MethodsX最新文献_第10页

SilhouetteScoreinR: Beyond traditional network layouts by leveraging local cohesion and nearest neighbor separation 廓形escoreinr：通过利用局部凝聚力和最近邻分离，超越传统的网络布局

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-09-11 DOI: 10.1016/j.mex.2025.103622

Hua-Ying Chuang , Willy Chou

The silhouette score (SS) quantifies how well each entity fits its assigned cluster by contrasting within‐cluster cohesion with nearest other–cluster separation. Although common in other fields, SS is rarely used in bibliometrics. Using 2,252 MethodsX articles (2020–2024), we show how SS evaluates clustering quality in co-word networks and author collaborations, independent of the chosen algorithm. We provide R scripts to compute SS for explicit (geographic/known coordinates) and implicit (PCA/UMAP) layouts and introduce a two-axis visualization that plots publication count against SS. The framework highlights coherent clusters (high SS) and flags boundary or misassigned entities (low/negative SS) that standard network plots can obscure. This improves interpretability at term, cluster, and corpus levels and supports more defensible decisions about labels, membership, and follow-up analysis. Code is released for replication and reuse; sensitivity to distance metrics and data regimes is discussed to guide application across bibliometrics and related domains.

•
Silhouette Scores Reveal Outliers: Silhouette scores not only validate cluster cohesion but also uncover meaningful outliers—insights often missed in traditional network layouts.
•
Novel Visualization Approach: Combining silhouette scores with publication counts enables a more nuanced visualization of co-word and collaboration networks.
•
Applied to Bibliometrics: This study applies silhouette analysis to 2252 MethodsX articles, offering new tools for evaluating clustering quality in bibliometric research.

剪影分数（SS）通过对比聚类内凝聚力与最近的其他聚类分离来量化每个实体适合其指定聚类的程度。虽然SS在其他领域很常见，但在文献计量学中很少使用。使用2252篇MethodsX文章（2020-2024），我们展示了SS如何独立于所选算法评估共词网络和作者合作中的聚类质量。我们提供了R脚本来计算显式（地理/已知坐标）和隐式（PCA/UMAP）布局的SS，并引入了两轴可视化，根据SS绘制出版计数。该框架突出显示了一致的集群（高SS），并标记了标准网络图可能模糊的边界或分配不当的实体（低/负SS）。这提高了术语、聚类和语料库级别的可解释性，并支持关于标签、成员关系和后续分析的更具防御性的决策。代码的发布是为了复制和重用；讨论了对距离度量和数据制度的敏感性，以指导跨文献计量学和相关领域的应用。•廓形分数揭示异常值：廓形分数不仅验证了集群内聚性，还揭示了有意义的异常值，这是传统网络布局中经常遗漏的见解。•新颖的可视化方法：将剪影分数与出版物计数相结合，可以更细致地可视化合著词和协作网络。•应用于文献计量学：本研究将剪影分析应用于2252篇MethodsX论文，为评价文献计量学研究中的聚类质量提供了新的工具。

{"title":"SilhouetteScoreinR: Beyond traditional network layouts by leveraging local cohesion and nearest neighbor separation","authors":"Hua-Ying Chuang , Willy Chou","doi":"10.1016/j.mex.2025.103622","DOIUrl":"10.1016/j.mex.2025.103622","url":null,"abstract":"<div><div>The silhouette score (SS) quantifies how well each entity fits its assigned cluster by contrasting within‐cluster cohesion with nearest other–cluster separation. Although common in other fields, SS is rarely used in bibliometrics. Using 2,252 <em>MethodsX</em> articles (2020–2024), we show how SS evaluates clustering quality in co-word networks and author collaborations, independent of the chosen algorithm. We provide R scripts to compute SS for explicit (geographic/known coordinates) and implicit (PCA/UMAP) layouts and introduce a two-axis visualization that plots publication count against SS. The framework highlights coherent clusters (high SS) and flags boundary or misassigned entities (low/negative SS) that standard network plots can obscure. This improves interpretability at term, cluster, and corpus levels and supports more defensible decisions about labels, membership, and follow-up analysis. Code is released for replication and reuse; sensitivity to distance metrics and data regimes is discussed to guide application across bibliometrics and related domains.<ul><li><span>•</span><span><div>Silhouette Scores Reveal Outliers: Silhouette scores not only validate cluster cohesion but also uncover meaningful outliers—insights often missed in traditional network layouts.</div></span></li><li><span>•</span><span><div>Novel Visualization Approach: Combining silhouette scores with publication counts enables a more nuanced visualization of co-word and collaboration networks.</div></span></li><li><span>•</span><span><div>Applied to Bibliometrics: This study applies silhouette analysis to 2252 MethodsX articles, offering new tools for evaluating clustering quality in bibliometric research.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103622"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The AI-DRM protocol to enhance the lifetime of wireless sensor network 采用AI-DRM协议提高无线传感器网络的寿命

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-09-25 DOI: 10.1016/j.mex.2025.103649

Santosh Anand, Anantha Narayanan V

Energy is a major research challenge in wireless sensor networks since it is placed in an area that is inaccessible to humans. In the current study, nodes send data to their neighboring nodes at any distance using the same energy level. Smaller distances require less energy to transmit to adjacent nodes, creating a strong research gap. High-distance transmissions require more energy. The node must tailor its transmission energy to distance, not fixed energy. The best transmission power for communication is determined via the neural network-based machine learning technique, which is based on the propagation model and network properties, such as the node density, residual energy, and energy harvesting rate. In this work, sensor nodes transmit information to their neighboring nodes via the multiple linear regression model for dynamic radio tuning with the FRIIS propagation model, and the simulation records the node's energy consumption. Compared with the four recent best current methods that increase the W.S.N. lifetime, the proposed protocol is better and uses less power. The proposed AI-DRM protocol has sufficient residual energy to transmit the packet until 1403 rounds, which is higher than those of two recent energy-efficient protocols, the ARORA and the EACHS-B2SPNN protocols.

1.
The AI-based dynamic transmission power protocol tunes the sensor nodes using a propagation model.
2.
Prediction of lifetime of WSN
3.
Effective utilization of all sensor nodes¹

能源是无线传感器网络的一个主要研究挑战，因为它被放置在人类无法进入的区域。在目前的研究中，节点使用相同的能级向任意距离的相邻节点发送数据。更小的距离需要更少的能量传输到相邻的节点，这就造成了一个很大的研究空白。远距离传输需要更多的能量。节点必须根据距离调整传输能量，而不是固定能量。通过基于神经网络的机器学习技术确定通信的最佳传输功率，该技术基于传播模型和网络特性，如节点密度、剩余能量和能量收集率。在这项工作中，传感器节点通过多元线性回归模型将信息传递给相邻节点，并使用FRIIS传播模型进行动态无线电调谐，仿真记录节点的能量消耗。与目前四种提高无线网络生存期的方法相比，该协议性能更好，功耗更低。提出的AI-DRM协议有足够的剩余能量将数据包传输到1403轮，这比最近的两个节能协议ARORA和EACHS-B2SPNN协议的剩余能量要高。基于人工智能的动态传输功率协议采用传播模型对传感器节点进行调谐。WSN3寿命预测。有效利用所有传感器节点1

{"title":"The AI-DRM protocol to enhance the lifetime of wireless sensor network","authors":"Santosh Anand, Anantha Narayanan V","doi":"10.1016/j.mex.2025.103649","DOIUrl":"10.1016/j.mex.2025.103649","url":null,"abstract":"<div><div>Energy is a major research challenge in wireless sensor networks since it is placed in an area that is inaccessible to humans. In the current study, nodes send data to their neighboring nodes at any distance using the same energy level. Smaller distances require less energy to transmit to adjacent nodes, creating a strong research gap. High-distance transmissions require more energy. The node must tailor its transmission energy to distance, not fixed energy. The best transmission power for communication is determined via the neural network-based machine learning technique, which is based on the propagation model and network properties, such as the node density, residual energy, and energy harvesting rate. In this work, sensor nodes transmit information to their neighboring nodes via the multiple linear regression model for dynamic radio tuning with the FRIIS propagation model, and the simulation records the node's energy consumption. Compared with the four recent best current methods that increase the W.S.N. lifetime, the proposed protocol is better and uses less power. The proposed AI-DRM protocol has sufficient residual energy to transmit the packet until 1403 rounds, which is higher than those of two recent energy-efficient protocols, the ARORA and the EACHS-B2SPNN protocols.<ul><li><span>1.</span><span><div>The AI-based dynamic transmission power protocol tunes the sensor nodes using a propagation model.</div></span></li><li><span>2.</span><span><div>Prediction of lifetime of WSN</div></span></li><li><span>3.</span><span><div>Effective utilization of all sensor nodes<span><span><sup>1</sup></span></span></div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103649"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Growth and differentiation factors and their orthodontic implications: A scoping review 生长和分化因子及其正畸意义：范围综述

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-06-12 DOI: 10.1016/j.mex.2025.103435

Crystal Runa Soans , M.S. Ravi , Monisha P Chelery , Sujata Shirodkar , Prachi Pundir , Shradha S. Parsekar

Background

Growth and differentiation factors (GDFs) are a class of biological mediators that play an important role to stimulate and regulate the wound healing process. Some of the GDFs are known to play a role in orthodontics.

Objectives

To map the evidence related to GDFs in orthodontics and to identify the role of GDFs in craniofacial morphogenesis, periodontal remodeling and orthodontic tooth movement.

Methods

We have planned a scoping review to achieve the objectives. Search will be conducted in various databases to identify English language publications. Additionally, we will search the first ten pages of Google Scholar and the reference lists of included studies. This review will include all animal or human studies exploring preventive, interceptive and corrective treatments in orthodontics. Two reviewers will independently screen titles and abstracts and full-texts and extract the data of included studies. Disagreement will be resolved by discussion. The results will be presented in a descriptive format using diagrams and tables.

Ethics and dissemination

The current study does not require ethical approval. Results of review findings will be disseminated through a peer-reviewed publication or conference presentation.

Registration

The protocol is registered with the Open Science Framework.

生长分化因子（growth and differentiation factors, GDFs）是一类在刺激和调节创面愈合过程中起重要作用的生物介质。已知一些GDFs在正畸中起作用。目的研究GDFs在正畸治疗中的作用，探讨GDFs在颅面形态发生、牙周重塑和正畸牙齿运动中的作用。方法我们计划进行范围审查以实现目标。将在不同的数据库中进行检索，以确定英文出版物。此外，我们将搜索b谷歌Scholar的前十页和纳入研究的参考文献列表。这篇综述将包括所有动物或人类的研究，探讨正畸的预防、拦截和矫正治疗。两名审稿人将独立筛选标题、摘要和全文，并提取纳入研究的数据。分歧将通过讨论来解决。结果将以图表和表格的描述性格式呈现。伦理和传播目前的研究不需要伦理批准。评审结果将通过同行评审的出版物或会议报告进行传播。该协议在开放科学框架中注册。

{"title":"Growth and differentiation factors and their orthodontic implications: A scoping review","authors":"Crystal Runa Soans , M.S. Ravi , Monisha P Chelery , Sujata Shirodkar , Prachi Pundir , Shradha S. Parsekar","doi":"10.1016/j.mex.2025.103435","DOIUrl":"10.1016/j.mex.2025.103435","url":null,"abstract":"<div><h3>Background</h3><div>Growth and differentiation factors (GDFs) are a class of biological mediators that play an important role to stimulate and regulate the wound healing process. Some of the GDFs are known to play a role in orthodontics.</div></div><div><h3>Objectives</h3><div>To map the evidence related to GDFs in orthodontics and to identify the role of GDFs in craniofacial morphogenesis, periodontal remodeling and orthodontic tooth movement.</div></div><div><h3>Methods</h3><div>We have planned a scoping review to achieve the objectives. Search will be conducted in various databases to identify English language publications. Additionally, we will search the first ten pages of Google Scholar and the reference lists of included studies. This review will include all animal or human studies exploring preventive, interceptive and corrective treatments in orthodontics. Two reviewers will independently screen titles and abstracts and full-texts and extract the data of included studies. Disagreement will be resolved by discussion. The results will be presented in a descriptive format using diagrams and tables.</div></div><div><h3>Ethics and dissemination</h3><div>The current study does not require ethical approval. Results of review findings will be disseminated through a peer-reviewed publication or conference presentation.</div></div><div><h3>Registration</h3><div>The protocol is registered with the Open Science Framework.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103435"},"PeriodicalIF":1.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GeoBM: A Python-based tool for integrated visualization of global bibliometric data GeoBM：一个基于python的工具，用于全球文献计量数据的集成可视化

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-07-11 DOI: 10.1016/j.mex.2025.103497

Chun Chong Fu , Jorge Fleta-Asín , Fernando Muñoz , Carlos Sáenz-Royo , Loo Keat Wei

The rapid proliferation of scientometric and bibliometric analyses has emphasized the need for robust, scalable methods to visualize complex, large-scale research data. Conventional geospatial visualization techniques—most notably choropleth maps—often introduce significant distortions due to their inability to adequately account for spatial heterogeneity and overdispersion in bibliometric distributions. To address these methodological shortcomings, we propose GeoBM (Geographic Bibliometric Mapping), a computational framework that enables enhanced geovisualization of global scientific output and collaboration patterns. GeoBM integrates normalized country-level publication volumes with bilateral collaboration frequencies to produce high-resolution, interpretable geographic maps that reflect both research intensity and international connectivity. Implemented in Python, the framework leverages modular, algorithmically optimized routines for real-time data processing and visualization, incorporating statistical controls to mitigate overdispersion and enhance visual fidelity. The system supports extensive customization and is deployed via open-source platforms such as Google Colab and GitHub, facilitating broad accessibility and reproducibility. By providing a dual-focus representation of publication density and collaborative strength, GeoBM offers a powerful tool for the spatial analysis of global research networks, contributing to more nuanced evaluations in science policy, research management, and innovation studies.

科学计量学和文献计量学分析的快速发展强调了对强大的、可扩展的方法来可视化复杂的、大规模的研究数据的需求。传统的地理空间可视化技术——最著名的是地形图——由于无法充分解释文献计量分布中的空间异质性和过度分散，常常会引入显著的扭曲。为了解决这些方法上的缺陷，我们提出了地理文献计量制图（geoobm），这是一个计算框架，可以增强全球科学产出和合作模式的地理可视化。GeoBM将标准化的国家级出版物量与双边合作频率相结合，生成高分辨率、可解释的地理地图，反映了研究强度和国际连通性。该框架使用Python实现，利用模块化、算法优化的例程进行实时数据处理和可视化，并结合统计控制来缓解过度分散并增强视觉保真度。该系统支持广泛的定制，并通过谷歌Colab和GitHub等开源平台部署，促进了广泛的可访问性和可重复性。通过提供出版密度和合作强度的双重焦点表示，GeoBM为全球研究网络的空间分析提供了一个强大的工具，有助于在科学政策、研究管理和创新研究方面进行更细致的评估。

{"title":"GeoBM: A Python-based tool for integrated visualization of global bibliometric data","authors":"Chun Chong Fu , Jorge Fleta-Asín , Fernando Muñoz , Carlos Sáenz-Royo , Loo Keat Wei","doi":"10.1016/j.mex.2025.103497","DOIUrl":"10.1016/j.mex.2025.103497","url":null,"abstract":"<div><div>The rapid proliferation of scientometric and bibliometric analyses has emphasized the need for robust, scalable methods to visualize complex, large-scale research data. Conventional geospatial visualization techniques—most notably choropleth maps—often introduce significant distortions due to their inability to adequately account for spatial heterogeneity and overdispersion in bibliometric distributions. To address these methodological shortcomings, we propose GeoBM (Geographic Bibliometric Mapping), a computational framework that enables enhanced geovisualization of global scientific output and collaboration patterns. GeoBM integrates normalized country-level publication volumes with bilateral collaboration frequencies to produce high-resolution, interpretable geographic maps that reflect both research intensity and international connectivity. Implemented in Python, the framework leverages modular, algorithmically optimized routines for real-time data processing and visualization, incorporating statistical controls to mitigate overdispersion and enhance visual fidelity. The system supports extensive customization and is deployed via open-source platforms such as Google Colab and GitHub, facilitating broad accessibility and reproducibility. By providing a dual-focus representation of publication density and collaborative strength, GeoBM offers a powerful tool for the spatial analysis of global research networks, contributing to more nuanced evaluations in science policy, research management, and innovation studies.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103497"},"PeriodicalIF":1.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian MCMC with Gibbs sampling for saturation flow rate estimation in heterogeneous traffic at pretimed signalized intersections 基于吉布斯采样的贝叶斯MCMC预定时信号交叉口非均匀交通饱和流量估计

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-07-16 DOI: 10.1016/j.mex.2025.103507

Lulusi Lulusi , Sugiarto Sugiarto , Sofyan M. Saleh , Muhammad Isya , Muhammad Rusdi , Roudhia Rahma

Pretimed signalized intersections significantly contribute to traffic congestion, especially under the heterogeneous traffic conditions commonly observed in emerging economies such as Indonesia. Accurate estimation of the base saturation flow rate (BSFR) is essential for reliable capacity assessment, which influences effective intersection design and operation. However, the current BSFR estimation methods outlined in the Indonesian Highway Capacity Guidelines (IHCG, 2023) rely on outdated linear models derived from the Indonesian Highway Capacity Manual (IHCM, 1997), which are inadequate for addressing contemporary heterogeneous traffic complexities. This study introduces a Bayesian Markov Chain Monte Carlo (MCMC) model employing Gibbs sampling to improve BSFR estimation accuracy. The Bayesian MCMC model achieved a Root Mean Square Error Approximation (RMSEA) of 8.638 % compared to the existing IHCG method, which produced an RMSEA of up to 51.428 %, enabling a more precise intersection capacity design. Additionally, the developed model reduced the BSFR overestimation associated with the IHCG method by approximately 42.79 %, highlighting the potential of Bayesian MCMC methods to effectively address heterogeneous traffic challenges, enhance traffic management strategies, and optimize intersection operations.

The Bayesian approach provides a probabilistic framework for quantifying uncertainty, allows for the incorporation of prior knowledge to enhance parameter estimation flexibility, and effectively mitigates model overfitting.

The developed model demonstrates robust statistical validity, characterized by a mean beta parameter value of 403.30, standard deviation of 8.66, and Monte Carlo Standard Error (MCSE) of 0.0008, confirming high reliability and predictive precision.

The proposed BSFR model exhibited superior performance in fitting empirical data, as evidenced by an RMSE of 240.403 PCU/g/h/We and RMSEA of 8.638 %, indicating an excellent model fit within acceptable thresholds (<10 %).

提前设置信号交叉口严重加剧了交通拥堵，尤其是在印度尼西亚等新兴经济体中常见的异质性交通状况下。基础饱和流量的准确估计是可靠的通行能力评估的基础，它直接影响到有效的交叉口设计和运营。然而，目前《印度尼西亚公路容量指南》（IHCG, 2023）中概述的BSFR估计方法依赖于《印度尼西亚公路容量手册》（IHCM, 1997）中过时的线性模型，这些模型不足以解决当代异构交通复杂性问题。为了提高BSFR的估计精度，提出了一种采用Gibbs抽样的贝叶斯马尔可夫链蒙特卡罗（MCMC）模型。与现有的IHCG方法相比，Bayesian MCMC模型的均方根误差近似（RMSEA）为8.638%，RMSEA高达51.428%，可以实现更精确的交叉口容量设计。此外，该模型将IHCG方法相关的BSFR高估降低了约42.79%，突出了贝叶斯MCMC方法在有效应对异构交通挑战、加强交通管理策略和优化交叉口运营方面的潜力。贝叶斯方法为量化不确定性提供了一个概率框架，允许结合先验知识来增强参数估计的灵活性，并有效地减轻模型过拟合。所建立的模型具有稳健的统计有效性，beta参数均值为403.30，标准差为8.66，蒙特卡罗标准误差（MCSE）为0.0008，具有较高的可靠性和预测精度。所提出的BSFR模型在拟合经验数据方面表现出优异的性能，RMSE为240.403 PCU/g/h/We， RMSEA为8.638%，表明模型在可接受阈值（< 10%）内拟合良好。

{"title":"Bayesian MCMC with Gibbs sampling for saturation flow rate estimation in heterogeneous traffic at pretimed signalized intersections","authors":"Lulusi Lulusi , Sugiarto Sugiarto , Sofyan M. Saleh , Muhammad Isya , Muhammad Rusdi , Roudhia Rahma","doi":"10.1016/j.mex.2025.103507","DOIUrl":"10.1016/j.mex.2025.103507","url":null,"abstract":"<div><div>Pretimed signalized intersections significantly contribute to traffic congestion, especially under the heterogeneous traffic conditions commonly observed in emerging economies such as Indonesia. Accurate estimation of the base saturation flow rate (BSFR) is essential for reliable capacity assessment, which influences effective intersection design and operation. However, the current BSFR estimation methods outlined in the Indonesian Highway Capacity Guidelines (IHCG, 2023) rely on outdated linear models derived from the Indonesian Highway Capacity Manual (IHCM, 1997), which are inadequate for addressing contemporary heterogeneous traffic complexities. This study introduces a Bayesian Markov Chain Monte Carlo (MCMC) model employing Gibbs sampling to improve BSFR estimation accuracy. The Bayesian MCMC model achieved a Root Mean Square Error Approximation (RMSEA) of 8.638 % compared to the existing IHCG method, which produced an RMSEA of up to 51.428 %, enabling a more precise intersection capacity design. Additionally, the developed model reduced the BSFR overestimation associated with the IHCG method by approximately 42.79 %, highlighting the potential of Bayesian MCMC methods to effectively address heterogeneous traffic challenges, enhance traffic management strategies, and optimize intersection operations.</div><div>The Bayesian approach provides a probabilistic framework for quantifying uncertainty, allows for the incorporation of prior knowledge to enhance parameter estimation flexibility, and effectively mitigates model overfitting.</div><div>The developed model demonstrates robust statistical validity, characterized by a mean beta parameter value of 403.30, standard deviation of 8.66, and Monte Carlo Standard Error (MCSE) of 0.0008, confirming high reliability and predictive precision.</div><div>The proposed BSFR model exhibited superior performance in fitting empirical data, as evidenced by an RMSE of 240.403 PCU/g/h/We and RMSEA of 8.638 %, indicating an excellent model fit within acceptable thresholds (<10 %).</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103507"},"PeriodicalIF":1.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144696759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Method for detecting rough road index using iot sensor fusion and v2v interaction for efficient road infrastructure management 基于物联网传感器融合和v2v交互的粗糙道路指数检测方法，实现有效的道路基础设施管理

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-06-13 DOI: 10.1016/j.mex.2025.103436

Akhilesh Kumar Singh, Damodar Reddy Edla

The method proposed explores the integration of Internet of Things (IoT) technologies and sensor fusion techniques into modern transportation systems to enhance efficiency, safety, and road quality assessment. The study not only emphasizes the importance of V2V communication using DSRC Dedicated Short Range Communication, Threshold Based Algorithms (TBA) and Dynamic Time Warping (DTW) but also proposes a novel approach of IoT multi-sensor fusion hardware model that is designed to identify clean and rough surface road conditions. By deploying multi sensor module into proposed model, real-time road surface data is collected and processed to classify them into flat clean or bumpy rough categories based on their smoothness index. In order to monitor the road surface in real time, this study suggests a novel IoT-based multi-sensor fusion hardware architecture that combines LiDAR, accelerometer, and ultrasonic sensors.

•
To improve road safety and navigation, the suggested methodical system makes advantage of DSRC-enabled V2V communication, primarily for luxury and driverless cars.
•
The proposed method provides revolutionary possibilities for intelligent transportation systems and fills in gaps in the high-accuracy identification of road anomalies.

该方法探索了将物联网技术和传感器融合技术融入现代交通系统，以提高效率、安全性和道路质量评估。该研究不仅强调了使用DSRC专用短距离通信、基于阈值算法（TBA）和动态时间扭曲（DTW）的V2V通信的重要性，而且提出了一种新的物联网多传感器融合硬件模型方法，旨在识别干净和粗糙的路面状况。通过在模型中部署多个传感器模块，采集实时路面数据并进行处理，根据路面的平滑度指数将路面分为平整干净和凹凸不平的粗糙两类。为了实时监测路面，本研究提出了一种新型的基于物联网的多传感器融合硬件架构，该架构结合了激光雷达、加速度计和超声波传感器。•为了改善道路安全和导航，建议的系统利用了支持dsrc的V2V通信，主要用于豪华汽车和无人驾驶汽车。•提出的方法为智能交通系统提供了革命性的可能性，填补了高精度道路异常识别的空白。

{"title":"Method for detecting rough road index using iot sensor fusion and v2v interaction for efficient road infrastructure management","authors":"Akhilesh Kumar Singh, Damodar Reddy Edla","doi":"10.1016/j.mex.2025.103436","DOIUrl":"10.1016/j.mex.2025.103436","url":null,"abstract":"<div><div>The method proposed explores the integration of Internet of Things (IoT) technologies and sensor fusion techniques into modern transportation systems to enhance efficiency, safety, and road quality assessment. The study not only emphasizes the importance of V2V communication using DSRC Dedicated Short Range Communication, Threshold Based Algorithms (TBA) and Dynamic Time Warping (DTW) but also proposes a novel approach of IoT multi-sensor fusion hardware model that is designed to identify clean and rough surface road conditions. By deploying multi sensor module into proposed model, real-time road surface data is collected and processed to classify them into flat clean or bumpy rough categories based on their smoothness index. In order to monitor the road surface in real time, this study suggests a novel IoT-based multi-sensor fusion hardware architecture that combines LiDAR, accelerometer, and ultrasonic sensors.<ul><li><span>•</span><span><div>To improve road safety and navigation, the suggested methodical system makes advantage of DSRC-enabled V2V communication, primarily for luxury and driverless cars.</div></span></li><li><span>•</span><span><div>The proposed method provides revolutionary possibilities for intelligent transportation systems and fills in gaps in the high-accuracy identification of road anomalies<em>.</em></div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103436"},"PeriodicalIF":1.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vocal features based Parkinson’s detection: An ensemble learning approach 基于声音特征的帕金森病检测：一种集成学习方法

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-10-04 DOI: 10.1016/j.mex.2025.103662

Megha Chakole , Sanjay Dorle , Rahul Agrawal , Priya Dasarwar , Uma Yadav , Rashmi Sharma

Parkinson’s disease (PD) primarily affects the central nervous system. In 2019, over 8.5 million cases were reported, with numbers continuing to rise. This growing prevalence emphasizes the urgent need for early detection and preventive strategies. To resolve this, numerous methods have been introduced, one of them being machine learning technique. By employing deep learning methods on the large-scale datasets, the early prediction and detection of PD is possible. These methods should be precisely evaluated on the basis of vocal features and the best method to predict this neurodegenerative ailment is disclosed. The core objective of this research is to facilitate the medical centers by providing an optimal machine learning technique to early detect PD. In order to decide an ideal method, the renowned machine learning algorithms like Random Forest, K Nearest Neighbor, Naïve Bayes, Gradient Boosting and XGBoost are evaluated according to their performance. Gradient Boosting outperforms earlier results with high recall, low log loss, and overfitting resistance.

Vocal features proved to be valuable indicators for early-stage Parkinson’s detection.

The Gradient Boosting model has scored the highest in terms of all the mentioned parameters, showing a promising result for predicting the occurrence of PD.

Machine learning can play a significant role in supporting clinical diagnosis and decision-making.

帕金森病（PD）主要影响中枢神经系统。2019年，报告了850多万例病例，这一数字还在继续上升。这种日益增长的流行强调迫切需要早期发现和预防战略。为了解决这个问题，已经引入了许多方法，其中之一就是机器学习技术。通过在大规模数据集上采用深度学习方法，PD的早期预测和检测成为可能。这些方法应根据声音特征进行精确评估，并揭示了预测这种神经退行性疾病的最佳方法。本研究的核心目标是通过提供最佳的机器学习技术来促进医疗中心早期检测PD。为了确定一个理想的方法，我们根据随机森林、K近邻、Naïve贝叶斯、梯度增强和XGBoost等著名的机器学习算法的性能进行评估。梯度增强在高召回率、低对数损失和抗过拟合方面优于早期的结果。声音特征被证明是早期帕金森病检测的有价值的指标。Gradient Boosting模型在上述所有参数中得分最高，在预测PD的发生方面显示出很好的效果。机器学习可以在支持临床诊断和决策方面发挥重要作用。

{"title":"Vocal features based Parkinson’s detection: An ensemble learning approach","authors":"Megha Chakole , Sanjay Dorle , Rahul Agrawal , Priya Dasarwar , Uma Yadav , Rashmi Sharma","doi":"10.1016/j.mex.2025.103662","DOIUrl":"10.1016/j.mex.2025.103662","url":null,"abstract":"<div><div>Parkinson’s disease (PD) primarily affects the central nervous system. In 2019, over 8.5 million cases were reported, with numbers continuing to rise. This growing prevalence emphasizes the urgent need for early detection and preventive strategies. To resolve this, numerous methods have been introduced, one of them being machine learning technique. By employing deep learning methods on the large-scale datasets, the early prediction and detection of PD is possible. These methods should be precisely evaluated on the basis of vocal features and the best method to predict this neurodegenerative ailment is disclosed. The core objective of this research is to facilitate the medical centers by providing an optimal machine learning technique to early detect PD. In order to decide an ideal method, the renowned machine learning algorithms like Random Forest, K Nearest Neighbor, Naïve Bayes, Gradient Boosting and XGBoost are evaluated according to their performance. Gradient Boosting outperforms earlier results with high recall, low log loss, and overfitting resistance.</div><div>Vocal features proved to be valuable indicators for early-stage Parkinson’s detection.</div><div>The Gradient Boosting model has scored the highest in terms of all the mentioned parameters, showing a promising result for predicting the occurrence of PD.</div><div>Machine learning can play a significant role in supporting clinical diagnosis and decision-making.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103662"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145265824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hybrid approach for real-time hand tracking using fiducial markers and inertial sensors 一种基于基准标记和惯性传感器的手部实时跟踪混合方法

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-09-08 DOI: 10.1016/j.mex.2025.103609

Ranjeet Bidwe , Shubhangi Deokar , Yash Parkhi , Tanisha Vyas , Nimita Jestin , Utkarsh Kumar , Satviki Budhia , Armaan Jeswani

This paper presents a cost-effective hybrid hand-tracking technique that integrates fiducial marker detection, capacitive touch sensing, and inertial measurement for real-time gesture recognition in immersive environments. The system is implemented on lightweight hardware comprising a Raspberry Pi Zero 2 W and an ESP32, with OpenCV’s ArUco marker detection enabling 3D hand pose estimation, capacitive sensors supporting finger-state recognition, and an Inertial Measurement Unit (IMU) providing orientation tracking. Optimizations such as exposure adjustment and region-of-interest processing ensure robust marker detection under variable illumination, while sensor data is transmitted via Bluetooth Low Energy (BLE) and WebSocket protocols for synchronization with external devices.

The methodological novelty of this work is highlighted as follows:

•High Accuracy Across Modalities: Achieved 3.4 mm localization accuracy, 85–91% orientation accuracy, and ∼2.9 mm hand pose keypoint accuracy, with trajectory fidelity maintained at 80–81%.

•Robust Finger-State Recognition: The capacitive sensing module consistently delivered 96.1% accuracy in detecting finger states across multiple runs.

•Validated Communication Trade-offs: Latency testing established complementary roles of Wi-Fi (high throughput, ∼467 msg/s) and BLE (low latency, ∼50 ms, >98% reliability) for real-time applications.

By fusing multiple sensing modalities, the method delivers enhanced accuracy, responsiveness, and stability while minimizing computational overhead. The system provides a reproducible, modular, and scalable solution suitable for VR/AR interaction, assistive technology, education, and human–computer interaction.

本文提出了一种具有成本效益的混合手跟踪技术，该技术集成了基准标记检测，电容触摸传感和惯性测量，用于沉浸式环境中的实时手势识别。该系统在轻量级硬件上实现，包括Raspberry Pi Zero 2w和ESP32， OpenCV的ArUco标记检测支持3D手部姿态估计，电容式传感器支持手指状态识别，惯性测量单元（IMU）提供方向跟踪。曝光调整和感兴趣区域处理等优化确保了在可变照明下稳健的标记检测，而传感器数据通过蓝牙低功耗（BLE）和WebSocket协议传输，以与外部设备同步。•跨模态高精度：实现3.4 mm定位精度，85-91%定向精度和~ 2.9 mm手位关键点精度，轨迹保真度保持在80-81%。•强大的手指状态识别：电容式传感模块在多次运行中检测手指状态时始终提供96.1%的准确率。•经过验证的通信权衡：延迟测试为实时应用建立了Wi-Fi（高吞吐量，~ 467 msg/s）和BLE（低延迟，~ 50 ms, >；98%可靠性）的互补作用。通过融合多种传感模式，该方法提供了更高的准确性、响应性和稳定性，同时最大限度地减少了计算开销。该系统提供了一个可复制的、模块化的、可扩展的解决方案，适用于VR/AR交互、辅助技术、教育和人机交互。

{"title":"A hybrid approach for real-time hand tracking using fiducial markers and inertial sensors","authors":"Ranjeet Bidwe , Shubhangi Deokar , Yash Parkhi , Tanisha Vyas , Nimita Jestin , Utkarsh Kumar , Satviki Budhia , Armaan Jeswani","doi":"10.1016/j.mex.2025.103609","DOIUrl":"10.1016/j.mex.2025.103609","url":null,"abstract":"<div><div>This paper presents a cost-effective hybrid hand-tracking technique that integrates fiducial marker detection, capacitive touch sensing, and inertial measurement for real-time gesture recognition in immersive environments. The system is implemented on lightweight hardware comprising a Raspberry Pi Zero 2 W and an ESP32, with OpenCV’s ArUco marker detection enabling 3D hand pose estimation, capacitive sensors supporting finger-state recognition, and an Inertial Measurement Unit (IMU) providing orientation tracking. Optimizations such as exposure adjustment and region-of-interest processing ensure robust marker detection under variable illumination, while sensor data is transmitted via Bluetooth Low Energy (BLE) and WebSocket protocols for synchronization with external devices.</div><div>The methodological novelty of this work is highlighted as follows:</div><div>•High Accuracy Across Modalities: Achieved 3.4 mm localization accuracy, 85–91% orientation accuracy, and ∼2.9 mm hand pose keypoint accuracy, with trajectory fidelity maintained at 80–81%.</div><div>•Robust Finger-State Recognition: The capacitive sensing module consistently delivered 96.1% accuracy in detecting finger states across multiple runs.</div><div>•Validated Communication Trade-offs: Latency testing established complementary roles of Wi-Fi (high throughput, ∼467 msg/s) and BLE (low latency, ∼50 ms, >98% reliability) for real-time applications.</div><div>By fusing multiple sensing modalities, the method delivers enhanced accuracy, responsiveness, and stability while minimizing computational overhead. The system provides a reproducible, modular, and scalable solution suitable for VR/AR interaction, assistive technology, education, and human–computer interaction.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103609"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

R-based workflow to estimate chilling requirements in multiple fruit tree genotypes using Partial Least Squares regression: Prunus armeniaca L. case 基于r的工作流程，利用偏最小二乘回归估计多种果树基因型的冷却需求：亚美尼亚李案例

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-10-26 DOI: 10.1016/j.mex.2025.103686

Ana M. Muñoz-Morales, Germán Ortuño-Hernández, Juan Alfonso Salazar, Pedro Martínez-Gómez, Jose A. Egea, David Ruiz, Alvaro Delgado

Accurate estimation of chilling requirements (CR) is essential for breeding and selecting temperate fruit trees adapted to specific agroclimatic conditions, particularly under global warming scenarios. Among the available methodologies to determine CR, the Partial Least Squares (PLS) regression procedure, based on long-term phenological and temperature records, offers a suitable approach to delineate the effective chill accumulation period. In this study, we present an R-based workflow developed using the agroclimatic functions integrated into the chillR package for R to determine the genotype-specific CR of 282 apricot (Prunus armeniaca L.) seedlings from two progenies grown in southwestern Spain. The pipeline generates standardized CR datasets suitable for downstream applications, including QTL mapping and the selection of promising genotypes for breeding purposes. This tool streamlines the estimation process, reducing the technical expertise and time required for CR estimation, thereby supporting efficient phenotypic selection and accelerating genetic research in temperate fruit trees. The complete code and associated datasets are freely available in a public repository (https://github.com/CEBASFruitBreed/R-workflow-ChillPLS), promoting the use across a range of temperate fruit species.

•
Uses long-term flowering observations and temperature records to determine genotype-specific chilling requirements.
•
Integrates PLS regression procedure within an R-based workflow to estimate chilling requirements from datasets comprising multiple genotypes.
•
Generates standardized outputs suitable to support genetic analysis and informed breeding decisions.

准确估计低温需要量（CR）对于培育和选择适应特定农业气候条件的温带果树至关重要，特别是在全球变暖的情况下。在确定CR的现有方法中，基于长期物候和温度记录的偏最小二乘（PLS）回归方法是描述有效冷积累期的合适方法。在这项研究中，我们提出了一个基于R的工作流程，利用集成在R软件包中的农业气候功能来确定来自西班牙西南部两个后代的282个杏（Prunus armeniaca L.）幼苗的基因型特异性CR。该管道生成适合下游应用的标准化CR数据集，包括QTL定位和为育种目的选择有前途的基因型。该工具简化了估算过程，减少了估算CR所需的技术专长和时间，从而支持有效的表型选择和加速温带果树的遗传研究。完整的代码和相关数据集在公共存储库（https://github.com/CEBASFruitBreed/R-workflow-ChillPLS）中免费提供，促进了温带水果物种的广泛使用。•使用长期开花观察和温度记录来确定基因型特定的冷却需求。•在基于r的工作流程中集成PLS回归程序，以估计包含多个基因型的数据集的冷却需求。生成适合于支持遗传分析和明智育种决策的标准化输出。

{"title":"R-based workflow to estimate chilling requirements in multiple fruit tree genotypes using Partial Least Squares regression: Prunus armeniaca L. case","authors":"Ana M. Muñoz-Morales, Germán Ortuño-Hernández, Juan Alfonso Salazar, Pedro Martínez-Gómez, Jose A. Egea, David Ruiz, Alvaro Delgado","doi":"10.1016/j.mex.2025.103686","DOIUrl":"10.1016/j.mex.2025.103686","url":null,"abstract":"<div><div>Accurate estimation of chilling requirements (CR) is essential for breeding and selecting temperate fruit trees adapted to specific agroclimatic conditions, particularly under global warming scenarios. Among the available methodologies to determine CR, the Partial Least Squares (PLS) regression procedure, based on long-term phenological and temperature records, offers a suitable approach to delineate the effective chill accumulation period. In this study, we present an R-based workflow developed using the agroclimatic functions integrated into the <em>chillR</em> package for R to determine the genotype-specific CR of 282 apricot (<em>Prunus armeniaca</em> L.) seedlings from two progenies grown in southwestern Spain. The pipeline generates standardized CR datasets suitable for downstream applications, including QTL mapping and the selection of promising genotypes for breeding purposes. This tool streamlines the estimation process, reducing the technical expertise and time required for CR estimation, thereby supporting efficient phenotypic selection and accelerating genetic research in temperate fruit trees. The complete code and associated datasets are freely available in a public repository (<span><span>https://github.com/CEBASFruitBreed/R-workflow-ChillPLS</span><svg><path></path></svg></span>), promoting the use across a range of temperate fruit species.<ul><li><span>•</span><span><div>Uses long-term flowering observations and temperature records to determine genotype-specific chilling requirements.</div></span></li><li><span>•</span><span><div>Integrates PLS regression procedure within an R-based workflow to estimate chilling requirements from datasets comprising multiple genotypes.</div></span></li><li><span>•</span><span><div>Generates standardized outputs suitable to support genetic analysis and informed breeding decisions.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103686"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design of an integrated model using deep reinforcement learning and Variational Autoencoders for enhanced quantum security 基于深度强化学习和变分自编码器的量子安全集成模型设计

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-12-01 Epub Date: 2025-06-21 DOI: 10.1016/j.mex.2025.103445

Harshala Shingne , Diptee Chikmurge , Priya Parkhi , Poorva Agrawal

The need for secure communication systems has driven extensive research into quantum-based security mechanisms, particularly Quantum Key Distribution (QKD). However, traditional QKD systems, within dynamic environments incorporating network fluctuation and attacks, have been relatively limited because static protocols cannot support high key generation rates and security. This work addresses these challenges by proposing the integration of AI and machine learning optimization techniques into quantum communication protocols to enhance both security and efficiency. We here propose three advanced models: first, Deep Reinforcement Learning is applied to adaptively optimize QKD protocols by dynamically adjusting the key generation parameters with respect to environmental conditions. In the state-of-the-art method, the DRL-based approach enlarges the secure key generation rate by 15–20 % and suppresses QBER 30–40 % under noisy conditions. A VAE is used for the detection of anomalies in quantum networks that effectively detects eavesdropping. By incorporating quantum-specific feature extraction and latent variable disentanglement, the VAE model detects attack detection accuracy of 85–90 % with a reduction of 25 % in false positives. Finally, it considers the optimization of cryptographic protocols in a distributed quantum network using Multi-Agent Deep Q-Networks. This multi-agent system strengthens both the security and computational efficiency by reducing attack vulnerabilities by 15–18 % and lowering the computational complexity by 20–25 %. In all, the integration of AI with machine learning methods brings far better enhancements in the field of quantum communication system security and efficiency, addressing critical limitations of conventional QKD systems and pointing to the way to more resilient adaptive quantum security solutions.

对安全通信系统的需求推动了对基于量子的安全机制的广泛研究，特别是量子密钥分发（QKD）。然而，在包含网络波动和攻击的动态环境中，传统的QKD系统相对有限，因为静态协议不能支持高密钥生成速率和安全性。这项工作通过提出将人工智能和机器学习优化技术集成到量子通信协议中来提高安全性和效率，从而解决了这些挑战。我们在此提出了三个先进的模型：首先，深度强化学习应用于根据环境条件动态调整密钥生成参数来自适应优化QKD协议。在最先进的方法中，基于drl的方法在噪声条件下将安全密钥生成率提高了15 - 20%，并抑制了30 - 40%的QBER。VAE用于检测量子网络中的异常，可以有效地检测窃听。通过结合量子特定特征提取和潜在变量解纠缠，VAE模型检测攻击检测准确率为85 - 90%，误报率降低25%。最后，研究了基于多智能体深度q网络的分布式量子网络加密协议优化问题。该多智能体系统将攻击漏洞减少15 - 18%，计算复杂度降低20 - 25%，提高了安全性和计算效率。总而言之，人工智能与机器学习方法的集成在量子通信系统的安全性和效率方面带来了更好的增强，解决了传统量子密钥分配系统的关键限制，并指出了更具弹性的自适应量子安全解决方案的道路。

{"title":"Design of an integrated model using deep reinforcement learning and Variational Autoencoders for enhanced quantum security","authors":"Harshala Shingne , Diptee Chikmurge , Priya Parkhi , Poorva Agrawal","doi":"10.1016/j.mex.2025.103445","DOIUrl":"10.1016/j.mex.2025.103445","url":null,"abstract":"<div><div>The need for secure communication systems has driven extensive research into quantum-based security mechanisms, particularly Quantum Key Distribution (QKD). However, traditional QKD systems, within dynamic environments incorporating network fluctuation and attacks, have been relatively limited because static protocols cannot support high key generation rates and security. This work addresses these challenges by proposing the integration of AI and machine learning optimization techniques into quantum communication protocols to enhance both security and efficiency. We here propose three advanced models: first, Deep Reinforcement Learning is applied to adaptively optimize QKD protocols by dynamically adjusting the key generation parameters with respect to environmental conditions. In the state-of-the-art method, the DRL-based approach enlarges the secure key generation rate by 15–20 % and suppresses QBER 30–40 % under noisy conditions. A VAE is used for the detection of anomalies in quantum networks that effectively detects eavesdropping. By incorporating quantum-specific feature extraction and latent variable disentanglement, the VAE model detects attack detection accuracy of 85–90 % with a reduction of 25 % in false positives. Finally, it considers the optimization of cryptographic protocols in a distributed quantum network using Multi-Agent Deep Q-Networks. This multi-agent system strengthens both the security and computational efficiency by reducing attack vulnerabilities by 15–18 % and lowering the computational complexity by 20–25 %. In all, the integration of AI with machine learning methods brings far better enhancements in the field of quantum communication system security and efficiency, addressing critical limitations of conventional QKD systems and pointing to the way to more resilient adaptive quantum security solutions.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"15 ","pages":"Article 103445"},"PeriodicalIF":1.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0