Software-defined networking(SDN) is a trending networking paradigm that focuses on decoupling of the control logic from the data plane. This decoupling brings programmability and flexibility for the network management...Software-defined networking(SDN) is a trending networking paradigm that focuses on decoupling of the control logic from the data plane. This decoupling brings programmability and flexibility for the network management by introducing centralized infrastructure. The complete control logic resides in the controller, and thus it becomes the intellectual and most important entity of the SDN infrastructure. With these advantages, SDN faces several security issues in various SDN layers that may prevent the growth and global adoption of this groundbreaking technology. Control plane exhaustion and switch buffer overflow are examples of such security issues. Distributed denial-of-service(DDoS) attacks are one of the most severe attacks that aim to exhaust the controller’s CPU to discontinue the whole functioning of the SDN network. Hence, it is necessary to design a quick as well as accurate detection scheme to detect the attack traffic at an early stage. In this paper, we present a defense solution to detect and mitigate spoofed flooding DDoS attacks. The proposed defense solution is implemented in the SDN controller. The detection method is based on the idea of an statistical measure — Interquartile Range(IQR). For the mitigation purpose, the existing SDN-in-built capabilities are utilized. In this work, the experiments are performed considering the spoofed SYN flooding attack. The proposed solution is evaluated using different performance parameters, i.e., detection time, detection accuracy, packet_in messages, and CPU utilization. The experimental results reveal that the proposed defense solution detects and mitigates the attack effectively in different attack scenarios.展开更多
In recent years,there has been a concerted effort to improve anomaly detection tech-niques,particularly in the context of high-dimensional,distributed clinical data.Analysing patient data within clinical settings reve...In recent years,there has been a concerted effort to improve anomaly detection tech-niques,particularly in the context of high-dimensional,distributed clinical data.Analysing patient data within clinical settings reveals a pronounced focus on refining diagnostic accuracy,personalising treatment plans,and optimising resource allocation to enhance clinical outcomes.Nonetheless,this domain faces unique challenges,such as irregular data collection,inconsistent data quality,and patient-specific structural variations.This paper proposed a novel hybrid approach that integrates heuristic and stochastic methods for anomaly detection in patient clinical data to address these challenges.The strategy combines HPO-based optimal Density-Based Spatial Clustering of Applications with Noise for clustering patient exercise data,facilitating efficient anomaly identification.Subsequently,a stochastic method based on the Interquartile Range filters unreliable data points,ensuring that medical tools and professionals receive only the most pertinent and accurate information.The primary objective of this study is to equip healthcare pro-fessionals and researchers with a robust tool for managing extensive,high-dimensional clinical datasets,enabling effective isolation and removal of aberrant data points.Furthermore,a sophisticated regression model has been developed using Automated Machine Learning(AutoML)to assess the impact of the ensemble abnormal pattern detection approach.Various statistical error estimation techniques validate the efficacy of the hybrid approach alongside AutoML.Experimental results show that implementing this innovative hybrid model on patient rehabilitation data leads to a notable enhance-ment in AutoML performance,with an average improvement of 0.041 in the R2 score,surpassing the effectiveness of traditional regression models.展开更多
This paper investigates the application ofmachine learning to develop a response model to cardiovascular problems and the use of AdaBoost which incorporates an application of Outlier Detection methodologies namely;Z-S...This paper investigates the application ofmachine learning to develop a response model to cardiovascular problems and the use of AdaBoost which incorporates an application of Outlier Detection methodologies namely;Z-Score incorporated with GreyWolf Optimization(GWO)as well as Interquartile Range(IQR)coupled with Ant Colony Optimization(ACO).Using a performance index,it is shown that when compared with the Z-Score and GWO with AdaBoost,the IQR and ACO,with AdaBoost are not very accurate(89.0%vs.86.0%)and less discriminative(Area Under the Curve(AUC)score of 93.0%vs.91.0%).The Z-Score and GWO methods also outperformed the others in terms of precision,scoring 89.0%;and the recall was also found to be satisfactory,scoring 90.0%.Thus,the paper helps to reveal various specific benefits and drawbacks associated with different outlier detection and feature selection techniques,which can be important to consider in further improving various aspects of diagnostics in cardiovascular health.Collectively,these findings can enhance the knowledge of heart disease prediction and patient treatment using enhanced and innovativemachine learning(ML)techniques.These findings when combined improve patient therapy knowledge and cardiac disease prediction through the use of cutting-edge and improved machine learning approaches.This work lays the groundwork for more precise diagnosis models by highlighting the benefits of combining multiple optimization methodologies.Future studies should focus on maximizing patient outcomes and model efficacy through research on these combinations.展开更多
文摘Software-defined networking(SDN) is a trending networking paradigm that focuses on decoupling of the control logic from the data plane. This decoupling brings programmability and flexibility for the network management by introducing centralized infrastructure. The complete control logic resides in the controller, and thus it becomes the intellectual and most important entity of the SDN infrastructure. With these advantages, SDN faces several security issues in various SDN layers that may prevent the growth and global adoption of this groundbreaking technology. Control plane exhaustion and switch buffer overflow are examples of such security issues. Distributed denial-of-service(DDoS) attacks are one of the most severe attacks that aim to exhaust the controller’s CPU to discontinue the whole functioning of the SDN network. Hence, it is necessary to design a quick as well as accurate detection scheme to detect the attack traffic at an early stage. In this paper, we present a defense solution to detect and mitigate spoofed flooding DDoS attacks. The proposed defense solution is implemented in the SDN controller. The detection method is based on the idea of an statistical measure — Interquartile Range(IQR). For the mitigation purpose, the existing SDN-in-built capabilities are utilized. In this work, the experiments are performed considering the spoofed SYN flooding attack. The proposed solution is evaluated using different performance parameters, i.e., detection time, detection accuracy, packet_in messages, and CPU utilization. The experimental results reveal that the proposed defense solution detects and mitigates the attack effectively in different attack scenarios.
文摘In recent years,there has been a concerted effort to improve anomaly detection tech-niques,particularly in the context of high-dimensional,distributed clinical data.Analysing patient data within clinical settings reveals a pronounced focus on refining diagnostic accuracy,personalising treatment plans,and optimising resource allocation to enhance clinical outcomes.Nonetheless,this domain faces unique challenges,such as irregular data collection,inconsistent data quality,and patient-specific structural variations.This paper proposed a novel hybrid approach that integrates heuristic and stochastic methods for anomaly detection in patient clinical data to address these challenges.The strategy combines HPO-based optimal Density-Based Spatial Clustering of Applications with Noise for clustering patient exercise data,facilitating efficient anomaly identification.Subsequently,a stochastic method based on the Interquartile Range filters unreliable data points,ensuring that medical tools and professionals receive only the most pertinent and accurate information.The primary objective of this study is to equip healthcare pro-fessionals and researchers with a robust tool for managing extensive,high-dimensional clinical datasets,enabling effective isolation and removal of aberrant data points.Furthermore,a sophisticated regression model has been developed using Automated Machine Learning(AutoML)to assess the impact of the ensemble abnormal pattern detection approach.Various statistical error estimation techniques validate the efficacy of the hybrid approach alongside AutoML.Experimental results show that implementing this innovative hybrid model on patient rehabilitation data leads to a notable enhance-ment in AutoML performance,with an average improvement of 0.041 in the R2 score,surpassing the effectiveness of traditional regression models.
文摘This paper investigates the application ofmachine learning to develop a response model to cardiovascular problems and the use of AdaBoost which incorporates an application of Outlier Detection methodologies namely;Z-Score incorporated with GreyWolf Optimization(GWO)as well as Interquartile Range(IQR)coupled with Ant Colony Optimization(ACO).Using a performance index,it is shown that when compared with the Z-Score and GWO with AdaBoost,the IQR and ACO,with AdaBoost are not very accurate(89.0%vs.86.0%)and less discriminative(Area Under the Curve(AUC)score of 93.0%vs.91.0%).The Z-Score and GWO methods also outperformed the others in terms of precision,scoring 89.0%;and the recall was also found to be satisfactory,scoring 90.0%.Thus,the paper helps to reveal various specific benefits and drawbacks associated with different outlier detection and feature selection techniques,which can be important to consider in further improving various aspects of diagnostics in cardiovascular health.Collectively,these findings can enhance the knowledge of heart disease prediction and patient treatment using enhanced and innovativemachine learning(ML)techniques.These findings when combined improve patient therapy knowledge and cardiac disease prediction through the use of cutting-edge and improved machine learning approaches.This work lays the groundwork for more precise diagnosis models by highlighting the benefits of combining multiple optimization methodologies.Future studies should focus on maximizing patient outcomes and model efficacy through research on these combinations.
