Pub Date : 2025-04-24DOI: 10.1016/j.mex.2025.103331
Urvashi Saini , Sindhuja Renganathan
The inconsistent charge and discharge patterns of electric vehicle batteries, coupled with their operation across varying voltage and current levels, pose a challenge for accurate capacity and state of health (SOH) assessment. Traditional methods rely on regular calibration, requiring controlled charge and discharge cycles, which are impractical in real-world scenarios. This research demonstrates an analysis-based method to obtain labeled capacity and SOH values in such conditions. This method not only provides labeled SOH values but also extracts health features that can be used for data-driven prediction of capacity or SOH.
•
Incremental capacity analysis (ICA) method has been presented to be used with electric vehicle (EV) battery data.
•
The approach to extract health features from a EV battery using ICA method as a function of age of the battery has been presented which can be used along with a machine learning or deep learning model.
•
State of health has been calculated for a vehicle battery using the proposed method.
{"title":"Incremental capacity analysis of battery under dynamic load conditions","authors":"Urvashi Saini , Sindhuja Renganathan","doi":"10.1016/j.mex.2025.103331","DOIUrl":"10.1016/j.mex.2025.103331","url":null,"abstract":"<div><div>The inconsistent charge and discharge patterns of electric vehicle batteries, coupled with their operation across varying voltage and current levels, pose a challenge for accurate capacity and state of health (SOH) assessment. Traditional methods rely on regular calibration, requiring controlled charge and discharge cycles, which are impractical in real-world scenarios. This research demonstrates an analysis-based method to obtain labeled capacity and SOH values in such conditions. This method not only provides labeled SOH values but also extracts health features that can be used for data-driven prediction of capacity or SOH.<ul><li><span>•</span><span><div>Incremental capacity analysis (ICA) method has been presented to be used with electric vehicle (EV) battery data.</div></span></li><li><span>•</span><span><div>The approach to extract health features from a EV battery using ICA method as a function of age of the battery has been presented which can be used along with a machine learning or deep learning model.</div></span></li><li><span>•</span><span><div>State of health has been calculated for a vehicle battery using the proposed method.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103331"},"PeriodicalIF":1.6,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874823","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}
Pub Date : 2025-04-21DOI: 10.1016/j.mex.2025.103326
Thi Ly Tran , Thi Le Na Vo , Hung-Anh Tran Vu , Quoc Viet Ho , Anh Tuan Duong , Viet Huong Nguyen , Huu Tuan Nguyen
This study investigates the development of ZnOCZnO sandwich structures using ZnO thin films fabricated via the spatial atomic layer deposition (SALD) technique under atmospheric pressure. Carbon powders obtained from candle soot were introduced to modify the structural, optical, and photocatalytic properties of ZnO. The influence of this carbon layer on the structural, optical, and photocatalytic characteristics of the materials was comprehensively analyzed. The results indicate that incorporating carbon significantly enhances light absorption and charge carrier separation, leading to superior photocatalytic activity under UV light. The ZnOCZnO structures exhibited a reduced bandgap (3.20 eV) compared to bare ZnO (3.27 eV), facilitating improved photon absorption. X-ray diffraction (XRD) analysis revealed weaker and broader peaks in ZnOCZnO, suggesting reduced crystallite size and increased structural disorder due to carbon incorporation. The photocatalytic efficiency was assessed via methylene blue degradation under UV–Vis irradiation. The ZnOCZnO structures achieved an 88.2 % degradation rate after 180 min, surpassing the 62.9 % degradation observed for bare ZnO film. This enhancement is attributed to improved charge separation and suppressed recombination facilitated by the carbon interlayer. The findings highlight the potential of ZnOCZnO structures for environmental remediation and energy applications.
•
Development of ZnOCZnO sandwich structures using SALD under atmospheric conditions.
•
Integration of a candle soot-derived carbon layer to improve material properties.
•
Achieved enhanced photocatalytic efficiency through enhanced surface area and improved charge separation.
{"title":"ZnOCZnO sandwich structures: Fabrication and photocatalytic applications","authors":"Thi Ly Tran , Thi Le Na Vo , Hung-Anh Tran Vu , Quoc Viet Ho , Anh Tuan Duong , Viet Huong Nguyen , Huu Tuan Nguyen","doi":"10.1016/j.mex.2025.103326","DOIUrl":"10.1016/j.mex.2025.103326","url":null,"abstract":"<div><div>This study investigates the development of ZnO<img>C<img>ZnO sandwich structures using ZnO thin films fabricated via the spatial atomic layer deposition (SALD) technique under atmospheric pressure. Carbon powders obtained from candle soot were introduced to modify the structural, optical, and photocatalytic properties of ZnO. The influence of this carbon layer on the structural, optical, and photocatalytic characteristics of the materials was comprehensively analyzed. The results indicate that incorporating carbon significantly enhances light absorption and charge carrier separation, leading to superior photocatalytic activity under UV light. The ZnO<img>C<img>ZnO structures exhibited a reduced bandgap (3.20 eV) compared to bare ZnO (3.27 eV), facilitating improved photon absorption. X-ray diffraction (XRD) analysis revealed weaker and broader peaks in ZnO<img>C<img>ZnO, suggesting reduced crystallite size and increased structural disorder due to carbon incorporation. The photocatalytic efficiency was assessed via methylene blue degradation under UV–Vis irradiation. The ZnO<img>C<img>ZnO structures achieved an 88.2 % degradation rate after 180 min, surpassing the 62.9 % degradation observed for bare ZnO film. This enhancement is attributed to improved charge separation and suppressed recombination facilitated by the carbon interlayer. The findings highlight the potential of ZnO<img>C<img>ZnO structures for environmental remediation and energy applications.<ul><li><span>•</span><span><div>Development of ZnO<img>C<img>ZnO sandwich structures using SALD under atmospheric conditions.</div></span></li><li><span>•</span><span><div>Integration of a candle soot-derived carbon layer to improve material properties.</div></span></li><li><span>•</span><span><div>Achieved enhanced photocatalytic efficiency through enhanced surface area and improved charge separation.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103326"},"PeriodicalIF":1.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868616","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}
Pub Date : 2025-04-18DOI: 10.1016/j.mex.2025.103318
Raghavendra M Devadas , Sowmya T
Quantum Machine Learning (QML) is the emerging confluence of quantum computing and artificial intelligence that promises to solve computational problems inaccessible to classical systems. Using quantum principles such as superposition, entanglement, and interference, QML promises exponential speed-ups and new paradigms for data processing in machine learning tasks. This review gives an overview of QML, from advancements in quantum-enhanced classical ML to native quantum algorithms and hybrid quantum-classical frameworks. It varies from applications in optimization, drug discovery, and quantum-secured communications, showcasing how QML can change healthcare, finance, and logistics industries. Even though this approach holds so much promise, significant challenges remain to be addressed-noisy qubits, error correction, and limitations in data encoding-that must be overcome by interdisciplinary research soon. The paper tries to collate the state of the art of QML in theoretical underpinnings, practical applications, and directions into the future.
{"title":"Quantum machine learning: A comprehensive review of integrating AI with quantum computing for computational advancements","authors":"Raghavendra M Devadas , Sowmya T","doi":"10.1016/j.mex.2025.103318","DOIUrl":"10.1016/j.mex.2025.103318","url":null,"abstract":"<div><div>Quantum Machine Learning (QML) is the emerging confluence of quantum computing and artificial intelligence that promises to solve computational problems inaccessible to classical systems. Using quantum principles such as superposition, entanglement, and interference, QML promises exponential speed-ups and new paradigms for data processing in machine learning tasks. This review gives an overview of QML, from advancements in quantum-enhanced classical ML to native quantum algorithms and hybrid quantum-classical frameworks. It varies from applications in optimization, drug discovery, and quantum-secured communications, showcasing how QML can change healthcare, finance, and logistics industries. Even though this approach holds so much promise, significant challenges remain to be addressed-noisy qubits, error correction, and limitations in data encoding-that must be overcome by interdisciplinary research soon. The paper tries to collate the state of the art of QML in theoretical underpinnings, practical applications, and directions into the future.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103318"},"PeriodicalIF":1.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854525","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}
Pub Date : 2025-04-17DOI: 10.1016/j.mex.2025.103317
D. Dhinakaran , S. Gopalakrishnan , D. Selvaraj , M.S. Girija , G. Prabaharan
In this era of data-driven decision-making, it is important to securely and efficiently extract knowledge from distributed datasets. However, in outsourced data for tasks like frequent itemset mining, privacy is an important issue. The difficulty is to secure sensitive data while delivering the insights of the data. First, this paper proposes a new multi-cloud approach to preserve privacy, which includes two main components, named the Transaction Hewer and Allocator module and the Facile Hash Algorithm (FHA), in extracting the frequent itemset. All these components work together to protect the privacy of the data, wherever it is, during the transmission phase or the computation phase, even if it is raw data or processed data, on the different distributed cloud platforms. The complexities involved in the mining of frequent itemsets led us to introduce the Apriori with Tid Reduction (ATid) algorithm considering scalability and computational operational improvements to the mining process due to the Tid Reduction concept. We conduct performance evaluation on several datasets and show that our proposed framework achieves higher performance than existing methods, and encryption and decryption processes reduce the computational time by up to 25 % compared to the best alternative. It also exhibits approximately 15 % reduction in communication costs and displays scalability with the growing number of transactions, compared to the state-of-the-art evaluation metrics that indicate improved communication overhead.
•
Introduces a multi-cloud privacy framework with Facile Hash Algorithm and Transaction Hewer and Allocator.
•
Enhances scalability using ATid algorithm with Tid Reduction.
{"title":"Mining privacy-preserving association rules using transaction hewer allocator and facile hash algorithm in multi-cloud environments","authors":"D. Dhinakaran , S. Gopalakrishnan , D. Selvaraj , M.S. Girija , G. Prabaharan","doi":"10.1016/j.mex.2025.103317","DOIUrl":"10.1016/j.mex.2025.103317","url":null,"abstract":"<div><div>In this era of data-driven decision-making, it is important to securely and efficiently extract knowledge from distributed datasets. However, in outsourced data for tasks like frequent itemset mining, privacy is an important issue. The difficulty is to secure sensitive data while delivering the insights of the data. First, this paper proposes a new multi-cloud approach to preserve privacy, which includes two main components, named the Transaction Hewer and Allocator module and the Facile Hash Algorithm (FHA), in extracting the frequent itemset. All these components work together to protect the privacy of the data, wherever it is, during the transmission phase or the computation phase, even if it is raw data or processed data, on the different distributed cloud platforms. The complexities involved in the mining of frequent itemsets led us to introduce the Apriori with Tid Reduction (ATid) algorithm considering scalability and computational operational improvements to the mining process due to the Tid Reduction concept. We conduct performance evaluation on several datasets and show that our proposed framework achieves higher performance than existing methods, and encryption and decryption processes reduce the computational time by up to 25 % compared to the best alternative. It also exhibits approximately 15 % reduction in communication costs and displays scalability with the growing number of transactions, compared to the state-of-the-art evaluation metrics that indicate improved communication overhead.<ul><li><span>•</span><span><div>Introduces a multi-cloud privacy framework with Facile Hash Algorithm and Transaction Hewer and Allocator.</div></span></li><li><span>•</span><span><div>Enhances scalability using ATid algorithm with Tid Reduction.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103317"},"PeriodicalIF":1.6,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868617","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}
The accurate prediction of the host of influenza viruses is a significant challenge in bioinformatics, as it is crucial for understanding viral transmission dynamics and host-virus interactions. This research
•
Introduces a novel approach for predicting the host of influenza viruses by leveraging protein sequences.
•
Extraction of features, including sequence length, Amino Acid Composition (AAC), Dipeptide Composition (DPC), Tripeptide Composition (TPC), aromaticity, secondary structure fraction, and entropy from protein sequence.
•
Addresses the data imbalance and improves model generalization, the oversampling technique is applied for data augmentation.
The prediction model employs a Deep Recurrent Neural Network (DRNN) optimized by Fractional Addax Optimization 34 Algorithm (FAOA), a hybrid of Addax Optimization Algorithm (AOA) and Fractional Concept (FC), designed to perform 35 influenza virus host prediction. The model's performance is evaluated using metrics, such as Matthews's Correlation 36 Coefficient (MCC), F1-Score, and Mean Squared Error (MSE). Experimental results demonstrate that the DRNN_FAOA 37 model significantly outperforms existing methods, achieving the highest MCC of 0.937, F1-Score of 0.917, and the 38 lowest MSE of 0.038. The proposed DRNN_FAOA model's ability to accurately predict influenza virus hosts suggests its 39 potential as a robust model in virus-host prediction.
{"title":"Deep recurrent neural network with fractional addax optimization algorithm for influenza virus host prediction","authors":"Shweta Ashish Koparde , Sonali Kothari , Sharad Adsure , Kapil Netaji Vhatkar , Vinod V. Kimbahune","doi":"10.1016/j.mex.2025.103319","DOIUrl":"10.1016/j.mex.2025.103319","url":null,"abstract":"<div><div>The accurate prediction of the host of influenza viruses is a significant challenge in bioinformatics, as it is crucial for understanding viral transmission dynamics and host-virus interactions. This research<ul><li><span>•</span><span><div>Introduces a novel approach for predicting the host of influenza viruses by leveraging protein sequences.</div></span></li><li><span>•</span><span><div>Extraction of features, including sequence length, Amino Acid Composition (AAC), Dipeptide Composition (DPC), Tripeptide Composition (TPC), aromaticity, secondary structure fraction, and entropy from protein sequence.</div></span></li><li><span>•</span><span><div>Addresses the data imbalance and improves model generalization, the oversampling technique is applied for data augmentation.</div></span></li></ul></div><div>The prediction model employs a Deep Recurrent Neural Network (DRNN) optimized by Fractional Addax Optimization 34 Algorithm (FAOA), a hybrid of Addax Optimization Algorithm (AOA) and Fractional Concept (FC), designed to perform 35 influenza virus host prediction. The model's performance is evaluated using metrics, such as Matthews's Correlation 36 Coefficient (MCC), F1-Score, and Mean Squared Error (MSE). Experimental results demonstrate that the DRNN_FAOA 37 model significantly outperforms existing methods, achieving the highest MCC of 0.937, F1-Score of 0.917, and the 38 lowest MSE of 0.038. The proposed DRNN_FAOA model's ability to accurately predict influenza virus hosts suggests its 39 potential as a robust model in virus-host prediction.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103319"},"PeriodicalIF":1.6,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850043","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}
Addressing the challenge of RNA extraction from hard tissues of wild animals is crucial, especially given the species' conservation and the ethical imperative to avoid lethal sampling methods. This study focuses on optimizing a protocol for non-invasive RNA extraction from the caudal scutes of Crocodylus moreletii, an endemic species in the Yucatan Peninsula, Mexico, highlighting the significance of conducting research in tropical areas with limited laboratory access. Accompanying with RNA preservation buffer for the scute tissue, we explored various tissue disruption and homogenization techniques to facilitate RNA isolation and purification. The purity and integrity of RNA were assessed to determine the best extraction method. The optimized protocol involved ultrasonication of 75 mg samples, followed by a 3-hour Proteinase K incubation, yielding RNA with concentrations from 18.7 to 154.7 ng/µL, satisfactory purity (260/280 ratio ∼2), and integrity (RNA Integrity Number >5.5). Further validation through quantitative PCR analyses confirmed the suitability of the extracted RNA for studies on gene expression levels and were sufficient for next-generation sequencing (NGS). This protocol may provide a basis for developing similar methodologies for other non-model species with hard tissues.
•
This study optimizes non-invasive RNA extraction from crocodile scutes, enabling conservation research and transcriptomic analysis.
{"title":"Developing an efficient protocol for RNA extraction from Morelet's crocodile caudal scute biopsies","authors":"Asela Marisol Buenfil-Rojas , Mauricio González-Jáuregui , Mari Ochiai , Hisato Iwata","doi":"10.1016/j.mex.2025.103315","DOIUrl":"10.1016/j.mex.2025.103315","url":null,"abstract":"<div><div>Addressing the challenge of RNA extraction from hard tissues of wild animals is crucial, especially given the species' conservation and the ethical imperative to avoid lethal sampling methods. This study focuses on optimizing a protocol for non-invasive RNA extraction from the caudal scutes of <em>Crocodylus moreletii</em>, an endemic species in the Yucatan Peninsula, Mexico, highlighting the significance of conducting research in tropical areas with limited laboratory access. Accompanying with RNA preservation buffer for the scute tissue, we explored various tissue disruption and homogenization techniques to facilitate RNA isolation and purification. The purity and integrity of RNA were assessed to determine the best extraction method. The optimized protocol involved ultrasonication of 75 mg samples, followed by a 3-hour Proteinase K incubation, yielding RNA with concentrations from 18.7 to 154.7 ng/µL, satisfactory purity (260/280 ratio ∼2), and integrity (RNA Integrity Number >5.5). Further validation through quantitative PCR analyses confirmed the suitability of the extracted RNA for studies on gene expression levels and were sufficient for next-generation sequencing (NGS). This protocol may provide a basis for developing similar methodologies for other non-model species with hard tissues.<ul><li><span>•</span><span><div>This study optimizes non-invasive RNA extraction from crocodile scutes, enabling conservation research and transcriptomic analysis.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103315"},"PeriodicalIF":1.6,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854646","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}
Pub Date : 2025-04-09DOI: 10.1016/j.mex.2025.103309
Shubham Rana, Matteo Gatti
This study investigates the application of modified Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic RGB and infrared (IR) datasets to meet the annotation requirements for wild radish (Raphanus raphanistrum). The RafanoSet dataset was used for evaluation. Traditional WGAN models struggle with vanishing gradients and poor convergence, affecting data quality. Customizations in WGAN-GP improved synthetic image quality, especially in maintaining SSIM for RGB datasets. However, generating high-quality IR images remains challenging due to spectral complexities, with lower SSIM scores. Architectural enhancements including transposed convolutions, dropout, and selective batch normalization improved SSIM scores from 0.5364 to 0.6615 for RGB and from 0.3306 to 0.4154 for IR images. This study highlights the customized model's key features:
•
Produces a 128 × 7 × 7 tensor, optimizes feature map size for subsequent layers, with two layers using 4 × 4 kernels and 128 and 64 filters for upsampling.
•
Uses 3 × 3 kernels in all convolutional layers to capture fine-grained spatial features, incorporates batch normalization for training stability, and applies dropout to reduce overfitting and improve generalization.
{"title":"Comparative Evaluation of Modified Wasserstein GAN-GP and State-of-the-Art GAN Models for Synthesizing Agricultural Weed Images in RGB and Infrared Domain","authors":"Shubham Rana, Matteo Gatti","doi":"10.1016/j.mex.2025.103309","DOIUrl":"10.1016/j.mex.2025.103309","url":null,"abstract":"<div><div>This study investigates the application of modified Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic RGB and infrared (IR) datasets to meet the annotation requirements for wild radish (Raphanus raphanistrum). The RafanoSet dataset was used for evaluation. Traditional WGAN models struggle with vanishing gradients and poor convergence, affecting data quality. Customizations in WGAN-GP improved synthetic image quality, especially in maintaining SSIM for RGB datasets. However, generating high-quality IR images remains challenging due to spectral complexities, with lower SSIM scores. Architectural enhancements including transposed convolutions, dropout, and selective batch normalization improved SSIM scores from 0.5364 to 0.6615 for RGB and from 0.3306 to 0.4154 for IR images. This study highlights the customized model's key features:<ul><li><span>•</span><span><div>Produces a 128 × 7 × 7 tensor, optimizes feature map size for subsequent layers, with two layers using 4 × 4 kernels and 128 and 64 filters for upsampling.</div></span></li><li><span>•</span><span><div>Uses 3 × 3 kernels in all convolutional layers to capture fine-grained spatial features, incorporates batch normalization for training stability, and applies dropout to reduce overfitting and improve generalization.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103309"},"PeriodicalIF":1.6,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833346","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}
Pub Date : 2025-04-08DOI: 10.1016/j.mex.2025.103297
Gi-Won Yoon, Segyeong Joo
Conventional manual or feature-based ECG analysis methods are limited by time inefficiencies and human error. This study explores the potential of transforming 1D signals into 2D Gramian Angular Field (GAF) images for improved classification of four ECG categories: Atrial Fibrillation (AFib), Left Ventricular Hypertrophy (LVH), Right Ventricular Hypertrophy (RVH), and Normal ECG.
•
The study employed GAF transformations to convert 1D ECG signals into 2D representations at three resolutions: 5000 × 5000, 512 × 512, and 256 × 256 pixels.
•
Segmentation methods were applied to enhance feature localization.
•
The ConvNext deep learning model, optimized for image classification, was used to evaluate the transformed ECG images, with performance assessed through accuracy, precision, recall, and F1-score metrics.
The 512 × 512 resolution achieved the optimal balance between computational efficiency and accuracy. F1-score for AFib, LVH, RVH and Normal ECG were 0.781, 0.71, 0.521 and 0.792 respectively. Segmentation methods improved classification performance, especially in detecting conditions like LVH and RVH. The 5000 × 5000 resolution offered the highest accuracy but was computationally intensive, whereas the 256 × 256 resolution showed reduced accuracy due to loss details.
{"title":"Enhanced electrocardiogram classification using Gramian angular field transformation with multi-lead analysis and segmentation techniques","authors":"Gi-Won Yoon, Segyeong Joo","doi":"10.1016/j.mex.2025.103297","DOIUrl":"10.1016/j.mex.2025.103297","url":null,"abstract":"<div><div>Conventional manual or feature-based ECG analysis methods are limited by time inefficiencies and human error. This study explores the potential of transforming 1D signals into 2D Gramian Angular Field (GAF) images for improved classification of four ECG categories: Atrial Fibrillation (AFib), Left Ventricular Hypertrophy (LVH), Right Ventricular Hypertrophy (RVH), and Normal ECG.<ul><li><span>•</span><span><div>The study employed GAF transformations to convert 1D ECG signals into 2D representations at three resolutions: 5000 × 5000, 512 × 512, and 256 × 256 pixels.</div></span></li><li><span>•</span><span><div>Segmentation methods were applied to enhance feature localization.</div></span></li><li><span>•</span><span><div>The ConvNext deep learning model, optimized for image classification, was used to evaluate the transformed ECG images, with performance assessed through accuracy, precision, recall, and F1-score metrics.</div></span></li></ul>The 512 × 512 resolution achieved the optimal balance between computational efficiency and accuracy. F1-score for AFib, LVH, RVH and Normal ECG were 0.781, 0.71, 0.521 and 0.792 respectively. Segmentation methods improved classification performance, especially in detecting conditions like LVH and RVH. The 5000 × 5000 resolution offered the highest accuracy but was computationally intensive, whereas the 256 × 256 resolution showed reduced accuracy due to loss details.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103297"},"PeriodicalIF":1.6,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850042","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}
Pub Date : 2025-04-07DOI: 10.1016/j.mex.2025.103305
Preethi , Mohammed Mujeer Ulla , Sapna R , Raghavendra M Devadas
Over the last few years, the conceptualization of Smart Home has received acceptance. The extensive issues regarding a smart home include offloading computational tasks, data security aspects, privacy issues, authentication of Internet of Things (IoT) devices, and so on. Presently, existing smart home automation addresses either of these issues, nevertheless, Smart Home automation that also necessitates decision-making for offloading computational tasks with improved QoS (i.e., latency and throughput) and systematic features apart from being reliable and safe is a definite necessity. To address these gaps in this, work a QoS-improved method called, Blockchain-modeled Swarm Optimized Lyapunov Smart Contract Deep Reinforced Tasks Offloading (BSOLSC-DRTO) in smart home is proposed. The BSOLSC-DRTO method is split into two sections, namely, Offloading Computational Tasks based on the Particle Swarm Optimized Lyapunov model and Temporal Difference Deep Reinforced Secured Offloading. First to solve the offloading issue and therefore improve the QoS, we developed a Particle Swarm Optimized Lyapunov model using a Lyapunov optimization function. This optimization problem aims to minimize latency and improve throughput considerably. Second, to boost the offloading security, we propose a trustworthy access control using the Temporal Difference Deep Reinforced Secured Offloading model that can safeguard devices against illegal offloading. Then to handle the computation management for addressing the offloading decisions in the queue temporal difference function is applied, therefore improving the smart contract accuracy and precision involved in offloading computational tasks. Evaluation results from experiments and numerical simulations exhibit the notable advantages of the proposed BSOLSC-DRTO method over existing methods.
•
Develop a Particle Swarm Optimized Lyapunov model to minimize latency and significantly improve throughput.
•
Proposed a Temporal Difference Deep Reinforced Secured Offloading model for trustworthy access control, protecting devices against illegal offloading.
{"title":"Blockchain modeled swarm optimized lyapunov smart contract deep reinforced secure tasks offloading in smart home","authors":"Preethi , Mohammed Mujeer Ulla , Sapna R , Raghavendra M Devadas","doi":"10.1016/j.mex.2025.103305","DOIUrl":"10.1016/j.mex.2025.103305","url":null,"abstract":"<div><div>Over the last few years, the conceptualization of Smart Home has received acceptance. The extensive issues regarding a smart home include offloading computational tasks, data security aspects, privacy issues, authentication of Internet of Things (IoT) devices, and so on. Presently, existing smart home automation addresses either of these issues, nevertheless, Smart Home automation that also necessitates decision-making for offloading computational tasks with improved QoS (i.e., latency and throughput) and systematic features apart from being reliable and safe is a definite necessity. To address these gaps in this, work a QoS-improved method called, Blockchain-modeled Swarm Optimized Lyapunov Smart Contract Deep Reinforced Tasks Offloading (BSOLSC-DRTO) in smart home is proposed. The BSOLSC-DRTO method is split into two sections, namely, Offloading Computational Tasks based on the Particle Swarm Optimized Lyapunov model and Temporal Difference Deep Reinforced Secured Offloading. First to solve the offloading issue and therefore improve the QoS, we developed a Particle Swarm Optimized Lyapunov model using a Lyapunov optimization function. This optimization problem aims to minimize latency and improve throughput considerably. Second, to boost the offloading security, we propose a trustworthy access control using the Temporal Difference Deep Reinforced Secured Offloading model that can safeguard devices against illegal offloading. Then to handle the computation management for addressing the offloading decisions in the queue temporal difference function is applied, therefore improving the smart contract accuracy and precision involved in offloading computational tasks. Evaluation results from experiments and numerical simulations exhibit the notable advantages of the proposed BSOLSC-DRTO method over existing methods.<ul><li><span>•</span><span><div>Develop a Particle Swarm Optimized Lyapunov model to minimize latency and significantly improve throughput.</div></span></li><li><span>•</span><span><div>Proposed a Temporal Difference Deep Reinforced Secured Offloading model for trustworthy access control, protecting devices against illegal offloading<em>.</em></div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103305"},"PeriodicalIF":1.6,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143814762","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}
The aim of our work was to estimate the composition of hydrosol produced as a byproduct of lavender steam distillation using UV–Vis spectrophotometry in the 200–600 nm wavelength range through a machine learning algorithm. The dissolved components of lavender essential oil (EO) from lavender hydrosol samples were extracted via liquid-liquid extraction, using three different solvents (pentane, heptane and diethyl ether). The UV–Vis absorbance spectra of the extracts were recorded and the composition analyzed using GC–MS. The composition data obtained allowed for the calculation of changes within the quantities of different EO components in the samples.
The partial least squares regression technique (PLS) was utilized to establish a connection between changes in the composition of the hydrosol and the changes in the UV–Vis spectra. After optimization the established PLS model showed an score above 0.95 for the prediction of hydrosol composition changes during cross-validation. The model can thus be utilized as a soft sensor to infer extracted mass of EO components and characterize the composition of hydrosol during the process directly from UV–Vis spectra.
•
Investigation of lavender water and extract using UV–Vis spectrophotometry
•
GC–MS analysis of extracts
•
PLS model development for composition estimation based on spectra
{"title":"Lavender hydrosol analysis using UV spectroscopy data and partial least squares regression","authors":"Sára Preiner, Bálint Levente Tarcsay, Dóra Pethő, Norbert Miskolczi","doi":"10.1016/j.mex.2025.103304","DOIUrl":"10.1016/j.mex.2025.103304","url":null,"abstract":"<div><div>The aim of our work was to estimate the composition of hydrosol produced as a byproduct of lavender steam distillation using UV–Vis spectrophotometry in the 200–600 nm wavelength range through a machine learning algorithm. The dissolved components of lavender essential oil (EO) from lavender hydrosol samples were extracted via liquid-liquid extraction, using three different solvents (pentane, heptane and diethyl ether). The UV–Vis absorbance spectra of the extracts were recorded and the composition analyzed using GC–MS. The composition data obtained allowed for the calculation of changes within the quantities of different EO components in the samples.</div><div>The partial least squares regression technique (PLS) was utilized to establish a connection between changes in the composition of the hydrosol and the changes in the UV–Vis spectra. After optimization the established PLS model showed an <span><math><msup><mi>R</mi><mn>2</mn></msup></math></span> score above 0.95 for the prediction of hydrosol composition changes during cross-validation. The model can thus be utilized as a soft sensor to infer extracted mass of EO components and characterize the composition of hydrosol during the process directly from UV–Vis spectra.<ul><li><span>•</span><span><div>Investigation of lavender water and extract using UV–Vis spectrophotometry</div></span></li><li><span>•</span><span><div>GC–MS analysis of extracts</div></span></li><li><span>•</span><span><div>PLS model development for composition estimation based on spectra</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103304"},"PeriodicalIF":1.6,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808445","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号