Recently,automatic diagnosis of diabetic retinopathy(DR)from the retinal image is the most significant ressearch topic in the medical applications.Diabetic macular edema(DME)is the.major reason for the loss of vision ...Recently,automatic diagnosis of diabetic retinopathy(DR)from the retinal image is the most significant ressearch topic in the medical applications.Diabetic macular edema(DME)is the.major reason for the loss of vision in patients suffering fom DR.Early identification of the DR enables to prevent the vision loss and encourage diabetic control activities.Many techniques are.developed to diagnose the DR.The major drawbacks of the existing techniques are low accuracy and high time complexity.To owercome these issues,this paper propases an enhanced particle swarm optimization differential evolution feature selection(PSO DEFS)based feature selection approach with biometric aut hentication for the identification of DR.Initially,a hybrid median filter(HMF)is used for pre processing the input images.Then,the pre-processed images are embedded with each other by using least significant bit(LSB)for authentication purpose.Si-multaneously,the image features are extracted using convoluted local tetra pattern(CLTrP)and Tamura features.Feature selection is performed using PSO DEFS and PSO-gravitational search algorithm(PSO GSA)to reduce time complexity.Based on some performance metrics,the PSO-DEFS is chosen as a better choice for feature selection.The feature selection is performed based on the fitness value.A multi-relevance vector machine(M-RVM)is introduced to dlassify the 13 normal and 62 abnormal images among 75 images from 60 patients.Finally,the DR patients are further dassified by M-RVM.The experimental results exhibit that the proposed approach achieves better accuracy,sensitivity,and specificity than the exist ing techniques.展开更多
Data packet drop can happen in Optical Burst-Switched(OBS)when two data bursts are competing on the same wavelength.Recently,many techniques have been developed to solve this problem but they do not consider the conge...Data packet drop can happen in Optical Burst-Switched(OBS)when two data bursts are competing on the same wavelength.Recently,many techniques have been developed to solve this problem but they do not consider the congestion.Also,it is necessary to balance the load system in the OBS network.The Ant Colony Optimization(ACO)technique can be applied to determine the straight and the safest route.However,the ACO technique raises both power utilization as well as the execution time.In this study,Cuckoo Search(CS)and ACO methods based approach is proposed to avoid the congestion and load balancing in the OBS network.This strategy evaluates the intensity of hotspot data and then launches the congestion rate optimization process that depends on their load situations.The congestion rate optimization represents the available bandwidth,data distribution rate,queue size,and access rate,and also these factors are optimized through the CS technique.The fitness utility in the CS technique adjusts the distribution rate in the OBS network,and the proposed ACO technique solves the energy utilization problem.The simulation results proved that the presented strategy evades both the end-to-end delay as well as the possibility of packet drop.展开更多
Recently,wind power has gained popularity as a sustainable energy source.Wind energy conversion systems(WECSs)can accept fixed speed and variable speed(VS)operations.VS-WECSs are preferable to conventional WECSs becau...Recently,wind power has gained popularity as a sustainable energy source.Wind energy conversion systems(WECSs)can accept fixed speed and variable speed(VS)operations.VS-WECSs are preferable to conventional WECSs because of their higher electricity collection capacity.Maximum power point tracking(MPPT)systems are essential for maximizing the efficiency of wind energy generation in wind turbine(WT)installations linked to power grids.This study introduces a hybrid fuzzy logic controller-based MPPT(FLC-MPPT)for WTs connected to permanent magnet synchronous generators(PMSGs)to accurately determine the maximum power output of WTs.This study employs a three-phase back-to-back converter to link a PMSG to a utility grid.The reference signals for pulse width modulation controllers comprise two-phase system currents.It constructs a converter that can transfer electrical energy in both directions using insulated-gate bipolar transistor technology and is powered by a battery.The machine-side converter uses model predictive control for the present control loop.Given the generator’s susceptibility to changes in wind conditions,this factor is of the utmost importance.A WT simulation was conducted using MATLAB/Simulink and an FLC methodology was employed.The model used a PMSG.Measurements of rotor speed,power,induced voltage,and current were taken in relation to variations in wind speed.The simulation results show that the FLC-MPPT can maximize the output power over a wide range of wind speeds with a higher efficiency of 92.6%and performance of 95.7%.展开更多
文摘Recently,automatic diagnosis of diabetic retinopathy(DR)from the retinal image is the most significant ressearch topic in the medical applications.Diabetic macular edema(DME)is the.major reason for the loss of vision in patients suffering fom DR.Early identification of the DR enables to prevent the vision loss and encourage diabetic control activities.Many techniques are.developed to diagnose the DR.The major drawbacks of the existing techniques are low accuracy and high time complexity.To owercome these issues,this paper propases an enhanced particle swarm optimization differential evolution feature selection(PSO DEFS)based feature selection approach with biometric aut hentication for the identification of DR.Initially,a hybrid median filter(HMF)is used for pre processing the input images.Then,the pre-processed images are embedded with each other by using least significant bit(LSB)for authentication purpose.Si-multaneously,the image features are extracted using convoluted local tetra pattern(CLTrP)and Tamura features.Feature selection is performed using PSO DEFS and PSO-gravitational search algorithm(PSO GSA)to reduce time complexity.Based on some performance metrics,the PSO-DEFS is chosen as a better choice for feature selection.The feature selection is performed based on the fitness value.A multi-relevance vector machine(M-RVM)is introduced to dlassify the 13 normal and 62 abnormal images among 75 images from 60 patients.Finally,the DR patients are further dassified by M-RVM.The experimental results exhibit that the proposed approach achieves better accuracy,sensitivity,and specificity than the exist ing techniques.
文摘Data packet drop can happen in Optical Burst-Switched(OBS)when two data bursts are competing on the same wavelength.Recently,many techniques have been developed to solve this problem but they do not consider the congestion.Also,it is necessary to balance the load system in the OBS network.The Ant Colony Optimization(ACO)technique can be applied to determine the straight and the safest route.However,the ACO technique raises both power utilization as well as the execution time.In this study,Cuckoo Search(CS)and ACO methods based approach is proposed to avoid the congestion and load balancing in the OBS network.This strategy evaluates the intensity of hotspot data and then launches the congestion rate optimization process that depends on their load situations.The congestion rate optimization represents the available bandwidth,data distribution rate,queue size,and access rate,and also these factors are optimized through the CS technique.The fitness utility in the CS technique adjusts the distribution rate in the OBS network,and the proposed ACO technique solves the energy utilization problem.The simulation results proved that the presented strategy evades both the end-to-end delay as well as the possibility of packet drop.
文摘Recently,wind power has gained popularity as a sustainable energy source.Wind energy conversion systems(WECSs)can accept fixed speed and variable speed(VS)operations.VS-WECSs are preferable to conventional WECSs because of their higher electricity collection capacity.Maximum power point tracking(MPPT)systems are essential for maximizing the efficiency of wind energy generation in wind turbine(WT)installations linked to power grids.This study introduces a hybrid fuzzy logic controller-based MPPT(FLC-MPPT)for WTs connected to permanent magnet synchronous generators(PMSGs)to accurately determine the maximum power output of WTs.This study employs a three-phase back-to-back converter to link a PMSG to a utility grid.The reference signals for pulse width modulation controllers comprise two-phase system currents.It constructs a converter that can transfer electrical energy in both directions using insulated-gate bipolar transistor technology and is powered by a battery.The machine-side converter uses model predictive control for the present control loop.Given the generator’s susceptibility to changes in wind conditions,this factor is of the utmost importance.A WT simulation was conducted using MATLAB/Simulink and an FLC methodology was employed.The model used a PMSG.Measurements of rotor speed,power,induced voltage,and current were taken in relation to variations in wind speed.The simulation results show that the FLC-MPPT can maximize the output power over a wide range of wind speeds with a higher efficiency of 92.6%and performance of 95.7%.
