Pub Date : 2024-08-29DOI: 10.1007/s13198-024-02472-y
Jyothi Padmaja Koduru, T. Vijay Kumar, Kedar Mallik Mantrala
Because of the reasonability of economically generating large-scale metal equipment with a very large rate of deposition, important development has been conducted in the learning of the “wire arc additive manufacturing (WAAM)” approach also the mechanical and microstructure features of the fabricated elements. The WAAM has emerged highly so the large range of the materials has accompanied the operation and its development fighting. It has enhanced as a very significant mechanism for the large metal equipment in various manufacturing organizations. Because of its arc-assisted deposition, high process cycle time, process stability, defect monitoring, and management are severe for the WAAM device to be employed in the organization. High improvements have been performed in the development of the process, control system, comprehensive operation monitoring, material evaluation, path slicing, and programming but still, it demands the improvement. Therefore, this article aims to give a detailed review of the WAAM systems to facilitate an easy and quick understanding of the current status and future prospects of WAAM. The stage-wise implementation of WAAM, usage of metals and alloys, process parameter effects, and methodologies used for improving the quality of WAAM components are discussed. The usage of hardware systems and technological parameters used for understanding the physical mechanism are also described in this research work. In addition, the monitoring systems such as acoustic sensing, optical inspection, thermal sensing, electrical sensing, and multi-sensor sensing are analyzed and the property characterization techniques also be evaluated in this study. On the other hand, the additive as well as the subtractive technologies and the artificial intelligence techniques utilized for improving the manufacturing level are discussed. Finally, the possible future research directions are provided for making further developments in WAAM by the researchers.
{"title":"A review of wire and arc additive manufacturing using different property characterization, challenges and future trends","authors":"Jyothi Padmaja Koduru, T. Vijay Kumar, Kedar Mallik Mantrala","doi":"10.1007/s13198-024-02472-y","DOIUrl":"https://doi.org/10.1007/s13198-024-02472-y","url":null,"abstract":"<p>Because of the reasonability of economically generating large-scale metal equipment with a very large rate of deposition, important development has been conducted in the learning of the “wire arc additive manufacturing (WAAM)” approach also the mechanical and microstructure features of the fabricated elements. The WAAM has emerged highly so the large range of the materials has accompanied the operation and its development fighting. It has enhanced as a very significant mechanism for the large metal equipment in various manufacturing organizations. Because of its arc-assisted deposition, high process cycle time, process stability, defect monitoring, and management are severe for the WAAM device to be employed in the organization. High improvements have been performed in the development of the process, control system, comprehensive operation monitoring, material evaluation, path slicing, and programming but still, it demands the improvement. Therefore, this article aims to give a detailed review of the WAAM systems to facilitate an easy and quick understanding of the current status and future prospects of WAAM. The stage-wise implementation of WAAM, usage of metals and alloys, process parameter effects, and methodologies used for improving the quality of WAAM components are discussed. The usage of hardware systems and technological parameters used for understanding the physical mechanism are also described in this research work. In addition, the monitoring systems such as acoustic sensing, optical inspection, thermal sensing, electrical sensing, and multi-sensor sensing are analyzed and the property characterization techniques also be evaluated in this study. On the other hand, the additive as well as the subtractive technologies and the artificial intelligence techniques utilized for improving the manufacturing level are discussed. Finally, the possible future research directions are provided for making further developments in WAAM by the researchers.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225047","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 : 2024-08-28DOI: 10.1007/s13198-024-02461-1
Manish Verma, Parma Nand
Android protects user privacy through its permission system and explains permission usage in privacy disclosure. Privacy disclosure often fails to predict app behavior accurately and leading to potential exploitation by malicious applications. To address this, we propose the VADER-RF technique, which combines VADER sentiment analysis with Random Forest machine learning to correlate privacy disclosures with app behavior. Our model analyzes privacy disclosure documents using sentiment analysis, extracting permissions from AndroidManifest.xml file, and explore the data flow analysis of Java files. These features were evaluated on Naive Bayes, SVM, Decision Tree and Random Forest machine learning models. The Random Forest model demonstrated superior performance with the highest accuracy (81.6%), precision (85.3%) and recall (89.4%). Kendall's Tau correlation coefficient is 0.54, which indicates that our model is moderate to strongly effective at predicting whether an app is malicious based on the selected features. Sentiment analysis significantly enhanced all models’ performance, underscoring the effectiveness of integrating sentiment analysis with traditional feature sets for advanced malware detection.
安卓通过权限系统保护用户隐私,并在隐私披露中解释权限的使用。隐私披露往往不能准确预测应用程序的行为,从而导致恶意应用程序的潜在利用。针对这一问题,我们提出了 VADER-RF 技术,该技术将 VADER 情感分析与随机森林机器学习相结合,将隐私披露与应用程序行为关联起来。我们的模型利用情感分析来分析隐私披露文件,从 AndroidManifest.xml 文件中提取权限,并探索 Java 文件的数据流分析。在 Naive Bayes、SVM、决策树和随机森林机器学习模型上对这些特征进行了评估。随机森林模型表现优异,准确率(81.6%)、精确率(85.3%)和召回率(89.4%)最高。Kendall's Tau 相关系数为 0.54,这表明我们的模型在根据所选特征预测应用程序是否为恶意应用程序方面具有中度到高度的有效性。情感分析大大提高了所有模型的性能,突出表明了将情感分析与传统特征集整合用于高级恶意软件检测的有效性。
{"title":"VADER-RF: a novel scheme for protecting user privacy on android devices","authors":"Manish Verma, Parma Nand","doi":"10.1007/s13198-024-02461-1","DOIUrl":"https://doi.org/10.1007/s13198-024-02461-1","url":null,"abstract":"<p>Android protects user privacy through its permission system and explains permission usage in privacy disclosure. Privacy disclosure often fails to predict app behavior accurately and leading to potential exploitation by malicious applications. To address this, we propose the VADER-RF technique, which combines VADER sentiment analysis with Random Forest machine learning to correlate privacy disclosures with app behavior. Our model analyzes privacy disclosure documents using sentiment analysis, extracting permissions from AndroidManifest.xml file, and explore the data flow analysis of Java files. These features were evaluated on Naive Bayes, SVM, Decision Tree and Random Forest machine learning models. The Random Forest model demonstrated superior performance with the highest accuracy (81.6%), precision (85.3%) and recall (89.4%). Kendall's Tau correlation coefficient is 0.54, which indicates that our model is moderate to strongly effective at predicting whether an app is malicious based on the selected features. Sentiment analysis significantly enhanced all models’ performance, underscoring the effectiveness of integrating sentiment analysis with traditional feature sets for advanced malware detection.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194366","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 : 2024-08-28DOI: 10.1007/s13198-024-02485-7
Wasiur Rhmann, Amaan Ishrat
Web services are a novel method of web application development. They allow business to adapt to a new environment and change quickly according to customer needs. The client requires high-quality web services with minimal response time, more security, and high availability. With the increasing demand for web services, the introduction of web services rapidly in the business environment has influenced rapidly the web service quality. In the present work, a novel model for web service classification is proposed. Three metaheuristic techniques: Whale optimization algorithm, Simulated annealing algorithm, and Ant colony optimization are used to select the best subset of features. Web service-based imbalanced dataset is balanced using SMOTETomek (Synthetic minority oversampling + Tomek link). Ensemble Adaboost and Gradient boosting algorithms are used for the creation of a web service prediction model. The publicly available QWS dataset is used for experimental purposes. The results of the proposed models are compared with machine learning techniques. It was observed that the Ant colony algorithm performed best for relevant feature selection and the Ensemble Adaboost and Gradient boosting algorithm outperformed all other machine learning techniques for web service classification.
{"title":"Imbalanced data preprocessing model for web service classification","authors":"Wasiur Rhmann, Amaan Ishrat","doi":"10.1007/s13198-024-02485-7","DOIUrl":"https://doi.org/10.1007/s13198-024-02485-7","url":null,"abstract":"<p>Web services are a novel method of web application development. They allow business to adapt to a new environment and change quickly according to customer needs. The client requires high-quality web services with minimal response time, more security, and high availability. With the increasing demand for web services, the introduction of web services rapidly in the business environment has influenced rapidly the web service quality. In the present work, a novel model for web service classification is proposed. Three metaheuristic techniques: Whale optimization algorithm, Simulated annealing algorithm, and Ant colony optimization are used to select the best subset of features. Web service-based imbalanced dataset is balanced using SMOTETomek (Synthetic minority oversampling + Tomek link). Ensemble Adaboost and Gradient boosting algorithms are used for the creation of a web service prediction model. The publicly available QWS dataset is used for experimental purposes. The results of the proposed models are compared with machine learning techniques. It was observed that the Ant colony algorithm performed best for relevant feature selection and the Ensemble Adaboost and Gradient boosting algorithm outperformed all other machine learning techniques for web service classification.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194337","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 : 2024-08-27DOI: 10.1007/s13198-024-02464-y
M. Uma Maheswari, K. Perumal
Internet of Things (IoT) gadget proliferation has resulted in unprecedented connectedness as well as simplicity, but it has raised serious security concerns. Botnet attacks can threaten the security, integrity and accessibility of critical data and services and IoT networks are susceptible to them. To increase the security to identify botnet attacks in IoT networks, this study suggests a model based on a Parallel Gradient Descent Optimized Four Layered Network (PGDOFLN).We gathered the CICIDS2017 dataset from Kaggle, which is used to train and assess the proposed model. Using a robust scalar to handle missing values allows for the normalization of data, the t-distributed stochastic neighbor embedding (t-SNE) technique is utilized for extracting the feature and the LASSO method is used for feature selection. This study on attack detection is based on PGDOFLN and uses a Python program. The simulated results showed that the suggested method outperforms existing methods with an accuracy (0.95), recall (0.95), precision (1.00), and f1 score (0.97). This study supports continuing attempts to protect IoT networks and safeguard private information, vital infrastructure, and sensitive data.
物联网(IoT)小工具的激增带来了前所未有的连接性和简便性,但也引发了严重的安全问题。僵尸网络攻击会威胁到关键数据和服务的安全性、完整性和可访问性,物联网网络很容易受到僵尸网络攻击的影响。为了提高识别物联网网络中僵尸网络攻击的安全性,本研究提出了一种基于并行梯度下降优化四层网络(PGDOFLN)的模型。我们从 Kaggle 收集了 CICIDS2017 数据集,用于训练和评估所提出的模型。我们从 Kaggle 收集了 CICIDS2017 数据集,并使用该数据集对所提出的模型进行了训练和评估。使用鲁棒标量处理缺失值可实现数据的归一化,使用 t 分布随机邻域嵌入(t-SNE)技术提取特征,并使用 LASSO 方法进行特征选择。该攻击检测研究基于 PGDOFLN,并使用 Python 程序。模拟结果表明,建议的方法在准确率(0.95)、召回率(0.95)、精确度(1.00)和 f1 分数(0.97)方面均优于现有方法。这项研究为保护物联网网络、保护私人信息、重要基础设施和敏感数据的持续尝试提供了支持。
{"title":"Enhancing the security of botnet attacks detection using parallel gradient descent optimized four layered network (PGDOFLN)","authors":"M. Uma Maheswari, K. Perumal","doi":"10.1007/s13198-024-02464-y","DOIUrl":"https://doi.org/10.1007/s13198-024-02464-y","url":null,"abstract":"<p>Internet of Things (IoT) gadget proliferation has resulted in unprecedented connectedness as well as simplicity, but it has raised serious security concerns. Botnet attacks can threaten the security, integrity and accessibility of critical data and services and IoT networks are susceptible to them. To increase the security to identify botnet attacks in IoT networks, this study suggests a model based on a Parallel Gradient Descent Optimized Four Layered Network (PGDOFLN).We gathered the CICIDS2017 dataset from Kaggle, which is used to train and assess the proposed model. Using a robust scalar to handle missing values allows for the normalization of data, the t-distributed stochastic neighbor embedding (t-SNE) technique is utilized for extracting the feature and the LASSO method is used for feature selection. This study on attack detection is based on PGDOFLN and uses a Python program. The simulated results showed that the suggested method outperforms existing methods with an accuracy (0.95), recall (0.95), precision (1.00), and f1 score (0.97). This study supports continuing attempts to protect IoT networks and safeguard private information, vital infrastructure, and sensitive data.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194367","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 : 2024-08-25DOI: 10.1007/s13198-024-02466-w
Monika Kumari, Ajay Kaul
Scene classification in remote sensing is challenging due to high inter-class similarity and low intra-class similarity. Numerous techniques have been introduced, but accurately classifying scenes remains arduous. To address this challenge, To address this, we propose a hybrid framework, DF-DNLSTM, integrating DenseNet-121 for feature extraction and BiLSTM for sequential modeling, enhancing accuracy and contextual understanding. Second, a Conditional Generative Adversarial Network (CGAN) is employed for data augmentation, improving training data quantity and quality. Finally, the study introduces SwarmHawk, a hybrid optimization algorithm that combines particle swarm optimization (PSO) and Harris hawk optimization (HHO). SwarmHawk ensures the selection of informative features while concurrently eliminating duplicates and redundancies. It also reduces computational time to 4863 s. The proposed DF-DNLSTM model is rigorously assessed on three public datasets-UCM, AID, and NWPU. Results demonstrate its superior efficacy, achieving 99.87% accuracy on UCM, equivalent accuracy on NWPU, and sustaining 98.57% accuracy on AID. This study establishes DF-DNLSTM’s effectiveness, highlighting its potential contributions to advancing remote sensing scene classification.
{"title":"Efficient classification of remote sensing images using DF-DNLSTM: a deep feature densenet bidirectional long short term memory model","authors":"Monika Kumari, Ajay Kaul","doi":"10.1007/s13198-024-02466-w","DOIUrl":"https://doi.org/10.1007/s13198-024-02466-w","url":null,"abstract":"<p>Scene classification in remote sensing is challenging due to high inter-class similarity and low intra-class similarity. Numerous techniques have been introduced, but accurately classifying scenes remains arduous. To address this challenge, To address this, we propose a hybrid framework, DF-DNLSTM, integrating DenseNet-121 for feature extraction and BiLSTM for sequential modeling, enhancing accuracy and contextual understanding. Second, a Conditional Generative Adversarial Network (CGAN) is employed for data augmentation, improving training data quantity and quality. Finally, the study introduces SwarmHawk, a hybrid optimization algorithm that combines particle swarm optimization (PSO) and Harris hawk optimization (HHO). SwarmHawk ensures the selection of informative features while concurrently eliminating duplicates and redundancies. It also reduces computational time to 4863 s. The proposed DF-DNLSTM model is rigorously assessed on three public datasets-UCM, AID, and NWPU. Results demonstrate its superior efficacy, achieving 99.87% accuracy on UCM, equivalent accuracy on NWPU, and sustaining 98.57% accuracy on AID. This study establishes DF-DNLSTM’s effectiveness, highlighting its potential contributions to advancing remote sensing scene classification.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224888","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 : 2024-08-25DOI: 10.1007/s13198-024-02448-y
Afrah Fathima, G. Shree Devi
Network traffic monitoring and visualization are essential for university network management and security. This research study uses the Paessler’s PRTG Network Monitoring Tool and Sophos Firewall to monitor and visualize a Campus network traffic in real time. The proposed system gives university network administrators complete access into traffic patterns, security concerns, and performance metrics for efficient network administration and improved security. The research begins with university network issues, including rising bandwidth demand, diversified traffic, and changing security threats. The paper then discusses the PRTG Tool, a popular network-monitoring tool with strong scalability, and Sophos Firewall, a sophisticated network security solution. The integration of the two tools underpins the proposed real-time monitoring system. It also describes the system design, which uses PRTG Network Monitor sensors strategically distributed throughout the network infrastructure to collect real-time network traffic statistics. These sensors collect traffic data using SNMP and flow technologies such as NetFlow or sFlow. The monitoring system and Sophos Firewall enable real-time threat detection and prevention to improve security. The research paper also discusses the data visualization features of the PRTG Network Monitor. It shows how graphs, charts, and dashboards help network managers understand traffic patterns and spot anomalies and make informed network optimization and security decisions. The paper also discusses a case study of a university network using the proposed approach. The results show that real-time monitoring and visualization can improve network administration and security. This paper presents a real-time network traffic monitoring and visualization solution for university networks.
{"title":"Enhancing university network management and security: a real-time monitoring, visualization & cyber attack detection approach using Paessler PRTG and Sophos Firewall","authors":"Afrah Fathima, G. Shree Devi","doi":"10.1007/s13198-024-02448-y","DOIUrl":"https://doi.org/10.1007/s13198-024-02448-y","url":null,"abstract":"<p>Network traffic monitoring and visualization are essential for university network management and security. This research study uses the Paessler’s PRTG Network Monitoring Tool and Sophos Firewall to monitor and visualize a Campus network traffic in real time. The proposed system gives university network administrators complete access into traffic patterns, security concerns, and performance metrics for efficient network administration and improved security. The research begins with university network issues, including rising bandwidth demand, diversified traffic, and changing security threats. The paper then discusses the PRTG Tool, a popular network-monitoring tool with strong scalability, and Sophos Firewall, a sophisticated network security solution. The integration of the two tools underpins the proposed real-time monitoring system. It also describes the system design, which uses PRTG Network Monitor sensors strategically distributed throughout the network infrastructure to collect real-time network traffic statistics. These sensors collect traffic data using SNMP and flow technologies such as NetFlow or sFlow. The monitoring system and Sophos Firewall enable real-time threat detection and prevention to improve security. The research paper also discusses the data visualization features of the PRTG Network Monitor. It shows how graphs, charts, and dashboards help network managers understand traffic patterns and spot anomalies and make informed network optimization and security decisions. The paper also discusses a case study of a university network using the proposed approach. The results show that real-time monitoring and visualization can improve network administration and security. This paper presents a real-time network traffic monitoring and visualization solution for university networks.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194369","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 : 2024-08-23DOI: 10.1007/s13198-024-02483-9
V. Nithya, M. S. Josephine, V. Jeyabalaraja
Agriculture is an expanding area of study. Crop prediction in agriculture is highly dependent on soil and environmental factors, such as rainfall, humidity, and temperature. Previously, farmers had the authority to select the crop to be farmed, oversee its development, and ascertain the optimal harvest time. The farming community is facing challenges in sustaining its practices due to the swift alterations in climatic conditions. Therefore, machine learning algorithms have replaced traditional methods in predicting agricultural productivity in recent years. To guarantee optimal precision through a specific machine learning approach. Authors extend their approach not limited to Machine Learning but also with Deep Learning Techniques. We use machine and deep learning algorithms to predict crop outcomes accurately. In this proposed model, we utilise machine learning algorithms such as Naive Bayes, decision tree, and KNN. It is worth noting that the decision tree algorithm demonstrates superior performance compared to the other algorithms, achieving an accuracy rate of 83%. In order to enhance the precision, we have suggested implementing a deep learning technique, specifically a convolutional neural network, to identify the crops. Achieving an accuracy of 93.54% was made possible by implementing this advanced deep-learning model.
{"title":"Comparative approach on crop detection using machine learning and deep learning techniques","authors":"V. Nithya, M. S. Josephine, V. Jeyabalaraja","doi":"10.1007/s13198-024-02483-9","DOIUrl":"https://doi.org/10.1007/s13198-024-02483-9","url":null,"abstract":"<p>Agriculture is an expanding area of study. Crop prediction in agriculture is highly dependent on soil and environmental factors, such as rainfall, humidity, and temperature. Previously, farmers had the authority to select the crop to be farmed, oversee its development, and ascertain the optimal harvest time. The farming community is facing challenges in sustaining its practices due to the swift alterations in climatic conditions. Therefore, machine learning algorithms have replaced traditional methods in predicting agricultural productivity in recent years. To guarantee optimal precision through a specific machine learning approach. Authors extend their approach not limited to Machine Learning but also with Deep Learning Techniques. We use machine and deep learning algorithms to predict crop outcomes accurately. In this proposed model, we utilise machine learning algorithms such as Naive Bayes, decision tree, and KNN. It is worth noting that the decision tree algorithm demonstrates superior performance compared to the other algorithms, achieving an accuracy rate of 83%. In order to enhance the precision, we have suggested implementing a deep learning technique, specifically a convolutional neural network, to identify the crops. Achieving an accuracy of 93.54% was made possible by implementing this advanced deep-learning model.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194406","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 : 2024-08-22DOI: 10.1007/s13198-024-02454-0
Akram Qashou, Sufian Yousef, Firas Hazzaa, Kahtan Aziz
The malfunction variables of power stations are related to the areas of weather, physical structure, control, and load behavior. To predict temporal power failure is difficult due to their unpredictable characteristics. As high accuracy is normally required, the estimation of failures of short-term temporal prediction is highly difficult. This study presents a method for converting stochastic behavior into a stable pattern, which can subsequently be used in a short-term estimator. For this conversion, K-means clustering is employed, followed by long-short-term memory and gated recurrent unit algorithms are used to perform the short-term estimation. The environment, the operation, and the generated signal factors are all simulated using mathematical models. Weather parameters and load samples have been collected as part of a dataset. Monte-Carlo simulation using MATLAB programming has been used to conduct experimental estimation of failures. The estimated failures of the experiment are then compared with the actual system temporal failures and found to be in good match. Therefore, to address the gap in knowledge for any future power grid estimated failures, the achieved results in this paper form good basis for a testbed to estimate any grid future failures.
发电站的故障变量与天气、物理结构、控制和负荷行为等方面有关。由于其不可预测的特性,预测时间性电力故障非常困难。由于通常要求高精度,短期时间预测的故障估计非常困难。本研究提出了一种将随机行为转换为稳定模式的方法,这种模式随后可用于短期估算。在这种转换中,采用了 K 均值聚类,然后使用长短期记忆和门控递归单元算法来进行短期估算。环境、运行和生成的信号因素都是通过数学模型模拟的。天气参数和负荷样本已作为数据集的一部分收集起来。使用 MATLAB 编程进行蒙特卡洛模拟,对故障进行实验估算。然后将实验估计的故障与实际的系统时间故障进行比较,发现两者非常吻合。因此,为了填补未来电网故障估计方面的知识空白,本文所取得的成果为电网未来故障估计试验台奠定了良好的基础。
{"title":"Temporal forecasting by converting stochastic behaviour into a stable pattern in electric grid","authors":"Akram Qashou, Sufian Yousef, Firas Hazzaa, Kahtan Aziz","doi":"10.1007/s13198-024-02454-0","DOIUrl":"https://doi.org/10.1007/s13198-024-02454-0","url":null,"abstract":"<p>The malfunction variables of power stations are related to the areas of weather, physical structure, control, and load behavior. To predict temporal power failure is difficult due to their unpredictable characteristics. As high accuracy is normally required, the estimation of failures of short-term temporal prediction is highly difficult. This study presents a method for converting stochastic behavior into a stable pattern, which can subsequently be used in a short-term estimator. For this conversion, K-means clustering is employed, followed by long-short-term memory and gated recurrent unit algorithms are used to perform the short-term estimation. The environment, the operation, and the generated signal factors are all simulated using mathematical models. Weather parameters and load samples have been collected as part of a dataset. Monte-Carlo simulation using MATLAB programming has been used to conduct experimental estimation of failures. The estimated failures of the experiment are then compared with the actual system temporal failures and found to be in good match. Therefore, to address the gap in knowledge for any future power grid estimated failures, the achieved results in this paper form good basis for a testbed to estimate any grid future failures.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194370","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 : 2024-08-20DOI: 10.1007/s13198-024-02474-w
Pengju Xia
Blockchain data asset transaction technology has advantages such as decentralization and data that cannot be tampered with, which can expand the application field of blockchain technology. However, the consensus algorithm widely used in the current blockchain system with the low consensus efficiency makes the development of blockchain technology significantly restricted. Regarding the above-mentioned problems, this research proposes an improved two-way transaction algorithm based on the theory of practical Byzantine fault-tolerant algorithm. The consensus protocol of the algorithm is improved when there is no Byzantine node. The purpose is to reduce the traffic generated during consensus so that the algorithm can be kept in the best state, and ensure that the algorithm can execute the consensus protocol in any period. The experimental results showed that the proposed two-way transaction algorithm had shorter transaction delay and lower traffic than the traditional Byzantine fault-tolerant algorithm. The former had the highest stability value of 0.98 at low, medium and high bandwidth, which was much higher than that the latter's 0.90. Applying the designed bidirectional trading algorithm to the blockchain data asset trading system, it is found that the number of blocks generated by the trading system was about 50 per second, the delay was about 8 s, and the success rate was 100%. In each node, the memory consumption of the peer node was about 128 M and the CPU consumption was about 48%. It can be seen that the transaction model proposed in this study can not only meet the usage needs, but also optimize the system security.
{"title":"Blockchain data asset management technology based on a two-way transaction algorithm","authors":"Pengju Xia","doi":"10.1007/s13198-024-02474-w","DOIUrl":"https://doi.org/10.1007/s13198-024-02474-w","url":null,"abstract":"<p>Blockchain data asset transaction technology has advantages such as decentralization and data that cannot be tampered with, which can expand the application field of blockchain technology. However, the consensus algorithm widely used in the current blockchain system with the low consensus efficiency makes the development of blockchain technology significantly restricted. Regarding the above-mentioned problems, this research proposes an improved two-way transaction algorithm based on the theory of practical Byzantine fault-tolerant algorithm. The consensus protocol of the algorithm is improved when there is no Byzantine node. The purpose is to reduce the traffic generated during consensus so that the algorithm can be kept in the best state, and ensure that the algorithm can execute the consensus protocol in any period. The experimental results showed that the proposed two-way transaction algorithm had shorter transaction delay and lower traffic than the traditional Byzantine fault-tolerant algorithm. The former had the highest stability value of 0.98 at low, medium and high bandwidth, which was much higher than that the latter's 0.90. Applying the designed bidirectional trading algorithm to the blockchain data asset trading system, it is found that the number of blocks generated by the trading system was about 50 per second, the delay was about 8 s, and the success rate was 100%. In each node, the memory consumption of the peer node was about 128 M and the CPU consumption was about 48%. It can be seen that the transaction model proposed in this study can not only meet the usage needs, but also optimize the system security.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224889","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}
Fault localization (FL) is the key activity while debugging a program. Any improvement to this activity leads to significant improvement in total software development cost. In the paper, we present a conditional probability statistics based fault localization technique that derives the association between statement coverage information and test case execution result. This association with the failed test case result shows the fault containing probability of that specific statement. Subsequently, we use a grouping method to refine the obtained statement ranking sequence for better fault localization. We named our proposed FL technique as CGFL, it is an abbreviation of Conditional probability and Grouping based Fault Localization. We evaluated the effectiveness of the proposed method over eleven open-source data sets from Defects4j and SIR repositories. Our obtained results show that on average, the proposed CGFL method is 24.56% more effective than contemporary FL techniques namely D(^*), Tarantula, Ochiai, Crosstab, BPNN, RBFNN, DNN, and CNN.
{"title":"Effective fault localization using probabilistic and grouping approach","authors":"Saksham Sahai Srivastava, Arpita Dutta, Rajib Mall","doi":"10.1007/s13198-024-02479-5","DOIUrl":"https://doi.org/10.1007/s13198-024-02479-5","url":null,"abstract":"<p>Fault localization (FL) is the key activity while debugging a program. Any improvement to this activity leads to significant improvement in total software development cost. In the paper, we present a conditional probability statistics based fault localization technique that derives the association between statement coverage information and test case execution result. This association with the failed test case result shows the fault containing probability of that specific statement. Subsequently, we use a grouping method to refine the obtained statement ranking sequence for better fault localization. We named our proposed FL technique as CGFL, it is an abbreviation of Conditional probability and Grouping based Fault Localization. We evaluated the effectiveness of the proposed method over eleven open-source data sets from Defects4j and SIR repositories. Our obtained results show that on average, the proposed CGFL method is 24.56% more effective than contemporary FL techniques namely D<span>(^*)</span>, Tarantula, Ochiai, Crosstab, BPNN, RBFNN, DNN, and CNN.</p>","PeriodicalId":14463,"journal":{"name":"International Journal of System Assurance Engineering and Management","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2024-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194371","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}