Predicting the blast-induced vibration velocity using a bagged support vector regression optimized with firefly algorithm

Ground vibration is the most detrimental effect induced by blasting in surface mines. This study presents an improved bagged support vector regression (BSVR) combined with the firefly algorithm (FA) to predict ground vibration. In other words, the FA was used to modify the weights of the SVR model. To verify the validity of the BSVR–FA, the back-propagation neural network (BPNN) and radial basis function network (RBFN) were also applied. The BSVR–FA, BPNN and RBFN models were constructed using a comprehensive database collected from Shur River dam region, in Iran. The proposed models were then evaluated by means of several statistical indicators such as root mean square error (RMSE) and symmetric mean absolute percentage error. Comparing the results, the BSVR–FA model was found to be the most accurate to predict ground vibration in comparison to the BPNN and RBFN models. This study indicates the successful application of the BSVR–FA model as a suitable and effective tool for the prediction of ground vibration.

     

A two-stage adaptive multi-fidelity surrogate model-assisted multi-objective genetic algorithm for computationally expensive problems

Surrogate model-assisted multi-objective genetic algorithms (MOGA) show great potential in solving engineering design problems since they can save computational cost by reducing the calls of expensive simulations. In this paper, a two-stage adaptive multi-fidelity surrogate (MFS) model-assisted MOGA (AMFS-MOGA) is developed to further relieve their computational burden. In the warm-up stage, a preliminary Pareto frontier is obtained relying only on the data from the low-fidelity (LF) model. In the second stage, an initial MFS model is constructed based on the data from both LF and high-fidelity (HF) models at the samples, which are selected from the preliminary Pareto set according to the crowding distance in the objective space. Then the fitness values of individuals are evaluated using the MFS model, which is adaptively updated according to two developed strategies, an individual-based updating strategy and a generation-based updating strategy. The former considers the prediction uncertainty from the MFS model, while the latter takes the discrete degree of the population into consideration. The effectiveness and merits of the proposed AMFS-MOGA approach are illustrated using three benchmark tests and the design optimization of a stiffened cylindrical shell. The comparisons between the proposed AMFS-MOGA approach and some existing approaches considering the quality of the obtained Pareto frontiers and computational efficiency are made. The results show that the proposed AMFS-MOGA method can obtain Pareto frontiers comparable to that obtained by the MOGA with HF model, while significantly reducing the number of evaluations of the expensive HF model.

     

The parameterized level set method for structural topology optimization with shape sensitivity constraint factor

In recent years, the parameterized level set method (PLSM) has attracted widespread attention for its good stability, high efficiency and the smooth result of topology optimization compared with the conventional level set method. In the PLSM, the radial basis functions (RBFs) are often used to perform interpolation fitting for the conventional level set equation, thereby transforming the iteratively updating partial differential equation (PDE) into ordinary differential equations (ODEs). Hence, the RBFs play a key role in improving efficiency, accuracy and stability of the numerical computation in the PLSM for structural topology optimization, which can describe the structural topology and its change in the optimization process. In particular, the compactly supported radial basis function (CS-RBF) has been widely used in the PLSM for structural topology optimization because it enjoys considerable advantages. In this work, based on the CS-RBF, we propose a PLSM for structural topology optimization by adding the shape sensitivity constraint factor to control the step length in the iterations while updating the design variables with the method of moving asymptote (MMA). With the shape sensitivity constraint factor, the updating step length is changeable and controllable in the iterative process of MMA algorithm so as to increase the optimization speed. Therefore, the efficiency and stability of structural topology optimization can be improved by this method. The feasibility and effectiveness of this method are demonstrated by several typical numerical examples involving topology optimization of single-material and multi-material structures.

     

IPv6网络中基于MF-DL的DDoS攻击快速防御机制

当前,分布式拒绝服务(Distributed Denial of Service,DDoS)攻击是互联网面临的十分严峻的安全威胁之一.IPv6网络考虑了IPv4网络中的诸多安全问题,但它对DDoS攻击仍未能起到很好的防护作用.针对IPv6网络中DDoS攻击的防御问题,本文设计了一种基于MF-DL(Membership Function and Deep Learning)的DDoS快速防御机制.该防御机制以MF-DL检测机制为核心,辅以响应机制等实现对DDoS攻击的防御功能.在检测机制中,首先使用基于隶属度函数的预检测方法,实现对网络流量数据的轻量级异常检测;接着通过基于深度学习方法中神经网络模型的深度检测,实现在异常发生后对流量进行高精度分类.在响应机制中,利用Anti-Fre响应算法实现对请求访问的IP地址进行信誉等级划分,进而实现流量定向阻断并恢复系统性能.最后,分别基于经典入侵检测数据集和校园网的模拟攻击数据集对本文提出的防御机制进行了实验.结果显示,本文提出的防御机制相比于三种对比算法,检测准确率可提高6.2％,误报率和漏报率可降低6.75％、8.46％,且能够有效处理攻击并恢复部分系统性能.     

Speech Enhancement via Residual Dense Generative Adversarial Network

Generative adversarial networks (GANs) are paid more attention to dealing with the end-to-end speech enhancement in recent years. Various GAN-based enhancement methods are presented to improve the quality of reconstructed speech. However, the performance of these GAN-based methods is worse than those of masking-based methods. To tackle this problem, we propose speech enhancement method with a residual dense generative adversarial network (RDGAN) contributing to map the log-power spectrum (LPS) of degraded speech to the clean one. In detail, a residual dense block (RDB) architecture is designed to better estimate the LPS of clean speech, which can extract rich local features of LPS through densely connected convolution layers. Meanwhile, sequential RDB connections are incorporated on various scales of LPS. It significantly increases the feature learning flexibility and robustness in the time-frequency domain. Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments. Specifically, in the untrained acoustic test with limited priors, e.g., unmatched signal-to-noise ratio (SNR) and unmatched noise category, RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes. It indicates that our method is more generalized in untrained conditions.     

Influence of content and creator characteristics on sharing disaster-related information on social media

Identifying the key factors of the disaster-related information propagation process can provide decision support for disaster management. This study characterizes the effects of content types, location, and social capital of social media users on the virality of disaster-related information. We found through the Weibo dataset of the Yiliang earthquake that the virality of different types of information can vary on the basis of the social capital of users who post the information. This study fills the current research gaps by examining the individual and joint effects of the content and creator characteristics on the virality of disaster-related information.     

Ultrasound image analysis technology under deep belief networks in evaluation on the effects of diagnosis and chemotherapy of cervical cancer

The purpose of this study was to explore the value of extraction of tumor features in contrast-enhanced ultrasonography (CEUS) images based on the deep belief networks (DBN) for the diagnosis of cervical cancer patients and realize the intelligent evaluation on effects of diagnosis and chemotherapy of the cervical cancer. An automatic extraction algorithm with the time-intensity curve (TIC) was proposed based on Sparse nonnegative matrix factorization (SNMF) in this study, and was applied to the framework of automatic analysis of cervical cancer tumors based on the deep belief networks, to assist doctors in the analysis of cervical cancer tumors. The framework was applied to the real clinical diagnostic data, and the feasibility of the method was verified by comparing the accuracy, sensitivity, and specificity. Later, the parameters of patients’ time to peak (TP), peak intensity (PI), mean transit time (MTT), and area under the curve (AUC) were obtained by drawing TICs, and the changes of p53 protein and ki-67 protein obtained by pathological section staining were analyzed to evaluate the therapeutic effect in the patients. It was found that the proposed model of tumor feature extraction based on the DBN had the higher accuracy (86.36%), sensitivity (83.33%), and specificity (87.50%). The related parameters of TIC curve obtained based on SNMF showed that there was a significant difference in p53 content between tissues with different degrees of disease (p?<?0.05), the PI of poorly differentiated tissues was significantly higher than that of those with high to medium differentiation (p?<?0.05). In addition, PI and AUC of patients after chemotherapy were significantly lower than that before chemotherapy (p?<?0.05), while MTT was significantly higher than that before chemotherapy (p?<?0.05). Therefore, the proposed TIC feature extraction of CEUS images based on SNMF and the automatic tumor classification based on deep learning can be used in the diagnosis and efficacy evaluation of cervical cancer patients.

     

Entity-level sentiment prediction in Danmaku video interaction

The Journal of Supercomputing - Sentiment analysis in Danmaku video interaction aims at measuring public mood in respect of the video, which is helpful for the potential applications in behavioral...     

Anomaly detection via a combination model in time series data

Since the time series data have the characteristics of a large amount of data and non-stationarity, we usually cannot obtain a satisfactory result by a single-model-based method to detect anomalies in time series data. To overcome this problem, in this paper, a combination-model-based approach is proposed by combining a similarity-measurement-based method and a model-based method for anomaly detection. First, the process of data representation is performed to generate a new data form to arrive at the purpose of reducing data volume. Furthermore, due to the anomalies being generally caused by changes in amplitude and shape, we take both the original time series data and their amplitude change data into consideration of the process of data representation to capture the shape and morphological features. Then, the results of data representation are employed to establish a model for anomaly detection. Compared with the state-of-the-art methods, experimental studies on a large number of datasets show that the proposed method can significantly improve the performance of anomaly detection with higher data anomaly resolution.

     

Influential facilities placement over moving objects

Distributed and Parallel Databases - In this paper we propose and study the problem of k-Collective influential facility placement over moving object. Specifically, given a set of candidate...