In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations a...In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.展开更多
The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a c...The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.展开更多
Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking p...Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking production. However, these MIQ parameters are difficult to be directly measured online, and large-time delay exists in off-line analysis through laboratory sampling. Focusing on the practical challenge, a data-driven modeling method was presented for the prediction of MIQ using the improved muhivariable incremental random vector functional-link net- works （M-I-RVFLNs）. Compared with the conventional random vector functional-link networks （RVFLNs） and the online sequential RVFLNs, the M-I-RVFLNs have solved the problem of deciding the optimal number of hidden nodes and overcome the overfitting problems. Moreover, the proposed M I RVFLNs model has exhibited the potential for multivariable prediction of the MIQ and improved the terminal condition for the multiple-input multiple-out- put （MIMO） dynamic system, which is suitable for the BF ironmaking process in practice. Ultimately, industrial experiments and contrastive researches have been conducted on the BF No. 2 in Liuzhou Iron and Steel Group Co. Ltd. of China using the proposed method, and the results demonstrate that the established model produces better estima ting accuracy than other MIQ modeling methods.展开更多
Forecasting wind speed is an extremely complicated and challenging problem due to its chaotic nature and its dependence on several atmospheric conditions.Although there are several intelligent techniques in the litera...Forecasting wind speed is an extremely complicated and challenging problem due to its chaotic nature and its dependence on several atmospheric conditions.Although there are several intelligent techniques in the literature for wind speed prediction,their accuracies are not yet very reliable.Therefore,in this paper,a new hybrid intelligent technique named the deep mixed kernel random vector functional-link network auto-encoder(AE)is proposed for wind speed prediction.The proposed method eliminates manual tuning of hidden nodes with random weights and biases,providing prediction model generalization and representation learning.This reduces reconstruction error due to the exact inversion of the kernel matrix,unlike the pseudo-inverse in a random vector functional-link network,and short-ens the execution time.Furthermore,the presence of a direct link from the input to the output reduces the complexity of the prediction model and improves the prediction accuracy.The kernel parameters and coefficients of the mixed kernel system are optimized using a new chaotic sine–cosine Levy flight optimization technique.The lowest errors in terms of mean absolute error(0.4139),mean absolute percentage error(4.0081),root mean square error(0.4843),standard deviation error(1.1431)and index of agreement(0.9733)prove the efficiency of the proposed model in comparison with other deep learning models such as deep AEs,deep kernel extreme learning ma-chine AEs,deep kernel random vector functional-link network AEs,benchmark models such as least square support vector machine,autoregressive integrated moving average,extreme learning machines and their hybrid models along with different state-of-the-art methods.展开更多
Electroencephalography(EEG),helps to analyze the neuronal activity of a human brain in the form of electrical signals with high temporal resolution in the millisecond range.To extract clean clinical information from E...Electroencephalography(EEG),helps to analyze the neuronal activity of a human brain in the form of electrical signals with high temporal resolution in the millisecond range.To extract clean clinical information from EEG signals,it is essential to remove unwanted artifacts that are due to different causes including at the time of acquisition.In this piece of work,the authors considered the EEG signal contaminated with Electrocardiogram(ECG)artifacts that occurs mostly in cardiac patients.The clean EEG is taken from the openly available Mendeley database whereas the ECG signal is collected from the Physionet database to create artifacts in the EEG signal and verify the proposed algorithm.Being the artifactual signal is non-linear and non-stationary the Random Vector Functional Link Network(RVFLN)model is used in this case.The Machine Learning approach has taken a leading role in every field of current research and RVFLN is one of them.For the proof of adaptive nature,the model is designed with EEG as a reference and artifactual EEG as input.The peaks of ECG signals are evaluated for artifact estimation as the amplitude is higher than the EEG signal.To vary the weight and reduce the error,an exponentially weighted Recursive Least Square(RLS)algorithm is used to design the adaptive filter with the novel RVFLN model.The random vectors are considered in this model with a radial basis function to satisfy the required signal experimentation.It is found that the result is excellent in terms of Mean Square Error(MSE),Normalized Mean Square Error(NMSE),Relative Error(RE),Gain in Signal to Artifact Ratio(GSAR),Signal Noise Ratio(SNR),Information Quantity(IQ),and Improvement in Normalized Power Spectrum(INPS).Also,the proposed method is compared with the earlier methods to show its efficacy.展开更多
针对传统随机向量函数链接网络集成模型时多样性不足和泛化性能差的问题,提出一种改进的随机向量函数链接集成模型.首先,通过6种简单回归模型替代传统随机向量函数链接网络中的直接链接;其次,采用高斯过程回归(Gaussian process regress...针对传统随机向量函数链接网络集成模型时多样性不足和泛化性能差的问题,提出一种改进的随机向量函数链接集成模型.首先,通过6种简单回归模型替代传统随机向量函数链接网络中的直接链接;其次,采用高斯过程回归(Gaussian process regression,GPR)方法初始化隐含层参数,增强各基分类器的多样性;最后,使用不同的结合策略,集成具有差异性的基分类器得到预测模型.结果表明,改进的随机向量函数链接集成模型的预测精度明显高于其他传统集成模型,较传统随机向量函数链接网络具有更好的泛化性能.展开更多
提出一种用最小二乘支持向量机(least squares support vector machine,LS-SVM)构造函数链接型神经网络(functional link artificial neural networks,FLANN)的滚动轴承故障诊断系统。介绍了相关原理和具体算法,并给出了滚动轴承故障诊...提出一种用最小二乘支持向量机(least squares support vector machine,LS-SVM)构造函数链接型神经网络(functional link artificial neural networks,FLANN)的滚动轴承故障诊断系统。介绍了相关原理和具体算法,并给出了滚动轴承故障诊断系统模型。首先,采用LS-SVM模型核函数代替常规FLANN模型的扩展函数,避免了扩展函数选择的任意性;其次,利用LS-SVM学习模型得到FLANN权重系数,避免了BP方法多次迭代寻优存在的耗时长、局部极小及迭代设置初值依赖经验等不足;最后,构造了多层LS-SVM-FLANN结构,对多类滚动轴承故障进行诊断。具体实验表明,用LS-SVM构造FLANN的滚动轴承故障识别系统精度高、鲁棒性好、实现简单。展开更多
文摘In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.
基金support of the National Key R&D Program of China(No.2022YFC2803903)the Key R&D Program of Zhejiang Province(No.2021C03013)the Zhejiang Provincial Natural Science Foundation of China(No.LZ20F020003).
文摘The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.
基金Item Sponsored by National Natural Science Foundation of China(61290323,61333007,61473064)Fundamental Research Funds for Central Universities of China(N130108001)+1 种基金National High Technology Research and Development Program of China(2015AA043802)General Project on Scientific Research for Education Department of Liaoning Province of China(L20150186)
文摘Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality （MIQ） indices in the blast furnace （BF） ironmaking, which requires strict monitoring during the whole ironmaking production. However, these MIQ parameters are difficult to be directly measured online, and large-time delay exists in off-line analysis through laboratory sampling. Focusing on the practical challenge, a data-driven modeling method was presented for the prediction of MIQ using the improved muhivariable incremental random vector functional-link net- works （M-I-RVFLNs）. Compared with the conventional random vector functional-link networks （RVFLNs） and the online sequential RVFLNs, the M-I-RVFLNs have solved the problem of deciding the optimal number of hidden nodes and overcome the overfitting problems. Moreover, the proposed M I RVFLNs model has exhibited the potential for multivariable prediction of the MIQ and improved the terminal condition for the multiple-input multiple-out- put （MIMO） dynamic system, which is suitable for the BF ironmaking process in practice. Ultimately, industrial experiments and contrastive researches have been conducted on the BF No. 2 in Liuzhou Iron and Steel Group Co. Ltd. of China using the proposed method, and the results demonstrate that the established model produces better estima ting accuracy than other MIQ modeling methods.
文摘Forecasting wind speed is an extremely complicated and challenging problem due to its chaotic nature and its dependence on several atmospheric conditions.Although there are several intelligent techniques in the literature for wind speed prediction,their accuracies are not yet very reliable.Therefore,in this paper,a new hybrid intelligent technique named the deep mixed kernel random vector functional-link network auto-encoder(AE)is proposed for wind speed prediction.The proposed method eliminates manual tuning of hidden nodes with random weights and biases,providing prediction model generalization and representation learning.This reduces reconstruction error due to the exact inversion of the kernel matrix,unlike the pseudo-inverse in a random vector functional-link network,and short-ens the execution time.Furthermore,the presence of a direct link from the input to the output reduces the complexity of the prediction model and improves the prediction accuracy.The kernel parameters and coefficients of the mixed kernel system are optimized using a new chaotic sine–cosine Levy flight optimization technique.The lowest errors in terms of mean absolute error(0.4139),mean absolute percentage error(4.0081),root mean square error(0.4843),standard deviation error(1.1431)and index of agreement(0.9733)prove the efficiency of the proposed model in comparison with other deep learning models such as deep AEs,deep kernel extreme learning ma-chine AEs,deep kernel random vector functional-link network AEs,benchmark models such as least square support vector machine,autoregressive integrated moving average,extreme learning machines and their hybrid models along with different state-of-the-art methods.
文摘Electroencephalography(EEG),helps to analyze the neuronal activity of a human brain in the form of electrical signals with high temporal resolution in the millisecond range.To extract clean clinical information from EEG signals,it is essential to remove unwanted artifacts that are due to different causes including at the time of acquisition.In this piece of work,the authors considered the EEG signal contaminated with Electrocardiogram(ECG)artifacts that occurs mostly in cardiac patients.The clean EEG is taken from the openly available Mendeley database whereas the ECG signal is collected from the Physionet database to create artifacts in the EEG signal and verify the proposed algorithm.Being the artifactual signal is non-linear and non-stationary the Random Vector Functional Link Network(RVFLN)model is used in this case.The Machine Learning approach has taken a leading role in every field of current research and RVFLN is one of them.For the proof of adaptive nature,the model is designed with EEG as a reference and artifactual EEG as input.The peaks of ECG signals are evaluated for artifact estimation as the amplitude is higher than the EEG signal.To vary the weight and reduce the error,an exponentially weighted Recursive Least Square(RLS)algorithm is used to design the adaptive filter with the novel RVFLN model.The random vectors are considered in this model with a radial basis function to satisfy the required signal experimentation.It is found that the result is excellent in terms of Mean Square Error(MSE),Normalized Mean Square Error(NMSE),Relative Error(RE),Gain in Signal to Artifact Ratio(GSAR),Signal Noise Ratio(SNR),Information Quantity(IQ),and Improvement in Normalized Power Spectrum(INPS).Also,the proposed method is compared with the earlier methods to show its efficacy.
文摘针对传统随机向量函数链接网络集成模型时多样性不足和泛化性能差的问题,提出一种改进的随机向量函数链接集成模型.首先,通过6种简单回归模型替代传统随机向量函数链接网络中的直接链接;其次,采用高斯过程回归(Gaussian process regression,GPR)方法初始化隐含层参数,增强各基分类器的多样性;最后,使用不同的结合策略,集成具有差异性的基分类器得到预测模型.结果表明,改进的随机向量函数链接集成模型的预测精度明显高于其他传统集成模型,较传统随机向量函数链接网络具有更好的泛化性能.
文摘提出一种用最小二乘支持向量机(least squares support vector machine,LS-SVM)构造函数链接型神经网络(functional link artificial neural networks,FLANN)的滚动轴承故障诊断系统。介绍了相关原理和具体算法,并给出了滚动轴承故障诊断系统模型。首先,采用LS-SVM模型核函数代替常规FLANN模型的扩展函数,避免了扩展函数选择的任意性;其次,利用LS-SVM学习模型得到FLANN权重系数,避免了BP方法多次迭代寻优存在的耗时长、局部极小及迭代设置初值依赖经验等不足;最后,构造了多层LS-SVM-FLANN结构,对多类滚动轴承故障进行诊断。具体实验表明,用LS-SVM构造FLANN的滚动轴承故障识别系统精度高、鲁棒性好、实现简单。
