The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by...The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.展开更多
Quasi-one-dimensional(quasi-1D)van der Waals(vdWs)materials,such as ZrTe_(5),exhibit unique elec-trical properties and quantum phenomena,making them attractive for advanced electronic applications.However,large-scale ...Quasi-one-dimensional(quasi-1D)van der Waals(vdWs)materials,such as ZrTe_(5),exhibit unique elec-trical properties and quantum phenomena,making them attractive for advanced electronic applications.However,large-scale growth of ZrTe_(5) thin films presents challenges.We address this by employing sput-tering,a common semiconductor industry technique.The as-deposited ZrTe_(5) film is amorphous,and post-annealing induces a crystallization process akin to transition-metal dichalcogenides.Our study in-vestigates the electrical and optical properties during this amorphous-to-crystalline transition,reveal-ing insights into the underlying mechanism.This work contributes to the fundamental understanding of quasi-1D materials and introduces a scalable fabrication method for ZrTe_(5) which offers the possibility of fabricating unique future electronic and optical devices.展开更多
角度域共成像点道集是衔接叠前地震数据与储层特征的重要桥梁,对地震偏移成像与储层描述具有重要意义.与克希霍夫偏移和单向波动方程偏移相比,逆时偏移是复杂地区最精确的成像方法.高效稳健地生成逆时偏移角度道集目前仍然是一个挑战....角度域共成像点道集是衔接叠前地震数据与储层特征的重要桥梁,对地震偏移成像与储层描述具有重要意义.与克希霍夫偏移和单向波动方程偏移相比,逆时偏移是复杂地区最精确的成像方法.高效稳健地生成逆时偏移角度道集目前仍然是一个挑战.本文主要讨论如何采用光学流方法高效、高质量地提取角度道集.在逆时偏移波场外推过程中,光学流方法可以估计波场传播方向.其中Lucas-Kanade(LK)和Horn-Schunck(HS)方法是光学流方法中两种典型的方法.LK光学流方法是一种局部方法,该方法依赖于局部点的梯度值,但是容易出现奇异现象,HS光学流方法属于全局方法,波场方向估计依赖于整个波场,易受噪声影响,对异常值比较敏感,导致整体波场方向计算精度不高.本文提出采用局部和整体结合(Combining Local and Global,CLG)的光学流方法估计波场传播方向.该方法可以有效地提高波场方向的精度,并且简单高效,便于并行处理.对比HS光学流方法,CLG光学流方法几乎不增加额外的计算量.另外,为了弱化光学流方法无法处理波前重叠问题,本文利用解析波场和方向滤波对波场进行方向分解,仅需波场的空间傅里叶变换即可实现任意波场方向分解,将分解后的波场分别估计波场反向,提取成像结果.进一步地,在估计反射张角和方位角时,本文提出有效的归一化方法和改进的最小二乘除法,提高角度估计的精度和稳定性.最后,理论和实际资料例证了本文提出方法的有效性.展开更多
基金described in this paper has been developed with in the project PRESECREL(PID2021-124502OB-C43)。
文摘The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.
基金supported by the JSPS KAKENHI(Grant Nos.21H05009,22K20474,and 24K00915)the Murata Science Foundation+1 种基金supported by the Commissioned Research(No.JPJ012368C03701)of the National Institute of Information and Communications Technology(NICT),Japansupport from the Hirose Foundation and Iketani Science and Technology Foundation.
文摘Quasi-one-dimensional(quasi-1D)van der Waals(vdWs)materials,such as ZrTe_(5),exhibit unique elec-trical properties and quantum phenomena,making them attractive for advanced electronic applications.However,large-scale growth of ZrTe_(5) thin films presents challenges.We address this by employing sput-tering,a common semiconductor industry technique.The as-deposited ZrTe_(5) film is amorphous,and post-annealing induces a crystallization process akin to transition-metal dichalcogenides.Our study in-vestigates the electrical and optical properties during this amorphous-to-crystalline transition,reveal-ing insights into the underlying mechanism.This work contributes to the fundamental understanding of quasi-1D materials and introduces a scalable fabrication method for ZrTe_(5) which offers the possibility of fabricating unique future electronic and optical devices.
文摘角度域共成像点道集是衔接叠前地震数据与储层特征的重要桥梁,对地震偏移成像与储层描述具有重要意义.与克希霍夫偏移和单向波动方程偏移相比,逆时偏移是复杂地区最精确的成像方法.高效稳健地生成逆时偏移角度道集目前仍然是一个挑战.本文主要讨论如何采用光学流方法高效、高质量地提取角度道集.在逆时偏移波场外推过程中,光学流方法可以估计波场传播方向.其中Lucas-Kanade(LK)和Horn-Schunck(HS)方法是光学流方法中两种典型的方法.LK光学流方法是一种局部方法,该方法依赖于局部点的梯度值,但是容易出现奇异现象,HS光学流方法属于全局方法,波场方向估计依赖于整个波场,易受噪声影响,对异常值比较敏感,导致整体波场方向计算精度不高.本文提出采用局部和整体结合(Combining Local and Global,CLG)的光学流方法估计波场传播方向.该方法可以有效地提高波场方向的精度,并且简单高效,便于并行处理.对比HS光学流方法,CLG光学流方法几乎不增加额外的计算量.另外,为了弱化光学流方法无法处理波前重叠问题,本文利用解析波场和方向滤波对波场进行方向分解,仅需波场的空间傅里叶变换即可实现任意波场方向分解,将分解后的波场分别估计波场反向,提取成像结果.进一步地,在估计反射张角和方位角时,本文提出有效的归一化方法和改进的最小二乘除法,提高角度估计的精度和稳定性.最后,理论和实际资料例证了本文提出方法的有效性.
