基于健康退化曲线对军用飞机故障预测与健康管理(PHM)技术的内涵、基本功能和能力需求进行探讨,在此基础上,以科学评价PHM(prognostics and health management)系统的诊断和预测能力为目标,从能力需求出发提出PHM系统性能度量方法体系(...基于健康退化曲线对军用飞机故障预测与健康管理(PHM)技术的内涵、基本功能和能力需求进行探讨,在此基础上,以科学评价PHM(prognostics and health management)系统的诊断和预测能力为目标,从能力需求出发提出PHM系统性能度量方法体系(包括诊断性能度量、预测性能度量以及综合度量),并对各个度量方法的定义和应用进行详细阐述。为PHM系统算法设计、改进及系统能力验证奠定基础,具有一定的工程应用价值。展开更多
Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation...Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .展开更多
The evolution of the current network has challenges of programmability, maintainability and manageability, due to network ossification. This challenge led to the concept of software-defined networking (SDN), to decoup...The evolution of the current network has challenges of programmability, maintainability and manageability, due to network ossification. This challenge led to the concept of software-defined networking (SDN), to decouple the control system from the infrastructure plane caused by ossification. The innovation created a problem with controller placement. That is how to effectively place controllers within a network topology to manage the network of data plane devices from the control plane. The study was designed to empirically evaluate and compare the functionalities of two controller placement algorithms: the POCO and MOCO. The methodology adopted in the study is the explorative and comparative investigation techniques. The study evaluated the performances of the Pareto optimal combination (POCO) and multi-objective combination (MOCO) algorithms in relation to calibrated positions of the controller within a software-defined network. The network environment and measurement metrics were held constant for both the POCO and MOCO models during the evaluation. The strengths and weaknesses of the POCO and MOCO models were justified. The results showed that the latencies of the two algorithms in relation to the GoodNet network are 3100 ms and 2500 ms for POCO and MOCO respectively. In Switch to Controller Average Case latency, the performance gives 2598 ms and 2769 ms for POCO and MOCO respectively. In Worst Case Switch to Controller latency, the performance shows 2776 ms and 2987 ms for POCO and MOCO respectively. The latencies of the two algorithms evaluated in relation to the Savvis network, compared as follows: 2912 ms and 2784 ms for POCO and MOCO respectively in Switch to Controller Average Case latency, 3129 ms and 3017 ms for POCO and MOCO respectively in Worst Case Switch to Controller latency, 2789 ms and 2693 ms for POCO and MOCO respectively in Average Case Controller to Controller latency, and 2873 ms and 2756 ms for POCO and MOCO in Worst Case Switch to Controller latency respectively. The latencies of the tw展开更多
Video streaming applications have grown considerably in recent years.As a result,this becomes one of the most significant contributors to global internet traffic.According to recent studies,the telecommunications indu...Video streaming applications have grown considerably in recent years.As a result,this becomes one of the most significant contributors to global internet traffic.According to recent studies,the telecommunications industry loses millions of dollars due to poor video Quality of Experience(QoE)for users.Among the standard proposals for standardizing the quality of video streaming over internet service providers(ISPs)is the Mean Opinion Score(MOS).However,the accurate finding of QoE by MOS is subjective and laborious,and it varies depending on the user.A fully automated data analytics framework is required to reduce the inter-operator variability characteristic in QoE assessment.This work addresses this concern by suggesting a novel hybrid XGBStackQoE analytical model using a two-level layering technique.Level one combines multiple Machine Learning(ML)models via a layer one Hybrid XGBStackQoE-model.Individual ML models at level one are trained using the entire training data set.The level two Hybrid XGBStackQoE-Model is fitted using the outputs(meta-features)of the layer one ML models.The proposed model outperformed the conventional models,with an accuracy improvement of 4 to 5 percent,which is still higher than the current traditional models.The proposed framework could significantly improve video QoE accuracy.展开更多
Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques...Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques have been viewed as a viable method for enhancing the accuracy of univariate streamflow estimation when compared to standalone approaches.Current researchers have also emphasised using hybrid models to improve forecast accuracy.Accordingly,this paper conducts an updated literature review of applications of hybrid models in estimating streamflow over the last five years,summarising data preprocessing,univariate machine learning modelling strategy,advantages and disadvantages of standalone ML techniques,hybrid models,and performance metrics.This study focuses on two types of hybrid models:parameter optimisation-based hybrid models(OBH)and hybridisation of parameter optimisation-based and preprocessing-based hybridmodels(HOPH).Overall,this research supports the idea thatmeta-heuristic approaches precisely improveML techniques.It’s also one of the first efforts to comprehensively examine the efficiency of various meta-heuristic approaches(classified into four primary classes)hybridised with ML techniques.This study revealed that previous research applied swarm,evolutionary,physics,and hybrid metaheuristics with 77%,61%,12%,and 12%,respectively.Finally,there is still room for improving OBH and HOPH models by examining different data pre-processing techniques and metaheuristic algorithms.展开更多
文摘基于健康退化曲线对军用飞机故障预测与健康管理(PHM)技术的内涵、基本功能和能力需求进行探讨,在此基础上,以科学评价PHM(prognostics and health management)系统的诊断和预测能力为目标,从能力需求出发提出PHM系统性能度量方法体系(包括诊断性能度量、预测性能度量以及综合度量),并对各个度量方法的定义和应用进行详细阐述。为PHM系统算法设计、改进及系统能力验证奠定基础,具有一定的工程应用价值。
文摘Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .
文摘The evolution of the current network has challenges of programmability, maintainability and manageability, due to network ossification. This challenge led to the concept of software-defined networking (SDN), to decouple the control system from the infrastructure plane caused by ossification. The innovation created a problem with controller placement. That is how to effectively place controllers within a network topology to manage the network of data plane devices from the control plane. The study was designed to empirically evaluate and compare the functionalities of two controller placement algorithms: the POCO and MOCO. The methodology adopted in the study is the explorative and comparative investigation techniques. The study evaluated the performances of the Pareto optimal combination (POCO) and multi-objective combination (MOCO) algorithms in relation to calibrated positions of the controller within a software-defined network. The network environment and measurement metrics were held constant for both the POCO and MOCO models during the evaluation. The strengths and weaknesses of the POCO and MOCO models were justified. The results showed that the latencies of the two algorithms in relation to the GoodNet network are 3100 ms and 2500 ms for POCO and MOCO respectively. In Switch to Controller Average Case latency, the performance gives 2598 ms and 2769 ms for POCO and MOCO respectively. In Worst Case Switch to Controller latency, the performance shows 2776 ms and 2987 ms for POCO and MOCO respectively. The latencies of the two algorithms evaluated in relation to the Savvis network, compared as follows: 2912 ms and 2784 ms for POCO and MOCO respectively in Switch to Controller Average Case latency, 3129 ms and 3017 ms for POCO and MOCO respectively in Worst Case Switch to Controller latency, 2789 ms and 2693 ms for POCO and MOCO respectively in Average Case Controller to Controller latency, and 2873 ms and 2756 ms for POCO and MOCO in Worst Case Switch to Controller latency respectively. The latencies of the tw
文摘Video streaming applications have grown considerably in recent years.As a result,this becomes one of the most significant contributors to global internet traffic.According to recent studies,the telecommunications industry loses millions of dollars due to poor video Quality of Experience(QoE)for users.Among the standard proposals for standardizing the quality of video streaming over internet service providers(ISPs)is the Mean Opinion Score(MOS).However,the accurate finding of QoE by MOS is subjective and laborious,and it varies depending on the user.A fully automated data analytics framework is required to reduce the inter-operator variability characteristic in QoE assessment.This work addresses this concern by suggesting a novel hybrid XGBStackQoE analytical model using a two-level layering technique.Level one combines multiple Machine Learning(ML)models via a layer one Hybrid XGBStackQoE-model.Individual ML models at level one are trained using the entire training data set.The level two Hybrid XGBStackQoE-Model is fitted using the outputs(meta-features)of the layer one ML models.The proposed model outperformed the conventional models,with an accuracy improvement of 4 to 5 percent,which is still higher than the current traditional models.The proposed framework could significantly improve video QoE accuracy.
基金This paper’s logical organisation and content quality have been enhanced,so the authors thank anonymous reviewers and journal editors for assistance.
文摘Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques have been viewed as a viable method for enhancing the accuracy of univariate streamflow estimation when compared to standalone approaches.Current researchers have also emphasised using hybrid models to improve forecast accuracy.Accordingly,this paper conducts an updated literature review of applications of hybrid models in estimating streamflow over the last five years,summarising data preprocessing,univariate machine learning modelling strategy,advantages and disadvantages of standalone ML techniques,hybrid models,and performance metrics.This study focuses on two types of hybrid models:parameter optimisation-based hybrid models(OBH)and hybridisation of parameter optimisation-based and preprocessing-based hybridmodels(HOPH).Overall,this research supports the idea thatmeta-heuristic approaches precisely improveML techniques.It’s also one of the first efforts to comprehensively examine the efficiency of various meta-heuristic approaches(classified into four primary classes)hybridised with ML techniques.This study revealed that previous research applied swarm,evolutionary,physics,and hybrid metaheuristics with 77%,61%,12%,and 12%,respectively.Finally,there is still room for improving OBH and HOPH models by examining different data pre-processing techniques and metaheuristic algorithms.
