MethodsX最新文献

英文中文

Assessing SPI and SPEI for drought forecasting through the power law process: A case study in South Sulawesi, Indonesia

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-19 DOI: 10.1016/j.mex.2025.103235

Nurtiti Sunusi, Nur Hikmah Auliana

This study presents a method for assessing drought events by integrating Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) into the Power Law Process (PLP) model. The method begins with identifying drought events based on SPI and SPEI, followed by the Cramér–von Mises goodness-of-fit test to ensure the drought data meets PLP assumptions. Parameter estimation is performed using Maximum Likelihood Estimation (MLE) with a time-truncated approach, treating drought as a random process within a defined observation period. Model validation is conducted by comparing actual drought events with predictions from the cumulative PLP function, while event probabilities are determined using the Nonhomogeneous Poisson Process. Applied to 24 regencies/cities in South Sulawesi, the method showed that 14 regions fit the PLP based on SPI, and 13 regions based on SPEI. Predictions indicate that over the next 12 months, drought will occur for one month based on SPI and two months based on SPEI. This method contributes to the development of drought monitoring and early warning systems, supporting mitigation and adaptation strategies in South Sulawesi.

The main contributions of this study include:

•
The development of a novel methodological framework by integrating SPI and SPEI into the PLP for drought analysis
•
Practical applications in drought early warning systems and drought risk management in South Sulawesi

本研究提出了一种通过将标准化降水指数 (SPI) 和标准化降水蒸散指数 (SPEI) 纳入幂律过程 (PLP) 模型来评估干旱事件的方法。该方法首先根据 SPI 和 SPEI 确定干旱事件，然后进行 Cramér-von Mises 拟合度检验，以确保干旱数据符合 PLP 假设。参数估计采用最大似然估计法 (MLE)，采用时间截断法，将干旱视为确定观测期内的随机过程。通过比较实际干旱事件和累积 PLP 函数的预测结果来验证模型，同时使用非均质泊松过程确定事件概率。该方法应用于南苏拉威西岛的 24 个地区/城市，结果显示 14 个地区符合基于 SPI 的 PLP，13 个地区符合基于 SPEI 的 PLP。预测结果表明，在未来 12 个月中，根据 SPI 将有一个月发生干旱，根据 SPEI 将有两个月发生干旱。本研究的主要贡献包括：-通过将 SPI 和 SPEI 纳入 PLP 进行干旱分析，开发了一种新颖的方法框架-在南苏拉威西干旱预警系统和干旱风险管理中的实际应用。

{"title":"Assessing SPI and SPEI for drought forecasting through the power law process: A case study in South Sulawesi, Indonesia","authors":"Nurtiti Sunusi, Nur Hikmah Auliana","doi":"10.1016/j.mex.2025.103235","DOIUrl":"10.1016/j.mex.2025.103235","url":null,"abstract":"<div><div>This study presents a method for assessing drought events by integrating Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) into the Power Law Process (PLP) model. The method begins with identifying drought events based on SPI and SPEI, followed by the Cramér–von Mises goodness-of-fit test to ensure the drought data meets PLP assumptions. Parameter estimation is performed using Maximum Likelihood Estimation (MLE) with a time-truncated approach, treating drought as a random process within a defined observation period. Model validation is conducted by comparing actual drought events with predictions from the cumulative PLP function, while event probabilities are determined using the Nonhomogeneous Poisson Process. Applied to 24 regencies/cities in South Sulawesi, the method showed that 14 regions fit the PLP based on SPI, and 13 regions based on SPEI. Predictions indicate that over the next 12 months, drought will occur for one month based on SPI and two months based on SPEI. This method contributes to the development of drought monitoring and early warning systems, supporting mitigation and adaptation strategies in South Sulawesi.</div><div>The main contributions of this study include:<ul><li><span>•</span><span><div>The development of a novel methodological framework by integrating SPI and SPEI into the PLP for drought analysis</div></span></li><li><span>•</span><span><div>Practical applications in drought early warning systems and drought risk management in South Sulawesi</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103235"},"PeriodicalIF":1.6,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating LiDAR technology for accurate measurement of tree metrics and carbon sequestration

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-18 DOI: 10.1016/j.mex.2025.103237

Suradet Tantrairatn , Auraluck Pichitkul , Nutchanan Petcharat , Pawarut Karaked , Atthaphon Ariyarit

Carbon credits play a crucial role in mitigating climate change by incentivizing reductions in greenhouse gas emissions and providing a measurable way to balance carbon dioxide output, fostering sustainable environmental practices. However, conventional methods of measuring carbon credits are often time-consuming and lack accuracy. This research examines carbon credit measurement in a 40 × 40 m² rubber forest, evaluating the effectiveness of LiDAR technology in measuring Tree Height (TH) and Diameter at Breast Height (DBH) using a dataset of 100 samples. The method is as follows:

•
Three measurement methods were compared: conventional techniques using diameter tape and hypsometers, manual LiDAR measurements, and automated measurements using 3D Forest Inventory software with the CloudCompare plugin.
•
The Mean Absolute Percentage Error (MAPE) for carbon sequestration was 4.276 % for manual LiDAR measurements and 6.901 % for the 3D Forest Inventory method.
•
Root Mean Square Error (RMSE) values for carbon sequestration using LiDAR measurements were 33.492 kgCO₂e, whereas RMSE values for the 3D Forest Inventory method were significantly higher. This indicates that manual LiDAR measurements are more accurate and consistent, while the higher RMSE in the 3D Forest Inventory method reflects greater variability and potential estimation errors.

The findings suggest that LiDAR technology, particularly manual measurements, provides a reliable and efficient alternative for carbon sequestration assessments in forest management.

碳信用额在减缓气候变化方面发挥着至关重要的作用，它激励人们减少温室气体排放，并提供了一种可衡量的方法来平衡二氧化碳的输出，促进可持续的环境实践。然而，传统的碳信用额度测量方法往往耗时且缺乏准确性。本研究考察了 40 × 40 平方米橡胶林的碳信用测量，使用 100 个样本数据集评估了激光雷达技术在测量树高（TH）和胸径（DBH）方面的有效性。方法如下：-比较了三种测量方法：使用直径尺和湿度计的传统技术、手动激光雷达测量以及使用带有 CloudCompare 插件的 3D Forest Inventory 软件进行的自动测量。使用激光雷达测量的固碳量均方根误差 (RMSE) 为 33.492 kgCO2e，而使用三维森林资源清查方法的 RMSE 值要高得多。研究结果表明，激光雷达技术（尤其是人工测量）为森林管理中的碳封存评估提供了一种可靠、高效的替代方法。

{"title":"Evaluating LiDAR technology for accurate measurement of tree metrics and carbon sequestration","authors":"Suradet Tantrairatn , Auraluck Pichitkul , Nutchanan Petcharat , Pawarut Karaked , Atthaphon Ariyarit","doi":"10.1016/j.mex.2025.103237","DOIUrl":"10.1016/j.mex.2025.103237","url":null,"abstract":"<div><div>Carbon credits play a crucial role in mitigating climate change by incentivizing reductions in greenhouse gas emissions and providing a measurable way to balance carbon dioxide output, fostering sustainable environmental practices. However, conventional methods of measuring carbon credits are often time-consuming and lack accuracy. This research examines carbon credit measurement in a 40 × 40 <em>m<sup>2</sup></em> rubber forest, evaluating the effectiveness of LiDAR technology in measuring Tree Height (TH) and Diameter at Breast Height (DBH) using a dataset of 100 samples. The method is as follows:<ul><li><span>•</span><span><div>Three measurement methods were compared: conventional techniques using diameter tape and hypsometers, manual LiDAR measurements, and automated measurements using 3D Forest Inventory software with the CloudCompare plugin.</div></span></li><li><span>•</span><span><div>The Mean Absolute Percentage Error (MAPE) for carbon sequestration was 4.276 % for manual LiDAR measurements and 6.901 % for the 3D Forest Inventory method.</div></span></li><li><span>•</span><span><div>Root Mean Square Error (RMSE) values for carbon sequestration using LiDAR measurements were 33.492 kgCO<sub>2</sub>e, whereas RMSE values for the 3D Forest Inventory method were significantly higher. This indicates that manual LiDAR measurements are more accurate and consistent, while the higher RMSE in the 3D Forest Inventory method reflects greater variability and potential estimation errors.</div></span></li></ul></div><div>The findings suggest that LiDAR technology, particularly manual measurements, provides a reliable and efficient alternative for carbon sequestration assessments in forest management.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103237"},"PeriodicalIF":1.6,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An enhanced light weight face liveness detection method using deep convolutional neural network

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-17 DOI: 10.1016/j.mex.2025.103229

Swapnil R. Shinde , Anupkumar M. Bongale , Deepak Dharrao , Sudeep D. Thepade

Authentication plays a pivotal role in contemporary security frameworks, with various methods utilized including passwords, hardware tokens, and biometrics. Biometric authentication and face recognition hold significant application potential, albeit susceptible to forgery, termed as face spoofing attacks. These attacks, encompassing 2D and 3D modalities, pose challenges through fake photos, warped images, video displays, and 3D masks. The existing counter measures are attack specific and use complex architecture adding to the computational cost. The deep transfer learning models such as AlexNet, ResNet, VGG, and Inception V3 can be used, but they are computationally expensive. This article proposes LwFLNeT, a lightweight deep CNN method that leverages parallel dropout layers to prevent over fitting and achieves excellent performance on 2D and 3D face spoofing datasets. The proposed methods is validated through the Cross-dataset train test evaluation. The methodology proposed in the article has the following key contributions:

•
Design of Light Weight Dual Stream CNN architecture with a parallel dropout layer to minimize over fitting issue.
•
Design of Generalized and Robust deep CNN architecture that detects both 2D and 3D attacks with higher efficiency compared to existing methodology.
•
Method validation done with State-of-the-Art methods using the standard performance metrics for face spoofing attack detection.

{"title":"An enhanced light weight face liveness detection method using deep convolutional neural network","authors":"Swapnil R. Shinde , Anupkumar M. Bongale , Deepak Dharrao , Sudeep D. Thepade","doi":"10.1016/j.mex.2025.103229","DOIUrl":"10.1016/j.mex.2025.103229","url":null,"abstract":"<div><div>Authentication plays a pivotal role in contemporary security frameworks, with various methods utilized including passwords, hardware tokens, and biometrics. Biometric authentication and face recognition hold significant application potential, albeit susceptible to forgery, termed as face spoofing attacks. These attacks, encompassing 2D and 3D modalities, pose challenges through fake photos, warped images, video displays, and 3D masks. The existing counter measures are attack specific and use complex architecture adding to the computational cost. The deep transfer learning models such as AlexNet, ResNet, VGG, and Inception V3 can be used, but they are computationally expensive. This article proposes LwFLNeT, a lightweight deep CNN method that leverages parallel dropout layers to prevent over fitting and achieves excellent performance on 2D and 3D face spoofing datasets. The proposed methods is validated through the Cross-dataset train test evaluation. The methodology proposed in the article has the following key contributions:<ul><li><span>•</span><span><div>Design of Light Weight Dual Stream CNN architecture with a parallel dropout layer to minimize over fitting issue.</div></span></li><li><span>•</span><span><div>Design of Generalized and Robust deep CNN architecture that detects both 2D and 3D attacks with higher efficiency compared to existing methodology.</div></span></li><li><span>•</span><span><div>Method validation done with State-of-the-Art methods using the standard performance metrics for face spoofing attack detection.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103229"},"PeriodicalIF":1.6,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing multimodal scene recognition through relevant feature selection approach for scene classification

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-17 DOI: 10.1016/j.mex.2025.103226

Sumathi K , Pramod Kumar S , H R Mahadevaswamy , Ujwala B S

Scene classification plays a vital role in various computer vision applications, but building deep learning models from scratch is a very time-intensive process. Transfer learning is an excellent classification method using the predefined model. In our proposed work, we introduce a novel method of multimodal feature extraction and a feature selection technique to improve the efficiency of transfer learning in scene classification. We leverage widely used convolutional neural networks (CNN) for feature extraction, followed by relevant feature selection techniques to enhance the performance of the model and increase computational efficiency. In this work, we have executed the proposed method on the Scene dataset of 6 classes and the AID dataset. Experimental results indicate that the MIFS-based approach reduces computational overhead and achieves competitive or superior classification accuracy. The proposed methodology offers a scalable and effective solution for scene classification tasks, with potential applications in real-time recognition and automated systems.

引用次数: 0

StopSpamX: A multi modal fusion approach for spam detection in social networking

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-16 DOI: 10.1016/j.mex.2025.103227

Dasari Siva Krishna , Gorla Srinivas

Social networking platforms like Twitter, Instagram, Youtube, Facebook, Whatsapp have completely changed people's daily routine. Users of these social media networks have total freedom to upload anything that has political, commercial, or entertainment value. The data collected from these sources can be genuine or fake. There are no concerns or problems if the data published is true and relevant. The main difficulty arises while we deal with the spam data. So, this problem of spam data should be properly handled. In order to achieve a spam free environment, researchers have proposed numerous methods and algorithms for spam detection. Out of them few algorithms are implemented to detect the spam data in twitter.

•
We compare the outcomes in each scenario using various state-of-the-art word embedding techniques, such as Word2Vecv, GloVe, and FastText.
•
To account for the restrictions, two deep learning hybrid fusion classifier techniques—Text-based classifier and Combined classifier—are used in this work. These classifiers are built using deep learning techniques including GRU, LSTM, and CNN.
•
These methods will be evaluated using a range of measures, including F1-score, accuracy, recall, and precision. These actions could enhance the performance of the hybrid fusion approach.

{"title":"StopSpamX: A multi modal fusion approach for spam detection in social networking","authors":"Dasari Siva Krishna , Gorla Srinivas","doi":"10.1016/j.mex.2025.103227","DOIUrl":"10.1016/j.mex.2025.103227","url":null,"abstract":"<div><div>Social networking platforms like Twitter, Instagram, Youtube, Facebook, Whatsapp have completely changed people's daily routine. Users of these social media networks have total freedom to upload anything that has political, commercial, or entertainment value. The data collected from these sources can be genuine or fake. There are no concerns or problems if the data published is true and relevant. The main difficulty arises while we deal with the spam data. So, this problem of spam data should be properly handled. In order to achieve a spam free environment, researchers have proposed numerous methods and algorithms for spam detection. Out of them few algorithms are implemented to detect the spam data in twitter.<ul><li><span>•</span><span><div>We compare the outcomes in each scenario using various state-of-the-art word embedding techniques, such as Word2Vecv, GloVe, and FastText.</div></span></li><li><span>•</span><span><div>To account for the restrictions, two deep learning hybrid fusion classifier techniques—Text-based classifier and Combined classifier—are used in this work. These classifiers are built using deep learning techniques including GRU, LSTM, and CNN.</div></span></li><li><span>•</span><span><div>These methods will be evaluated using a range of measures, including F1-score, accuracy, recall, and precision. These actions could enhance the performance of the hybrid fusion approach.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103227"},"PeriodicalIF":1.6,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Conversion between the numerical simulation and the calculation using the Deformation Energy Ratio approach

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-15 DOI: 10.1016/j.mex.2025.103221

Kirill Golubiatnikov, František Wald

In numerical simulations and calculations, material curves are defined in different ways. A direct transfer of quantities between them is inaccurate, requiring a proper transformation of key values. The Deformation Energy Ratio approach is based on well-established mechanical principles, such as Neuber's rule and the Equivalent Strain Energy Density method, which express deformation energy as a function of stress and strain. This approach accounts for material conditions in both analyses and enables a more precise limit adjustment. Its simplicity allows for application in both analytical and numerical solutions.

•
Allows conversion of values between numerical simulation and calculation for any steel.
•
It takes into account the influence of material properties, thus comprehensively considering the effects of different factors.
•
The verification has presented a high accuracy of the values obtained. The average deviation is <5.0 % and the maximum deviation is 5.6 %.

引用次数: 0

Eco-friendly pH monitoring in aquaculture: A comparative study of biomass waste extracts with different setup designs

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-15 DOI: 10.1016/j.mex.2025.103223

Farhad Nadi , Elham Fazel Najafabadi , Hajar Rastegari

Maintaining optimal water quality is critical for the success of aquaculture operations, where pH monitoring plays a pivotal role. This study presents a novel approach for pH monitoring in aquaculture ponds by harnessing biomass-based indicators and smartphone-based colorimetric sensing using different setups designs. Three biomass indicators including red cabbage, mango leaf, and used coffee grounds extracts were tested. Standard solutions across a pH range of 1–13 were tested using four setups: black and white polypropylene enclosures, a polyethylene pipe assembly, and a polystyrene tray configuration. The polystyrene tray configuration was determined to be the most effective, as its longer light path (4.5 cm) significantly enhanced color visibility and produced more vibrant color changes, making it ideal for further investigations. The method is as follows:

•
Water samples were collected from aquaculture ponds. pH were analyzed using this method and standard pH meters.
•
Mango leaf extract showed strong pH sensitivity and correlation (R² =0.9654).
•
The mango leaf extract attained a quantification accuracy of 0.5 pH units within a pH range of 3–12.
•
This smartphone-based approach offers simplicity and ease of implementation empowering aquaculture farmers with a practical tool for monitoring water quality.

{"title":"Eco-friendly pH monitoring in aquaculture: A comparative study of biomass waste extracts with different setup designs","authors":"Farhad Nadi , Elham Fazel Najafabadi , Hajar Rastegari","doi":"10.1016/j.mex.2025.103223","DOIUrl":"10.1016/j.mex.2025.103223","url":null,"abstract":"<div><div>Maintaining optimal water quality is critical for the success of aquaculture operations, where pH monitoring plays a pivotal role. This study presents a novel approach for pH monitoring in aquaculture ponds by harnessing biomass-based indicators and smartphone-based colorimetric sensing using different setups designs. Three biomass indicators including red cabbage, mango leaf, and used coffee grounds extracts were tested. Standard solutions across a pH range of 1–13 were tested using four setups: black and white polypropylene enclosures, a polyethylene pipe assembly, and a polystyrene tray configuration. The polystyrene tray configuration was determined to be the most effective, as its longer light path (4.5 cm) significantly enhanced color visibility and produced more vibrant color changes, making it ideal for further investigations. The method is as follows:<ul><li><span>•</span><span><div>Water samples were collected from aquaculture ponds. pH were analyzed using this method and standard pH meters.</div></span></li><li><span>•</span><span><div>Mango leaf extract showed strong pH sensitivity and correlation (R² =0.9654).</div></span></li><li><span>•</span><span><div>The mango leaf extract attained a quantification accuracy of 0.5 pH units within a pH range of 3–12.</div></span></li><li><span>•</span><span><div>This smartphone-based approach offers simplicity and ease of implementation empowering aquaculture farmers with a practical tool for monitoring water quality.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103223"},"PeriodicalIF":1.6,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advanced image preprocessing and context-aware spatial decomposition for enhanced breast cancer segmentation

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-15 DOI: 10.1016/j.mex.2025.103224

G. Kalpana , N. Deepa , D. Dhinakaran

The segmentation of breast cancer diagnosis and medical imaging contains issues such as noise, variation in contrast, and low resolutions which make it challenging to distinguish malignant sites. In this paper, we propose a new solution that integrates with AIPT (Advanced Image Preprocessing Techniques) and CASDN (Context-Aware Spatial Decomposition Network) to overcome these problems. The preprocessing pipeline apply bunch of methods including Adaptive Thresholding, Hierarchical Contrast Normalization, Contextual Feature Augmentation, Multi-Scale Region Enhancement, and Dynamic Histogram Equalization for image quality. These methods smooth edges, equalize the contrasting picture and inlay contextual details in a way which effectively eliminate the noise and make the images clearer and with fewer distortions. Experimental outcomes demonstrate its effectiveness by delivering a Dice Coefficient of 0.89, IoU of 0.85, and a Hausdorff Distance of 5.2 demonstrating its enhanced capability in segmenting significant tumor margins over other techniques. Furthermore, the use of the improved preprocessing pipeline benefits classification models with improved Convolutional Neural Networks having a classification accuracy of 85.3 % coupled with AUC-ROC of 0.90 which shows a significant enhancement from conventional techniques.

•
Enhanced segmentation accuracy with advanced preprocessing and CASDN, achieving superior performance metrics.
•
Robust multi-modality compatibility, ensuring effectiveness across mammograms, ultrasounds, and MRI scans.

{"title":"Advanced image preprocessing and context-aware spatial decomposition for enhanced breast cancer segmentation","authors":"G. Kalpana , N. Deepa , D. Dhinakaran","doi":"10.1016/j.mex.2025.103224","DOIUrl":"10.1016/j.mex.2025.103224","url":null,"abstract":"<div><div>The segmentation of breast cancer diagnosis and medical imaging contains issues such as noise, variation in contrast, and low resolutions which make it challenging to distinguish malignant sites. In this paper, we propose a new solution that integrates with AIPT (Advanced Image Preprocessing Techniques) and CASDN (Context-Aware Spatial Decomposition Network) to overcome these problems. The preprocessing pipeline apply bunch of methods including Adaptive Thresholding, Hierarchical Contrast Normalization, Contextual Feature Augmentation, Multi-Scale Region Enhancement, and Dynamic Histogram Equalization for image quality. These methods smooth edges, equalize the contrasting picture and inlay contextual details in a way which effectively eliminate the noise and make the images clearer and with fewer distortions. Experimental outcomes demonstrate its effectiveness by delivering a Dice Coefficient of 0.89, IoU of 0.85, and a Hausdorff Distance of 5.2 demonstrating its enhanced capability in segmenting significant tumor margins over other techniques. Furthermore, the use of the improved preprocessing pipeline benefits classification models with improved Convolutional Neural Networks having a classification accuracy of 85.3 % coupled with AUC-ROC of 0.90 which shows a significant enhancement from conventional techniques.<ul><li><span>•</span><span><div>Enhanced segmentation accuracy with advanced preprocessing and CASDN, achieving superior performance metrics.</div></span></li><li><span>•</span><span><div>Robust multi-modality compatibility, ensuring effectiveness across mammograms, ultrasounds, and MRI scans.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103224"},"PeriodicalIF":1.6,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An efficient method of modulo adder design for Digital Signal Processing applications

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-15 DOI: 10.1016/j.mex.2025.103216

Subodh Kumar Singhal , Sumit Kumar , Sujit Kumar Patel , K. Anjali Rao , Gaurav Saxena

Modulo adder is a widely used arithmetic component in many Digital Signal Processing (DSP) applications such as Finite Impulse Response (FIR), Infinite Impulse Response (IIR) filters, digital signal processors, image processing modules, discrete cosine transform, and cryptography. Therefore, in this paper, the critical path delay and area of modulo adder are analyzed. An optimized diminished-one modulo adder for

2^{n} + 1

is proposed based on the analysis results.

•
Theoretical comparison shows that the suggested modulo adder involves 23.41 % less area (transistors count) and 31.64 % less delay than the best existing design for an average bit-width.
•
Synthesis result reveals that the proposed modulo adder involves 13.71 % less area and 14.5 % less delay compared to the best existing modulo adder structure design in the literature for an average bit-width.
•
To observe the overall efficacy of the suggested modulo adder design, the area delay product (ADP) and power delay product (PDP) values of the proposed and existing modulo adder designs are computed using synthesis data. The values obtained for ADP and PDP reveal that the proposed design achieves a 26.2 % reduction in ADP and a 32.8 % improvement in PDP compared to the best available modulo-adder structure.

{"title":"An efficient method of modulo adder design for Digital Signal Processing applications","authors":"Subodh Kumar Singhal , Sumit Kumar , Sujit Kumar Patel , K. Anjali Rao , Gaurav Saxena","doi":"10.1016/j.mex.2025.103216","DOIUrl":"10.1016/j.mex.2025.103216","url":null,"abstract":"<div><div>Modulo adder is a widely used arithmetic component in many Digital Signal Processing (DSP) applications such as Finite Impulse Response (FIR), Infinite Impulse Response (IIR) filters, digital signal processors, image processing modules, discrete cosine transform, and cryptography. Therefore, in this paper, the critical path delay and area of modulo adder are analyzed. An optimized diminished-one modulo adder for <span><math><mrow><msup><mrow><mn>2</mn></mrow><mi>n</mi></msup><mo>+</mo><mn>1</mn></mrow></math></span> is proposed based on the analysis results.<ul><li><span>•</span><span><div>Theoretical comparison shows that the suggested modulo adder involves 23.41 % less area (transistors count) and 31.64 % less delay than the best existing design for an average bit-width.</div></span></li><li><span>•</span><span><div>Synthesis result reveals that the proposed modulo adder involves 13.71 % less area and 14.5 % less delay compared to the best existing modulo adder structure design in the literature for an average bit-width.</div></span></li><li><span>•</span><span><div>To observe the overall efficacy of the suggested modulo adder design, the area delay product (ADP) and power delay product (PDP) values of the proposed and existing modulo adder designs are computed using synthesis data. The values obtained for ADP and PDP reveal that the proposed design achieves a 26.2 % reduction in ADP and a 32.8 % improvement in PDP compared to the best available modulo-adder structure.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103216"},"PeriodicalIF":1.6,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

“Optimizing sEMG Gesture Recognition with Stacked Autoencoder Neural Network for Bionic Hand” "利用堆叠式自动编码器神经网络优化仿生手的 sEMG 手势识别"

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2025-02-15 DOI: 10.1016/j.mex.2025.103207

Mr. Amol Pandurang Yadav , Dr. Sandip.R. Patil

This study presents a novel deep learning approach for surface electromyography (sEMG) gesture recognition using stacked autoencoder neural network (SAE)s. The method leverages hierarchical representation learning to extract meaningful features from raw sEMG signals, enhancing the precision and robustness of gesture classification.

•
Feature Extraction and Classification MODWT Decomposition: The sEMG signals were decomposed using the MODWT DECOMPOSITION(Maximal Overlap Discrete Wavelet Transform) to capture various frequency components.
•
Time Domain Parameters: A total of 28 features per subject were extracted from the time domain, including statistical and spectral features.
•
Classifier Evaluation: Initial evaluations involved Autoencoder and LDA (Linear Discriminant Analysis) classifiers, with Autoencoder achieving an average accuracy of 77.96 % ± 1.24, outperforming LDA's 65.36 % ± 1.09.

Advanced Neural Network Approach: Stacked Autoencoder Neural Network: To address challenges in distinguishing similar gestures within grasp groups, a Stacked Autoencoder Neural Network was employed. This advanced neural network architecture improved classification accuracy to over 100 %, demonstrating its effectiveness in handling complex gesture recognition tasks. These findings emphasize the significant potential of deep learning models in enhancing prosthetic control and rehabilitation technologies. . To verify these findings, we developed a 3d hand module in ADAMS software that is simulated using Matlab-ADAMS cosimulation.

{"title":"“Optimizing sEMG Gesture Recognition with Stacked Autoencoder Neural Network for Bionic Hand”","authors":"Mr. Amol Pandurang Yadav , Dr. Sandip.R. Patil","doi":"10.1016/j.mex.2025.103207","DOIUrl":"10.1016/j.mex.2025.103207","url":null,"abstract":"<div><div>This study presents a novel deep learning approach for surface electromyography (sEMG) gesture recognition using stacked autoencoder neural network (SAE)s. The method leverages hierarchical representation learning to extract meaningful features from raw sEMG signals, enhancing the precision and robustness of gesture classification.<ul><li><span>•</span><span><div>Feature Extraction and Classification MODWT Decomposition: The sEMG signals were decomposed using the MODWT DECOMPOSITION(Maximal Overlap Discrete Wavelet Transform) to capture various frequency components.</div></span></li><li><span>•</span><span><div>Time Domain Parameters: A total of 28 features per subject were extracted from the time domain, including statistical and spectral features.</div></span></li><li><span>•</span><span><div>Classifier Evaluation: Initial evaluations involved Autoencoder and LDA (Linear Discriminant Analysis) classifiers, with Autoencoder achieving an average accuracy of 77.96 % ± 1.24, outperforming LDA's 65.36 % ± 1.09.</div></span></li></ul>Advanced Neural Network Approach: Stacked Autoencoder Neural Network: To address challenges in distinguishing similar gestures within grasp groups, a Stacked Autoencoder Neural Network was employed. This advanced neural network architecture improved classification accuracy to over 100 %, demonstrating its effectiveness in handling complex gesture recognition tasks. These findings emphasize the significant potential of deep learning models in enhancing prosthetic control and rehabilitation technologies. . To verify these findings, we developed a 3d hand module in ADAMS software that is simulated using Matlab-ADAMS cosimulation.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103207"},"PeriodicalIF":1.6,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

MethodsX

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀