GPU-accelerated and parallelized ELM ensembles for large-scale regression

The paper presents an approach for performing regression on large data sets in reasonable time, using an ensemble of extreme learning machines (ELMs). The main purpose and contribution of this paper are to explore how the evaluation of this ensemble of ELMs can be accelerated in three distinct ways: (1) training and model structure selection of the individual ELMs are accelerated by performing these steps on the graphics processing unit (GPU), instead of the processor (CPU); (2) the training of ELM is performed in such a way that computed results can be reused in the model structure selection, making training plus model structure selection more efficient; (3) the modularity of the ensemble model is exploited and the process of model training and model structure selection is parallelized across multiple GPU and CPU cores, such that multiple models can be built at the same time. The experiments show that competitive performance is obtained on the regression tasks, and that the GPU-accelerated and parallelized ELM ensemble achieves attractive speedups over using a single CPU. Furthermore, the proposed approach is not limited to a specific type of ELM and can be employed for a large variety of ELMs.     

TROP-ELM: A double-regularized ELM using LARS and Tikhonov regularization

In this paper an improvement of the optimally pruned extreme learning machine (OP-ELM) in the form of a L₂ regularization penalty applied within the OP-ELM is proposed. The OP-ELM originally proposes a wrapper methodology around the extreme learning machine (ELM) meant to reduce the sensitivity of the ELM to irrelevant variables and obtain more parsimonious models thanks to neuron pruning. The proposed modification of the OP-ELM uses a cascade of two regularization penalties: first a L₁ penalty to rank the neurons of the hidden layer, followed by a L₂ penalty on the regression weights (regression between hidden layer and output layer) for numerical stability and efficient pruning of the neurons. The new methodology is tested against state of the art methods such as support vector machines or Gaussian processes and the original ELM and OP-ELM, on 11 different data sets; it systematically outperforms the OP-ELM (average of 27% better mean square error) and provides more reliable results - in terms of standard deviation of the results - while remaining always less than one order of magnitude slower than the OP-ELM.     

Automatic recognition of epileptic EEG patterns via Extreme Learning Machine and multiresolution feature extraction

Epilepsy is one of the most common neurological disorders- approximately one in every 100 people worldwide are suffering from it. In this paper, a novel pattern recognition model is presented for automatic epilepsy diagnosis. Wavelet transform is investigated to decompose EEG into five EEG frequency bands which approximate to delta (δ), theta (θ), alpha (α), beta (β), and gamma (γ) bands. Complexity based features such as permutation entropy (PE), sample entropy (SampEn), and the Hurst exponent (HE) are extracted from both the original EEG signals and each of the frequency bands. The wavelet-based methodology separates the alterations in PE, SampEn, and HE in specific frequency bands of the EEG. The effectiveness of these complexity based measures in discriminating between normal brain state and brain state during the absence of seizures is evaluated using the Extreme Learning Machine (ELM). It is discovered that although there exists no significant differences in the feature values extracted from the original EEG signals, differences can be recognized when the features are examined within specific EEG frequency bands. A genetic algorithm (GA) is developed to choose feature subsets that are effective for enhancing the recognition performance. The GA is also examined for weight alteration for both sensitivity and specificity. The results show that the abnormal EEG diagnosis rate of the model without the involvement of the genetic algorithm is 85.9%. However, the diagnosis rate of the model increases to 94.2% when the genetic algorithm is integrated as a feature selector.     

The observation of small ELM post-cursor mode in EAST

A ‘post-cursor' quasi-coherent mode with frequency ～50 k Hz has been observed following the crash of small edge localized modes(ELMs) in the Experimental Advanced Superconducting Tokamak by using a reciprocating Langmuir probe system inserted at the outboard midplane.This mode with strong potential and magnetic perturbations propagates in the electrondiamagnetic drift direction in the laboratory frame.In addition,these quasi-coherent fluctuations appear to be modulated by a MHD mode with lower frequency(～5 k Hz).The bi-coherence analysis shows that the post-cursor mode and the MHD mode have nonlinear interaction through three-wave coupling.The understanding on post-cursor mode can enhance our knowledge of ELMs and pedestal physics,and give new insight into the ELM process itself.     

Rapid Thermal-Hydraulic Analysis and Design Optimization of ITER Upper ELM Coils

ITER edge localized mode （ELM） coils are important components of the in-vessel coils （IVCs） and they are designed for mitigating or suppressing ELMs. The coils located on the vacuum vessel （VV） and behind the blanket are subjected to high temperature due to the nuclear heat from the plasma, the Ohmic heat induced by the working current and the thermal radiation from the environment. The water serves as coolant to remove the heat deposited into the coils. Based on the results of nuclear analysis, the thermal-hydraulic analysis is performed for the preliminary design of upper ELM coils using a rapid evaluation method based on 1D treatment. The thermal-hydraulic design and operating parameters including the water flow velocity are optimized. It is found that the rapid evaluation method based on 1D treatment is feasible and reliable. According to the rapid analysis method, the thermal hydraulic parameters of two water flow schemes are computed and proved similar to each other, providing an effective basis for the coil design. Finally, considering jointly the pressure drop requirement and the cooling capacity, the flow velocity is optimized to 5 m/s.     

基于深度极限学习机的危险源识别算法HIELM

危险源识别是民用航空管理的重要环节之一,危险源识别结果必须高度准确才能确保飞行的安全。为此,提出了一种基于深度极限学习机的危险源识别算法HIELM(Hazard Identification Algorithm Based on Extreme Lear-ning Machine),设计了一种由多个深层栈式极限学习机(S-ELM)和一个单隐藏层极限学习机(ELM)构成的深层网络结构。算法中,多个深层S-ELM使用平行结构,各自可以拥有不同的隐藏结点个数,按照危险源领域分类接受危险源状态信息完成预学习,并结合识别特征改进网络输入权重的产生方式。在单隐藏层ELM中,深层ELM的预学习结果作为其输入,改进了反向传播算法,提高了网络识别的精确度。同时,分别训练各深层S-ELM,缓解了高维数据训练的内存压力和节点过多产生的过拟合现象。     

用于航空发动机动态辨识的MSMEA-ELM算法

针对传统思维进化算法搜索半径缺乏目的性,临时子群体补充缺乏方向性以及神经网络训练速度慢、泛化能力不足,传统极端学习机隐含层神经元个数多的缺点,提出一种多群体自适应思维进化算法优化的极端学习机(MSMEA-ELM)算法,通过传感器数据训练该算法用于对航空发动机大范围动态过程进行辨识.以训练均方误差与权值2范数的加权和最小为优化目标,采用多群体自适应思维进化算法优化极端学习机.以某型涡扇发动机为研究对象,采用MSMEA-ELM算法进行航空发动机动态过程辨识,验证了该算法的有效性.     

基于模拟退火算法的改进极限学习机

传统的极限学习机作为一种有监督的学习模型,任意对隐藏层神经元的输入权值和偏置进行赋值,通过计算隐藏层神经元的输出权值完成学习过程.针对传统的极限学习机在数据分析预测研究中存在预测精度不足的问题,提出一种基于模拟退火算法改进的极限学习机.首先,利用传统的极限学习机对训练集进行学习,得到隐藏层神经元的输出权值,选取预测结果评价标准.然后利用模拟退火算法,将传统的极限学习机隐藏层输入权值和偏置视为初始解,预测结果评价标准视为目标函数,通过模拟退火的降温过程,找到最优解即学习过程中预测误差最小的极限学习机的隐藏层神经元输入权值和偏置,最后通过传统的极限学习机计算得到隐藏层输出权值.实验选取鸢尾花分类数据和波士顿房价预测数据进行分析.实验发现与传统的极限学习机相比,基于模拟退火改进的极限学习机在分类和回归性能上都更优.     

极限学习机的分类器集成模型研究

将极限学习机算法与旋转森林算法相结合,提出了以ELM算法为基分类器并以旋转森林算法为框架的RF-ELM集成学习模型。在8个数据集上进行了3组预测实验,根据实验结果讨论了ELM算法中隐含层神经元个数对预测结果的影响以及单个ELM模型预测结果不稳定的缺陷;将RF-ELM模型与单ELM模型和基于Bagging算法集成的ELM模型相比较,由稳定性和预测精度的两组对比实验的实验结果表明,对ELM的集成学习可以有效地提高ELM模型的性能,且RF-ELM模型较其他两个模型具有更好的稳定性和更高的准确率,验证了RF-ELM是一种有效的ELM集成学习模型。     

极限学习机在机场旅客吞吐量预测中的应用

极限学习机(ELM)是一种新型单馈层神经网络算法,在训练过程中只需要设置合适的隐藏层节点个数,随机赋值输入权值和隐藏层偏差,一次完成无需迭代.结合遗传算法在预测模型参数寻优方面的优势,找到极限学习机的最优参数取值,建立成都双流国际机场旅客吞吐量预测模型,通过对比支持向量机、BP神经网络,分析遗传-极限学习机算法在旅客吞吐量预测中的可行性和优势.仿真结果表明遗传-极限学习机算法不仅可行,并且与原始极限学习机算法相比,在预测精度和训练速度上具有比较明显的优势.