Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin o...Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin optical networks introduce challenges that can jeopardize the network with a variety of faults.The existingliterature witnessed various partial or inadequate solutions.On the other hand,Machine Learning(ML)hasrevolutionized as a promising technique for fault detection and prevention.Unlike traditional fault managementsystems,this research has three-fold contributions.First,this research leverages the ML and Deep Learning(DL)multi-classification system and evaluates their accuracy in detecting six distinct fault types,including fiber cut,fibereavesdropping,splicing,bad connector,bending,and PC connector.Secondly,this paper assesses the classificationdelay of each classification algorithm.Finally,this work proposes a fiber optics fault prevention algorithm thatdetermines to mitigate the faults accordingly.This work utilized a publicly available fiber optics dataset namedOTDR_Data and applied different ML classifiers,such as Gaussian Naive Bayes(GNB),Logistic Regression(LR),Support Vector Machine(SVM),K-Nearest Neighbor(KNN),Random Forest(RF),and Decision Tree(DT).Moreover,Ensemble Learning(EL)techniques are applied to evaluate the accuracy of various classifiers.In addition,this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory(CNN-LSTM)hybrid classifier.The findings reveal that the CNN-LSTM hybrid technique achieved the highestaccuracy of 99%with a delay of 360 s.On the other hand,EL techniques improved the accuracy in detecting fiberoptic faults.Thus,this research comprehensively assesses accuracy and delay metrics for various classifiers andproposes the most efficient attack detection system in fiber optics.展开更多
Two-year long field study was conducted using a permanent layout to investigate the economics of crop residues incorporation (2 t·ha-1) and P application (0, 40, 80 and 120 kg P2O5 ha-1) to directly sowing o...Two-year long field study was conducted using a permanent layout to investigate the economics of crop residues incorporation (2 t·ha-1) and P application (0, 40, 80 and 120 kg P2O5 ha-1) to directly sowing of rice and wheat crops gown under naturally salt-affected calcareous soil (ECe = 4.59 dS m-1;pHs = 8.38;SAR = 6.57 (mmolc L-1)1/2;CaCO3 = 3.21%;Extractable P = 4.07 mg·kg-1;sandy clay loam) at farmers field in district Hafizabad during the year 2012-13. Split plot design (crop residues in main plots and P application in sub plots) was followed with three replications. Agronomic data on growth and yield were collected at the time of each crop maturity. Maximum growth and yield of both the crops were harvested from the plots where P2O5 was applied @ 80 kg·ha-1 along with crop residues incorporation. On an average of two years, maximum paddy (3.26 t·ha-1) and wheat grain (3.56 t·ha-1) yield were produced with P application @ 80 kg P2O5 ha-1 along with crop residues incorporation. Although, the yield harvested with this treatment (80 kg P2O5 ha-1 + crop residues) performed statistically equal to 120 kg P2O5 ha-1 without crop residues incorporation during both the years, however, on an average of two years, grain yield of directly sowing rice and subsequent wheat was significantly superior (22% and 24% respectively) than that of higher P rate (120 kg·ha-1) without crop residues. Overall, continuous two-year crop residues incorporation further increased (17%) paddy yields during the follow up year of crop harvest. Economic analyses of both the crops were carried out to choose the best treatment with adequate economic benefits as compared to those without crop residue incorporation. Maximum net benefit of Rs = 108,680/- for direct seeded rice and Rs = 99,362/- for wheat grown with 80 kg P2O5 ha-1 application under crop residues incorporation was determined. Among P application treatments without crop residues incorporation, the maximum net benefit (Rs = 75,874/- and Rs = 65,725/-) and highest residual values (49,809 and 39,160) for direct seeded rice and wheat respectively, were obtained with extended P application rate (120 kg P2O5 ha-1) which was not again as much as that of 80 kg P2O5 ha-1 application with crop residues incorporation.展开更多
基金in part by the National Natural Science Foundation of China under Grants 62271079,61875239,62127802in part by the Fundamental Research Funds for the Central Universities under Grant 2023PY01+1 种基金in part by the National Key Research and Development Program of China under Grant 2018YFB2200903in part by the Beijing Nova Program with Grant Number Z211100002121138.
文摘Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)satisfaction.The emerging faultsin optical networks introduce challenges that can jeopardize the network with a variety of faults.The existingliterature witnessed various partial or inadequate solutions.On the other hand,Machine Learning(ML)hasrevolutionized as a promising technique for fault detection and prevention.Unlike traditional fault managementsystems,this research has three-fold contributions.First,this research leverages the ML and Deep Learning(DL)multi-classification system and evaluates their accuracy in detecting six distinct fault types,including fiber cut,fibereavesdropping,splicing,bad connector,bending,and PC connector.Secondly,this paper assesses the classificationdelay of each classification algorithm.Finally,this work proposes a fiber optics fault prevention algorithm thatdetermines to mitigate the faults accordingly.This work utilized a publicly available fiber optics dataset namedOTDR_Data and applied different ML classifiers,such as Gaussian Naive Bayes(GNB),Logistic Regression(LR),Support Vector Machine(SVM),K-Nearest Neighbor(KNN),Random Forest(RF),and Decision Tree(DT).Moreover,Ensemble Learning(EL)techniques are applied to evaluate the accuracy of various classifiers.In addition,this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory(CNN-LSTM)hybrid classifier.The findings reveal that the CNN-LSTM hybrid technique achieved the highestaccuracy of 99%with a delay of 360 s.On the other hand,EL techniques improved the accuracy in detecting fiberoptic faults.Thus,this research comprehensively assesses accuracy and delay metrics for various classifiers andproposes the most efficient attack detection system in fiber optics.
文摘Two-year long field study was conducted using a permanent layout to investigate the economics of crop residues incorporation (2 t·ha-1) and P application (0, 40, 80 and 120 kg P2O5 ha-1) to directly sowing of rice and wheat crops gown under naturally salt-affected calcareous soil (ECe = 4.59 dS m-1;pHs = 8.38;SAR = 6.57 (mmolc L-1)1/2;CaCO3 = 3.21%;Extractable P = 4.07 mg·kg-1;sandy clay loam) at farmers field in district Hafizabad during the year 2012-13. Split plot design (crop residues in main plots and P application in sub plots) was followed with three replications. Agronomic data on growth and yield were collected at the time of each crop maturity. Maximum growth and yield of both the crops were harvested from the plots where P2O5 was applied @ 80 kg·ha-1 along with crop residues incorporation. On an average of two years, maximum paddy (3.26 t·ha-1) and wheat grain (3.56 t·ha-1) yield were produced with P application @ 80 kg P2O5 ha-1 along with crop residues incorporation. Although, the yield harvested with this treatment (80 kg P2O5 ha-1 + crop residues) performed statistically equal to 120 kg P2O5 ha-1 without crop residues incorporation during both the years, however, on an average of two years, grain yield of directly sowing rice and subsequent wheat was significantly superior (22% and 24% respectively) than that of higher P rate (120 kg·ha-1) without crop residues. Overall, continuous two-year crop residues incorporation further increased (17%) paddy yields during the follow up year of crop harvest. Economic analyses of both the crops were carried out to choose the best treatment with adequate economic benefits as compared to those without crop residue incorporation. Maximum net benefit of Rs = 108,680/- for direct seeded rice and Rs = 99,362/- for wheat grown with 80 kg P2O5 ha-1 application under crop residues incorporation was determined. Among P application treatments without crop residues incorporation, the maximum net benefit (Rs = 75,874/- and Rs = 65,725/-) and highest residual values (49,809 and 39,160) for direct seeded rice and wheat respectively, were obtained with extended P application rate (120 kg P2O5 ha-1) which was not again as much as that of 80 kg P2O5 ha-1 application with crop residues incorporation.