respective characteristics of these two signals, a radio frequency fingerprinting method combining transient and steady-state signals based on prior information of wireless signals is proposed. This method combines the characteristic stability of steady-state signals and the integrity characteristics of transient signals, which can effectively identify and classify wireless signals and achieve excellent recognition under low signal-to-noise ratio conditions. The effectiveness of the proposed method is verified by experimental comparison with the traditional radio frequency fingerprinting method on the LFM signal dataset.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142326562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FgDAP: A blockchain-based privacy-enhanced decentralized anonymous payment system with fine-grained traceability FgDAP：基于区块链的隐私增强型去中心化匿名支付系统，具有细粒度可追溯性

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-26 DOI: 10.1016/j.compeleceng.2024.109723

Decentralized Anonymous Payment (DAP) frameworks provide users with the capability to securely and privately transfer cryptocurrencies. These frameworks enable direct peer-to-peer transactions, eliminating the involvement of central authorities and ensuring user anonymity. Several advanced anonymous digital currencies have been developed with the primary goal of enhancing user privacy, including Monero and Zerocash. Despite the robust privacy, it results in unexpected criminal activities, like money laundering and online extortion. In this article, we put forward a blockchain-based privacy-enhanced decentralized anonymous payment system with fine-grained traceability (FgDAP) to alleviate the aforementioned threats. It primarily utilizes several essential components, including multimodal private signatures (CRYPTO’22), along with our proposed dual-mode non-interactive zero-knowledge proofs. Specifically, a signing function, along with a set of disclosing functions, is introduced to establish an open algorithm that ensures fine-grained traceability. Finally, we provide an in-depth security analysis and a comprehensive performance evaluation for our proposal. The findings indicate the feasibility of our solution.

去中心化匿名支付（DAP）框架为用户提供了安全、私密地转移加密货币的能力。这些框架实现了直接的点对点交易，消除了中央机构的参与，确保了用户的匿名性。一些先进的匿名数字货币，包括 Monero 和 Zerocash，都是以提高用户隐私为主要目标而开发的。尽管具有强大的隐私保护功能，但却导致了意想不到的犯罪活动，如洗钱和在线勒索。在本文中，我们提出了一种基于区块链的隐私增强型去中心化匿名支付系统（FgDAP），以减轻上述威胁。它主要利用了几个基本组件，包括多模式私人签名（CRYPTO'22）以及我们提出的双模式非交互式零知识证明。具体来说，我们引入了一个签名函数和一组披露函数，以建立一种确保细粒度可追溯性的开放算法。最后，我们对我们的建议进行了深入的安全分析和全面的性能评估。研究结果表明了我们解决方案的可行性。

{"title":"FgDAP: A blockchain-based privacy-enhanced decentralized anonymous payment system with fine-grained traceability","authors":"","doi":"10.1016/j.compeleceng.2024.109723","DOIUrl":"10.1016/j.compeleceng.2024.109723","url":null,"abstract":"<div><div>Decentralized Anonymous Payment (DAP) frameworks provide users with the capability to securely and privately transfer cryptocurrencies. These frameworks enable direct peer-to-peer transactions, eliminating the involvement of central authorities and ensuring user anonymity. Several advanced anonymous digital currencies have been developed with the primary goal of enhancing user privacy, including Monero and Zerocash. Despite the robust privacy, it results in unexpected criminal activities, like money laundering and online extortion. In this article, we put forward a blockchain-based privacy-enhanced decentralized anonymous payment system with fine-grained traceability (FgDAP) to alleviate the aforementioned threats. It primarily utilizes several essential components, including multimodal private signatures (CRYPTO’22), along with our proposed dual-mode non-interactive zero-knowledge proofs. Specifically, a signing function, along with a set of disclosing functions, is introduced to establish an open algorithm that ensures fine-grained traceability. Finally, we provide an in-depth security analysis and a comprehensive performance evaluation for our proposal. The findings indicate the feasibility of our solution.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DEAC-IoT: Design of lightweight authenticated key agreement protocol for Intra and Inter-IoT device communication using ECC with FPGA implementation DEAC-IoT：利用 ECC 和 FPGA 实现物联网设备内和设备间通信的轻量级认证密钥协议设计

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-26 DOI: 10.1016/j.compeleceng.2024.109696

The growing reliance on wireless communication in Internet-of-Things (IoT) devices highlights the critical need for secure and efficient communication protocols, especially in environments vulnerable to cyber threats. Existing IoT protocols often lack sufficient security, creating a need for robust authentication and key exchange mechanisms that can resist attacks while maintaining low computational overhead. In this paper, we propose a fog-enabled network architecture integrated with IoT devices (Intra and Inter IoT device) and develop the DEAC-IoT scheme using Elliptic Curve Cryptography (ECC) for secure authentication and key agreement. Our protocol is designed to protect device-to-device communication from security threats in resource-constrained IoT environments. We validate DEAC-IoT’s security through both informal analysis and formal verification using the Real-Or-Random (RoR) model, demonstrating its resistance to major attacks. Simulation via the Scyther tool confirms that private parameters remain secure throughout the protocol’s execution. For practical feasibility, we implement DEAC-IoT on a Field Programmable Gate Array (FPGA) and conduct performance evaluations. The results show that our protocol surpasses existing protocols in both computational and communication efficiency, making it highly suitable for real-world IoT applications.

物联网（IoT）设备对无线通信的依赖与日俱增，这凸显了对安全高效通信协议的迫切需求，尤其是在易受网络威胁的环境中。现有的物联网协议往往缺乏足够的安全性，因此需要既能抵御攻击又能保持较低计算开销的强大认证和密钥交换机制。在本文中，我们提出了一种与物联网设备（物联网设备内部和物联网设备之间）集成的雾化网络架构，并开发了使用椭圆曲线加密法（ECC）进行安全认证和密钥协议的 DEAC-IoT 方案。我们的协议旨在保护设备与设备之间的通信在资源有限的物联网环境中免受安全威胁。我们通过使用真实或随机（RoR）模型进行非正式分析和正式验证，验证了 DEAC-IoT 的安全性，证明它能抵御重大攻击。通过 Scyther 工具进行的仿真证实，私人参数在整个协议执行过程中都是安全的。为了确保实际可行性，我们在现场可编程门阵列（FPGA）上实现了 DEAC-IoT 并进行了性能评估。结果表明，我们的协议在计算和通信效率方面都超越了现有协议，因此非常适合实际物联网应用。

{"title":"DEAC-IoT: Design of lightweight authenticated key agreement protocol for Intra and Inter-IoT device communication using ECC with FPGA implementation","authors":"","doi":"10.1016/j.compeleceng.2024.109696","DOIUrl":"10.1016/j.compeleceng.2024.109696","url":null,"abstract":"<div><div>The growing reliance on wireless communication in Internet-of-Things (IoT) devices highlights the critical need for secure and efficient communication protocols, especially in environments vulnerable to cyber threats. Existing IoT protocols often lack sufficient security, creating a need for robust authentication and key exchange mechanisms that can resist attacks while maintaining low computational overhead. In this paper, we propose a fog-enabled network architecture integrated with IoT devices (Intra and Inter IoT device) and develop the <em>DEAC-IoT</em> scheme using Elliptic Curve Cryptography (ECC) for secure authentication and key agreement. Our protocol is designed to protect device-to-device communication from security threats in resource-constrained IoT environments. We validate <em>DEAC-IoT</em>’s security through both informal analysis and formal verification using the Real-Or-Random (RoR) model, demonstrating its resistance to major attacks. Simulation via the Scyther tool confirms that private parameters remain secure throughout the protocol’s execution. For practical feasibility, we implement <em>DEAC-IoT</em> on a Field Programmable Gate Array (FPGA) and conduct performance evaluations. The results show that our protocol surpasses existing protocols in both computational and communication efficiency, making it highly suitable for real-world IoT applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SMUP: A technique to improve MC/DC using specified patterns SMUP：利用指定模式改进 MC/DC 的技术

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-09-26 DOI: 10.1016/j.compeleceng.2024.109706

According to recent study, a number of poorly explored aspects, like program structure and not producing high-quality random inputs for testing, can have a significant impact on the overall efficacy of the testing process. Existing concolic testers found to be more cost-effective than random testers for code coverage. Modified condition/decision coverage (MC/DC) has gained its popularity as the strongest criterion for safety-critical systems proposed by RTCA/DO-178B(C), after multiple condition coverage (MCC). This paper proposes a new source code transformation technique that produces additional test cases to achieve higher MC/DC. The technical contribution of this work is threefold. First, it uses a pattern-based code transformation technique that produces effective MC/DC test cases. This pattern-based approach guides the concolic tester to generate test cases as per the MC/DC requirements. Second, the generated patterns are further simplified to minimize the execution time. Third, we have developed a tool named “Java MC/DC Analyzer” to measure MC/DC score for the input programs. The proposed approach is experimented on thirty Java programs and achieved an average increase of 32.86% MC/DC score which validates our work. Also, we have compared our approach with other code transformation techniques and reported a significant improvement.

根据最近的研究，程序结构和没有为测试提供高质量的随机输入等一些探索不足的方面，会对测试过程的整体效率产生重大影响。在代码覆盖率方面，现有的协程测试仪比随机测试仪更具成本效益。修正条件/判定覆盖率（MC/DC）是继多重条件覆盖率（MCC）之后，RTCA/DO-178B(C)提出的安全关键型系统的最强标准。本文提出了一种新的源代码转换技术，可生成额外的测试用例，以实现更高的 MC/DC。这项工作的技术贡献体现在三个方面。首先，它采用了一种基于模式的代码转换技术，可生成有效的 MC/DC 测试用例。这种基于模式的方法可指导协同测试人员根据 MC/DC 要求生成测试用例。其次，对生成的模式进行进一步简化，以尽量减少执行时间。第三，我们开发了一个名为 "Java MC/DC Analyzer "的工具，用于测量输入程序的 MC/DC 分数。我们在 30 个 Java 程序上对所提出的方法进行了实验，结果发现 MC/DC 分数平均提高了 32.86%，这验证了我们的工作。此外，我们还将我们的方法与其他代码转换技术进行了比较，并报告了显著的改进。

{"title":"SMUP: A technique to improve MC/DC using specified patterns","authors":"","doi":"10.1016/j.compeleceng.2024.109706","DOIUrl":"10.1016/j.compeleceng.2024.109706","url":null,"abstract":"<div><div>According to recent study, a number of poorly explored aspects, like program structure and not producing high-quality random inputs for testing, can have a significant impact on the overall efficacy of the testing process. Existing concolic testers found to be more cost-effective than random testers for code coverage. Modified condition/decision coverage (MC/DC) has gained its popularity as the strongest criterion for safety-critical systems proposed by RTCA/DO-178B(C), after multiple condition coverage (MCC). This paper proposes a new source code transformation technique that produces additional test cases to achieve higher MC/DC. The technical contribution of this work is threefold. First, it uses a pattern-based code transformation technique that produces effective MC/DC test cases. This pattern-based approach guides the concolic tester to generate test cases as per the MC/DC requirements. Second, the generated patterns are further simplified to minimize the execution time. Third, we have developed a tool named “Java MC/DC Analyzer” to measure MC/DC score for the input programs. The proposed approach is experimented on thirty Java programs and achieved an average increase of 32.86% MC/DC score which validates our work. Also, we have compared our approach with other code transformation techniques and reported a significant improvement.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0