This paper describes the application of principal component analysis (PCA) and artificial neural network (ANN) to predict the air pollutant index (API) within the seven selected Malaysian air monitoring stations in th...This paper describes the application of principal component analysis (PCA) and artificial neural network (ANN) to predict the air pollutant index (API) within the seven selected Malaysian air monitoring stations in the southern region of Peninsular Malaysia based on seven years database (2005-2011). Feed-forward ANN was used as a prediction method. The feed-forward ANN analysis demonstrated that the rotated principal component scores (RPCs) were the best input parameters to predict API. From the 4 RPCs, only 10 (CO, O3, PM10, NO2, CH4, NmHC, THC, wind direction, humidity and ambient temp) out of 12 prediction variables were the most significant parameters to predict API. The results proved that the ANN method can be applied successfully as tools for decision making and problem solving for better atmospheric management.展开更多
In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other...In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other factors. In order to ensure high equipment performance and avoid high-cost losses, it is essential to identify the source of possible failures in the early stage. However, this requires additional maintenance fees and human power. Moreover, the losses caused by these problems may lead to interruptions in the whole production process. In order to minimize maintenance costs, in this paper, we introduce a model for predicting equipment failure based on processing the historical data collected from multiple sensors. The state of the system is predicted by a Feed-Forward Neural Network (FFNN) with an SGD and Backpropagation algorithm is applied in the training process. Our model’s primary goal is to identify potential malfunctions at an early stage to ensure the production process’ continued high performance. We also evaluated the effectiveness of our model against other solutions currently available in the industry. The results of our study show that the FFNN can attain an accuracy score of 97% on the given dataset, which exceeds the performance of the models provided.展开更多
In recent years,the development in the field of computer-aided diagnosis(CAD)has increased rapidly.Many traditional machine learning algorithms have been proposed for identifying the pathological brain using magnetic ...In recent years,the development in the field of computer-aided diagnosis(CAD)has increased rapidly.Many traditional machine learning algorithms have been proposed for identifying the pathological brain using magnetic resonance images.The existing algorithms have drawbacks with respect to their accuracy,efficiency,and limited learning processes.To address these issues,we propose a pathological brain tumour detection method that utilizes the Weiner filter to improve the image contrast,2D-discrete wavelet transformation(2D-DWT)to extract the features,probabilistic principal component analysis(PPCA)and linear discriminant analysis(LDA)to normalize and reduce the features,and a feed-forward neural network(FNN)and modified particle swarm optimization(MPSO)with ant colony optimization(ACO)to improve the accuracy,stability,and overcome fitting issues in the classification of brain magnetic resonance images.The proposed method achieves better results than other existing algorithms.展开更多
This paper offer an artificial neural network (ANN) model to calculate drag force on an axisymmetric underwater vehicle by obtaining dataset from a computational fluid dynamic analysis. First, great effort was done to...This paper offer an artificial neural network (ANN) model to calculate drag force on an axisymmetric underwater vehicle by obtaining dataset from a computational fluid dynamic analysis. First, great effort was done to calculate the pressure and viscous data forces by increasing the precision and numerical data in order to extend and raise quality of dataset. In this step, numerous different geometry models (configurations of axisymmetric body) were designed, examined and evaluated input parameters including: diameter of body, diameter of nose disc, length of body, length of nose and velocity whereas outputs contain pressure and viscous forces. This dataset was used to train the ANN model. Feed-forward neural network (FFNN) is selected which is more common and suitable in this field’s study. A three-layer neural network was opted and after training this network, the results showed good agreement with CFD data. This study shows that applying the ANN model helps to reach final purpose in the least time and error, in addition a variety of tests can be performed to have a desired design in this way.展开更多
We propose a dual feed-forward neural network(DFNN)model,consisting of a cavity parameter feature expander(CPFE)and a dynamic process predictor(DPP),for predicting the complex nonlinear dynamics of mode-locked fiber l...We propose a dual feed-forward neural network(DFNN)model,consisting of a cavity parameter feature expander(CPFE)and a dynamic process predictor(DPP),for predicting the complex nonlinear dynamics of mode-locked fiber lasers.The output of the CPFE,following layer normalization,is combined with the pulse complex electric field amplitude and then fed into the DPP to predict the dynamics.The pulse evolution process from the detuned steady state to the steady state under different cavity configurations is rapidly calculated.The predicted results of the proposed DFNN are consistent with the numerical split-step Fourier method(SSFM).The simulation speed has been greatly improved with low computational complexity,which is approximately 152 times faster than the SSFM and 4 times faster than the long short-term memory recurrent neural network(LSTM)model.The findings provide a new low computational complexity and efficient machine learning approach to model the complex nonlinear dynamics of mode-locked lasers.展开更多
The migration of tasks aided by machine learning(ML)predictions IN(DPM)is a system-level design technique that is used to reduce energy by enhancing the overall performance of the processor.In this paper,we address th...The migration of tasks aided by machine learning(ML)predictions IN(DPM)is a system-level design technique that is used to reduce energy by enhancing the overall performance of the processor.In this paper,we address the issue of system-level higher task dissipation during the execution of parallel workloads with common deadlines by introducing a machine learning-based framework that includes task migration using energy-efficient earliest deadline first scheduling(EA-EDF).ML-based EA-EDF enhances the overall throughput and optimizes the energy to avoid delay and performance degradation in a multiprocessor system.The proposed system model allocates processors to the ready task set in such a way that their deadlines are guaranteed.A full task migration policy is also integrated to ensure proper task mapping that ensures inter-process linkage among the arrived tasks with the same deadlines.The execution of a task can halt on one CPU and reschedule the execution on a different processor to avoid delay and ensure meeting the deadline.Our approach shows promising potential for machine-learning-based schedulability analysis enables a comparison between different ML models and shows a promising reduction in energy as compared with other ML-aware task migration techniques for SoC like Multi-Layer Feed-Forward Neural Networks(MLFNN)based on convolutional neural network(CNN),Random Forest(RF)and Deep learning(DL)algorithm.The Simulations are conducted using super pipelined microarchitecture of advanced micro devices(AMD)XScale PXA270 using instruction and data cache per core 32 Kbyte I-cache and 32 Kbyte D-cache on various utilization factors(u_(i))12%,31%and 50%.The proposed approach consumes 5.3%less energy when almost half of the CPU is running and on a lower workload consumes 1.04%less energy.The proposed design accumulatively gives significant improvements by reducing the energy dissipation on three clock rates by 4.41%,on 624 MHz by 5.4%and 5.9%on applications operating on 416 and 312 MHz standard operating frequencies.展开更多
Mechanical joints can have significant effects on the dynamics of assembled structures.However,the lack of efficacious predictive dynamic models tot joints hinders accurate prediction of their dynamic behavior.The goa...Mechanical joints can have significant effects on the dynamics of assembled structures.However,the lack of efficacious predictive dynamic models tot joints hinders accurate prediction of their dynamic behavior.The goal of our work is to develop physics-based,reduced-order,finite element models that are capable of replicating the effects of joints on vi- brating structures.The authors recently developed the so-called two-dimensional adjusted lwan beam element(2-D AIBE) to simulate the hysteretic behavior of bolted joints in 2-D beam structures.In this paper,2-D AIBE is extended to three-di- mensional cases by formulating a three-dimensional adjusted lwan beam element(3-D AIBE).hupulsive loading experi- ments are applied to a jointed frame structure and a beam structure containing the same joint.The frame is subjected to ex- citation out of plane so that the joint is under rotation and single axis bending.By assuming that the rotation in the joint is linear elastic,the parameters of the joint associated with bending in the flame are identified from acceleration responses of the jointed beam structure,using a multi-layer teed-torward neural network(MLFF).Numerieal simulation is then per- formed on the frame structure using the identified parameters.The good agreement between the simulated and experimental impulsive acceleration responses of the frame structure validates the efficacy of the presented 3-D AIBE,and indicates that the model can potentially be applied to more complex structural systems with joint parameters identified from a relatively simple structure.展开更多
This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is deve...This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is developed based on a data set containing 20000 samples of damage scenarios,obtained via finite element(FE)simulation,of the FG-CNTRC plates.The elemental modal kinetic energy(MKE)values,calculated from natural frequencies and translational nodal displacements of the structures,are utilized as input of the DFNN model while the damage locations and corresponding severities are considered as output.The state-of-the art Exponential Linear Units(ELU)activation function and the Adamax algorithm are employed to train the DFNN model.Additionally,in order to enhance the performance of the DFNN model,the mini-batch and early-stopping techniques are applied to the training process.A trial-and-error procedure is implemented to determine suitable parameters of the network such as the number of hidden layers and the number of neurons in each layer.The accuracy and capability of the proposed DFNN model are illustrated through two distinct configurations of the CNT-fibers constituting the FG-CNTRC plates including uniform distribution(UD)and functionally graded-V distribution(FG-VD).Furthermore,the performance and stability of the DFNN model with the consideration of noise effects on the input data are also investigated.Obtained results indicate that the proposed DFNN model is able to give sufficiently accurate damage detection outcomes for the FG-CNTRC plates for both cases of noise-free and noise-influenced data.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
Controlling and optimizing carbon capture processes is vital for improving efficiency,reducing energy consumption,and enhancing sustainability.Process analytical technology(PAT)plays a crucial role in achieving these ...Controlling and optimizing carbon capture processes is vital for improving efficiency,reducing energy consumption,and enhancing sustainability.Process analytical technology(PAT)plays a crucial role in achieving these goals.Establishing the relationship between physico-chemical properties(PCPs)and solvent characteristics,such as loading and strength,can facilitate the practical implementation of PAT.This study develops empirical models for the PCPs of potassium carbonate solutions,including density,refractive index,and electrical conductivity,as well as a mechanistic model for pH across varying temperatures,solvent concentration,and solvent loadings.The models showed strong agreement with experimental data.Density and refractive index increased with solvent strength and decreased with temperature,while conductivity correlated with solvent strength and temperature but decreased with solvent loading.A feedforward neural network was trained to predict solvent strength and loading using eight input scenarios.The highest accuracy was achieved with PCPs combined with Fourier transform infrared(FTIR)or ultraviolet-visible(UV-Vis),using only PCPs,or using PCPs with FTIR and UV-Vis while excluding pH.The findings provide essential insights into K_(2)CO_(3)solution behavior,contributing to advances in carbon capture technologies.展开更多
This paper aims to propose a framework for manifold regularization(MR) based distributed semi-supervised learning(DSSL) using single layer feed-forward neural network(SLFNN). The proposed framework, denoted as DSSL-SL...This paper aims to propose a framework for manifold regularization(MR) based distributed semi-supervised learning(DSSL) using single layer feed-forward neural network(SLFNN). The proposed framework, denoted as DSSL-SLFNN is based on the SLFNN, MR framework, and distributed optimization strategy. Then, a series of algorithms are derived to solve DSSL problems. In DSSL problems, data consisting of labeled and unlabeled samples are distributed over a communication network, where each node has only access to its own data and can only communicate with its neighbors. In some scenarios, DSSL problems cannot be solved by centralized algorithms. According to the DSSL-SLFNN framework, each node over the communication network exchanges the initial parameters of the SLFNN with the same basis functions for semi-supervised learning(SSL). All nodes calculate the global optimal coefficients of the SLFNN by using distributed datasets and local updates. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that DSSL-SLFNN based algorithms work in a fully distributed fashion and are privacy preserving methods. Finally, several simulations are presented to show the efficiency of the proposed framework and the derived algorithms.展开更多
An intelligent security systems engineering approach is used to analyze fire and explosive critical incidents, a growing concern in urban communities. A feed-forward back-propagation neural network models the damages ...An intelligent security systems engineering approach is used to analyze fire and explosive critical incidents, a growing concern in urban communities. A feed-forward back-propagation neural network models the damages arising from these critical incidents. The overall goal is to promote fire safety and sustainable security. The intelligent security systems engineering prediction model uses a fully connected multilayer neural network, and considers a number of factors related to the fire or explosive incident including the type of property affected, the time of day, and the ignition source. The network was trained on a large number of critical incident records reported in Toronto, Canada between 2000 and 2006. Our intelligent security systems engineering approach can help emergency responders by improving cr^tical incident analysis, sustainable security, and fire risk management.展开更多
Extreme learning machine （ELM） is a learning algorithm for generalized single-hidden-layer feed-forward networks （SLFNs）. In order to obtain a suitable network architecture, Incremental Extreme Learning Machine （...Extreme learning machine （ELM） is a learning algorithm for generalized single-hidden-layer feed-forward networks （SLFNs）. In order to obtain a suitable network architecture, Incremental Extreme Learning Machine （I-ELM） is a sort of ELM constructing SLFNs by adding hidden nodes one by one. Although kinds of I-ELM-class algorithms were proposed to improve the convergence rate or to obtain minimal training error, they do not change the construction way of I-ELM or face the over-fitting risk. Making the testing error converge quickly and stably therefore becomes an important issue. In this paper, we proposed a new incremental ELM which is referred to as Length-Changeable Incremental Extreme Learning Machine （LCI-ELM）. It allows more than one hidden node to be added to the network and the existing network will be regarded as a whole in output weights tuning. The output weights of newly added hidden nodes are determined using a partial error-minimizing method. We prove that an SLFN constructed using LCI-ELM has approximation capability on a universal compact input set as well as on a finite training set. Experimental results demonstrate that LCI-ELM achieves higher convergence rate as well as lower over-fitting risk than some competitive I-ELM-class algorithms.展开更多
The present work aims to develop an object tracking controller for the Stewart platform using a computer vision-assisted machine learning-based approach.This research is divided into two modules.The first module focus...The present work aims to develop an object tracking controller for the Stewart platform using a computer vision-assisted machine learning-based approach.This research is divided into two modules.The first module focuses on the design of a motion controller for the Physik Instrumente(PI)-based Stewart platform.In contrast,the second module deals with the development of a machine-learning-based spatial object tracking algorithm by collecting information from the Zed 2 stereo vision system.Presently,simple feed-forward neural networks(NN)are used to predict the orientation of the top table of the platform.While training,the x,y,and z coordinates of the three-dimensional(3D)object,extracted from images,are used as the input to the NN.In contrast,the orientation information of the platform(that is,rotation about the x,y,and z-axes)is considered as the output from the network.The orientation information obtained from the network is fed to the inverse kinematics-based motion controller(module 1)to move the platform while tracking the object.After training,the optimised NN is used to track the continuously moving 3D object.The experimental results show that the developed NN-based controller has successfully tracked the moving spatial object with reasonably good accuracy.展开更多
文摘This paper describes the application of principal component analysis (PCA) and artificial neural network (ANN) to predict the air pollutant index (API) within the seven selected Malaysian air monitoring stations in the southern region of Peninsular Malaysia based on seven years database (2005-2011). Feed-forward ANN was used as a prediction method. The feed-forward ANN analysis demonstrated that the rotated principal component scores (RPCs) were the best input parameters to predict API. From the 4 RPCs, only 10 (CO, O3, PM10, NO2, CH4, NmHC, THC, wind direction, humidity and ambient temp) out of 12 prediction variables were the most significant parameters to predict API. The results proved that the ANN method can be applied successfully as tools for decision making and problem solving for better atmospheric management.
文摘In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other factors. In order to ensure high equipment performance and avoid high-cost losses, it is essential to identify the source of possible failures in the early stage. However, this requires additional maintenance fees and human power. Moreover, the losses caused by these problems may lead to interruptions in the whole production process. In order to minimize maintenance costs, in this paper, we introduce a model for predicting equipment failure based on processing the historical data collected from multiple sensors. The state of the system is predicted by a Feed-Forward Neural Network (FFNN) with an SGD and Backpropagation algorithm is applied in the training process. Our model’s primary goal is to identify potential malfunctions at an early stage to ensure the production process’ continued high performance. We also evaluated the effectiveness of our model against other solutions currently available in the industry. The results of our study show that the FFNN can attain an accuracy score of 97% on the given dataset, which exceeds the performance of the models provided.
文摘In recent years,the development in the field of computer-aided diagnosis(CAD)has increased rapidly.Many traditional machine learning algorithms have been proposed for identifying the pathological brain using magnetic resonance images.The existing algorithms have drawbacks with respect to their accuracy,efficiency,and limited learning processes.To address these issues,we propose a pathological brain tumour detection method that utilizes the Weiner filter to improve the image contrast,2D-discrete wavelet transformation(2D-DWT)to extract the features,probabilistic principal component analysis(PPCA)and linear discriminant analysis(LDA)to normalize and reduce the features,and a feed-forward neural network(FNN)and modified particle swarm optimization(MPSO)with ant colony optimization(ACO)to improve the accuracy,stability,and overcome fitting issues in the classification of brain magnetic resonance images.The proposed method achieves better results than other existing algorithms.
文摘This paper offer an artificial neural network (ANN) model to calculate drag force on an axisymmetric underwater vehicle by obtaining dataset from a computational fluid dynamic analysis. First, great effort was done to calculate the pressure and viscous data forces by increasing the precision and numerical data in order to extend and raise quality of dataset. In this step, numerous different geometry models (configurations of axisymmetric body) were designed, examined and evaluated input parameters including: diameter of body, diameter of nose disc, length of body, length of nose and velocity whereas outputs contain pressure and viscous forces. This dataset was used to train the ANN model. Feed-forward neural network (FFNN) is selected which is more common and suitable in this field’s study. A three-layer neural network was opted and after training this network, the results showed good agreement with CFD data. This study shows that applying the ANN model helps to reach final purpose in the least time and error, in addition a variety of tests can be performed to have a desired design in this way.
基金supported by the National Natural Science Foundation of China(No.62203473)the Project of State Key Laboratory of Precision Manufacturing for Extreme Service Performance,Central South University(No.ZZYJKT2023-15)the Hunan Provincial Natural Science Foundation(No.2023JJ40778).
文摘We propose a dual feed-forward neural network(DFNN)model,consisting of a cavity parameter feature expander(CPFE)and a dynamic process predictor(DPP),for predicting the complex nonlinear dynamics of mode-locked fiber lasers.The output of the CPFE,following layer normalization,is combined with the pulse complex electric field amplitude and then fed into the DPP to predict the dynamics.The pulse evolution process from the detuned steady state to the steady state under different cavity configurations is rapidly calculated.The predicted results of the proposed DFNN are consistent with the numerical split-step Fourier method(SSFM).The simulation speed has been greatly improved with low computational complexity,which is approximately 152 times faster than the SSFM and 4 times faster than the long short-term memory recurrent neural network(LSTM)model.The findings provide a new low computational complexity and efficient machine learning approach to model the complex nonlinear dynamics of mode-locked lasers.
文摘The migration of tasks aided by machine learning(ML)predictions IN(DPM)is a system-level design technique that is used to reduce energy by enhancing the overall performance of the processor.In this paper,we address the issue of system-level higher task dissipation during the execution of parallel workloads with common deadlines by introducing a machine learning-based framework that includes task migration using energy-efficient earliest deadline first scheduling(EA-EDF).ML-based EA-EDF enhances the overall throughput and optimizes the energy to avoid delay and performance degradation in a multiprocessor system.The proposed system model allocates processors to the ready task set in such a way that their deadlines are guaranteed.A full task migration policy is also integrated to ensure proper task mapping that ensures inter-process linkage among the arrived tasks with the same deadlines.The execution of a task can halt on one CPU and reschedule the execution on a different processor to avoid delay and ensure meeting the deadline.Our approach shows promising potential for machine-learning-based schedulability analysis enables a comparison between different ML models and shows a promising reduction in energy as compared with other ML-aware task migration techniques for SoC like Multi-Layer Feed-Forward Neural Networks(MLFNN)based on convolutional neural network(CNN),Random Forest(RF)and Deep learning(DL)algorithm.The Simulations are conducted using super pipelined microarchitecture of advanced micro devices(AMD)XScale PXA270 using instruction and data cache per core 32 Kbyte I-cache and 32 Kbyte D-cache on various utilization factors(u_(i))12%,31%and 50%.The proposed approach consumes 5.3%less energy when almost half of the CPU is running and on a lower workload consumes 1.04%less energy.The proposed design accumulatively gives significant improvements by reducing the energy dissipation on three clock rates by 4.41%,on 624 MHz by 5.4%and 5.9%on applications operating on 416 and 312 MHz standard operating frequencies.
文摘Mechanical joints can have significant effects on the dynamics of assembled structures.However,the lack of efficacious predictive dynamic models tot joints hinders accurate prediction of their dynamic behavior.The goal of our work is to develop physics-based,reduced-order,finite element models that are capable of replicating the effects of joints on vi- brating structures.The authors recently developed the so-called two-dimensional adjusted lwan beam element(2-D AIBE) to simulate the hysteretic behavior of bolted joints in 2-D beam structures.In this paper,2-D AIBE is extended to three-di- mensional cases by formulating a three-dimensional adjusted lwan beam element(3-D AIBE).hupulsive loading experi- ments are applied to a jointed frame structure and a beam structure containing the same joint.The frame is subjected to ex- citation out of plane so that the joint is under rotation and single axis bending.By assuming that the rotation in the joint is linear elastic,the parameters of the joint associated with bending in the flame are identified from acceleration responses of the jointed beam structure,using a multi-layer teed-torward neural network(MLFF).Numerieal simulation is then per- formed on the frame structure using the identified parameters.The good agreement between the simulated and experimental impulsive acceleration responses of the frame structure validates the efficacy of the presented 3-D AIBE,and indicates that the model can potentially be applied to more complex structural systems with joint parameters identified from a relatively simple structure.
基金This research was funded by Vietnam National Foundation for Science and Technology Development(NAFOSTED)under No.107.02-2019.330.
文摘This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is developed based on a data set containing 20000 samples of damage scenarios,obtained via finite element(FE)simulation,of the FG-CNTRC plates.The elemental modal kinetic energy(MKE)values,calculated from natural frequencies and translational nodal displacements of the structures,are utilized as input of the DFNN model while the damage locations and corresponding severities are considered as output.The state-of-the art Exponential Linear Units(ELU)activation function and the Adamax algorithm are employed to train the DFNN model.Additionally,in order to enhance the performance of the DFNN model,the mini-batch and early-stopping techniques are applied to the training process.A trial-and-error procedure is implemented to determine suitable parameters of the network such as the number of hidden layers and the number of neurons in each layer.The accuracy and capability of the proposed DFNN model are illustrated through two distinct configurations of the CNT-fibers constituting the FG-CNTRC plates including uniform distribution(UD)and functionally graded-V distribution(FG-VD).Furthermore,the performance and stability of the DFNN model with the consideration of noise effects on the input data are also investigated.Obtained results indicate that the proposed DFNN model is able to give sufficiently accurate damage detection outcomes for the FG-CNTRC plates for both cases of noise-free and noise-influenced data.
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.
基金support from the Swedish Energy Agency(Project number P2021-00008)is gratefully acknowledged.
文摘Controlling and optimizing carbon capture processes is vital for improving efficiency,reducing energy consumption,and enhancing sustainability.Process analytical technology(PAT)plays a crucial role in achieving these goals.Establishing the relationship between physico-chemical properties(PCPs)and solvent characteristics,such as loading and strength,can facilitate the practical implementation of PAT.This study develops empirical models for the PCPs of potassium carbonate solutions,including density,refractive index,and electrical conductivity,as well as a mechanistic model for pH across varying temperatures,solvent concentration,and solvent loadings.The models showed strong agreement with experimental data.Density and refractive index increased with solvent strength and decreased with temperature,while conductivity correlated with solvent strength and temperature but decreased with solvent loading.A feedforward neural network was trained to predict solvent strength and loading using eight input scenarios.The highest accuracy was achieved with PCPs combined with Fourier transform infrared(FTIR)or ultraviolet-visible(UV-Vis),using only PCPs,or using PCPs with FTIR and UV-Vis while excluding pH.The findings provide essential insights into K_(2)CO_(3)solution behavior,contributing to advances in carbon capture technologies.
基金supported by National Natural Science Foundation of China (Nos. 61877047, 61877046, 62106186 and 62063031)the Fundamental Research Funds for the Central Universities (Nos. JB210701 and JB210718)。
文摘This paper aims to propose a framework for manifold regularization(MR) based distributed semi-supervised learning(DSSL) using single layer feed-forward neural network(SLFNN). The proposed framework, denoted as DSSL-SLFNN is based on the SLFNN, MR framework, and distributed optimization strategy. Then, a series of algorithms are derived to solve DSSL problems. In DSSL problems, data consisting of labeled and unlabeled samples are distributed over a communication network, where each node has only access to its own data and can only communicate with its neighbors. In some scenarios, DSSL problems cannot be solved by centralized algorithms. According to the DSSL-SLFNN framework, each node over the communication network exchanges the initial parameters of the SLFNN with the same basis functions for semi-supervised learning(SSL). All nodes calculate the global optimal coefficients of the SLFNN by using distributed datasets and local updates. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that DSSL-SLFNN based algorithms work in a fully distributed fashion and are privacy preserving methods. Finally, several simulations are presented to show the efficiency of the proposed framework and the derived algorithms.
文摘An intelligent security systems engineering approach is used to analyze fire and explosive critical incidents, a growing concern in urban communities. A feed-forward back-propagation neural network models the damages arising from these critical incidents. The overall goal is to promote fire safety and sustainable security. The intelligent security systems engineering prediction model uses a fully connected multilayer neural network, and considers a number of factors related to the fire or explosive incident including the type of property affected, the time of day, and the ignition source. The network was trained on a large number of critical incident records reported in Toronto, Canada between 2000 and 2006. Our intelligent security systems engineering approach can help emergency responders by improving cr^tical incident analysis, sustainable security, and fire risk management.
基金This work was partially supported by the National Natural Science Foundation of China under Grant Nos. 61673159 and 61370144, and the Natural Science Foundation of Hebei Province of China under Grant No. F2016202145.
文摘Extreme learning machine （ELM） is a learning algorithm for generalized single-hidden-layer feed-forward networks （SLFNs）. In order to obtain a suitable network architecture, Incremental Extreme Learning Machine （I-ELM） is a sort of ELM constructing SLFNs by adding hidden nodes one by one. Although kinds of I-ELM-class algorithms were proposed to improve the convergence rate or to obtain minimal training error, they do not change the construction way of I-ELM or face the over-fitting risk. Making the testing error converge quickly and stably therefore becomes an important issue. In this paper, we proposed a new incremental ELM which is referred to as Length-Changeable Incremental Extreme Learning Machine （LCI-ELM）. It allows more than one hidden node to be added to the network and the existing network will be regarded as a whole in output weights tuning. The output weights of newly added hidden nodes are determined using a partial error-minimizing method. We prove that an SLFN constructed using LCI-ELM has approximation capability on a universal compact input set as well as on a finite training set. Experimental results demonstrate that LCI-ELM achieves higher convergence rate as well as lower over-fitting risk than some competitive I-ELM-class algorithms.
文摘The present work aims to develop an object tracking controller for the Stewart platform using a computer vision-assisted machine learning-based approach.This research is divided into two modules.The first module focuses on the design of a motion controller for the Physik Instrumente(PI)-based Stewart platform.In contrast,the second module deals with the development of a machine-learning-based spatial object tracking algorithm by collecting information from the Zed 2 stereo vision system.Presently,simple feed-forward neural networks(NN)are used to predict the orientation of the top table of the platform.While training,the x,y,and z coordinates of the three-dimensional(3D)object,extracted from images,are used as the input to the NN.In contrast,the orientation information of the platform(that is,rotation about the x,y,and z-axes)is considered as the output from the network.The orientation information obtained from the network is fed to the inverse kinematics-based motion controller(module 1)to move the platform while tracking the object.After training,the optimised NN is used to track the continuously moving 3D object.The experimental results show that the developed NN-based controller has successfully tracked the moving spatial object with reasonably good accuracy.
