AIM:To analyze ultrasound biomicroscopy(UBM)images using random forest network to find new features to make predictions about vault after implantable collamer lens(ICL)implantation.METHODS:A total of 450 UBM images we...AIM:To analyze ultrasound biomicroscopy(UBM)images using random forest network to find new features to make predictions about vault after implantable collamer lens(ICL)implantation.METHODS:A total of 450 UBM images were collected from the Lixiang Eye Hospital to provide the patient’s preoperative parameters as well as the vault of the ICL after implantation.The vault was set as the prediction target,and the input elements were mainly ciliary sulcus shape parameters,which included 6 angular parameters,2 area parameters,and 2 parameters,distance between ciliary sulci,and anterior chamber height.A random forest regression model was applied to predict the vault,with the number of base estimators(n_estimators)of 2000,the maximum tree depth(max_depth)of 17,the number of tree features(max_features)of Auto,and the random state(random_state)of 40.0.RESULTS:Among the parameters selected in this study,the distance between ciliary sulci had a greater importance proportion,reaching 52%before parameter optimization is performed,and other features had less influence,with an importance proportion of about 5%.The importance of the distance between the ciliary sulci increased to 53% after parameter optimization,and the importance of angle 3 and area 1 increased to 5% and 8%respectively,while the importance of the other parameters remained unchanged,and the distance between the ciliary sulci was considered the most important feature.Other features,although they accounted for a relatively small proportion,also had an impact on the vault prediction.After parameter optimization,the best prediction results were obtained,with a predicted mean value of 763.688μm and an actual mean value of 776.9304μm.The R²was 0.4456 and the root mean square error was 201.5166.CONCLUSION:A study based on UBM images using random forest network can be performed for prediction of the vault after ICL implantation and can provide some reference for ICL size selection.展开更多
In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (...In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.展开更多
The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four exper...The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.展开更多
The increasing amount and intricacy of network traffic in the modern digital era have worsened the difficulty of identifying abnormal behaviours that may indicate potential security breaches or operational interruptio...The increasing amount and intricacy of network traffic in the modern digital era have worsened the difficulty of identifying abnormal behaviours that may indicate potential security breaches or operational interruptions. Conventional detection approaches face challenges in keeping up with the ever-changing strategies of cyber-attacks, resulting in heightened susceptibility and significant harm to network infrastructures. In order to tackle this urgent issue, this project focused on developing an effective anomaly detection system that utilizes Machine Learning technology. The suggested model utilizes contemporary machine learning algorithms and frameworks to autonomously detect deviations from typical network behaviour. It promptly identifies anomalous activities that may indicate security breaches or performance difficulties. The solution entails a multi-faceted approach encompassing data collection, preprocessing, feature engineering, model training, and evaluation. By utilizing machine learning methods, the model is trained on a wide range of datasets that include both regular and abnormal network traffic patterns. This training ensures that the model can adapt to numerous scenarios. The main priority is to ensure that the system is functional and efficient, with a particular emphasis on reducing false positives to avoid unwanted alerts. Additionally, efforts are directed on improving anomaly detection accuracy so that the model can consistently distinguish between potentially harmful and benign activity. This project aims to greatly strengthen network security by addressing emerging cyber threats and improving their resilience and reliability.展开更多
Mobile network operators are facing many challenges to satisfy their subscribers in terms of quality of service and quality of experience provided. To achieve this goal, technological progress and scientific advances ...Mobile network operators are facing many challenges to satisfy their subscribers in terms of quality of service and quality of experience provided. To achieve this goal, technological progress and scientific advances offer good opportunities for efficiency in the management of faults occurring in a mobile network. Machine learning techniques allow systems to learn from past experiences and can predict, solutions to be applied to correct the root cause of a failure. This paper evaluates machine learning techniques and identifies the decision tree as a learning model that provides the most optimal error rate in predicting outages that may occur in a mobile network. Three machine learning techniques are presented in this study and compared with regard to accuracy. This study demonstrates that the appropriate machine learning technique improves the accuracy of the model. By using the decision tree as a machine learning model, it was possible to predict solutions to network failures, with an error rate less than 2%. In addition, the use of Machine Learning makes it possible to eliminate steps in the network failure processing chain;resulting in reduced service disruption time and improved the network availability which is a key network performance index.展开更多
文摘AIM:To analyze ultrasound biomicroscopy(UBM)images using random forest network to find new features to make predictions about vault after implantable collamer lens(ICL)implantation.METHODS:A total of 450 UBM images were collected from the Lixiang Eye Hospital to provide the patient’s preoperative parameters as well as the vault of the ICL after implantation.The vault was set as the prediction target,and the input elements were mainly ciliary sulcus shape parameters,which included 6 angular parameters,2 area parameters,and 2 parameters,distance between ciliary sulci,and anterior chamber height.A random forest regression model was applied to predict the vault,with the number of base estimators(n_estimators)of 2000,the maximum tree depth(max_depth)of 17,the number of tree features(max_features)of Auto,and the random state(random_state)of 40.0.RESULTS:Among the parameters selected in this study,the distance between ciliary sulci had a greater importance proportion,reaching 52%before parameter optimization is performed,and other features had less influence,with an importance proportion of about 5%.The importance of the distance between the ciliary sulci increased to 53% after parameter optimization,and the importance of angle 3 and area 1 increased to 5% and 8%respectively,while the importance of the other parameters remained unchanged,and the distance between the ciliary sulci was considered the most important feature.Other features,although they accounted for a relatively small proportion,also had an impact on the vault prediction.After parameter optimization,the best prediction results were obtained,with a predicted mean value of 763.688μm and an actual mean value of 776.9304μm.The R²was 0.4456 and the root mean square error was 201.5166.CONCLUSION:A study based on UBM images using random forest network can be performed for prediction of the vault after ICL implantation and can provide some reference for ICL size selection.
文摘In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.
基金supported by the National Natural Science Foundation of China(Grant Nos.41501361,41401385,30871965)the China Postdoctoral Science Foundation(No.2018M630728)+2 种基金the Open Fund of Fujian Provincial Key Laboratory of Resources and Environment Monitoring&Sustainable Management and Utilization(No.ZD1403)the Open Fund of Fujian Mine Ecological Restoration Engineering Technology Research Center(No.KS2018005)the Scientific Research Foundation of Fuzhou University(No.XRC1345)
文摘The construction of a pest detection algorithm is an important step to couple"ground-space"characteristics,which is also the basis for rapid and accurate monitoring and detection of pest damage.In four experimental areas in Sanming City,Jiangle County,Sha County and Yanping District in Fujian Province,sample data on pest damage in 182 sets of Dendrolimus punctatus were collected.The data were randomly divided into a training set and testing set,and five duplicate tests and one eliminating-indicator test were done.Based on the characterization analysis of the host for D.punctatus damage,seven characteristic indicators of ground and remote sensing including leaf area index,standard error of leaf area index(SEL)of pine forest,normalized difference vegetation index(NDVI),wetness from tasseled cap transformation(WET),green band(B2),red band(B3),near-infrared band(B4)of remote sensing image are obtained to construct BP neural networks and random forest models of pest levels.The detection results of these two algorithms were comprehensively compared from the aspects of detection precision,kappa coefficient,receiver operating characteristic curve,and a paired t test.The results showed that the seven indicators all were responsive to pest damage,and NDVI was relatively weak;the average pest damage detection precision of six tests by BP neural networks was 77.29%,the kappa coefficient was 0.6869 and after the RF algorithm,the respective values were 79.30%and 0.7151,showing that the latter is more optimized,but there was no significant difference(p>0.05);the detection precision,kappa coefficient and AUC of the RF algorithm was higher than the BP neural networks for three pest levels(no damage,moderate damage and severe damage).The detection precision and AUC of BP neural networks were a little higher for mild damage,but the difference was not significant(p>0.05)except for the kappa coefficient for the no damage level(p<0.05).An"over-fitting"phenomenon tends to occur in BP neural networks,while RF method is more robust,providing a detection effect that is better than the BP neural networks.Thus,the application of the random forest algorithm for pest damage and multilevel dispersed variables is thus feasible and suggests that attention to the proportionality of sample data from various categories is needed when collecting data.
文摘The increasing amount and intricacy of network traffic in the modern digital era have worsened the difficulty of identifying abnormal behaviours that may indicate potential security breaches or operational interruptions. Conventional detection approaches face challenges in keeping up with the ever-changing strategies of cyber-attacks, resulting in heightened susceptibility and significant harm to network infrastructures. In order to tackle this urgent issue, this project focused on developing an effective anomaly detection system that utilizes Machine Learning technology. The suggested model utilizes contemporary machine learning algorithms and frameworks to autonomously detect deviations from typical network behaviour. It promptly identifies anomalous activities that may indicate security breaches or performance difficulties. The solution entails a multi-faceted approach encompassing data collection, preprocessing, feature engineering, model training, and evaluation. By utilizing machine learning methods, the model is trained on a wide range of datasets that include both regular and abnormal network traffic patterns. This training ensures that the model can adapt to numerous scenarios. The main priority is to ensure that the system is functional and efficient, with a particular emphasis on reducing false positives to avoid unwanted alerts. Additionally, efforts are directed on improving anomaly detection accuracy so that the model can consistently distinguish between potentially harmful and benign activity. This project aims to greatly strengthen network security by addressing emerging cyber threats and improving their resilience and reliability.
文摘Mobile network operators are facing many challenges to satisfy their subscribers in terms of quality of service and quality of experience provided. To achieve this goal, technological progress and scientific advances offer good opportunities for efficiency in the management of faults occurring in a mobile network. Machine learning techniques allow systems to learn from past experiences and can predict, solutions to be applied to correct the root cause of a failure. This paper evaluates machine learning techniques and identifies the decision tree as a learning model that provides the most optimal error rate in predicting outages that may occur in a mobile network. Three machine learning techniques are presented in this study and compared with regard to accuracy. This study demonstrates that the appropriate machine learning technique improves the accuracy of the model. By using the decision tree as a machine learning model, it was possible to predict solutions to network failures, with an error rate less than 2%. In addition, the use of Machine Learning makes it possible to eliminate steps in the network failure processing chain;resulting in reduced service disruption time and improved the network availability which is a key network performance index.
