In this paper proposes a krill herd optimization algorithm with Deep Convolutional neural network fostered Breast Cancer Classification using Mammogram Images (BC-APPDRC-DCNN-KHO). Here, the input images are taken fro...
详细信息
In this paper proposes a krill herd optimization algorithm with Deep Convolutional neural network fostered Breast Cancer Classification using Mammogram Images (BC-APPDRC-DCNN-KHO). Here, the input images are taken from Real time and MAMMOSET datasets. These images are pre-processed using Altered Phase Preserving Dynamic Range Compression (APPDRC) technique. This APPDRC is applied for preserving local features, compressing dynamic range of images, and enhancing the speckle noise filtering, these are all necessary for better boundary detection. Then, the Pre-processed images are classified using Deep Convolutional neural network (DCNN). The DCNN weight parameters are optimized based on krill herd optimization algorithm. The Proposed BCC-DCNN-KHO-MI method classifies the input breast cancer imageries into 3 categories: benign, malignant, and normal. The proposed BCC-DCNN-KHO-MI method in Real time dataset attains 18.505%, 19.45%, 16.19%, 17.56% and 16.19% higher accuracy;15.38%, 12.06%, 12.71%, 26.62% and 18.902% higher Precision;3.12%, 10.52%, 13.57%, 22.75% and 14.93% higher F-score, 59.56%, 41.25%, 56.47%, 42.36% and 37.27% lower computation time;23.87%, 21.87%, 32.87%, 42.76% and 21.05% higher AUC compared with the existing methods, like BCC-Google Net-MI, BCC-Visual Geometry Group Network-MI, BCC-Residual Networks-MI, BC-RERNN-LOA-MI and BC-CNN-MI respectively.
krill herd optimization algorithm which is a new metaheuristic search algorithm mimics the herding behavior of krill individuals. The significant characteristic of meta heuristic algorithms is their ability in combina...
详细信息
ISBN:
(纸本)9781479954865
krill herd optimization algorithm which is a new metaheuristic search algorithm mimics the herding behavior of krill individuals. The significant characteristic of meta heuristic algorithms is their ability in combination of local search and global search. This property can adjust the contribution of local search and global search in initial step and during searching process and plays crucial role in the algorithm performance. One hazard which threats the meta heuristic algorithms is getting stuck in local optimum traps. An appropriate solution to deal with this problem is using chaos theory which brings dynamism and instability properties to the algorithm so that by strengthening the performance of random search helps the algorithm to escape from local optimum traps. In this paper, we propose a new method called chaotic krill herd optimization algorithm which by adopting chaos theory in krill herd optimization algorithm heighten its performance in dealing with various optimization problems. The obtained results by the proposed method in comparison with those of the standard krill herd optimization algorithm indicates the higher performance of the proposed algorithm.
In this paper, two recent heuristic optimizationalgorithms are presented to optimally manage the operation of the micro-grid (MG) with installed renewable energy sources (RESs);krillherd (KH) optimization and ant li...
详细信息
In this paper, two recent heuristic optimizationalgorithms are presented to optimally manage the operation of the micro-grid (MG) with installed renewable energy sources (RESs);krillherd (KH) optimization and ant lion optimizer (ALO) algorithms. The first algorithm is used for solving single-objective function represents either total operation cost or total pollutant emission injected from the installed generating units while ALO is applied to solve the multi-objective function of both total operating cost and emission. The problem is formulated as nonlinear constrained objective function with equality and inequality constraints. In this work;the devices installed in MGs are photovoltaic panel (PV), wind turbine (WT), micro-turbine (MT), fuel cell (FC), battery and grid. Two scenarios are studied;the first one is optimizing MG with installing all RESs within specified limits in addition to grid, while the second scenario is operating both PV and WT at their rated powers. The obtained results are compared with different reported algorithms like genetic algorithm (GA), Fuzzy self-adaptive PSO (FSAPSO) and others programmed like particle swarm optimization (PSO), grey-wolf optimizer (GWO) and whale optimizationalgorithm (WOA). For first scenario;the proposed KH gives the best optimal cost of 105.94 Euroct while the best emission is 420.57kg, the best optimal cost and emission of 592.86 Euroct 339.71kg are obtained via KH in the second scenario.
Industry 4.0 enable novel business cases, such as client-specific production, real-time monitoring of process condition and progress, independent decision making and remote maintenance, to name a few. However, they ar...
详细信息
Industry 4.0 enable novel business cases, such as client-specific production, real-time monitoring of process condition and progress, independent decision making and remote maintenance, to name a few. However, they are more susceptible to a broad range of cyber threats because of limited resources and heterogeneous nature. Such risks cause financial and reputational damages for businesses, well as the theft of sensitive information. The higher level of diversity in industrial network prevents the attackers from such attacks. Therefore, to efficiently detect the intrusions, a novel intrusion detection system known as Bidirectional Long Short-Term Memory based Explainable Artificial Intelligence framework (BiLSTMXAI) is developed. Initially, the preprocessing task using data cleaning and normalization is performed to enhance the data quality for detecting network intrusions. Subsequently, the significant features are selected from the databases using the krillherdoptimization (KHO) algorithm. The proposed BiLSTM-XAI approach provides better security and privacy inside the industry networking system by detecting intrusions very precisely. In this, we utilized SHAP and LIME explainable AI algorithms to improve interpretation of prediction results. The experimental setup is made by MATLAB 2016 software using Honeypot and NSL-KDD datasets as input. The analysis result reveals that the proposed method achieves superior performance in detecting intrusions with a classification accuracy of 98.2%.
Purpose - The purpose of this paper is to improve dynamic performance of the permanent magnet synchronous motor (PMSM) field-oriented control by means of optimizing its PI controller's coefficients. Design/methodo...
详细信息
Purpose - The purpose of this paper is to improve dynamic performance of the permanent magnet synchronous motor (PMSM) field-oriented control by means of optimizing its PI controller's coefficients. Design/methodology/approach - In this paper, krillherd (KH) optimizationalgorithm is proposed to optimize PI controller coefficients. Moreover, drive control system and steady state estimator are implemented in discrete mode. In order to evaluate the performance of the proposed algorithm, a comparison is carried out between KH and particle swarm optimization (PSO) algorithms. It is noteworthy that PSO algorithm has presented the best dynamic response among the studied approaches in literature. Findings - By using the proposed optimizationalgorithm, the system tracks the reference speed with a very low error. In addition, the discrete mode simulations do not require initiating integrators. Moreover, it significantly increases the processing speed. The proposed approach is carried out in both sensor and sensorless drive systems. The simulation results indicate lower torque ripple, shorter settling time, lower overshoot, faster dynamic response and higher robustness against speed, torque and machine parameter changes. Practical implications - The PI controller is extensively used in practical drive systems, due to its simple structure and implementation as well as its acceptable performance. On the other hand, PMSM benefits from high-power density, high efficiency, low torque ripple, low inertia, and high performance in a wide speed range. This paper presents an efficient approach to optimize PI coefficients of the PMSM drive system. Originality/value - This paper proposes a new algorithm (KH algorithm) to determine the coefficients of PI controllers in order to improve dynamic performance of the PMSM drive system.
This paper introduces a new robust controller with cascaded fuzzy blocks as a power system stabilizer (CFPSS) to enhance damping during low-frequency oscillations. This CFPSS is designed to act as a nonlinear lead-lag...
详细信息
This paper introduces a new robust controller with cascaded fuzzy blocks as a power system stabilizer (CFPSS) to enhance damping during low-frequency oscillations. This CFPSS is designed to act as a nonlinear lead-lag PSS with a given number of compensation blocks. To demonstrate the efficiency and the robustness of this proposed stabilizer, simulation results performed on the IEEE three-generator nine-bus multi-machine power system subjected to a three-phase short-circuit fault have been carried out. The parameters of the proposed PSS and those of the conventional IEEE linear lead-lag PSS have been tuned by a recently developed optimization technique (krillherdalgorithm). The robustness of this novel CFPSS is proved, by optimizing the parameters of the two PSSs for one operating point (normally loaded system) and applying them to other operating points (case of heavy and low loads) with some key parameters variation. The obtained results have shown the superiority and the robustness of the CFPSS comparatively to the conventional IEEE lead-lag PSS in terms of oscillations damping over a wide range of operating conditions and against parametric variation. The same conclusions have been drawn in the case of a large power system (IEEE 16-machine, 68-bus test system) characterized by its local and inter-area oscillations modes.
Due to advantages of the sensorless cascade controllers, i.e. simple structure and no need to use the mechanical sensors, they are widely used in industry. An important problem with such controllers is setting their p...
详细信息
ISBN:
(纸本)9781479976539
Due to advantages of the sensorless cascade controllers, i.e. simple structure and no need to use the mechanical sensors, they are widely used in industry. An important problem with such controllers is setting their parameters in order to achieve suitable response. This paper presents a sensorless control scheme for a permanent magnet synchronous motor (PMSM) based on optimizing the parameters of the speed and torque PI-Controllers, using krillherd (KH) algorithm. They are optimized to minimize the speed tracking error in steady state. Since the proposed method uses the discrete-time model, it does not depend on initial conditions of integrators. The system is tested under variable operating conditions. Simulation results with MATLAB/Simulink software show a satisfactory performance of the proposed controller against load disturbances as well as robustness against machine parameters' variations.
To optimal manage of lithium-ion (Li-ion) batteries, different features like the state of charge (SOC), state of health (SOH) should be considered. This consideration should also consider good reliability and precisio...
详细信息
To optimal manage of lithium-ion (Li-ion) batteries, different features like the state of charge (SOC), state of health (SOH) should be considered. This consideration should also consider good reliability and precision for the battery modeling. This study introduces a new fractional model for a Lithium-ion battery by considering several operating conditions, temperatures, and SOCs. To achieve a suitable model, the parameters of the fractional model were optimized based on a newly developed design of the krillherd (DKH) optimizer. After verifying and comparing the capability of the algorithm with several different metaheuristics, it has been applied to the model and the best values have been obtained. The optimized fractional-order model is then validated by various characteristics regarding precision and reliability. The test data was considered under different SOC ranges, working conditions, and temperatures. The results showed that the ability of the proposed DKH method based on dynamic stress test (DST), test of hybrid pulse power characteristic (HPPC), and FUDS simulated condition in the ambient temperature is 7.18 mV, 8.75 mV, and 6.83 mV that are small RMSE values and shows higher reliability of the in different performing condition. The small value of RMDE was also proved in temperature and SOC which show its proper efficiency in different condition vales. Finally, the model has been compared with an RC integer equivalent circuit model. The comparison results showed that the proposed DKH method with 0.040 % relative mean error provides higher accuracy than the Second-order RC model with 0.045 % relative mean error which displays its excellence toward that model.
暂无评论