Prediction of the undrained shear strength of remolded soil with non-linear regression,fuzzy logic,and artificial neural network

This study aims to predict the undrained shear strength of remolded soil samples using non-linear regression analyses,fuzzy logic,and artificial neural network modeling.A total of 1306 undrained shear strength results from 230 different remolded soil test settings reported in 21 publications were collected,utilizing six different measurement devices.Although water content,plastic limit,and liquid limit were used as input parameters for fuzzy logic and artificial neural network modeling,liquidity index or water content ratio was considered as an input parameter for non-linear regression analyses.In non-linear regression analyses,12 different regression equations were derived for the prediction of undrained shear strength of remolded soil.Feed-Forward backpropagation and the TANSIG transfer function were used for artificial neural network modeling,while the Mamdani inference system was preferred with trapezoidal and triangular membership functions for fuzzy logic modeling.The experimental results of 914 tests were used for training of the artificial neural network models,196 for validation and 196 for testing.It was observed that the accuracy of the artificial neural network and fuzzy logic modeling was higher than that of the non-linear regression analyses.Furthermore,a simple and reliable regression equation was proposed for assessments of undrained shear strength values with higher coefficients of determination.

Editing Algorithms for Non-Linear Editing Systems Based on MPEG-2

MPEG-1/2-based non-linear editing systems appear to have a tendency to replace the M-JPEG systems, but in so doing it is difficult to realize the video, audio and the synchronization editing algorithms. Such editing algorithms are presented. Based on an analysis of the structure of the MPEG-1/2 stream, and using parameters of the video, audio and the synchronization information, the video, audio and synchronization editing algorithms are provided. The characters of the algorithms are efficient, the quality loss of frames is low because it only decodes and codes part of the data; the editing algorithm is fast through use of some index files; synchronization editing is realized using the synchronization information, such as PTS, ESCR and other parameters.

Non-linear Chemical Process Modelling and Application in Epichlorhydrine Production Plant Using Wavelet Networks

A type of wavelet neural network, in which the scale function isadopted only, is proposed in this paper for non-linear dynamicprocess modelling. Its network size is decreased significantly andthe weight coefficients can be estimated by a linear algorithm. Thewavelet neural network holds some advantages superior to other typesof neural networks. First, its network structure is easy to specifybased on its theoretical analysis and intuition. Secondly, networktraining does not rely on stochastic gradient type techniques andavoids the problem of poor convergence or undesirable local minima.

产品之三：Legato NetWorker Business Edition

Legato公司的NetWorker Business Edition产品包支持8个客户端，支持26个槽位以下的磁带库和多个磁带驱动器．并提供对集群服务器支持等先进的备份功能。NetWorker Business Edition可升级到Network Edition或Power Edition，以支持更多的备份客户端和SAN的应用，可平滑迁移到Unix或Linux的备份环境而无需对原有备份数据作任何改变。

Adoption of network and plan-do-check-action in the international classification of disease 10 coding

BACKGROUND with the widespread application of computer network systems in the medical field,the plan-do-check-action(PDCA)and the international classification of diseases tenth edition(ICD-10)coding system have also achieved favorable results in clinical medical record management.However,research on their combined application is relatively lacking.Objective:it was to explore the impact of network systems and PDCA management mode on ICD-10 encoding.Material and Method:a retrospective collection of 768 discharged medical records from the Medical Record Management Department of Meishan People’s Hospital was conducted.They were divided into a control group(n=232)and an observation group(n=536)based on whether the PDCA management mode was implemented.The two sets of coding accuracy,time spent,case completion rate,satisfaction,and other indicators were compared.AIM To study the adoption of network and PDCA in the ICD-10.METHODS A retrospective collection of 768 discharged medical records from the Medical Record Management Department of Meishan People’s Hospital was conducted.They were divided into a control group(n=232)and an observation group(n=536)based on whether the PDCA management mode was implemented.The two sets of coding accuracy,time spent,case completion rate,satisfaction,and other indicators were compared.RESULTS In the 3,6,12,18,and 24 months of PDCA cycle management mode,the coding accuracy and medical record completion rate were higher,and the coding time was lower in the observation group as against the controls(P<0.05).The satisfaction of coders(80.22%vs 53.45%)and patients(84.89%vs 51.72%)in the observation group was markedly higher as against the controls(P<0.05).CONCLUSION The combination of computer networks and PDCA can improve the accuracy,efficiency,completion rate,and satisfaction of ICD-10 coding.

THE MODEL VALIDATION OF DYNAMIC NEURAL NETWORKS

This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.

大洋X-EDIT在我校非线性编辑网络实验平台上的应用

非线性网络编辑系统作为电视后期制作的一大趋势,越来越受到学校教育技术学专业和新闻传播专业学生的重视,对我校使用的大洋X-EDIT系统网络实验平台的构成、网络性能及网络软件特点进行了讨论分析.

非线性编辑网络实验室建设研究——以大洋D3-Edit3200B,D3-EDIT1000非线性编辑系统为例

随着网络新技术的不断涌现,学校在构建非线性编辑网络实验室时应当在先进性、实用性和可扩充性之间找一个平衡点,以满足学校实验和实训教学的要求,充分考虑各种因素,构建适合自己学校的非线性编辑网络实验室.本文以大洋D3-Edit3200B,D3-EDIT1000非线性编辑系统为例就非线性编辑网络实验室设计原则、非线性编辑网络实验室技术分析、非线性编辑网络实验室具体应用进行了初步研究.

Determination of Active Components in a Natural Herb with Near Infrared Spectroscopy Based on Artificial Neural Networks

The non-linear relationships between the contents of ginsenoside Rg 1, Rb 1, Rd and Panax notoginseng saponins(PNS) in Panax notoginseng root herb and the near infrared(NIR) diffuse reflectance spectra of the herb were established by means of artificial neural networks(ANNs). Four three-layered perception feed-forward networks were trained with an error back-propagation algorithm. The significant principal components of the NIR spectral data matrix were utilized as the input of the networks. The networks architecture and parameters were selected so as to offer less prediction errors. Relative prediction errors for Rg 1, Rb 1, Rd and PNS obtained with the optimum ANN models were 8.99%, 6.54%, 8.29%, and 5.17%, respectively, which were superior to those obtained with PLSR methods. It is verified that ANN is a suitable approach to model this complex non-linearity. The developed method is fast, non-destructive and accurate and it provides a new efficient approach for determining the active components in the complex system of natural herbs.

Nucleus accumbens-linked executive control networks mediating reversal learning in tree shrew brain

DEAR EDITOR,Cognitive flexibility is crucial for animal survival but is frequently impaired in neuropsychiatric disorders.Although many brain structures and functional networks are involved in cognitive flexibility,the neural mechanisms underlying cooperation among specific functional networks remain unclear from a global perspective.In this study,[^(18)F]-fluorodeoxyglucose positron emission tomography(FDG-PET)was performed on 19 male tree shrews after four different visual discrimination tasks,including baseline,learning expert(LE),reversal naive(RN),and reversal expert(RE).

The application of modeling and prediction with MRA wavelet network

As there are lots of non-linear systems in the real engineering, it is very important to do more researches on the modeling and prediction of non-linear systems. Based on the multi-resolution analysis (MRA) of wavelet theory, this paper combined the wavelet theory with neural network and established a MRA wavelet network with the scaling function and wavelet function as its neurons. From the analysis in the frequency domain, the results indicated that MRA wavelet network was better than other wavelet networks in the ability of approaching to the signals. An essential research was can:led out on modeling and prediction with MRA wavelet network in the non-linear system. Using the lengthwise sway data received from the experiment of ship model, a model of offline prediction was established and was applied to the short-time prediction of ship motion. The simulation results indicated that the forecasting model improved the prediction precision effectively, lengthened the forecasting time and had a better prediction results than that of AR linear model. The research indicates that it is feasible to use the MRA wavelet network in the short-time prediction of ship motion.

A Hybrid Neural Network and Box-Jenkins Models for Time Series Forecasting

Time series forecasting plays a significant role in numerous applications,including but not limited to,industrial planning,water consumption,medical domains,exchange rates and consumer price index.The main problem is insufficient forecasting accuracy.The present study proposes a hybrid forecastingmethods to address this need.The proposed method includes three models.The first model is based on the autoregressive integrated moving average(ARIMA)statistical model;the second model is a back propagation neural network(BPNN)with adaptive slope and momentum parameters;and the thirdmodel is a hybridization between ARIMA and BPNN(ARIMA/BPNN)and artificial neural networks and ARIMA(ARIMA/ANN)to gain the benefits of linear and nonlinearmodeling.The forecasting models proposed in this study are used to predict the indices of the consumer price index(CPI),and predict the expected number of cancer patients in the Ibb Province in Yemen.Statistical standard measures used to evaluate the proposed method include(i)mean square error,(ii)mean absolute error,(iii)root mean square error,and(iv)mean absolute percentage error.Based on the computational results,the improvement rate of forecasting the CPI dataset was 5%,71%,and 4%for ARIMA/BPNN model,ARIMA/ANN model,and BPNN model respectively;while the result for cancer patients’dataset was 7%,200%,and 19%for ARIMA/BPNNmodel,ARIMA/ANN model,and BPNNmodel respectively.Therefore,it is obvious that the proposed method reduced the randomness degree,and the alterations affected the time series with data non-linearity.The ARIMA/ANN model outperformed each of its components when it was applied separately in terms of increasing the accuracy of forecasting and decreasing the overall errors of forecasting.

GA-BASED PID NEURAL NETWORK CONTROL FOR MAGNETIC BEARING SYSTEMS

In order to overcome the system non-linearity and uncertainty inherent in magnetic bearing systems, a GA（genetic algnrithm）-based PID neural network controller is designed and trained tO emulate the operation of a complete system （magnetic bearing, controller, and power amplifiers）. The feasibility of using a neural network to control nonlinear magnetic bearing systems with unknown dynamics is demonstrated. The key concept of the control scheme is to use GA to evaluate the candidate solutions （chromosomes）, increase the generalization ability of PID neural network and avoid suffering from the local minima problem in network learning due to the use of gradient descent learning method. The simulation results show that the proposed architecture provides well robust performance and better reinforcement learning capability in controlling magnetic bearing systems.

Software Defect Prediction Based on Non-Linear Manifold Learning and Hybrid Deep Learning Techniques

Software defect prediction plays a very important role in software quality assurance,which aims to inspect as many potentially defect-prone software modules as possible.However,the performance of the prediction model is susceptible to high dimensionality of the dataset that contains irrelevant and redundant features.In addition,software metrics for software defect prediction are almost entirely traditional features compared to the deep semantic feature representation from deep learning techniques.To address these two issues,we propose the following two solutions in this paper:(1)We leverage a novel non-linear manifold learning method-SOINN Landmark Isomap(SL-Isomap)to extract the representative features by selecting automatically the reasonable number and position of landmarks,which can reveal the complex intrinsic structure hidden behind the defect data.(2)We propose a novel defect prediction model named DLDD based on hybrid deep learning techniques,which leverages denoising autoencoder to learn true input features that are not contaminated by noise,and utilizes deep neural network to learn the abstract deep semantic features.We combine the squared error loss function of denoising autoencoder with the cross entropy loss function of deep neural network to achieve the best prediction performance by adjusting a hyperparameter.We compare the SL-Isomap with seven state-of-the-art feature extraction methods and compare the DLDD model with six baseline models across 20 open source software projects.The experimental results verify that the superiority of SL-Isomap and DLDD on four evaluation indicators.

Optimal resource allocation solutions for heterogeneous cognitive radio networks

Cognitive Radio Networks （CRN） are currently gaining immense recognition as the most-likely next-generation wireless communication paradigm, because of their enticing promise of mitigating the spectrum scarcity and/or underutilisation challenge. Indisputably, for this promise to ever materialise, CRN must of necessity devise appropriate mechanisms to judiciously allocate their rather scarce or limited resources （spectrum and others） among their numerous users. ＇Resource Allocation （RA） in CRN＇, which essentially describes mechanisms that can effectively and optimally carry out such allocation, so as to achieve the utmost for the network, has therefore recently become an important research focus. However, in most research works on RA in CRN, a highly significant factor that describes a more realistic and practical consideration of CRN has been ignored （or only partially explored）, i.e., the aspect of the heterogeneity of CRN. To address this important aspect, in this paper, RA models that incorporate the most essential concepts of heterogeneity, as applicable to CRN, are developed and the imports of such inclusion in the overall networking are investigated. Furthermore, to fully explore the relevance and implications of the various heterogeneous classifications to the RA formulations, weights are attached to the different classes and their effects on the network performance are studied. In solving the developed complex RA problems for heterogeneous CRN, a solution approach that examines and exploits the structure of the problem in achieving a less-complex reformulation, is extensively employed. This approach, as the results presented show, makes it possible to obtain optimal solutions to the rather difficult RA problems of heterogeneous CRN.

A Multipath Routing Algorithm Based on Traffic Prediction in Wireless Mesh Networks

The technology of QoS routing has become a great challenge in Wireless Mesh Networks (WMNs). There exist a lot of literatures on QoS routing in WMNs, but the current algorithms have some deficiencies, such as high complexity, poor scalability and flexibility. To solve the problems above, a multipath routing algorithm based on traffic prediction (MRATP) is proposed in WMNs. MRATP consists of three modules including an algo-rithm on multipath routing built, a congestion discovery mechanism based on wavelet-neural network and a load balancing algorithm via multipath. Simulation results show that MRATP has some characteristics, such as better scalability, flexibility and robustness. Compared with the current algorithms, MRATP has higher success ratio, lower end to end delay and overhead. So MRATP can guarantee the end to end QoS of WMNs.

Optimal PV Allocation&Minimal tap-Changing Transformers Achieving Best Distribution Voltage Profile&Minimum Losses in active distribution networks

In distribution systems,voltage levels of the various buses should be maintained within the permissible limits for satisfactory operation of all electrical installations and equipment.The task of voltage control is closely associated with fluctuating load conditions and corresponding requirements of reactive power compensation.The problem of load bus voltage optimization in distribution systems that have distributed generation(DG)has recently become an issue.In Oman,the distribution code limits the load bus voltage variations within±6%of the nominal value.Several voltage control methods are employed in active distribution systems with a high share of photovoltaic systems(PV)to keep the voltage levels within the desirable limits.In addition to the constraint of targeting the best voltage profile,another constraint has to be achieved which is the minimum loss in the distribution network.An optimised solution for voltage of load busses with on-load tap-changing(OLTC)tarnsformers and PV sources is presented in this paper.This study addresses the problem of optimizing the injected power from PV systems associated with the facilities of tap-changing transformers,as it is an important means of controlling voltage throughout the system.To avoid violating tap-changing constraints,a method is depicted for determining the minimal changes in transformer taps to control voltage levels with distributed PV sources.The taps of a range+5 to-15%,can be achieved by tap-changing transformers.The OLTC operation was designed to keep the secondary bus within the voltage standard for MV networks.

风河公司与Cavium Networks联合推出支持OCTEON多内核MIPS64处理器的多内核设备软件优化解决方案

全球领先的设备软件优化（DSO）厂商风河系统公司与全球领先的网络、安全和嵌入式处理器解决方案供应商Cavium Networks公司日前共同宣布，Wind River Platform for Network Equipment、Linux Edition和Wind River VxWorks6、1已全面支持Cavium Networks的OCTEON多内核MllPS64处理器产品系列。

RESEARCH ON APPLICATION OF ARTIFICAL NEURAL NETWORK EXPERT SYSTEM IN DIAGNOSIS OF DAMAGE OF PRESTRESSED CONCERETE PILES AND BOLT

The expert system (ES) techology is combined with artificial neural network (ANN) theory and engineering experience. Based on the framework of artificial meural network, a BackPropagation is structured. Discuss the use of ANN for non-linear diagnosis of damage of prestressed bolt and prestressed concrete piles (PCP) during driving in rock underground engineering and civil engineering. IN terms of Chinese windows95 utilizes C+ + and AINET and XI-PLUS software, make it a reality.

采用偏好编辑的轻量自注意降噪序列推荐模型

在自注意序列推荐中,除项目嵌入矩阵带来巨大内存消耗问题和自注意层中的不相关信息带来噪声问题,还存在如何在用户行为数据稀疏的情况下准确提取和表示用户偏好的关键问题。针对这些问题,提出一种采用偏好编辑的轻量自注意降噪序列推荐模型(LDSR-PE)。采用上下文感知的动态嵌入组合方案缓解内存消耗问题,在每个自注意层上附加可训练的二进制掩膜,实现自适应修剪不相关噪声项。为更好训练模型,设计基于偏好编辑的自监督学习策略,促使序列推荐模型在不同的交互序列之间区分公共和唯一的偏好。在3个公开数据集上的实验结果表明,LDSR-PE优于主流先进推荐模型。