It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper propos...It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper proposes an approach to layer nodes of a BN by using the conditional independence testing.The parents of a node layer only belong to the layer,or layers who have priority over the layer.When a set of nodes has been layered,the number of feasible structures over the nodes can be remarkably reduced,which makes it possible to learn optimal BN structures for bigger sizes of nodes by accurate algorithms.Integrating the dynamic programming(DP)algorithm with the layering approach,we propose a hybrid algorithm—layered optimal learning(LOL)to learn BN structures.Benefitted by the layering approach,the complexity of the DP algorithm reduces to O(ρ2^n?1)from O(n2^n?1),whereρ<n.Meanwhile,the memory requirements for storing intermediate results are limited to O(C k#/k#^2 )from O(Cn/n^2 ),where k#<n.A case study on learning a standard BN with 50 nodes is conducted.The results demonstrate the superiority of the LOL algorithm,with respect to the Bayesian information criterion(BIC)score criterion,over the hill-climbing,max-min hill-climbing,PC,and three-phrase dependency analysis algorithms.展开更多
The rapid evolution of wireless technologies and the advent of 6G networks present new challenges and opportunities for Internet ofThings(IoT)applications,particularly in terms of ultra-reliable,secure,and energyeffic...The rapid evolution of wireless technologies and the advent of 6G networks present new challenges and opportunities for Internet ofThings(IoT)applications,particularly in terms of ultra-reliable,secure,and energyefficient communication.This study explores the integration of Reconfigurable Intelligent Surfaces(RIS)into IoT networks to enhance communication performance.Unlike traditional passive reflector-based approaches,RIS is leveraged as an active optimization tool to improve both backscatter and direct communication modes,addressing critical IoT challenges such as energy efficiency,limited communication range,and double-fading effects in backscatter communication.We propose a novel computational framework that combines RIS functionality with Physical Layer Security(PLS)mechanisms,optimized through the algorithm known as Deep Deterministic Policy Gradient(DDPG).This framework adaptively adapts RIS configurations and transmitter beamforming to reduce key challenges,including imperfect channel state information(CSI)and hardware limitations like quantized RIS phase shifts.By optimizing both RIS settings and beamforming in real-time,our approach outperforms traditional methods by significantly increasing secrecy rates,improving spectral efficiency,and enhancing energy efficiency.Notably,this framework adapts more effectively to the dynamic nature of wireless channels compared to conventional optimization techniques,providing scalable solutions for large-scale RIS deployments.Our results demonstrate substantial improvements in communication performance setting a new benchmark for secure,efficient and scalable 6G communication.This work offers valuable insights for the future of IoT networks,with a focus on computational optimization,high spectral efficiency and energy-aware operations.展开更多
This paper investigates the security and reliability of information transmission within an underlay wiretap energy harvesting cognitive two-way relay network.In the network,energy-constrained secondary network(SN)node...This paper investigates the security and reliability of information transmission within an underlay wiretap energy harvesting cognitive two-way relay network.In the network,energy-constrained secondary network(SN)nodes harvest energy from radio frequency signals of a multi-antenna power beacon.Two SN sources exchange their messages via a SN decode-and-forward relay in the presence of a multiantenna eavesdropper by using a four-phase time division broadcast protocol,and the hardware impairments of SN nodes and eavesdropper are modeled.To alleviate eavesdropping attacks,the artificial noise is applied by SN nodes.The physical layer security performance of SN is analyzed and evaluated by the exact closed-form expressions of outage probability(OP),intercept probability(IP),and OP+IP over quasistatic Rayleigh fading channel.Additionally,due to the complexity of OP+IP expression,a self-adaptive chaotic quantum particle swarm optimization-based resource allocation algorithm is proposed to jointly optimize energy harvesting ratio and power allocation factor,which can achieve security-reliability tradeoff for SN.Extensive simulations demonstrate the correctness of theoretical analysis and the effectiveness of the proposed optimization algorithm.展开更多
Based on the characteristics of guaranteed handover （GH） algorithm, the finite capacity in one system makes the blocking probability （PB） of GH algorithm increase rapidly in the case of high traffic losd. So, when...Based on the characteristics of guaranteed handover （GH） algorithm, the finite capacity in one system makes the blocking probability （PB） of GH algorithm increase rapidly in the case of high traffic losd. So, when large amounts of multimedia services are transmitted via a single low earth orbit （LEO） satellite system, the PB of it is much higher. In order to solve the problem, a novel handover scheme defined by multi-tier optimal layer selection is proposed. The scheme sufficiently takes into account the characteristics of double-tier satellite network, which is constituted by LEO satellites combined with medium earth orbit （MEO） satellites, and the multimedia transmitted by such network, so it can augment this systematic capacity and effectively reduces the traffic loed in the LEO which performs GH algorithm. The detailed processes are also presented. The simulation and numerical results show that the approach integrated with GH algorithm achieves a significant improvement in the PB and practicality, as compared to the single LEO layer network.展开更多
The scope of this paper is to forecast wind speed. Wind speed, temperature, wind direction, relative humidity, precipitation of water content and air pressure are the main factors make the wind speed forecasting as a ...The scope of this paper is to forecast wind speed. Wind speed, temperature, wind direction, relative humidity, precipitation of water content and air pressure are the main factors make the wind speed forecasting as a complex problem and neural network performance is mainly influenced by proper hidden layer neuron units. This paper proposes new criteria for appropriate hidden layer neuron unit’s determination and attempts a novel hybrid method in order to achieve enhanced wind speed forecasting. This paper proposes the following two main innovative contributions 1) both either over fitting or under fitting issues are avoided by means of the proposed new criteria based hidden layer neuron unit’s estimation. 2) ELMAN neural network is optimized through Modified Grey Wolf Optimizer (MGWO). The proposed hybrid method (ELMAN-MGWO) performance, effectiveness is confirmed by means of the comparison between Grey Wolf Optimizer (GWO), Adaptive Gbest-guided Gravitational Search Algorithm (GGSA), Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Cuckoo Search (CS), Particle Swarm Optimization (PSO), Evolution Strategy (ES), Genetic Algorithm (GA) algorithms, meanwhile proposed new criteria effectiveness and precise are verified comparison with other existing selection criteria. Three real-time wind data sets are utilized in order to analysis the performance of the proposed approach. Simulation results demonstrate that the proposed hybrid method (ELMAN-MGWO) achieve the mean square error AVG ± STD of 4.1379e-11 ± 1.0567e-15, 6.3073e-11 ± 3.5708e-15 and 7.5840e-11 ± 1.1613e-14 respectively for evaluation on three real-time data sets. Hence, the proposed hybrid method is superior, precise, enhance wind speed forecasting than that of other existing methods and robust.展开更多
A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their...A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.展开更多
Computation is spanning from PC to Mobile devices. The Mobile Ad hoc Networks (MANETs) are optimal choice to accommodate this growing trend but there is a problem, security is the core issue. MANETs rely on wireless l...Computation is spanning from PC to Mobile devices. The Mobile Ad hoc Networks (MANETs) are optimal choice to accommodate this growing trend but there is a problem, security is the core issue. MANETs rely on wireless links for communication. Wireless networks are considered more exposed to security attacks as compared to wired networks, especially;MANETs are the soft target due to vulnerable in nature. Lack of infrastructure, open peer to peer connectivity, shared wireless medium, dynamic topology and scalability are the key characteristics of MANETs which make them ideal for security attacks. In this paper, we shall discuss in detail, what does security mean, why MANETs are more susceptible to security attacks than wired networks, taxonomy of network attacks and layer wise analysis of network attacks. Finally, we shall propose solutions to meet the security challenges, according to our framed security criteria.展开更多
双有源桥变换器因其优异的功率密度和双向功率传输能力,在众多工业应用中得到广泛关注。随着电力电子设备对能效和可靠性要求的不断提高,双有源桥变换器的电流应力已成为衡量其性能的关键指标之一。过大的电流应力不仅会导致功率器件损...双有源桥变换器因其优异的功率密度和双向功率传输能力,在众多工业应用中得到广泛关注。随着电力电子设备对能效和可靠性要求的不断提高,双有源桥变换器的电流应力已成为衡量其性能的关键指标之一。过大的电流应力不仅会导致功率器件损耗增加,系统效率下降,还会影响变换器的可靠性和使用寿命。针对上述问题,提出了一种基于TabNet-LN-LSTM协同预测与粒子群优化的电流应力优化方法。该方法通过利用TabNet和层归一化长短期记忆神经网络(Long-short term memory neural network with layer normalization,LN-LSTM)协同构建电感电流时序预测模型,并结合粒子群优化算法对双有源桥变换器在不同运行工况下的电流应力进行优化。通过算法试验和硬件试验证明,所提方法不仅能够精确预测电感电流波形,其预测波形与硬件实测波形相比,其平均绝对误差仅为0.3525,决定系数高达97.17%;同时,能够有效降低双有源桥变换器的电流应力,进一步提升系统的整体效能和可靠性。展开更多
For fault characteristics of cyber-physical-systems(CPS)based distribution network,a spatiotemporal incidence matrix to represent correlation of concurrent faults on cyberspace and physical space is proposed,and strat...For fault characteristics of cyber-physical-systems(CPS)based distribution network,a spatiotemporal incidence matrix to represent correlation of concurrent faults on cyberspace and physical space is proposed,and strategies of fault location,removal,and recovery of concurrent faults are analyzed in this paper.Considering the multiple objectives of minimum network loss,voltage deviation,and switching operation times,a collaborative power supply restoration model of a CPS-based distribution network with the strategy that restoration of the communication layer is prior to the physical layer is constructed using the Dijkstra’s dynamic routing algorithm and second-order cone relaxation distribution network reconfiguration method,to realize orderly recovery of a distribution network during CPS concurrent faults.Related investigations are made based on the DCPS-160 case,and the accuracy and effectiveness of the proposed model are also verified.展开更多
Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selecti...Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selection and the need for more hidden neurons adversely influence network usability.Further,choosing the optimal number of hidden nodes for a network usually requires intensive human intervention,which may lead to an ill-conditioned situation.In this context,chemical reaction optimization(CRO)is a meta-heuristic paradigm with increased success in a large number of application areas.It is characterized by faster convergence capability and requires fewer tunable parameters.This study develops a learning framework combining the advantages of ELM and CRO,called extreme learning with chemical reaction optimization(ELCRO).ELCRO simultaneously optimizes the weight and bias vector and number of hidden neurons of a single layer feed-forward neural network without compromising prediction accuracy.We evaluate its performance by predicting the daily volatility and closing prices of BSE indices.Additionally,its performance is compared with three other similarly developed models—ELM based on particle swarm optimization,genetic algorithm,and gradient descent—and find the performance of the proposed algorithm superior.Wilcoxon signed-rank and Diebold–Mariano tests are then conducted to verify the statistical significance of the proposed model.Hence,this model can be used as a promising tool for financial forecasting.展开更多
Now a days,Remote Sensing(RS)techniques are used for earth observation and for detection of soil types with high accuracy and better reliability.This technique provides perspective view of spatial resolution and aids ...Now a days,Remote Sensing(RS)techniques are used for earth observation and for detection of soil types with high accuracy and better reliability.This technique provides perspective view of spatial resolution and aids in instantaneous measurement of soil’s minerals and its characteristics.There are a few challenges that is present in soil classification using image enhancement such as,locating and plotting soil boundaries,slopes,hazardous areas,drainage condition,land use,vegetation etc.There are some traditional approaches which involves few drawbacks such as,manual involvement which results in inaccuracy due to human interference,time consuming,inconsistent prediction etc.To overcome these draw backs and to improve the predictive analysis of soil characteristics,we propose a Hybrid Deep Learning improved BAT optimization algorithm(HDIB)for soil classification using remote sensing hyperspectral features.In HDIB,we propose a spontaneous BAT optimization algorithm for feature extraction of both spectral-spatial features by choosing pure pixels from the Hyper Spectral(HS)image.Spectral-spatial vector as training illustrations is attained by merging spatial and spectral vector by means of priority stacking methodology.Then,a recurring Deep Learning(DL)Neural Network(NN)is used for classifying the HS images,considering the datasets of Pavia University,Salinas and Tamil Nadu Hill Scene,which in turn improves the reliability of classification.Finally,the performance of the proposed HDIB based soil classifier is compared and analyzed with existing methodologies like Single Layer Perceptron(SLP),Convolutional Neural Networks(CNN)and Deep Metric Learning(DML)and it shows an improved classification accuracy of 99.87%,98.34%and 99.9%for Tamil Nadu Hills dataset,Pavia University and Salinas scene datasets respectively.展开更多
基金supported by the National Natural Science Foundation of China(61573285)
文摘It is unpractical to learn the optimal structure of a big Bayesian network(BN)by exhausting the feasible structures,since the number of feasible structures is super exponential on the number of nodes.This paper proposes an approach to layer nodes of a BN by using the conditional independence testing.The parents of a node layer only belong to the layer,or layers who have priority over the layer.When a set of nodes has been layered,the number of feasible structures over the nodes can be remarkably reduced,which makes it possible to learn optimal BN structures for bigger sizes of nodes by accurate algorithms.Integrating the dynamic programming(DP)algorithm with the layering approach,we propose a hybrid algorithm—layered optimal learning(LOL)to learn BN structures.Benefitted by the layering approach,the complexity of the DP algorithm reduces to O(ρ2^n?1)from O(n2^n?1),whereρ<n.Meanwhile,the memory requirements for storing intermediate results are limited to O(C k#/k#^2 )from O(Cn/n^2 ),where k#<n.A case study on learning a standard BN with 50 nodes is conducted.The results demonstrate the superiority of the LOL algorithm,with respect to the Bayesian information criterion(BIC)score criterion,over the hill-climbing,max-min hill-climbing,PC,and three-phrase dependency analysis algorithms.
基金funded by the deanship of scientific research(DSR),King Abdukaziz University,Jeddah,under grant No.(G-1436-611-225)。
文摘The rapid evolution of wireless technologies and the advent of 6G networks present new challenges and opportunities for Internet ofThings(IoT)applications,particularly in terms of ultra-reliable,secure,and energyefficient communication.This study explores the integration of Reconfigurable Intelligent Surfaces(RIS)into IoT networks to enhance communication performance.Unlike traditional passive reflector-based approaches,RIS is leveraged as an active optimization tool to improve both backscatter and direct communication modes,addressing critical IoT challenges such as energy efficiency,limited communication range,and double-fading effects in backscatter communication.We propose a novel computational framework that combines RIS functionality with Physical Layer Security(PLS)mechanisms,optimized through the algorithm known as Deep Deterministic Policy Gradient(DDPG).This framework adaptively adapts RIS configurations and transmitter beamforming to reduce key challenges,including imperfect channel state information(CSI)and hardware limitations like quantized RIS phase shifts.By optimizing both RIS settings and beamforming in real-time,our approach outperforms traditional methods by significantly increasing secrecy rates,improving spectral efficiency,and enhancing energy efficiency.Notably,this framework adapts more effectively to the dynamic nature of wireless channels compared to conventional optimization techniques,providing scalable solutions for large-scale RIS deployments.Our results demonstrate substantial improvements in communication performance setting a new benchmark for secure,efficient and scalable 6G communication.This work offers valuable insights for the future of IoT networks,with a focus on computational optimization,high spectral efficiency and energy-aware operations.
基金supported in part by the National Natural Science Foundation of China under Grant 61971450in part by the Hunan Provincial Science and Technology Project Foundation under Grant 2018TP1018+1 种基金in part by the Natural Science Foundation of Hunan Province under Grant 2018JJ2533in part by Hunan Province College Students Research Learning and Innovative Experiment Project under Grant S202110542056。
文摘This paper investigates the security and reliability of information transmission within an underlay wiretap energy harvesting cognitive two-way relay network.In the network,energy-constrained secondary network(SN)nodes harvest energy from radio frequency signals of a multi-antenna power beacon.Two SN sources exchange their messages via a SN decode-and-forward relay in the presence of a multiantenna eavesdropper by using a four-phase time division broadcast protocol,and the hardware impairments of SN nodes and eavesdropper are modeled.To alleviate eavesdropping attacks,the artificial noise is applied by SN nodes.The physical layer security performance of SN is analyzed and evaluated by the exact closed-form expressions of outage probability(OP),intercept probability(IP),and OP+IP over quasistatic Rayleigh fading channel.Additionally,due to the complexity of OP+IP expression,a self-adaptive chaotic quantum particle swarm optimization-based resource allocation algorithm is proposed to jointly optimize energy harvesting ratio and power allocation factor,which can achieve security-reliability tradeoff for SN.Extensive simulations demonstrate the correctness of theoretical analysis and the effectiveness of the proposed optimization algorithm.
文摘Based on the characteristics of guaranteed handover （GH） algorithm, the finite capacity in one system makes the blocking probability （PB） of GH algorithm increase rapidly in the case of high traffic losd. So, when large amounts of multimedia services are transmitted via a single low earth orbit （LEO） satellite system, the PB of it is much higher. In order to solve the problem, a novel handover scheme defined by multi-tier optimal layer selection is proposed. The scheme sufficiently takes into account the characteristics of double-tier satellite network, which is constituted by LEO satellites combined with medium earth orbit （MEO） satellites, and the multimedia transmitted by such network, so it can augment this systematic capacity and effectively reduces the traffic loed in the LEO which performs GH algorithm. The detailed processes are also presented. The simulation and numerical results show that the approach integrated with GH algorithm achieves a significant improvement in the PB and practicality, as compared to the single LEO layer network.
文摘The scope of this paper is to forecast wind speed. Wind speed, temperature, wind direction, relative humidity, precipitation of water content and air pressure are the main factors make the wind speed forecasting as a complex problem and neural network performance is mainly influenced by proper hidden layer neuron units. This paper proposes new criteria for appropriate hidden layer neuron unit’s determination and attempts a novel hybrid method in order to achieve enhanced wind speed forecasting. This paper proposes the following two main innovative contributions 1) both either over fitting or under fitting issues are avoided by means of the proposed new criteria based hidden layer neuron unit’s estimation. 2) ELMAN neural network is optimized through Modified Grey Wolf Optimizer (MGWO). The proposed hybrid method (ELMAN-MGWO) performance, effectiveness is confirmed by means of the comparison between Grey Wolf Optimizer (GWO), Adaptive Gbest-guided Gravitational Search Algorithm (GGSA), Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Cuckoo Search (CS), Particle Swarm Optimization (PSO), Evolution Strategy (ES), Genetic Algorithm (GA) algorithms, meanwhile proposed new criteria effectiveness and precise are verified comparison with other existing selection criteria. Three real-time wind data sets are utilized in order to analysis the performance of the proposed approach. Simulation results demonstrate that the proposed hybrid method (ELMAN-MGWO) achieve the mean square error AVG ± STD of 4.1379e-11 ± 1.0567e-15, 6.3073e-11 ± 3.5708e-15 and 7.5840e-11 ± 1.1613e-14 respectively for evaluation on three real-time data sets. Hence, the proposed hybrid method is superior, precise, enhance wind speed forecasting than that of other existing methods and robust.
文摘A brain-computer interface(BCI)system is one of the most effective ways that translates brain signals into output commands.Different imagery activities can be classified based on the changes inμandβrhythms and their spatial distributions.Multi-layer perceptron neural networks(MLP-NNs)are commonly used for classification.Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently.Conventional methods for training NNs,such as gradient descent and recursive methods,have some disadvantages including low accuracy,slow convergence speed and trapping in local minimums.In this paper,in order to overcome these issues,the MLP-NN trained by a hybrid population-physics-based algorithm,the combination of particle swarm optimization and gravitational search algorithm(PSOGSA),is proposed for our classification problem.To show the advantages of using PSOGSA that trains NNs,this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization(PSO),gravitational search algorithm(GSA)and new versions of PSO.The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics.The results show that the proposed algorithm in most subjects of encephalography(EEG)dataset has very better or acceptable performance compared to others.
文摘Computation is spanning from PC to Mobile devices. The Mobile Ad hoc Networks (MANETs) are optimal choice to accommodate this growing trend but there is a problem, security is the core issue. MANETs rely on wireless links for communication. Wireless networks are considered more exposed to security attacks as compared to wired networks, especially;MANETs are the soft target due to vulnerable in nature. Lack of infrastructure, open peer to peer connectivity, shared wireless medium, dynamic topology and scalability are the key characteristics of MANETs which make them ideal for security attacks. In this paper, we shall discuss in detail, what does security mean, why MANETs are more susceptible to security attacks than wired networks, taxonomy of network attacks and layer wise analysis of network attacks. Finally, we shall propose solutions to meet the security challenges, according to our framed security criteria.
文摘双有源桥变换器因其优异的功率密度和双向功率传输能力,在众多工业应用中得到广泛关注。随着电力电子设备对能效和可靠性要求的不断提高,双有源桥变换器的电流应力已成为衡量其性能的关键指标之一。过大的电流应力不仅会导致功率器件损耗增加,系统效率下降,还会影响变换器的可靠性和使用寿命。针对上述问题,提出了一种基于TabNet-LN-LSTM协同预测与粒子群优化的电流应力优化方法。该方法通过利用TabNet和层归一化长短期记忆神经网络(Long-short term memory neural network with layer normalization,LN-LSTM)协同构建电感电流时序预测模型,并结合粒子群优化算法对双有源桥变换器在不同运行工况下的电流应力进行优化。通过算法试验和硬件试验证明,所提方法不仅能够精确预测电感电流波形,其预测波形与硬件实测波形相比,其平均绝对误差仅为0.3525,决定系数高达97.17%;同时,能够有效降低双有源桥变换器的电流应力,进一步提升系统的整体效能和可靠性。
基金This work is supported by Funds for International Cooperation and Exchange of the National Natural Science Foundation of China(Grant No.52061635104,Sustainable urban power supply through intelligent control and enhanced restoration of AC/DC networks).
文摘For fault characteristics of cyber-physical-systems(CPS)based distribution network,a spatiotemporal incidence matrix to represent correlation of concurrent faults on cyberspace and physical space is proposed,and strategies of fault location,removal,and recovery of concurrent faults are analyzed in this paper.Considering the multiple objectives of minimum network loss,voltage deviation,and switching operation times,a collaborative power supply restoration model of a CPS-based distribution network with the strategy that restoration of the communication layer is prior to the physical layer is constructed using the Dijkstra’s dynamic routing algorithm and second-order cone relaxation distribution network reconfiguration method,to realize orderly recovery of a distribution network during CPS concurrent faults.Related investigations are made based on the DCPS-160 case,and the accuracy and effectiveness of the proposed model are also verified.
文摘Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selection and the need for more hidden neurons adversely influence network usability.Further,choosing the optimal number of hidden nodes for a network usually requires intensive human intervention,which may lead to an ill-conditioned situation.In this context,chemical reaction optimization(CRO)is a meta-heuristic paradigm with increased success in a large number of application areas.It is characterized by faster convergence capability and requires fewer tunable parameters.This study develops a learning framework combining the advantages of ELM and CRO,called extreme learning with chemical reaction optimization(ELCRO).ELCRO simultaneously optimizes the weight and bias vector and number of hidden neurons of a single layer feed-forward neural network without compromising prediction accuracy.We evaluate its performance by predicting the daily volatility and closing prices of BSE indices.Additionally,its performance is compared with three other similarly developed models—ELM based on particle swarm optimization,genetic algorithm,and gradient descent—and find the performance of the proposed algorithm superior.Wilcoxon signed-rank and Diebold–Mariano tests are then conducted to verify the statistical significance of the proposed model.Hence,this model can be used as a promising tool for financial forecasting.
文摘Now a days,Remote Sensing(RS)techniques are used for earth observation and for detection of soil types with high accuracy and better reliability.This technique provides perspective view of spatial resolution and aids in instantaneous measurement of soil’s minerals and its characteristics.There are a few challenges that is present in soil classification using image enhancement such as,locating and plotting soil boundaries,slopes,hazardous areas,drainage condition,land use,vegetation etc.There are some traditional approaches which involves few drawbacks such as,manual involvement which results in inaccuracy due to human interference,time consuming,inconsistent prediction etc.To overcome these draw backs and to improve the predictive analysis of soil characteristics,we propose a Hybrid Deep Learning improved BAT optimization algorithm(HDIB)for soil classification using remote sensing hyperspectral features.In HDIB,we propose a spontaneous BAT optimization algorithm for feature extraction of both spectral-spatial features by choosing pure pixels from the Hyper Spectral(HS)image.Spectral-spatial vector as training illustrations is attained by merging spatial and spectral vector by means of priority stacking methodology.Then,a recurring Deep Learning(DL)Neural Network(NN)is used for classifying the HS images,considering the datasets of Pavia University,Salinas and Tamil Nadu Hill Scene,which in turn improves the reliability of classification.Finally,the performance of the proposed HDIB based soil classifier is compared and analyzed with existing methodologies like Single Layer Perceptron(SLP),Convolutional Neural Networks(CNN)and Deep Metric Learning(DML)and it shows an improved classification accuracy of 99.87%,98.34%and 99.9%for Tamil Nadu Hills dataset,Pavia University and Salinas scene datasets respectively.
