This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and clas...This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.展开更多
情感计算是现代人机交互中的关键问题,随着人工智能的发展,基于脑电信号(electroencephalogram, EEG)的情绪识别已经成为重要的研究方向.为了提高情绪识别的分类精度,本研究引入堆叠自动编码器(stacked autoencoder, SAE)对EEG多通道信...情感计算是现代人机交互中的关键问题,随着人工智能的发展,基于脑电信号(electroencephalogram, EEG)的情绪识别已经成为重要的研究方向.为了提高情绪识别的分类精度,本研究引入堆叠自动编码器(stacked autoencoder, SAE)对EEG多通道信号进行深度特征提取,并提出一种基于广义正态分布优化的支持向量机(generalized normal distribution optimization based support vector machine, GNDO-SVM)情绪识别模型.实验结果表明,与基于遗传算法、粒子群算法和麻雀搜索算法优化的支持向量机模型相比,所提出的GNDO-SVM模型具有更优的分类性能,基于SAE深度特征的情感识别准确率达到了90.94%,表明SAE能够有效地挖掘EEG信号不同通道间的深度相关性信息.因此,利用SAE深度特征结合GNDO-SVM模型可以有效地实现EEG信号的情绪识别.展开更多
This paper presents a binary gravitational search algorithm (BGSA) is applied to solve the problem of optimal allotment of DG sets and Shunt capacitors in radial distribution systems. The problem is formulated as a no...This paper presents a binary gravitational search algorithm (BGSA) is applied to solve the problem of optimal allotment of DG sets and Shunt capacitors in radial distribution systems. The problem is formulated as a nonlinear constrained single-objective optimization problem where the total line loss (TLL) and the total voltage deviations (TVD) are to be minimized separately by incorporating optimal placement of DG units and shunt capacitors with constraints which include limits on voltage, sizes of installed capacitors and DG. This BGSA is applied on the balanced IEEE 10 Bus distribution network and the results are compared with conventional binary particle swarm optimization.展开更多
为了提高旋转机械设备故障诊断的准确率,提出一种基于广义正态分布优化(Generalized Normal Distribution Optimization,GNDO)的支持向量机(Support Vector Machine,SVM)算法。在SVM算法的基础上,使GNDO对其进行寻优求解,找到SVM算法的...为了提高旋转机械设备故障诊断的准确率,提出一种基于广义正态分布优化(Generalized Normal Distribution Optimization,GNDO)的支持向量机(Support Vector Machine,SVM)算法。在SVM算法的基础上,使GNDO对其进行寻优求解,找到SVM算法的最优参数组,以此推导出GNDO-SVM算法。结果表明,在电机轴承故障诊断中,GNDO-SVM算法相较于SVM算法的分类准确率提高了3.9个百分点,有着更好的有效性和准确性。展开更多
Intrusion detection is critical to guaranteeing the safety of the data in the network.Even though,since Internet commerce has grown at a breakneck pace,network traffic kinds are rising daily,and network behavior chara...Intrusion detection is critical to guaranteeing the safety of the data in the network.Even though,since Internet commerce has grown at a breakneck pace,network traffic kinds are rising daily,and network behavior characteristics are becoming increasingly complicated,posing significant hurdles to intrusion detection.The challenges in terms of false positives,false negatives,low detection accuracy,high running time,adversarial attacks,uncertain attacks,etc.lead to insecure Intrusion Detection System(IDS).To offset the existing challenge,the work has developed a secure Data Mining Intrusion detection system(DataMIDS)framework using Functional Perturbation(FP)feature selection and Bengio Nesterov Momentum-based Tuned Generative Adversarial Network(BNM-tGAN)attack detection technique.The data mining-based framework provides shallow learning of features and emphasizes feature engineering as well as selection.Initially,the IDS data are analyzed for missing values based on the Marginal Likelihood Fisher Information Matrix technique(MLFIMT)that identifies the relationship among the missing values and attack classes.Based on the analysis,the missing values are classified as Missing Completely at Random(MCAR),Missing at random(MAR),Missing Not at Random(MNAR),and handled according to the types.Thereafter,categorical features are handled followed by feature scaling using Absolute Median Division based Robust Scalar(AMDRS)and the Handling of the imbalanced dataset.The selection of relevant features is initiated using FP that uses‘3’Feature Selection(FS)techniques i.e.,Inverse Chi Square based Flamingo Search(ICS-FSO)wrapper method,Hyperparameter Tuned Threshold based Decision Tree(HpTT-DT)embedded method,and Xavier Normal Distribution based Relief(XavND-Relief)filter method.Finally,the selected features are trained and tested for detecting attacks using BNM-tGAN.The Experimental analysis demonstrates that the introduced DataMIDS framework produces an accurate diagnosis about the attack with low computation time.The work avoids false alarm rate of attacks and remains to be relatively robust against malicious attacks as compared to existing methods.展开更多
安装于配电网联络线上的智能软开关(soft normally open point,SNOP)除了能够传输有功功率外,还能够调节无功输出以实现对电压水平的支撑。配电网的无功优化需要综合考虑有载调压变压器(on-load tap changer,OLTC)的分接头、SNOP与分布...安装于配电网联络线上的智能软开关(soft normally open point,SNOP)除了能够传输有功功率外,还能够调节无功输出以实现对电压水平的支撑。配电网的无功优化需要综合考虑有载调压变压器(on-load tap changer,OLTC)的分接头、SNOP与分布式电源(distributed generation,DG)的无功输出。针对这一多控制变量的求解难题,首先建立了以系统有功网损和与上级电网无功交换功率最小为目标函数的优化模型,该问题属于带时间耦合的混合整数规划问题。然后,提出了基于粒子群算法的两阶段无功优化方法,第一阶段忽略时间耦合性,通过聚类算法得出OLTC动作方案,第二阶段获得SNOP与DG的组合状态。最后,以改进的IEEE 33节点系统为算例,计算结果表明考虑SNOP与DG灵活运行的配电网无功优化满足网损减小、无功就地平衡的要求。展开更多
基金This work has supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1A2C1010362)and the Soonchunhyang University Research Fund.
文摘This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.
文摘情感计算是现代人机交互中的关键问题,随着人工智能的发展,基于脑电信号(electroencephalogram, EEG)的情绪识别已经成为重要的研究方向.为了提高情绪识别的分类精度,本研究引入堆叠自动编码器(stacked autoencoder, SAE)对EEG多通道信号进行深度特征提取,并提出一种基于广义正态分布优化的支持向量机(generalized normal distribution optimization based support vector machine, GNDO-SVM)情绪识别模型.实验结果表明,与基于遗传算法、粒子群算法和麻雀搜索算法优化的支持向量机模型相比,所提出的GNDO-SVM模型具有更优的分类性能,基于SAE深度特征的情感识别准确率达到了90.94%,表明SAE能够有效地挖掘EEG信号不同通道间的深度相关性信息.因此,利用SAE深度特征结合GNDO-SVM模型可以有效地实现EEG信号的情绪识别.
文摘This paper presents a binary gravitational search algorithm (BGSA) is applied to solve the problem of optimal allotment of DG sets and Shunt capacitors in radial distribution systems. The problem is formulated as a nonlinear constrained single-objective optimization problem where the total line loss (TLL) and the total voltage deviations (TVD) are to be minimized separately by incorporating optimal placement of DG units and shunt capacitors with constraints which include limits on voltage, sizes of installed capacitors and DG. This BGSA is applied on the balanced IEEE 10 Bus distribution network and the results are compared with conventional binary particle swarm optimization.
文摘为了提高旋转机械设备故障诊断的准确率,提出一种基于广义正态分布优化(Generalized Normal Distribution Optimization,GNDO)的支持向量机(Support Vector Machine,SVM)算法。在SVM算法的基础上,使GNDO对其进行寻优求解,找到SVM算法的最优参数组,以此推导出GNDO-SVM算法。结果表明,在电机轴承故障诊断中,GNDO-SVM算法相较于SVM算法的分类准确率提高了3.9个百分点,有着更好的有效性和准确性。
文摘Intrusion detection is critical to guaranteeing the safety of the data in the network.Even though,since Internet commerce has grown at a breakneck pace,network traffic kinds are rising daily,and network behavior characteristics are becoming increasingly complicated,posing significant hurdles to intrusion detection.The challenges in terms of false positives,false negatives,low detection accuracy,high running time,adversarial attacks,uncertain attacks,etc.lead to insecure Intrusion Detection System(IDS).To offset the existing challenge,the work has developed a secure Data Mining Intrusion detection system(DataMIDS)framework using Functional Perturbation(FP)feature selection and Bengio Nesterov Momentum-based Tuned Generative Adversarial Network(BNM-tGAN)attack detection technique.The data mining-based framework provides shallow learning of features and emphasizes feature engineering as well as selection.Initially,the IDS data are analyzed for missing values based on the Marginal Likelihood Fisher Information Matrix technique(MLFIMT)that identifies the relationship among the missing values and attack classes.Based on the analysis,the missing values are classified as Missing Completely at Random(MCAR),Missing at random(MAR),Missing Not at Random(MNAR),and handled according to the types.Thereafter,categorical features are handled followed by feature scaling using Absolute Median Division based Robust Scalar(AMDRS)and the Handling of the imbalanced dataset.The selection of relevant features is initiated using FP that uses‘3’Feature Selection(FS)techniques i.e.,Inverse Chi Square based Flamingo Search(ICS-FSO)wrapper method,Hyperparameter Tuned Threshold based Decision Tree(HpTT-DT)embedded method,and Xavier Normal Distribution based Relief(XavND-Relief)filter method.Finally,the selected features are trained and tested for detecting attacks using BNM-tGAN.The Experimental analysis demonstrates that the introduced DataMIDS framework produces an accurate diagnosis about the attack with low computation time.The work avoids false alarm rate of attacks and remains to be relatively robust against malicious attacks as compared to existing methods.
文摘安装于配电网联络线上的智能软开关(soft normally open point,SNOP)除了能够传输有功功率外,还能够调节无功输出以实现对电压水平的支撑。配电网的无功优化需要综合考虑有载调压变压器(on-load tap changer,OLTC)的分接头、SNOP与分布式电源(distributed generation,DG)的无功输出。针对这一多控制变量的求解难题,首先建立了以系统有功网损和与上级电网无功交换功率最小为目标函数的优化模型,该问题属于带时间耦合的混合整数规划问题。然后,提出了基于粒子群算法的两阶段无功优化方法,第一阶段忽略时间耦合性,通过聚类算法得出OLTC动作方案,第二阶段获得SNOP与DG的组合状态。最后,以改进的IEEE 33节点系统为算例,计算结果表明考虑SNOP与DG灵活运行的配电网无功优化满足网损减小、无功就地平衡的要求。
