Computers & Electrical Engineering最新文献_第7页

AMOUE: Adaptive modified optimized unary encoding method for local differential privacy data preservation AMOUE：用于局部差分隐私数据保护的自适应修正优化单值编码方法

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

Computers & Electrical Engineering

Pub Date : 2024-10-25 DOI: 10.1016/j.compeleceng.2024.109791

Tianchong Gao , Hailong Fu , Shunwei Wang , Niu Zhang

Deep learning has gained popularity recently, and privacy concerns have increased simultaneously. Adversaries gain unauthorized access to the private training data and model parameters through model inversion attacks and membership inference attacks. To address these problems, researchers proposed several defense mechanisms based on a decisive privacy criterion - Local Differential Privacy (LDP). Although the LDP-based deep learning model preserves data privacy well, its strict privacy criterion sometimes affects accuracy. It is a non-trivial task to intelligently add noise that satisfies LDP and minimizes its impact on learning results. This paper proposes a novel LDP-based deep learning method named AMOUE with a novel encoding technique. Because input data has different proportions of 1s and 0s, adding fixed noise to 1s and 0s may result in unnecessary data utility loss. The proposed encoding method dynamically adjusts the noise added on 1s and 0s according to the input data distribution. Theoretical analysis demonstrates that AMOUE has a lower error expectation and variance. Experiments on real-world datasets show that AMOUE outperforms other LDP-based mechanisms in deep learning classification accuracy.

最近，深度学习越来越受欢迎，人们对隐私的关注也同时增加。对手通过模型反转攻击和成员推理攻击，在未经授权的情况下获取私人训练数据和模型参数。为了解决这些问题，研究人员提出了几种基于决定性隐私标准--局部差分隐私（LDP）--的防御机制。虽然基于 LDP 的深度学习模型能很好地保护数据隐私，但其严格的隐私标准有时会影响准确性。如何智能地添加满足 LDP 的噪声，并将其对学习结果的影响降至最低，是一项非同小可的任务。本文提出了一种基于 LDP 的新型深度学习方法 AMOUE，并采用了一种新型编码技术。由于输入数据中 1 和 0 的比例不同，给 1 和 0 添加固定噪声可能会造成不必要的数据效用损失。所提出的编码方法可根据输入数据的分布动态调整添加到 1 和 0 上的噪声。理论分析表明，AMOUE 具有更低的误差期望值和方差。在真实世界数据集上的实验表明，AMOUE 在深度学习分类准确性方面优于其他基于 LDP 的机制。

{"title":"AMOUE: Adaptive modified optimized unary encoding method for local differential privacy data preservation","authors":"Tianchong Gao , Hailong Fu , Shunwei Wang , Niu Zhang","doi":"10.1016/j.compeleceng.2024.109791","DOIUrl":"10.1016/j.compeleceng.2024.109791","url":null,"abstract":"<div><div>Deep learning has gained popularity recently, and privacy concerns have increased simultaneously. Adversaries gain unauthorized access to the private training data and model parameters through model inversion attacks and membership inference attacks. To address these problems, researchers proposed several defense mechanisms based on a decisive privacy criterion - Local Differential Privacy (LDP). Although the LDP-based deep learning model preserves data privacy well, its strict privacy criterion sometimes affects accuracy. It is a non-trivial task to intelligently add noise that satisfies LDP and minimizes its impact on learning results. This paper proposes a novel LDP-based deep learning method named AMOUE with a novel encoding technique. Because input data has different proportions of 1s and 0s, adding fixed noise to 1s and 0s may result in unnecessary data utility loss. The proposed encoding method dynamically adjusts the noise added on 1s and 0s according to the input data distribution. Theoretical analysis demonstrates that AMOUE has a lower error expectation and variance. Experiments on real-world datasets show that AMOUE outperforms other LDP-based mechanisms in deep learning classification accuracy.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109791"},"PeriodicalIF":4.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534364","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

Robust load frequency control in interval power systems via reduced-order generalized active disturbance rejection control 通过降阶广义有源干扰抑制控制实现区间电力系统的鲁棒负载频率控制

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

Computers & Electrical Engineering

Pub Date : 2024-10-23 DOI: 10.1016/j.compeleceng.2024.109788

Safiullah, Yogesh V. Hote

Abrupt load changes, structural discrepancies, and parametric uncertainties cause degraded performance of the high-order power systems. This situation creates a problematic endeavor while analyzing the performance of such high-order systems. Hence, a simple and efficient lower-order control methodology can be deployed to sort out the issues related to load frequency control (LFC) in such systems. This study resolves the LFC problem in parametric bounded power systems by developing a worst-case reduced-order generalized active disturbance rejection control (WRGADRC) method. The core concept of the proposed technique entails that a controller will perform well in nominal scenarios if it performs satisfactorily in worst-case conditions. Therefore, an interval system’s worst-case reduced-order model is first obtained from its different uncertain models; the reduced order controller is then designed using the GADRC technique. The proposed scheme is rigorously validated on various parametric bounded minimum and non-minimum phase single-area and multi-area power systems, instilling confidence in its ability to achieve minimum frequency deviation in multiple scenarios. The supremacy of the proposed scheme is highlighted over some well-established control techniques in the literature related to the LFC problem.

负载突变、结构差异和参数不确定性会导致高阶电力系统性能下降。这种情况给分析此类高阶系统的性能带来了难题。因此，可以采用一种简单高效的低阶控制方法来解决此类系统中与负载频率控制（LFC）相关的问题。本研究通过开发一种最坏情况下的降阶广义有源干扰抑制控制（WRGADRC）方法，解决了参数有界电力系统中的 LFC 问题。所提技术的核心理念是，如果控制器在最坏情况下的表现令人满意，那么它在标称情况下的表现也会很好。因此，首先要从不同的不确定模型中获得区间系统的最坏情况降阶模型，然后利用 GADRC 技术设计降阶控制器。所提出的方案在各种参数有界的最小相位和非最小相位单区和多区电力系统上得到了严格验证，使人们对其在多种情况下实现最小频率偏差的能力充满信心。与 LFC 问题相关文献中一些成熟的控制技术相比，所提出方案的优越性更加突出。

{"title":"Robust load frequency control in interval power systems via reduced-order generalized active disturbance rejection control","authors":"Safiullah, Yogesh V. Hote","doi":"10.1016/j.compeleceng.2024.109788","DOIUrl":"10.1016/j.compeleceng.2024.109788","url":null,"abstract":"<div><div>Abrupt load changes, structural discrepancies, and parametric uncertainties cause degraded performance of the high-order power systems. This situation creates a problematic endeavor while analyzing the performance of such high-order systems. Hence, a simple and efficient lower-order control methodology can be deployed to sort out the issues related to load frequency control (LFC) in such systems. This study resolves the LFC problem in parametric bounded power systems by developing a worst-case reduced-order generalized active disturbance rejection control (WRGADRC) method. The core concept of the proposed technique entails that a controller will perform well in nominal scenarios if it performs satisfactorily in worst-case conditions. Therefore, an interval system’s worst-case reduced-order model is first obtained from its different uncertain models; the reduced order controller is then designed using the GADRC technique. The proposed scheme is rigorously validated on various parametric bounded minimum and non-minimum phase single-area and multi-area power systems, instilling confidence in its ability to achieve minimum frequency deviation in multiple scenarios. The supremacy of the proposed scheme is highlighted over some well-established control techniques in the literature related to the LFC problem.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109788"},"PeriodicalIF":4.0,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533656","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 load frequency control strategy based on double deep Q-network and upper confidence bound algorithm of multi-area interconnected power systems 基于双深 Q 网络和多区域互联电力系统置信上限算法的负载频率控制策略

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

Computers & Electrical Engineering

Pub Date : 2024-10-23 DOI: 10.1016/j.compeleceng.2024.109778

Jing Zhang , Feifei Peng , Lulu Wang , Yang Yang , Yingna Li

The reinforcement learning (RL)-based generation control strategies have been widely studied to address the limited adaptability of traditional automatic generation control (AGC) strategies to the load disturbance problem resulting from heterogeneous energy sources. To improve the control accuracy of the RL-based strategy in load frequency control (LFC), a double deep Q-network combined with an upper confidence bound (DDQN-UCB)-based strategy is designed to solve the problem of agent decision-making in a nonlinear environment. Firstly, the area control error (ACE) and control performance standard 1 (CPS1) of the LFC power system are considered in the design of the RL reward function. Secondly, the actual and estimated Q-values are calculated using the Q-network and the target Q-network combined with the reward value. Thirdly, the deviation loss of the two Q-values is calculated, and the network is updated based on the loss value using gradient descent. Finally, the UCB algorithm is introduced to equalize the frequency of being selected for each action during the random exploration of the actions, and the agent uses the greedy algorithm in combination with the UCB algorithm to select a power-compensated control action to send to the environment. In this paper, the IEEE multi-area LFC power system is used as an experimental validation model. A comparison of the proposed RL control algorithm with five other algorithms revealed that the pre-learning convergence accuracy was improved by 57.5%. Furthermore, the LFC effectiveness test demonstrated that the DDQN-UCB control strategy enhances LFC accuracy while simultaneously stabilizing the power exchange of the inter-area tie-line to within 1.8972 MW, thereby maintaining the stability of the power system.

为了解决传统自动发电控制（AGC）策略对异质能源导致的负荷扰动问题的适应性有限的问题，基于强化学习（RL）的发电控制策略已被广泛研究。为了提高基于 RL 的策略在负荷频率控制（LFC）中的控制精度，设计了一种基于双深度 Q 网络与置信上限（DDQN-UCB）相结合的策略，以解决非线性环境中的代理决策问题。首先，在设计 RL 奖励函数时考虑了 LFC 电力系统的区域控制误差（ACE）和控制性能标准 1（CPS1）。其次，利用 Q 网络和目标 Q 网络结合奖励值计算实际 Q 值和估计 Q 值。第三，计算两个 Q 值的偏差损失，并使用梯度下降法根据损失值更新网络。最后，引入 UCB 算法，在随机探索行动的过程中均衡每个行动的被选频率，代理使用贪婪算法结合 UCB 算法选择一个功率补偿控制行动发送给环境。本文使用 IEEE 多区域 LFC 电力系统作为实验验证模型。将所提出的 RL 控制算法与其他五种算法进行比较后发现，预学习收敛精度提高了 57.5%。此外，LFC 效果测试表明，DDQN-UCB 控制策略在提高 LFC 精度的同时，还能将区域间连接线的功率交换稳定在 1.8972 MW 以内，从而保持了电力系统的稳定性。

{"title":"A load frequency control strategy based on double deep Q-network and upper confidence bound algorithm of multi-area interconnected power systems","authors":"Jing Zhang , Feifei Peng , Lulu Wang , Yang Yang , Yingna Li","doi":"10.1016/j.compeleceng.2024.109778","DOIUrl":"10.1016/j.compeleceng.2024.109778","url":null,"abstract":"<div><div>The reinforcement learning (RL)-based generation control strategies have been widely studied to address the limited adaptability of traditional automatic generation control (AGC) strategies to the load disturbance problem resulting from heterogeneous energy sources. To improve the control accuracy of the RL-based strategy in load frequency control (LFC), a double deep Q-network combined with an upper confidence bound (DDQN-UCB)-based strategy is designed to solve the problem of agent decision-making in a nonlinear environment. Firstly, the area control error (ACE) and control performance standard 1 (CPS1) of the LFC power system are considered in the design of the RL reward function. Secondly, the actual and estimated Q-values are calculated using the Q-network and the target Q-network combined with the reward value. Thirdly, the deviation loss of the two Q-values is calculated, and the network is updated based on the loss value using gradient descent. Finally, the UCB algorithm is introduced to equalize the frequency of being selected for each action during the random exploration of the actions, and the agent uses the greedy algorithm in combination with the UCB algorithm to select a power-compensated control action to send to the environment. In this paper, the IEEE multi-area LFC power system is used as an experimental validation model. A comparison of the proposed RL control algorithm with five other algorithms revealed that the pre-learning convergence accuracy was improved by 57.5%. Furthermore, the LFC effectiveness test demonstrated that the DDQN-UCB control strategy enhances LFC accuracy while simultaneously stabilizing the power exchange of the inter-area tie-line to within 1.8972 MW, thereby maintaining the stability of the power system.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109778"},"PeriodicalIF":4.0,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533703","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

Improving Diabetic Retinopathy grading using Feature Fusion for limited data samples 利用特征融合改进有限数据样本的糖尿病视网膜病变分级

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

Computers & Electrical Engineering

Pub Date : 2024-10-22 DOI: 10.1016/j.compeleceng.2024.109782

K Ashwini, Ratnakar Dash

Early detection of Diabetic Retinopathy (DR) and its grading has been a growing demand among researchers in this community. Computer-aided diagnostic (CAD) systems have the potential to enhance the sensitivity and effectiveness of early diagnoses, benefiting ophthalmic specialists by offering additional insights for more efficient treatment options. The proposed study addresses the challenges of improved detection of mild stage and the limited number of samples with fewer parameters. Fundus images are initially pre-processed for this task using resizing, augmentation and oversampling. Oversampling is employed to guarantee the balanced inclusion of images from every grade category throughout the training stage. The proposed approach utilizes a Convolutional Neural Network (CNN) to extract texture and vessel features separately from the fundus images. This methodology exploited Local Binary Pattern (LBP) for improved texture features before applying CNN. Similarly, we utilized Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the blood vessels of the fundus images, enabling the extraction of relevant features using CNN. The extracted features are combined and classified using fully connected layers. The proposed approach is validated using standard datasets such as IDRiD, APTOS, DDR, and EyePACS with limited samples. The experimental results demonstrate that the proposed model in this research outperforms state-of-the-art models across all standard performance metrics, with classification accuracies of 92.46%, 98.08%, 95.66% and 88.84%.

糖尿病视网膜病变（DR）的早期检测及其分级一直是该领域研究人员日益增长的需求。计算机辅助诊断（CAD）系统有可能提高早期诊断的灵敏度和有效性，为眼科专家提供更多更有效的治疗方案。拟议的研究解决了改善轻度阶段检测和参数较少样本数量有限的难题。眼底图像最初是通过调整大小、增强和过采样进行预处理的。采用过采样是为了保证在整个训练阶段均衡地包含每个等级类别的图像。所提出的方法利用卷积神经网络（CNN）从眼底图像中分别提取纹理和血管特征。在应用 CNN 之前，该方法利用局部二进制模式（LBP）改进了纹理特征。同样，我们利用对比度受限自适应直方图均衡化（CLAHE）来增强眼底图像中的血管，从而利用 CNN 提取相关特征。提取的特征通过全连接层进行组合和分类。使用 IDRiD、APTOS、DDR 和 EyePACS 等标准数据集（样本有限）对所提出的方法进行了验证。实验结果表明，本研究提出的模型在所有标准性能指标上都优于最先进的模型，分类准确率分别为 92.46%、98.08%、95.66% 和 88.84%。

{"title":"Improving Diabetic Retinopathy grading using Feature Fusion for limited data samples","authors":"K Ashwini, Ratnakar Dash","doi":"10.1016/j.compeleceng.2024.109782","DOIUrl":"10.1016/j.compeleceng.2024.109782","url":null,"abstract":"<div><div>Early detection of Diabetic Retinopathy (DR) and its grading has been a growing demand among researchers in this community. Computer-aided diagnostic (CAD) systems have the potential to enhance the sensitivity and effectiveness of early diagnoses, benefiting ophthalmic specialists by offering additional insights for more efficient treatment options. The proposed study addresses the challenges of improved detection of mild stage and the limited number of samples with fewer parameters. Fundus images are initially pre-processed for this task using resizing, augmentation and oversampling. Oversampling is employed to guarantee the balanced inclusion of images from every grade category throughout the training stage. The proposed approach utilizes a Convolutional Neural Network (CNN) to extract texture and vessel features separately from the fundus images. This methodology exploited Local Binary Pattern (LBP) for improved texture features before applying CNN. Similarly, we utilized Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the blood vessels of the fundus images, enabling the extraction of relevant features using CNN. The extracted features are combined and classified using fully connected layers. The proposed approach is validated using standard datasets such as IDRiD, APTOS, DDR, and EyePACS with limited samples. The experimental results demonstrate that the proposed model in this research outperforms state-of-the-art models across all standard performance metrics, with classification accuracies of 92.46%, 98.08%, 95.66% and 88.84%.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109782"},"PeriodicalIF":4.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533654","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

Fractional order PI-PD controller design for time delayed processes 时延过程的分数阶 PI-PD 控制器设计

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

Computers & Electrical Engineering

Pub Date : 2024-10-22 DOI: 10.1016/j.compeleceng.2024.109776

Erdal Cokmez, Ibrahim Kaya

In this study, a method for modifying the settings of fractional order PI-PD (FOPI-PD) controllers to handle time-delayed stable, unstable, and integrating processes is presented. The goal is to reduce the computational complexity associated with fractional controller design using analytical techniques. The approach involves updating the analytical weighted geometrical center (AWGC) method for tuning FOPI-PD controllers. The fractional integral and derivative orders are computed by minimizing the Integral of Squared Time Error (ISTE) using straightforward formulas. Additionally, there are analytical formulas provided for robustness characteristics such as maximum sensitivity (Ms), phase margin (PM), and gain margin (GM). The effectiveness of the technique is illustrated through unit-step responses under nominal, disturbed, and measurement situations. The method was evaluated using various metrics and an inverted pendulum mechanical system to demonstrate its industrial applicability. The results showed satisfactory outcomes in both performance and robustness.

本研究提出了一种修改分数阶 PI-PD (FOPI-PD) 控制器设置的方法，以处理延时稳定、不稳定和积分过程。其目的是利用分析技术降低与分数控制器设计相关的计算复杂性。该方法涉及更新用于调整 FOPI-PD 控制器的分析加权几何中心 (AWGC) 方法。分数积分和导数阶次是通过使用直接公式最小化时间平方误差积分 (ISTE) 计算得出的。此外，还为最大灵敏度（Ms）、相位裕度（PM）和增益裕度（GM）等鲁棒性特征提供了分析公式。通过标称、干扰和测量情况下的单位步骤响应，说明了该技术的有效性。使用各种指标和倒立摆机械系统对该方法进行了评估，以证明其工业适用性。结果表明，该方法在性能和鲁棒性方面都取得了令人满意的结果。

引用次数: 0

A reinforcement learning-based optimization method for task allocation of agricultural multi-robots clusters 基于强化学习的农业多机器人集群任务分配优化方法

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

Computers & Electrical Engineering

Pub Date : 2024-10-22 DOI: 10.1016/j.compeleceng.2024.109752

Zaiwang Lu , Yancong Wang , Feng Dai , Yike Ma , Long Long , Zixu Zhao , Yucheng Zhang , Jintao Li

The Agricultural multi-robot task allocation (AMRTA) can allocate the optimal operation sequence for the cluster of agricultural robots and improve overall operational efficiency, which is an important research direction for the development of intelligent agriculture. In this paper, we first analyzed the practical requirements of multi-robot task allocation in agriculture and reformulate it as Node Workload-Constrained Multi Traveling Salesman Problem (NWC-MTSP), aiming to minimize the maximum operating time of sub-robots while ensuring a balanced distribution of workload as much as possible. Then, we implemented path planning algorithm required for task allocation and constructed an objective function based on it; we also constructed a graph structure containing workloads of nodes, used graph neural networks to obtain node feature information, and propose a Reinforcement Learning-based Attention Mechanism Policy Optimization Network (NWC-APONet) method to find the optimal allocation scheme. Finally, our model evaluated using real agricultural datasets, i.e., the TSPLIB public dataset and random datasets. Experiments results demonstrate that NWC-APONet achieves superior task allocation, which prove our model’s practical applicability and effectiveness in AMRTA.

农业多机器人任务分配（AMRTA）可以为农业机器人集群分配最优作业序列，提高整体作业效率，是智能农业发展的重要研究方向。本文首先分析了农业领域多机器人任务分配的实际需求，并将其重新表述为节点工作量约束的多旅行推销员问题（NWC-MTSP），目的是在保证工作量均衡分配的前提下，尽可能减少子机器人的最大作业时间。然后，我们实现了任务分配所需的路径规划算法，并在此基础上构建了目标函数；我们还构建了包含节点工作量的图结构，利用图神经网络获取节点特征信息，并提出了基于强化学习的注意机制策略优化网络（NWC-APONet）方法，以找到最优分配方案。最后，我们利用真实的农业数据集（即 TSPLIB 公共数据集和随机数据集）对模型进行了评估。实验结果表明，NWC-APONet 实现了更优越的任务分配，证明了我们的模型在 AMRTA 中的实用性和有效性。

{"title":"A reinforcement learning-based optimization method for task allocation of agricultural multi-robots clusters","authors":"Zaiwang Lu , Yancong Wang , Feng Dai , Yike Ma , Long Long , Zixu Zhao , Yucheng Zhang , Jintao Li","doi":"10.1016/j.compeleceng.2024.109752","DOIUrl":"10.1016/j.compeleceng.2024.109752","url":null,"abstract":"<div><div>The Agricultural multi-robot task allocation (AMRTA) can allocate the optimal operation sequence for the cluster of agricultural robots and improve overall operational efficiency, which is an important research direction for the development of intelligent agriculture. In this paper, we first analyzed the practical requirements of multi-robot task allocation in agriculture and reformulate it as Node Workload-Constrained Multi Traveling Salesman Problem (NWC-MTSP), aiming to minimize the maximum operating time of sub-robots while ensuring a balanced distribution of workload as much as possible. Then, we implemented path planning algorithm required for task allocation and constructed an objective function based on it; we also constructed a graph structure containing workloads of nodes, used graph neural networks to obtain node feature information, and propose a Reinforcement Learning-based Attention Mechanism Policy Optimization Network (NWC-APONet) method to find the optimal allocation scheme. Finally, our model evaluated using real agricultural datasets, i.e., the TSPLIB public dataset and random datasets. Experiments results demonstrate that NWC-APONet achieves superior task allocation, which prove our model’s practical applicability and effectiveness in AMRTA.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109752"},"PeriodicalIF":4.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534366","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

Anonymous quantum-safe secure and authorized communication protocol under dynamic identities for Internet of Drones 无人机互联网动态身份下的匿名量子安全授权通信协议

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

Computers & Electrical Engineering

Pub Date : 2024-10-22 DOI: 10.1016/j.compeleceng.2024.109774

Dharminder Chaudhary , Cheng-Chi Lee

The Internet of Drones (IoD) refers to the integration of unmanned aerial vehicles (UAVs) into the broader Internet of Things (IoT) ecosystem. This connection enables a wide range of applications and uses. An authenticated key agreement for the Internet of Drones (IoD) allows mobile device owners to establish a connection with a group of drones remotely for safe and effective services including supply delivery, sending photos and data from surveillance, and other communication services. The exchange of sensitive information through open channel, such as the internet, comes with challenges in terms of data protection and authentication. The invention of Shor’s technique, though, creates complications for authorized and secure communication in the era of highly advanced quantum computers. Therefore, we have proposed a secure authenticated key agreement the Internet of Drones (IoD) based on lattice assumption called ”Ring Learning With Error” on lattices. The RLWE operates on algebraic structures known as polynomial rings, which permits faster and space-efficient cryptographic operations. This efficiency is especially beneficial for limited storage devices (IoD/IoT). This framework is able to withstand quantum attacks, and it is suitable for low computation devices. This protocol provides anonymous communication for both user and drone. Additionally, this protocol ensures user privacy, from breaking session key security, or from withstanding impersonation attacks, and enables mutual authentication, and it utilizes dynamic identities and ensures freshness of messages. The performance analysis indicates that the proposed system performs better than existing state-of-the-art solutions when tested on benchmark datasets using various evaluation metrics.

无人机互联网（IoD）是指将无人驾驶飞行器（UAV）整合到更广泛的物联网（IoT）生态系统中。这种连接实现了广泛的应用和用途。无人机互联网（IoD）的认证密钥协议允许移动设备所有者远程与一组无人机建立连接，以提供安全有效的服务，包括供应品交付、发送监控照片和数据以及其他通信服务。通过互联网等开放渠道交换敏感信息，在数据保护和身份验证方面存在挑战。不过，肖尔技术的发明为高度发达的量子计算机时代的授权和安全通信带来了复杂性。因此，我们提出了一种基于网格假设的无人机互联网（IoD）安全认证密钥协议，称为网格上的 "带错环学习"（Ring Learning With Error）。RLWE 在被称为多项式环的代数结构上运行，从而允许更快、空间效率更高的加密操作。这种效率尤其适用于有限的存储设备（物联网/物联网）。该框架能够抵御量子攻击，适用于低计算设备。该协议可为用户和无人机提供匿名通信。此外，该协议还能确保用户隐私，防止破坏会话密钥安全或抵御冒名顶替攻击，实现相互验证，并利用动态身份，确保信息的新鲜度。性能分析表明，在使用各种评估指标对基准数据集进行测试时，拟议系统的性能优于现有的最先进解决方案。

{"title":"Anonymous quantum-safe secure and authorized communication protocol under dynamic identities for Internet of Drones","authors":"Dharminder Chaudhary , Cheng-Chi Lee","doi":"10.1016/j.compeleceng.2024.109774","DOIUrl":"10.1016/j.compeleceng.2024.109774","url":null,"abstract":"<div><div>The Internet of Drones (IoD) refers to the integration of unmanned aerial vehicles (UAVs) into the broader Internet of Things (IoT) ecosystem. This connection enables a wide range of applications and uses. An authenticated key agreement for the Internet of Drones (IoD) allows mobile device owners to establish a connection with a group of drones remotely for safe and effective services including supply delivery, sending photos and data from surveillance, and other communication services. The exchange of sensitive information through open channel, such as the internet, comes with challenges in terms of data protection and authentication. The invention of Shor’s technique, though, creates complications for authorized and secure communication in the era of highly advanced quantum computers. Therefore, we have proposed a secure authenticated key agreement the Internet of Drones (IoD) based on lattice assumption called ”Ring Learning With Error” on lattices. The RLWE operates on algebraic structures known as polynomial rings, which permits faster and space-efficient cryptographic operations. This efficiency is especially beneficial for limited storage devices (IoD/IoT). This framework is able to withstand quantum attacks, and it is suitable for low computation devices. This protocol provides anonymous communication for both user and drone. Additionally, this protocol ensures user privacy, from breaking session key security, or from withstanding impersonation attacks, and enables mutual authentication, and it utilizes dynamic identities and ensures freshness of messages. The performance analysis indicates that the proposed system performs better than existing state-of-the-art solutions when tested on benchmark datasets using various evaluation metrics.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109774"},"PeriodicalIF":4.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533655","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

BTTAS: Blockchain-based Two-Level Transferable Authentication Scheme for V2I communication in VANET BTTAS：基于区块链的两级可转移验证方案，用于 VANET 中的 V2I 通信

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

Computers & Electrical Engineering

Pub Date : 2024-10-21 DOI: 10.1016/j.compeleceng.2024.109767

Divya Rani, Sachin Tripathi

The progress of the Intelligent Transport System has significantly enhanced vehicle communication with both other vehicles and Road Side Units. This has become crucial due to the necessity for highly accurate information transmission while vehicles operate at high speeds. Additionally, the escalating vehicle count demands heightened processing speed, minimized superfluous computation, reduced data transmission delays, and decentralized storage solutions. Therefore, the proposed work involves a Blockchain-based Two-level Transferable Authentication Scheme (BTTAS) for secure V2I communication in Vehicular ad hoc networks. Unlike existing approaches that rely on centralized frameworks, the suggested model establishes a distributed environment utilizing a Consortium Blockchain furnished with a dedicated communication channel, ensuring the utmost confidentiality. Furthermore, a two-tier transferable authentication mechanism effectively curtails extraneous computations on the vehicles’ end. The Consortium Blockchain is implemented using the Hyperledger Fabric and its performance evaluation is conducted via Hyperledger Caliper. There is an ECC-based protocol for secure communication. The proposed work includes a ROR model-based Formal Analysis, simulation using the Scyther tool, and Informal Analysis. Additionally, by analyzing blockchain performance with different transaction volumes and rates, along with comparative analysis, the proposed work demonstrates enhanced effectiveness and security.

智能交通系统的发展大大加强了车辆与其他车辆和路侧装置的通信。由于车辆在高速行驶时需要高度准确的信息传输，这一点变得至关重要。此外，不断增加的车辆数量要求更高的处理速度、最小化多余计算、减少数据传输延迟和分散存储解决方案。因此，拟议的工作涉及一种基于区块链的两级可转移认证方案（BTTAS），用于在车载特设网络中实现安全的 V2I 通信。与依赖于集中式框架的现有方法不同，所建议的模型建立了一个分布式环境，利用配备专用通信渠道的联盟区块链，确保最大限度的保密性。此外，双层可转移认证机制可有效减少车辆端的无关计算。联盟区块链使用 Hyperledger Fabric 实现，其性能评估通过 Hyperledger Caliper 进行。安全通信采用基于 ECC 的协议。建议的工作包括基于 ROR 模型的形式分析、使用 Scyther 工具的仿真和非正式分析。此外，通过分析不同交易量和交易率下的区块链性能，并进行比较分析，拟议的工作展示了增强的有效性和安全性。

{"title":"BTTAS: Blockchain-based Two-Level Transferable Authentication Scheme for V2I communication in VANET","authors":"Divya Rani, Sachin Tripathi","doi":"10.1016/j.compeleceng.2024.109767","DOIUrl":"10.1016/j.compeleceng.2024.109767","url":null,"abstract":"<div><div>The progress of the Intelligent Transport System has significantly enhanced vehicle communication with both other vehicles and Road Side Units. This has become crucial due to the necessity for highly accurate information transmission while vehicles operate at high speeds. Additionally, the escalating vehicle count demands heightened processing speed, minimized superfluous computation, reduced data transmission delays, and decentralized storage solutions. Therefore, the proposed work involves a Blockchain-based Two-level Transferable Authentication Scheme (BTTAS) for secure V2I communication in Vehicular ad hoc networks. Unlike existing approaches that rely on centralized frameworks, the suggested model establishes a distributed environment utilizing a Consortium Blockchain furnished with a dedicated communication channel, ensuring the utmost confidentiality. Furthermore, a two-tier transferable authentication mechanism effectively curtails extraneous computations on the vehicles’ end. The Consortium Blockchain is implemented using the Hyperledger Fabric and its performance evaluation is conducted via Hyperledger Caliper. There is an ECC-based protocol for secure communication. The proposed work includes a ROR model-based Formal Analysis, simulation using the Scyther tool, and Informal Analysis. Additionally, by analyzing blockchain performance with different transaction volumes and rates, along with comparative analysis, the proposed work demonstrates enhanced effectiveness and security.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109767"},"PeriodicalIF":4.0,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533708","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

Wavelet kernel large margin distribution machine-based regression for modelling the river suspended sediment load 基于小波核大边缘分布机的河流悬浮泥沙负荷建模回归方法

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

Computers & Electrical Engineering

Pub Date : 2024-10-21 DOI: 10.1016/j.compeleceng.2024.109783

Deepak Gupta , Barenya Bikash Hazarika , Mohanadhas Berlin

Estimating the suspended sediment load (SSL) in rivers is among the key challenges in rivers. The major reason is that the daily river SSL data may contain non-linear components. Therefore, the traditional models face difficulty in handling the nonlinearity in the datasets. Very recently, a large margin distribution machine-based regression (LDMR) was proposed in the spirit of the large margin distribution machine (LDM). LDMR uses the Gaussian kernel for the selection of nonlinear kernels and tries to reduce the quadratic loss function and insensitive loss function concurrently. Wavelet kernels are very effective in approximating any arbitrary non-linear functions. To realize the benefit of wavelet kernel in LDMR, this paper suggests two novel wavelet kernel-based LDMR models as Morlet kernelized LDMR (MKLDMR) and Mexican hat kernelized LDMR (MHKLDMR) for river SSL estimation. The experiments were performed on a few SSL datasets which were gathered from the Tawang Chu River, India. Further, these models were also applied to a few artificially generated datasets and some real-world datasets. To validate the efficacy of MKLDMR and MHKLDMR, their generalization performance was collated with support vector regression (SVR), twin SVR (TSVR), random vector functional link without direct link (RVFLwoDL), iterative-based Lagrangian twin parametric insensitive SVR (ILTPISVR), robust support vector quantile regression (RSVQR), neuro fuzzy RVFL (NF-RVFL), ensemble deep RVFL (edRVFL) and LDMR. The experimental outcomes on the artificial datasets, real-world datasets and SSL datasets of the MKLDMR and MHKLDMR models imply the usability and effectiveness of the proposed models for SSL prediction.

估算河流中的悬浮泥沙负荷（SSL）是河流研究的主要挑战之一。主要原因是每日河流 SSL 数据可能包含非线性成分。因此，传统模型很难处理数据集中的非线性问题。最近，基于大边际分布机（LDM）的精神提出了基于大边际分布机的回归（LDMR）。LDMR 使用高斯核来选择非线性核，并试图同时减少二次损失函数和不敏感损失函数。小波核在逼近任意非线性函数方面非常有效。为了实现小波核在 LDMR 中的优势，本文提出了两种基于小波核的新型 LDMR 模型，即 Morlet 核化 LDMR（MKLDMR）和 Mexican hat 核化 LDMR（MHKLDMR），用于河流 SSL 估计。实验在从印度塔旺楚河收集的一些 SSL 数据集上进行。此外，这些模型还被应用于一些人工生成的数据集和一些真实世界的数据集。为了验证 MKLDMR 和 MHKLDMR 的功效，将它们的泛化性能与支持向量回归 (SVR)、孪生 SVR (TSVR)、无直接联系的随机向量功能联系 (RVFLwoDL)、基于迭代的拉格朗日孪生参数不敏感 SVR (ILTPISVR)、鲁棒性支持向量量化回归 (RSVQR)、神经模糊 RVFL (NF-RVFL)、集合深度 RVFL (edRVFL) 和 LDMR 进行了比较。MKLDMR 和 MHKLDMR 模型在人工数据集、真实世界数据集和 SSL 数据集上的实验结果表明，所提出的模型在 SSL 预测中具有可用性和有效性。

{"title":"Wavelet kernel large margin distribution machine-based regression for modelling the river suspended sediment load","authors":"Deepak Gupta , Barenya Bikash Hazarika , Mohanadhas Berlin","doi":"10.1016/j.compeleceng.2024.109783","DOIUrl":"10.1016/j.compeleceng.2024.109783","url":null,"abstract":"<div><div>Estimating the suspended sediment load (SSL) in rivers is among the key challenges in rivers. The major reason is that the daily river SSL data may contain non-linear components. Therefore, the traditional models face difficulty in handling the nonlinearity in the datasets. Very recently, a large margin distribution machine-based regression (LDMR) was proposed in the spirit of the large margin distribution machine (LDM). LDMR uses the Gaussian kernel for the selection of nonlinear kernels and tries to reduce the quadratic loss function and insensitive loss function concurrently. Wavelet kernels are very effective in approximating any arbitrary non-linear functions. To realize the benefit of wavelet kernel in LDMR, this paper suggests two novel wavelet kernel-based LDMR models as Morlet kernelized LDMR (MKLDMR) and Mexican hat kernelized LDMR (MHKLDMR) for river SSL estimation. The experiments were performed on a few SSL datasets which were gathered from the Tawang Chu River, India. Further, these models were also applied to a few artificially generated datasets and some real-world datasets. To validate the efficacy of MKLDMR and MHKLDMR, their generalization performance was collated with support vector regression (SVR), twin SVR (TSVR), random vector functional link without direct link (RVFLwoDL), iterative-based Lagrangian twin parametric insensitive SVR (ILTPISVR), robust support vector quantile regression (RSVQR), neuro fuzzy RVFL (NF-RVFL), ensemble deep RVFL (edRVFL) and LDMR. The experimental outcomes on the artificial datasets, real-world datasets and SSL datasets of the MKLDMR and MHKLDMR models imply the usability and effectiveness of the proposed models for SSL prediction.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109783"},"PeriodicalIF":4.0,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533712","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

Detection of overhead line glass insulator condition using dual function device and deep learning approach 利用双功能装置和深度学习方法检测架空线路玻璃绝缘子状况

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

Computers & Electrical Engineering

Pub Date : 2024-10-21 DOI: 10.1016/j.compeleceng.2024.109764

Ali Ahmed Ali Salem , Kwan Yiew Lau , Ahmed Abu-Saida

This paper presents a design of a multifunction smart wireless device for online condition monitoring of transmission line insulators. The proposed device can measure the insulator leakage current and take images of the high-voltage insulation. Yolov5-based models and deep convolutional neural networks (DCCN) are developed to analyze and classify the measured data and estimate the insulator's health condition. We have developed and tested a prototype of the proposed device. The device can issue a real-time warning message when a sudden change takes place in the leakage current value. The control center or smartphones receive the collected data wirelessly. We analyze the transmitted data using the developed methods to detect any anomalies and take appropriate remedial action. The performance and feasibility of the developed device are assessed through extensive experimental analysis. Results attest to the robustness of the proposed device, which is easy to install for existing and future overhead transmission line insulators.

本文介绍了一种用于输电线路绝缘子在线状态监测的多功能智能无线设备的设计。该设备可测量绝缘体的泄漏电流并拍摄高压绝缘体的图像。我们开发了基于 Yolov5 的模型和深度卷积神经网络 (DCCN)，用于对测量数据进行分析和分类，并估计绝缘体的健康状况。我们开发并测试了拟议设备的原型。当泄漏电流值发生突然变化时，该设备可发出实时警告信息。控制中心或智能手机通过无线方式接收收集到的数据。我们利用开发的方法对传输的数据进行分析，以检测任何异常情况并采取适当的补救措施。我们通过大量的实验分析评估了所开发设备的性能和可行性。结果证明了所提设备的稳健性，而且易于安装到现有和未来的架空输电线路绝缘子上。

引用次数: 0