MethodsX最新文献_第5页

Resume data extract and job recruitment Chatbot features for AI-based resume screening & analytics 基于人工智能的简历筛选和分析的聊天机器人功能

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-17 DOI: 10.1016/j.mex.2025.103775

Kar Weng Chong, Kok Why Ng, Yong Hong Fu

AI technologies are changing the field of manpower recruitment since they make it much more efficient, accurate, and scalable than conventional approaches. The project builds an AI recruitment system that is combined to have two main elements of an integrated AI recruitment system including a Resume Screening AI and a Job Recruitment Chatbot, which have the goal of improving the process in hiring as well as making the experience of the candidates better in the process.

The Resume Screening AI uses a mixed approach incorporating both classical document processing, and capabilities of advanced language models. The unstructured data of raw resumes are mined and normalized into standard forms to allow evaluation and ranking of the candidates in an organized and systematic manner according to the position’s requirements. The Job Recruitment Chatbot entails a programmed chat system of interactive communication during the job recruitment procedure comprising the component of FAQ, conversation-based direction, and voice-to-text dynamic to make the system more accessible to a diverse group of users.

•
Document Processing Pipeline: Parsed all-format resumes by the means of PyPDF2 and python-docx libraries and programmed the data in a structured manner, via Google Gemini 1.5 Flash API and engineered special prompts to validate the set of JSON-Schema.
•
Intelligent Screening System: Created automated candidate screening based on (large language model) inference process to compare resume text with job requirements, producing relevance scores and classified evaluations.
•
Interactive Chatbot Development: Developed natural language processing AI interface with chat capabilities and with speech-to-text and FAQ automation that could be used to answer candidate questions and optimize the recruitment process.

人工智能技术正在改变人力招聘领域，因为它比传统方法更高效、更准确、更可扩展。该项目构建了一个人工智能招聘系统，该系统结合了集成人工智能招聘系统的两个主要元素，包括简历筛选人工智能和工作招聘聊天机器人，其目标是改善招聘过程，并使候选人在此过程中获得更好的体验。简历筛选人工智能使用了一种混合的方法，结合了传统的文档处理和高级语言模型的功能。对原始简历中的非结构化数据进行挖掘，并将其规范化为标准表格，以便根据职位要求，有组织、系统地对候选人进行评估和排名。工作招聘聊天机器人需要一个编程聊天系统，在工作招聘过程中进行互动交流，包括常见问题解答、基于对话的指导和语音到文本的动态，使系统更容易被不同群体的用户访问。•文档处理管道：通过PyPDF2和python-docx库解析所有格式的简历，并通过谷歌Gemini 1.5 Flash API以结构化方式编程数据，并设计特殊提示来验证JSON-Schema集。•智能筛选系统：创建基于（大型语言模型）推理过程的自动候选人筛选，将简历文本与工作要求进行比较，产生相关性分数和分类评估。•交互式聊天机器人开发：开发具有聊天功能的自然语言处理AI界面，具有语音转文本和FAQ自动化功能，可用于回答候选人问题并优化招聘流程。

{"title":"Resume data extract and job recruitment Chatbot features for AI-based resume screening & analytics","authors":"Kar Weng Chong, Kok Why Ng, Yong Hong Fu","doi":"10.1016/j.mex.2025.103775","DOIUrl":"10.1016/j.mex.2025.103775","url":null,"abstract":"<div><div>AI technologies are changing the field of manpower recruitment since they make it much more efficient, accurate, and scalable than conventional approaches. The project builds an AI recruitment system that is combined to have two main elements of an integrated AI recruitment system including a Resume Screening AI and a Job Recruitment Chatbot, which have the goal of improving the process in hiring as well as making the experience of the candidates better in the process.</div><div>The Resume Screening AI uses a mixed approach incorporating both classical document processing, and capabilities of advanced language models. The unstructured data of raw resumes are mined and normalized into standard forms to allow evaluation and ranking of the candidates in an organized and systematic manner according to the position’s requirements. The Job Recruitment Chatbot entails a programmed chat system of interactive communication during the job recruitment procedure comprising the component of FAQ, conversation-based direction, and voice-to-text dynamic to make the system more accessible to a diverse group of users.<ul><li><span>•</span><span><div><strong>Document Processing Pipeline</strong>: Parsed all-format resumes by the means of PyPDF2 and python-docx libraries and programmed the data in a structured manner, via Google Gemini 1.5 Flash API and engineered special prompts to validate the set of JSON-Schema.</div></span></li><li><span>•</span><span><div><strong>Intelligent Screening System</strong>: Created automated candidate screening based on (large language model) inference process to compare resume text with job requirements, producing relevance scores and classified evaluations.</div></span></li><li><span>•</span><span><div><strong>Interactive Chatbot Development</strong>: Developed natural language processing AI interface with chat capabilities and with speech-to-text and FAQ automation that could be used to answer candidate questions and optimize the recruitment process.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103775"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926466","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

Analyzing the mahakam river water quality using the geographically weighted panel regression model 利用地理加权面板回归模型分析玛哈干河水质

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-19 DOI: 10.1016/j.mex.2025.103773

Zabrina Nathania Fauziyah, Suyitno Suyitno, Darnah, Memi Nor Hayati, Meirinda Fauziyah

This study discusses the geographically weighted panel regression (GWPR) model. GWPR is an extension of geographically weighted regression model, designed for spatially heterogeneous panel data. In this study, GWPR model is applied to panel data on biochemical oxygen demand (BOD) in Mahakam River water 2022–2024. The model is estimated at each spatial location using a fixed effects model (FEM) as the global model, with temporal effects addressed through a demeaning transformation. All statistical analyses and spatial processing are conducted using R software, GNU Octave, QGIS, and Google Earth. This study aims to map factors influencing Mahakam River water BOD using GWPR model. The results indicate that GWPR outperforms FEM, with AIC = -60.6419,

R^{2} = 80.321 %

, and root mean square error of 0.7122. The factors influencing BOD include temperature, water pH, color degree, nitrate, ammonia, total suspended solids, and sulfate.

•
We present a GWPR model using FEM as global model, applied to the spatially heterogeneous panel data, namely demeaned Mahakam River water BOD data 2022–2024.
•
The mapping of factors influencing BOD is analyzed locally using GWPR model.
•
The optimal adaptive bandwidth is determined using Akaike Information Criterion, and model goodness-of-fit is evaluated using the coefficient of determination and root mean square error.

本研究探讨地理加权面板回归（GWPR）模型。GWPR是对地理加权回归模型的扩展，是针对空间异质性面板数据而设计的。本研究将GWPR模型应用于2022-2024年Mahakam河水体生化需氧量（BOD）面板数据。该模型在每个空间位置使用固定效应模型（FEM）作为全局模型进行估计，并通过降级转换处理时间效应。所有的统计分析和空间处理使用R软件、GNU Octave、QGIS和谷歌Earth进行。本研究旨在利用GWPR模型绘制马哈坎河水BOD的影响因子。结果表明，GWPR优于FEM， AIC = -60.6419, R2=80.321%，均方根误差为0.7122。影响BOD的因素包括温度、水pH、色度、硝酸盐、氨、总悬浮物和硫酸盐。•我们提出了一个GWPR模型，将FEM作为全球模型，应用于空间异质性面板数据，即2022-2024年Mahakam河水BOD数据。•利用GWPR模型局部分析了BOD影响因素的映射。•使用赤池信息准则确定最优自适应带宽，使用决定系数和均方根误差评估模型的拟合优度。

{"title":"Analyzing the mahakam river water quality using the geographically weighted panel regression model","authors":"Zabrina Nathania Fauziyah, Suyitno Suyitno, Darnah, Memi Nor Hayati, Meirinda Fauziyah","doi":"10.1016/j.mex.2025.103773","DOIUrl":"10.1016/j.mex.2025.103773","url":null,"abstract":"<div><div>This study discusses the geographically weighted panel regression (GWPR) model. GWPR is an extension of geographically weighted regression model, designed for spatially heterogeneous panel data. In this study, GWPR model is applied to panel data on biochemical oxygen demand (BOD) in Mahakam River water 2022–2024. The model is estimated at each spatial location using a fixed effects model (FEM) as the global model, with temporal effects addressed through a demeaning transformation. All statistical analyses and spatial processing are conducted using R software, GNU Octave, QGIS, and Google Earth. This study aims to map factors influencing Mahakam River water BOD using GWPR model. The results indicate that GWPR outperforms FEM, with AIC = -60.6419, <span><math><mrow><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup><mo>=</mo><mn>80.321</mn><mo>%</mo></mrow></math></span>, and root mean square error of 0.7122. The factors influencing BOD include temperature, water pH, color degree, nitrate, ammonia, total suspended solids, and sulfate.<ul><li><span>•</span><span><div><em>We present a GWPR model using FEM as global model, applied to the spatially heterogeneous panel data, namely demeaned Mahakam River water BOD data 2022–2024.</em></div></span></li><li><span>•</span><span><div><em>The mapping of factors influencing BOD is analyzed locally using GWPR model.</em></div></span></li><li><span>•</span><span><div><em>The optimal adaptive bandwidth is determined using Akaike Information Criterion, and model goodness-of-fit is evaluated using the coefficient of determination and root mean square error.</em></div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103773"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977396","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

Real-time vehicle control via edge cloud sensor fusion and CNN based perceptron 基于边缘云传感器融合和CNN感知器的实时车辆控制

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-24 DOI: 10.1016/j.mex.2025.103779

Sumukh Chaurasia , Parambrata Sanyal , Gagandeep Kaur , Satvik Barhanpure , Kshitij Bhele , Amol D. Wable , Suhashini Awadhesh Chaurasia , Rutuja Rajendra Patil , Devika Verma

Reliable real-time vehicle control is essential for intelligent transport systems where accurate perception and decision-making depend on fast sensor data processing. This study developed a hybrid edge–cloud method integrating deep learning with Internet of Things (IoT) sensor fusion for adaptive vehicle control. Ultrasonic range data were combined with convolutional neural networks (CNNs) to enable object detection, stopping-time prediction, and braking control under varying environmental conditions. The CNN-based model was trained and evaluated under normal and simulated adverse driving scenarios. Results indicated strong performance with R² = 0.99 under normal and 0.98 under adverse conditions, and a mean squared error (MSE) of 0.0085. Average inference latency is 110–116 ms on Jetson Nano and 210–230 ms on Raspberry Pi, confirming suitability for real-time deployment on edge hardware.

The hybrid edge–cloud method enables adaptive, real-time vehicle control through IoT sensor fusion.

CNN-based perception enhances prediction accuracy and operational safety under variable driving conditions.

Demonstrates feasibility of deep learning deployment on low-cost edge devices for intelligent transport applications.

Thus, integrating deep learning with IoT-enabled sensors on an edge–cloud platform provides a reliable and scalable pathway toward safe, adaptive, and efficient vehicle control in intelligent transportation systems.

可靠的实时车辆控制对于智能交通系统至关重要，因为智能交通系统的准确感知和决策依赖于快速的传感器数据处理。本研究开发了一种融合深度学习和物联网传感器融合的混合边缘云方法，用于自适应车辆控制。超声波距离数据与卷积神经网络（cnn）相结合，实现了不同环境条件下的目标检测、停车时间预测和制动控制。基于cnn的模型在正常和模拟的不良驾驶场景下进行训练和评估。结果表明，在正常条件下R²= 0.99，在不良条件下R²= 0.98，均方误差（MSE）为0.0085。Jetson Nano上的平均推理延迟为110-116毫秒，Raspberry Pi上的平均推理延迟为210-230毫秒，证实了在边缘硬件上实时部署的适用性。混合边缘云方法通过物联网传感器融合实现自适应实时车辆控制。基于cnn的感知增强了在可变驾驶条件下的预测精度和操作安全性。展示了深度学习在智能交通应用的低成本边缘设备上部署的可行性。因此，将深度学习与支持物联网的传感器集成在边缘云平台上，为智能交通系统中的安全、自适应和高效车辆控制提供了可靠且可扩展的途径。

{"title":"Real-time vehicle control via edge cloud sensor fusion and CNN based perceptron","authors":"Sumukh Chaurasia , Parambrata Sanyal , Gagandeep Kaur , Satvik Barhanpure , Kshitij Bhele , Amol D. Wable , Suhashini Awadhesh Chaurasia , Rutuja Rajendra Patil , Devika Verma","doi":"10.1016/j.mex.2025.103779","DOIUrl":"10.1016/j.mex.2025.103779","url":null,"abstract":"<div><div>Reliable real-time vehicle control is essential for intelligent transport systems where accurate perception and decision-making depend on fast sensor data processing. This study developed a hybrid edge–cloud method integrating deep learning with Internet of Things (IoT) sensor fusion for adaptive vehicle control. Ultrasonic range data were combined with convolutional neural networks (CNNs) to enable object detection, stopping-time prediction, and braking control under varying environmental conditions. The CNN-based model was trained and evaluated under normal and simulated adverse driving scenarios. Results indicated strong performance with R² = 0.99 under normal and 0.98 under adverse conditions, and a mean squared error (MSE) of 0.0085. Average inference latency is 110–116 ms on Jetson Nano and 210–230 ms on Raspberry Pi, confirming suitability for real-time deployment on edge hardware.</div><div>The hybrid edge–cloud method enables adaptive, real-time vehicle control through IoT sensor fusion.</div><div>CNN-based perception enhances prediction accuracy and operational safety under variable driving conditions.</div><div>Demonstrates feasibility of deep learning deployment on low-cost edge devices for intelligent transport applications.</div><div>Thus, integrating deep learning with IoT-enabled sensors on an edge–cloud platform provides a reliable and scalable pathway toward safe, adaptive, and efficient vehicle control in intelligent transportation systems.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103779"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977503","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

An accessible HPLC-DAD method for the direct detection of acrolein-trapping compounds in complex plant matrices 直接检测复杂植物基质中丙烯醛捕获化合物的高效液相色谱- dad方法

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-03 DOI: 10.1016/j.mex.2025.103747

Andy Zedet , Alison Aebischer , Marc Pudlo , Luca Marchisio , Samba Fama Ndoye , Corine Girard , François Senejoux

Acrolein is a highly reactive α,β-unsaturated aldehyde implicated in numerous diseases and pathological conditions. Developing strategies to alleviate its harmful effects is thus of key importance, with scavengers that trap acrolein emerging as a promising approach. Recent efforts have focused on identifying effective phytoconstituents, but detecting active components in complex plant matrices remains a challenging and time-consuming task. This study introduces a new application of HPLC-DAD for the instantaneous detection of acrolein scavengers in such complex extracts. To mimic this chemical diversity and test the method’s efficiency, a multicomponent mixture of ten phytochemical standards was employed. The procedure involved pre-column incubation of the mixture with varying concentrations of acrolein, allowing for the selective identification of active components through signal reduction. The results were further validated through conventional evaluation of individual constituents, confirming the method's reliability.

•
Development of a novel application of HPLC-DAD for the instantaneous detection of acrolein-trapping constituents in complex plant matrices
•
Application of the method to a ten-phytoconstituent mixture designed to simulate the chemical complexity of a plant extract
•
Validation of method efficiency through comparison with conventional scavenging evaluations of individual compounds

丙烯醛是一种高活性的α，β-不饱和醛，与许多疾病和病理状况有关。因此，制定减轻其有害影响的策略至关重要，捕集丙烯醛的清除剂正在成为一种有前途的方法。最近的努力集中在鉴定有效的植物成分，但检测复杂植物基质中的有效成分仍然是一项具有挑战性和耗时的任务。本研究介绍了HPLC-DAD快速检测此类复杂提取物中丙烯醛清除剂的新应用。为了模拟这种化学多样性并测试方法的效率，采用了十种植物化学标准的多组分混合物。该程序包括柱前孵育的混合物与不同浓度的丙烯醛，允许选择性识别活性成分通过信号还原。通过对单个成分的常规评价进一步验证了结果，证实了该方法的可靠性。•开发一种新的HPLC-DAD应用于复杂植物基质中丙烯醛捕获成分的瞬时检测•将该方法应用于十种植物成分混合物，旨在模拟植物提取物的化学复杂性•通过与传统的单个化合物清除评估的比较验证方法效率

{"title":"An accessible HPLC-DAD method for the direct detection of acrolein-trapping compounds in complex plant matrices","authors":"Andy Zedet , Alison Aebischer , Marc Pudlo , Luca Marchisio , Samba Fama Ndoye , Corine Girard , François Senejoux","doi":"10.1016/j.mex.2025.103747","DOIUrl":"10.1016/j.mex.2025.103747","url":null,"abstract":"<div><div>Acrolein is a highly reactive α,β-unsaturated aldehyde implicated in numerous diseases and pathological conditions. Developing strategies to alleviate its harmful effects is thus of key importance, with scavengers that trap acrolein emerging as a promising approach. Recent efforts have focused on identifying effective phytoconstituents, but detecting active components in complex plant matrices remains a challenging and time-consuming task. This study introduces a new application of HPLC-DAD for the instantaneous detection of acrolein scavengers in such complex extracts. To mimic this chemical diversity and test the method’s efficiency, a multicomponent mixture of ten phytochemical standards was employed. The procedure involved pre-column incubation of the mixture with varying concentrations of acrolein, allowing for the selective identification of active components through signal reduction. The results were further validated through conventional evaluation of individual constituents, confirming the method's reliability.<ul><li><span>•</span><span><div>Development of a novel application of HPLC-DAD for the instantaneous detection of acrolein-trapping constituents in complex plant matrices</div></span></li><li><span>•</span><span><div>Application of the method to a ten-phytoconstituent mixture designed to simulate the chemical complexity of a plant extract</div></span></li><li><span>•</span><span><div>Validation of method efficiency through comparison with conventional scavenging evaluations of individual compounds</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103747"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749535","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 statistical inference framework for FSNBLR: Modeling underdeveloped regional status in Eastern Indonesia FSNBLR的统计推断框架：模拟印尼东部欠发达地区状况

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-01 DOI: 10.1016/j.mex.2025.103746

Muhammad Zulfadhli, I Nyoman Budiantara, Vita Ratnasari, Afiqah Saffa Suriaslan, Risdiana Chandra Dhewy

Persistent regional disparities in Indonesia, particularly in Eastern provinces, necessitate advanced modeling to understand underdevelopment determinants. This study enhances the Fourier Series Nonparametric Binary Logistic Regression (FSNBLR) model by introducing a statistical inference framework comprising simultaneous and partial hypothesis testing using the Likelihood Ratio Test (LRT). Applying the model to data from 232 regencies in Eastern Indonesia (2021) identifies infrastructure quality and local fiscal capacity as significant predictors of underdevelopment. Compared with the conventional Binary Logistic Regression (BLR), the FSNBLR with significant parameters demonstrates superior classification accuracy and lower AIC values, effectively capturing nonlinear relationships among predictors. The proposed framework strengthens the inferential foundation of FSNBLR and broadens its applicability to complex binary response analyses in socioeconomic studies. The highlights of this study are:

Developed inferential hypothesis testing for the FSNBLR model.

Implemented LRT for simultaneous and partial inference.

The FSNBLR model outperforms BLR model in capturing nonlinearities.

印度尼西亚持续存在的地区差异，特别是在东部省份，需要先进的模型来理解不发达的决定因素。本研究通过引入一个统计推断框架，包括使用似然比检验（LRT）的同时和部分假设检验，增强了傅立叶级数非参数二元逻辑回归（FSNBLR）模型。将该模型应用于印度尼西亚东部232个县（2021年）的数据，发现基础设施质量和地方财政能力是不发达的重要预测因素。与传统的二元逻辑回归（BLR）相比，具有显著参数的FSNBLR具有更高的分类精度和更低的AIC值，可以有效地捕捉预测因子之间的非线性关系。该框架加强了FSNBLR的推理基础，拓宽了其在社会经济研究中复杂二元响应分析的适用性。本研究的重点是：建立了FSNBLR模型的推理假设检验。实现LRT同时和部分推理。FSNBLR模型在捕获非线性方面优于BLR模型。

{"title":"A statistical inference framework for FSNBLR: Modeling underdeveloped regional status in Eastern Indonesia","authors":"Muhammad Zulfadhli, I Nyoman Budiantara, Vita Ratnasari, Afiqah Saffa Suriaslan, Risdiana Chandra Dhewy","doi":"10.1016/j.mex.2025.103746","DOIUrl":"10.1016/j.mex.2025.103746","url":null,"abstract":"<div><div>Persistent regional disparities in Indonesia, particularly in Eastern provinces, necessitate advanced modeling to understand underdevelopment determinants. This study enhances the Fourier Series Nonparametric Binary Logistic Regression (FSNBLR) model by introducing a statistical inference framework comprising simultaneous and partial hypothesis testing using the Likelihood Ratio Test (LRT). Applying the model to data from 232 regencies in Eastern Indonesia (2021) identifies infrastructure quality and local fiscal capacity as significant predictors of underdevelopment. Compared with the conventional Binary Logistic Regression (BLR), the FSNBLR with significant parameters demonstrates superior classification accuracy and lower AIC values, effectively capturing nonlinear relationships among predictors. The proposed framework strengthens the inferential foundation of FSNBLR and broadens its applicability to complex binary response analyses in socioeconomic studies. The highlights of this study are:</div><div>Developed inferential hypothesis testing for the FSNBLR model.</div><div>Implemented LRT for simultaneous and partial inference.</div><div>The FSNBLR model outperforms BLR model in capturing nonlinearities.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103746"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749542","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

YOLO-AVCA-CBAMNet: Attention-driven framework for detection and classification of green pepper maturity stages YOLO-AVCA-CBAMNet：青椒成熟期检测与分类的注意驱动框架

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2026-01-08 DOI: 10.1016/j.mex.2026.103784

Bipin Nair B J, Abrav Nanda K M, V Raghavendra

Accurate identification of pepper berry maturity is essential for ensuring optimal harvest timing and maintaining quality standards in spice production. This study proposes “YOLO-AVCA-CBAMNet” an integrated detection-and-classification framework designed to operate effectively under natural field conditions. A self-collected dataset of pepper berries, captured using a smartphone across diverse illumination settings and background complexities, forms the basis of the evaluation. The pipeline first applies YOLOv8 to detect individual berries within cluttered scenes. The extracted regions are then classified using convolutional neural networks enhanced with two complementary attention mechanisms. The Adaptive Visual Cortex Attention Module (AVCAM) strengthens global contextual weighting by adaptively recalibrating salient features, while the Convolutional Block Attention Module (CBAM) improves spatial and channel-specific discrimination through sequential attention refinement. This dual-attention design enables more reliable separation of visually similar maturity stages. Experimental results indicate accuracy gains of 5–9 % across all backbone architectures, with the DenseNet121-based configuration achieving a peak accuracy of 96.19 %. The findings demonstrate the potential of attention-driven models to support interpretable, efficient, and scalable maturity assessment solutions in precision agriculture.

•
Developed an end-to-end framework “YOLO-AVCA-CBAMNet” integrating object detection and attention-driven classification for pepper maturity assessment in natural field conditions.
•
Employed a field-derived image dataset of pepper berries collected under naturally varying illumination and environmental conditions, thereby supporting the ecological validity and practical relevance of the proposed maturity assessment approach.
•
Incorporated complementary attention mechanisms—AVCAM to enhance global contextual representation and CBAM to refine spatial and channel-specific feature responses—thereby improving discrimination among visually similar maturity stages.

在香料生产中，准确识别胡椒浆果成熟度对于确保最佳采收时机和保持质量标准至关重要。本研究提出了“YOLO-AVCA-CBAMNet”，这是一个集成的检测和分类框架，旨在有效地在自然野外条件下运行。使用智能手机在不同的照明设置和复杂的背景下拍摄辣椒浆果的自我收集数据集，形成了评估的基础。流水线首先应用YOLOv8来检测杂乱场景中的单个浆果。然后使用卷积神经网络对提取的区域进行分类，卷积神经网络增强了两种互补的注意机制。自适应视觉皮层注意模块（AVCAM）通过自适应重新校准显著特征来增强全局上下文权重，而卷积块注意模块（CBAM）通过顺序注意细化来提高空间和通道特异性区分。这种双重注意设计使视觉上相似的成熟阶段的分离更加可靠。实验结果表明，在所有主干架构中，准确率提高了5 - 9%，其中基于densenet121的配置达到了96.19%的峰值准确率。研究结果表明，注意力驱动模型在支持精准农业中可解释、高效和可扩展的成熟度评估解决方案方面具有潜力。•开发了一个端到端框架“YOLO-AVCA-CBAMNet”，集成了目标检测和注意力驱动分类，用于自然田间条件下的辣椒成熟度评估。•采用在自然变化的光照和环境条件下采集的辣椒浆果的现场衍生图像数据集，从而支持所提出的成熟度评估方法的生态有效性和实际相关性。•整合互补注意机制——avcam增强全局上下文表示，CBAM细化空间和渠道特定特征反应——从而提高视觉相似成熟阶段之间的辨别能力。

{"title":"YOLO-AVCA-CBAMNet: Attention-driven framework for detection and classification of green pepper maturity stages","authors":"Bipin Nair B J, Abrav Nanda K M, V Raghavendra","doi":"10.1016/j.mex.2026.103784","DOIUrl":"10.1016/j.mex.2026.103784","url":null,"abstract":"<div><div>Accurate identification of pepper berry maturity is essential for ensuring optimal harvest timing and maintaining quality standards in spice production. This study proposes “<strong>YOLO-AVCA-CBAMNet”</strong> an integrated detection-and-classification framework designed to operate effectively under natural field conditions. A self-collected dataset of pepper berries, captured using a smartphone across diverse illumination settings and background complexities, forms the basis of the evaluation. The pipeline first applies YOLOv8 to detect individual berries within cluttered scenes. The extracted regions are then classified using convolutional neural networks enhanced with two complementary attention mechanisms. The <strong>Adaptive Visual Cortex Attention Module (AVCAM)</strong> strengthens global contextual weighting by adaptively recalibrating salient features, while the <strong>Convolutional Block Attention Module (CBAM)</strong> improves spatial and channel-specific discrimination through sequential attention refinement. This dual-attention design enables more reliable separation of visually similar maturity stages. Experimental results indicate accuracy gains of <strong>5–9</strong> <strong>%</strong> across all backbone architectures, with the DenseNet121-based configuration achieving a peak accuracy of <strong>96.19</strong> <strong>%</strong>. The findings demonstrate the potential of attention-driven models to support interpretable, efficient, and scalable maturity assessment solutions in precision agriculture.<ul><li><span>•</span><span><div>Developed an end-to-end framework “YOLO-AVCA-CBAMNet” integrating object detection and attention-driven classification for pepper maturity assessment in natural field conditions.</div></span></li><li><span>•</span><span><div>Employed a field-derived image dataset of pepper berries collected under naturally varying illumination and environmental conditions, thereby supporting the ecological validity and practical relevance of the proposed maturity assessment approach.</div></span></li><li><span>•</span><span><div>Incorporated complementary attention mechanisms—AVCAM to enhance global contextual representation and CBAM to refine spatial and channel-specific feature responses—thereby improving discrimination among visually similar maturity stages.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103784"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977502","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

Actor-critic guided CDBN with GAN augmentation for robust facial emotion recognition 演员评论家引导的GAN增强CDBN鲁棒性面部情绪识别

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-17 DOI: 10.1016/j.mex.2025.103774

Akshay S , Jnana Sai S R , Sinchana B R , Kannan M , Adwitiya Mukhopadhyay

Facial emotion recognition (FER) remains challenging under limited data, noise, and occlusion. This study introduces an Actor–Critic Convolutional Deep Belief Network (ACCDBN) that unifies Generative Adversarial Network (GAN)–based augmentation, deep probabilistic feature learning, and reinforcement-driven optimization. Conditional GANs expand minority emotion classes, enhancing data diversity, while the CDBN extracts hierarchical texture features through convolutional and restricted Boltzmann layers. An Actor–Critic module dynamically refines representations by rewarding accurate emotion classification and penalizing uncertain predictions. Trained and validated on the CK+ dataset with five-fold cross-validation, the proposed model achieves higher accuracy and stability than CNN, LSTM, and ResNet-50 baselines, maintaining strong performance under noise and occlusion. The approach demonstrates how reinforcement-guided generative learning can improve both accuracy and robustness in FER tasks.

1. To implement this, the research utilised the publicly available Cohn-Kanade+ dataset, consisting of eight classes with samples of 920 grey-scale images.

2. An improved ACCDBN model outperformed with 90.4% accuracy and 0.69 MCC (Mathew’s Correlation Coefficient) in 5-fold cross-validation using the cGAN-generated dataset and 87% on the CK+ dataset

3. The main objective is to present an advanced facial emotion recognition (FER) system that combines a Convolution Deep Belief Network (CDBN) with a model-free reinforcement learning technique, namely the actor-critic approach.

面部情绪识别（FER）在有限的数据、噪声和遮挡下仍然具有挑战性。本研究引入了一种Actor-Critic卷积深度信念网络（ACCDBN），该网络将基于生成对抗网络（GAN）的增强、深度概率特征学习和强化驱动优化相结合。条件gan扩展了少数情感类，增强了数据多样性，而CDBN通过卷积和受限玻尔兹曼层提取分层纹理特征。演员-评论家模块通过奖励准确的情绪分类和惩罚不确定的预测来动态地改进表征。在CK+数据集上进行5倍交叉验证，该模型比CNN、LSTM和ResNet-50基线具有更高的准确率和稳定性，在噪声和遮挡下保持了较强的性能。该方法展示了强化引导的生成学习如何提高FER任务的准确性和鲁棒性。为了实现这一目标，该研究利用了公开可用的Cohn-Kanade+数据集，该数据集由8个类别和920个灰度图像样本组成。改进的ACCDBN模型在使用cgan生成的数据集的5倍交叉验证中表现出90.4%的准确率和0.69的MCC（马修相关系数），在CK+数据集上表现为87%。主要目标是提出一种先进的面部情绪识别（FER）系统，该系统将卷积深度信念网络（CDBN）与无模型强化学习技术（即演员批评方法）相结合。

{"title":"Actor-critic guided CDBN with GAN augmentation for robust facial emotion recognition","authors":"Akshay S , Jnana Sai S R , Sinchana B R , Kannan M , Adwitiya Mukhopadhyay","doi":"10.1016/j.mex.2025.103774","DOIUrl":"10.1016/j.mex.2025.103774","url":null,"abstract":"<div><div>Facial emotion recognition (FER) remains challenging under limited data, noise, and occlusion. This study introduces an <strong>Actor–Critic Convolutional Deep Belief Network (ACCDBN)</strong> that unifies Generative Adversarial Network (GAN)–based augmentation, deep probabilistic feature learning, and reinforcement-driven optimization. Conditional GANs expand minority emotion classes, enhancing data diversity, while the CDBN extracts hierarchical texture features through convolutional and restricted Boltzmann layers. An Actor–Critic module dynamically refines representations by rewarding accurate emotion classification and penalizing uncertain predictions. Trained and validated on the CK+ dataset with five-fold cross-validation, the proposed model achieves higher accuracy and stability than CNN, LSTM, and ResNet-50 baselines, maintaining strong performance under noise and occlusion. The approach demonstrates how reinforcement-guided generative learning can improve both accuracy and robustness in FER tasks.</div><div>1. To implement this, the research utilised the publicly available Cohn-Kanade+ dataset, consisting of eight classes with samples of 920 grey-scale images.</div><div>2. An improved ACCDBN model outperformed with 90.4% accuracy and 0.69 MCC (Mathew’s Correlation Coefficient) in 5-fold cross-validation using the cGAN-generated dataset and 87% on the CK+ dataset</div><div>3. The main objective is to present an advanced facial emotion recognition (FER) system that combines a Convolution Deep Belief Network (CDBN) with a model-free reinforcement learning technique, namely the actor-critic approach.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103774"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926349","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 estimating discharge, hydraulic depth, and mean velocity in rivers through spatial interpolation of at-a-station hydraulic geometry in data- scarce regions 在数据匮乏地区，通过站内水力几何空间插值估计河流流量、水力深度和平均流速的方法

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2026-01-24 DOI: 10.1016/j.mex.2026.103804

Eduardo Zamudio-Huertas , César Augusto García-Ubaque , Nelson Obregón-Neira

Reliable discharge estimation is essential for water resource management, yet many regions lack sufficient hydrological stations. To address this limitation, we propose the Spatial Hydraulic Geometry Interpolation (SHGI) method, which estimates discharge (Q), hydraulic depth (D), and mean velocity (V) from river width (W) obtained via surveys or satellite imagery. SHGI integrates hydraulic geometry theory with multiquadric radial basis interpolation, applied to the Meta and Atrato river basins in Colombia. Parameters of at‑station hydraulic geometry (coefficients

a

, c, k and exponents b, f, m) were derived using least squares and transformed into log‑ratio space to preserve their compositional constraints. Interpolation along upstream distance ensures spatial continuity, and closure operations guarantee internal consistency. Validation against observed data in basins with contrasting geomorphology and data density confirmed the method’s robustness.

The principal contributions of SHGI are:

•
Longitudinal continuity: explicit incorporation of upstream distance to interpolate parameters consistently along channels and tributaries.
•
Compositional integrity: preservation of the multiplicative and additive constraints of hydraulic geometry parameters during interpolation.
•
Estimation under data scarcity: enabling calculation of Q, D, and V at ungauged sites using only river width.

可靠的流量估算对水资源管理至关重要，但许多地区缺乏足够的水文站。为了解决这一限制，我们提出了空间水力几何插值（SHGI）方法，该方法根据通过调查或卫星图像获得的河流宽度(W)估算流量(Q)、水力深度(D)和平均流速(V)。SHGI将水力几何理论与多二次径向基插值相结合，应用于哥伦比亚的Meta和atratto河流域。利用最小二乘法推导了站内水力几何参数（系数a、c、k和指数b、f、m），并将其转换为对数比空间，以保持其组成约束。沿上游距离插值确保空间连续性，闭包操作保证内部一致性。对具有不同地貌和数据密度的盆地观测数据的验证证实了该方法的鲁棒性。SHGI的主要贡献是：•纵向连续性：明确纳入上游距离，以便沿河道和支流一致地插值参数。•组成完整性：在插值过程中保留水力几何参数的乘法和加法约束。•数据稀缺下的估计：仅使用河流宽度在未测量的地点计算Q， D和V。

{"title":"Method for estimating discharge, hydraulic depth, and mean velocity in rivers through spatial interpolation of at-a-station hydraulic geometry in data- scarce regions","authors":"Eduardo Zamudio-Huertas , César Augusto García-Ubaque , Nelson Obregón-Neira","doi":"10.1016/j.mex.2026.103804","DOIUrl":"10.1016/j.mex.2026.103804","url":null,"abstract":"<div><div>Reliable discharge estimation is essential for water resource management, yet many regions lack sufficient hydrological stations. To address this limitation, we propose the Spatial Hydraulic Geometry Interpolation (SHGI) method, which estimates discharge (Q), hydraulic depth (D), and mean velocity (V) from river width (W) obtained via surveys or satellite imagery. SHGI integrates hydraulic geometry theory with multiquadric radial basis interpolation, applied to the Meta and Atrato river basins in Colombia. Parameters of at‑station hydraulic geometry (coefficients <span><math><mi>a</mi></math></span>, <em>c, k</em> and exponents <em>b, f, m</em>) were derived using least squares and transformed into log‑ratio space to preserve their compositional constraints. Interpolation along upstream distance ensures spatial continuity, and closure operations guarantee internal consistency. Validation against observed data in basins with contrasting geomorphology and data density confirmed the method’s robustness.</div><div>The principal contributions of SHGI are:<ul><li><span>•</span><span><div>Longitudinal continuity: explicit incorporation of upstream distance to interpolate parameters consistently along channels and tributaries.</div></span></li><li><span>•</span><span><div>Compositional integrity: preservation of the multiplicative and additive constraints of hydraulic geometry parameters during interpolation.</div></span></li><li><span>•</span><span><div>Estimation under data scarcity: enabling calculation of Q, D, and V at ungauged sites using only river width.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103804"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077547","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

Application of a thermoelectric cooling approach for localized hypothermia in a murine model 热电冷却方法在小鼠模型局部低温治疗中的应用

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2025-12-09 DOI: 10.1016/j.mex.2025.103754

Kosala D. Waduthanthri , Gregory S. Korbutt , Andrew R. Pepper , Larry D. Unsworth

Achieving localized and adjustable hypothermia is critical for various clinical and experimental applications, including reducing oxidative stress, modulating inflammatory responses, and enabling temperature-triggered drug delivery. However, existing cooling techniques such as ice packs, and cryogenic sprays limitations in precision, efficiency, duration, and cooling capacity. In this study, we used a commercially available thermoelectric cooling module to construct a simple and low-cost cooling system, and applied it in a preclinical mouse model to achieve focal hypothermia at a subcutaneous transplant site.

•
The system, assembled using a TES1–4903 thermoelectric module, a heat sink, and a power supply, achieved rapid temperature reduction rates. At 5 V, the subcutaneous temperature decreased at an average rate of ∼1.5 °C/s during the first 10 s, reaching a stable temperature of ∼8 °C within 120 s. At 2 V, the average rate was ∼0.4 °C/s, stabilizing at ∼17 °C over the same period.
•
The system demonstrated precise temperature control with minimal variability, maintaining temperature steps of <2 °C and ensuring a stable temperature range.
•
Compared to literature, our system highlights the utility of thermoelectric modules for biomedical cooling applications, demonstrating faster and safer subcutaneous hypothermia with more precise temperature control than other approaches.

实现局部和可调节的低温对于各种临床和实验应用至关重要，包括减少氧化应激，调节炎症反应，以及实现温度触发的药物递送。然而，现有的冷却技术，如冰袋和低温喷雾，在精度、效率、持续时间和冷却能力方面存在局限性。在本研究中，我们使用市售的热电冷却模块构建了一个简单、低成本的冷却系统，并将其应用于临床前小鼠模型，实现皮下移植部位的局灶性低温。•该系统使用TES1-4903热电模块、散热器和电源组装，实现了快速降温速率。在5 V下，皮下温度在前10 s内以平均~ 1.5°C/s的速度下降，在120 s内达到稳定的~ 8°C。在2 V时，平均速率为~ 0.4°C/s，在相同的时间内稳定在~ 17°C。•该系统具有精确的温度控制，最小的变化，保持温度步长为<；2°C，并确保稳定的温度范围。•与文献相比，我们的系统突出了热电模块在生物医学冷却应用中的实用性，展示了比其他方法更快，更安全的皮下低温，更精确的温度控制。

{"title":"Application of a thermoelectric cooling approach for localized hypothermia in a murine model","authors":"Kosala D. Waduthanthri , Gregory S. Korbutt , Andrew R. Pepper , Larry D. Unsworth","doi":"10.1016/j.mex.2025.103754","DOIUrl":"10.1016/j.mex.2025.103754","url":null,"abstract":"<div><div>Achieving localized and adjustable hypothermia is critical for various clinical and experimental applications, including reducing oxidative stress, modulating inflammatory responses, and enabling temperature-triggered drug delivery. However, existing cooling techniques such as ice packs, and cryogenic sprays limitations in precision, efficiency, duration, and cooling capacity. In this study, we used a commercially available thermoelectric cooling module to construct a simple and low-cost cooling system, and applied it in a preclinical mouse model to achieve focal hypothermia at a subcutaneous transplant site.<ul><li><span>•</span><span><div>The system, assembled using a TES1–4903 thermoelectric module, a heat sink, and a power supply, achieved rapid temperature reduction rates. At 5 V, the subcutaneous temperature decreased at an average rate of ∼1.5 °C/s during the first 10 s, reaching a stable temperature of ∼8 °C within 120 s. At 2 V, the average rate was ∼0.4 °C/s, stabilizing at ∼17 °C over the same period.</div></span></li><li><span>•</span><span><div>The system demonstrated precise temperature control with minimal variability, maintaining temperature steps of <2 °C and ensuring a stable temperature range.</div></span></li><li><span>•</span><span><div>Compared to literature, our system highlights the utility of thermoelectric modules for biomedical cooling applications, demonstrating faster and safer subcutaneous hypothermia with more precise temperature control than other approaches.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103754"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749538","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

Random vs. blocked perturbation training on reactive balance control in peripheral neuropathy: A protocol study for a randomized controlled trial 随机与阻断扰动训练对周围神经病变反应性平衡控制的影响：一项随机对照试验的方案研究

IF 1.9 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2026-06-01 Epub Date: 2026-01-12 DOI: 10.1016/j.mex.2026.103796

Razieh Javadian Kootenayi , Razieh Mofateh , Mehrnoosh Zakerkish , Neda Orakifar , Saeideh Monjezi , Mohammad Mehravar , Maryam Seyedtabib

Diabetic peripheral neuropathy (DPN) is the leading cause of disturbances in reactive balance control. The repeated, external mechanical perturbations in perturbation-based balance training(PBBT) evoke balance recovery strategies; which subsequently improve reactive balance performance. Using the practice schedule concept of motor learning in the design of PBBT is a relatively new approach related to balance exercises. This study aims to investigate the effects of blocked and random PBBT on reactive balance control and its persistency and transfer to conditions different from those experienced during training.

Individuals with DPN will be recruited and randomly allocated to one of the three groups: random, blocked, and control group. Random and blocked PBBT groups will receive single-session balance training, including unexpected perturbations of platform during quiet standing in two directions (anterior and posterior), and three difficulty levels of platform motion (displacement, velocity, and acceleration). Each balance perturbation in blocked group will be repeated over blocks of four trials. For the random group, perturbation sequence will be unpredictable for these four trials in each block. Primary outcomes (i.e., center of pressure variables, reaction time, movement time, and total response time variables) will be assessed at baseline as well as immediately and one day after intervention.

糖尿病周围神经病变（DPN）是反应性平衡控制紊乱的主要原因。在基于扰动的平衡训练（PBBT）中，重复的外部机械扰动唤起平衡恢复策略；从而提高反应性平衡性能。在PBBT的设计中运用运动学习的练习计划概念是一种相对较新的与平衡训练相关的方法。本研究旨在探讨阻断和随机PBBT对反应性平衡控制的影响及其持续性和转移到不同于训练时所经历的条件。将招募患有DPN的个体并随机分配到三组中的一组：随机组、阻塞组和对照组。随机和阻塞的PBBT组将接受单次平衡训练，包括安静站立时平台在两个方向（前和后）的意外扰动，以及平台运动的三个难度级别（位移、速度和加速度）。阻塞组中的每个平衡扰动将在四组试验中重复。对于随机组，每个区块的这四个试验的扰动序列是不可预测的。主要结果（即压力中心变量、反应时间、运动时间和总反应时间变量）将在基线以及干预后立即和一天进行评估。

{"title":"Random vs. blocked perturbation training on reactive balance control in peripheral neuropathy: A protocol study for a randomized controlled trial","authors":"Razieh Javadian Kootenayi , Razieh Mofateh , Mehrnoosh Zakerkish , Neda Orakifar , Saeideh Monjezi , Mohammad Mehravar , Maryam Seyedtabib","doi":"10.1016/j.mex.2026.103796","DOIUrl":"10.1016/j.mex.2026.103796","url":null,"abstract":"<div><div>Diabetic peripheral neuropathy (DPN) is the leading cause of disturbances in reactive balance control. The repeated, external mechanical perturbations in perturbation-based balance training(PBBT) evoke balance recovery strategies; which subsequently improve reactive balance performance. Using the practice schedule concept of motor learning in the design of PBBT is a relatively new approach related to balance exercises. This study aims to investigate the effects of blocked and random PBBT on reactive balance control and its persistency and transfer to conditions different from those experienced during training.</div><div>Individuals with DPN will be recruited and randomly allocated to one of the three groups: random, blocked, and control group. Random and blocked PBBT groups will receive single-session balance training, including unexpected perturbations of platform during quiet standing in two directions (anterior and posterior), and three difficulty levels of platform motion (displacement, velocity, and acceleration). Each balance perturbation in blocked group will be repeated over blocks of four trials. For the random group, perturbation sequence will be unpredictable for these four trials in each block. Primary outcomes (i.e., center of pressure variables, reaction time, movement time, and total response time variables) will be assessed at baseline as well as immediately and one day after intervention.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"16 ","pages":"Article 103796"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034289","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