Recognition of Hybrid PQ Disturbances Based on Multi-Resolution S-Transform and Decision Tree

Aiming at the problems of multiple types of power quality composite disturbances,strong feature correlation and high recognition error rate,a method of power quality composite disturbances identification based on multiresolution S-transform and decision tree was proposed.Firstly,according to IEEE standard,the signal models of seven single power quality disturbances and 17 combined power quality disturbances are given,and the disturbance waveform samples are generated in batches.Then,in order to improve the recognition accuracy,the adjustment factor is introduced to obtain the controllable time-frequency resolution through multi-resolution S-transform time-frequency domain analysis.On this basis,five disturbance time-frequency domain features are extracted,which quantitatively reflect the characteristics of the analyzed power quality disturbance signal,which is less than the traditional method based on S-transform.Finally,three classifiers such as K-nearest neighbor,support vector machine and decision tree algorithm are used to effectively complete the identification of power quality composite disturbances.Simulation results showthat the classification accuracy of decision tree algorithmis higher than that of K-nearest neighbor and support vector machine.Finally,the proposed method is compared with other commonly used recognition algorithms.Experimental results show that the proposedmethod is effective in terms of detection accuracy,especially for combined PQ interference.

Hybrid Recommender System Using Systolic Tree for Pattern Mining

A recommender system is an approach performed by e-commerce for increasing smooth users’experience.Sequential pattern mining is a technique of data mining used to identify the co-occurrence relationships by taking into account the order of transactions.This work will present the implementation of sequence pattern mining for recommender systems within the domain of e-com-merce.This work will execute the Systolic tree algorithm for mining the frequent patterns to yield feasible rules for the recommender system.The feature selec-tion's objective is to pick a feature subset having the least feature similarity as well as highest relevancy with the target class.This will mitigate the feature vector's dimensionality by eliminating redundant,irrelevant,or noisy data.This work pre-sents a new hybrid recommender system based on optimized feature selection and systolic tree.The features were extracted using Term Frequency-Inverse Docu-ment Frequency(TF-IDF),feature selection with the utilization of River Forma-tion Dynamics(RFD),and the Particle Swarm Optimization(PSO)algorithm.The systolic tree is used for pattern mining,and based on this,the recommendations are given.The proposed methods were evaluated using the MovieLens dataset,and the experimental outcomes confirmed the efficiency of the techniques.It was observed that the RFD feature selection with systolic tree frequent pattern mining with collaborativefiltering,the precision of 0.89 was achieved.

Identification of differentially expressed genes associated with bud dormancy release in tree peony(Paeonia suffruticosa) by suppression subtractive hybridization

A subtractive cDNA library was developed to study genes associated with bud dormancy release in tree peonies. In order to identify genes that are highly expressed in buds released from dormancy, 588 clones were examined by differential screening. Of these, 185 clones were selected to be sequenced. A total of 37 unique sequences were obtained of which only 31 sequences have matches in the NCBI database or the Arabidopsis thaliana protein database. Semi-quantitative RT-PCR was used to confirm further the expression profiles for 12 transcripts identified within the subtractive cDNA library. Gene ontology analyses indicated that many of the different genes identified have unknown or hypothetical functions while it is speculated that other genes play different mo- lecular roles. In our study, genes involved in bud dormancy release were growth-related or stress-responsive, while low-temperature-induced ribosomal proteins may also play a role in bud dormancy release. Our results provide interesting information for further understanding of the molecular mechanism of bud dormancy release in tree peonies.

Research on the adaptive hybrid search tree anti-collision algorithm in RFID system

Due to more tag-collisions result in failed transmissions,tag anti-collision is a very vital issue in the radio frequency identification(RFID) system.However,so far decreases in communication time and increases in throughput are very limited.In order to solve these problems,this paper presents a novel tag anti-collision scheme,namely adaptive hybrid search tree(AHST),by combining two algorithms of the adaptive binary-tree disassembly(ABD) and the combination query tree(CQT),in which ABD has superior tag identification velocity and CQT has optimum performance in system throughput and search timeslots.From the theoretical analysis and numerical simulations,the proposed algorithm can colligate the advantages of above algorithms,improve the system throughput and reduce the searching timeslots dramatically.

Prediction method of restoring force based on online AdaBoost regression tree algorithm in hybrid test

In order to solve the poor generalization ability of the back-propagation(BP)neural network in the model updating hybrid test,a novel method called the AdaBoost regression tree algorithm is introduced into the model updating procedure in hybrid tests.During the learning phase,the regression tree is selected as a weak regression model to be trained,and then multiple trained weak regression models are integrated into a strong regression model.Finally,the training results are generated through voting by all the selected regression models.A 2-DOF nonlinear structure was numerically simulated by utilizing the online AdaBoost regression tree algorithm and the BP neural network algorithm as a contrast.The results show that the prediction accuracy of the online AdaBoost regression algorithm is 48.3%higher than that of the BP neural network algorithm,which verifies that the online AdaBoost regression tree algorithm has better generalization ability compared to the BP neural network algorithm.Furthermore,it can effectively eliminate the influence of weight initialization and improve the prediction accuracy of the restoring force in hybrid tests.

Hybrid tree guided PatchMatch and quantizing acceleration for multiple views disparity estimation

Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view images.Hybrid tree method can obtain a disparity estimation fast with relatively low accuracy,while PatchMatch can give high-precision disparity value with relatively high computational cost.In this work,we propose the Hybrid Tree Guided PatchMatch which can calculate the disparity fast and accurate.Firstly,an initial disparity map is estimated by employing hybrid tree cost aggregation,which is used to constrain the label searching range of the PatchMatch.Furthermore,a reliable normal searching range for each current normal vector defined on the initial disparity map is calculated to refine the PatchMatch.Finally,an effective quantizing acceleration strategy is designed to decrease the matching computational cost of continuous disparity.Experimental results demonstrate that the disparity estimation based on our algorithm is better in binocular image benchmarks such as Middlebury and KITTI.We also provide the disparity estimation results for multi-view stereo in real scenes.

面向科技文献多维语义组织的混合倒排索引构建方法

[目的/意义]为满足科研人员对科技文献内部细粒度语义信息进行高效查询的迫切需求,前期研究提出了面向科技文献的多维语义索引体系,然而基于HashMap的常见倒排索引会导致查询效率低下。本文旨在通过面向不同维度语义特征建立混合倒排索引,以改进语义查询性能。[方法/过程]本文以Treap、B+树等多种数据结构探索适合不同语义维度的倒排索引构建方法,并将其组合形成多种适用于科技文献多维语义组织的混合倒排索引构建方法,并通过对比实验,在排序查询和布尔查询条件下分析验证不同类型倒排索引构建方法的查询性能。[结果/结论]实验结果表明,组合形成的8种混合倒排索引构建方法中,表2所示的C3(HHHB)被证明在排序查询条件下具有最高的效率,而C4(TTTB)则在布尔查询条件下被证明最为高效。本文的方法能有效解决单一索引结构导致的查询效率问题。

大花黄牡丹与日本牡丹杂交试验

大花黄牡丹(Paeonia ludlowii)是我国9个牡丹原生种之一,为西藏特有植物。挖掘大花黄牡丹的基因潜能,筛选优质杂交父本,可为进一步培育株型高大的黄色系牡丹新品种提供实践依据。以大花黄牡丹为母本,‘皇嘉门’('Kokamon')、‘芳纪’('Hoki')、‘岛大臣’('Shimadaijin')、‘日暮’('Higurashi')、‘新日月锦’('Shin-jitsugetu')、‘八千代椿’('Yachiyotsubaki')和‘花竞’('Hanakisoi')7个日本牡丹品种为父本进行杂交,测定结实率、饱满种子率和出苗率等指标。结果表明,从109朵杂交授粉花朵中,获得杂交种子219粒,饱满种子22粒,出苗10株,平均结实率为13.61%,平均饱满种子率为10.05%,平均出苗率为4.57%。7个日本牡丹品种与大花黄牡丹杂交均具有一定亲和性,杂交亲和性表现为‘新日月锦’>‘皇嘉门’>‘八千代椿’>‘岛大臣’>‘花竞’>‘芳纪’>‘日暮’。结合结实率和出苗率,以‘新日月锦’和‘八千代椿’2个品种为父本,杂交效果较佳。

编译型嵌入式Python的设计与实现

针对面向微控制器的解释型MicroPython具有实时性弱、占用存储空间大和可移植性较差等问题,提出一种将Python语言转化为C++语言并将构件层与应用层分离的编译型嵌入式Python方案,设计基于抽象语法树及类型注释的源码映射机制。在此基础上,设计嵌入式Python编译器,实现集成开发环境AHL-GEC-IDE(for Python版),完成Python源文件的编辑、编译、链接和下载。实践结果表明,该编译型Python方案可行,为嵌入式人工智能领域提供了一种实时性较高、编辑编译方便、可移植性较强的编译型Python集成开发环境。

基于改进决策树的不平衡数据集分类算法研究

不平衡数据集中各类样本数量不均,导致分类模型难以训练。针对不平衡数据分类模型稳定性差,准确率低的问题,提出一种基于改进C4.5决策树数据分类算法,通过融合SMOTE优化采样算法,构建出N_C4.5-IDC不平衡数据分类模型。模型首先利用K-Means聚类对数据集进行状态分布分析,并使用SMOTE采样法进行混合采样,通过增加人为样本点提高少数类样本数,对数据集进行平衡处理;然后对C4.5决策树的核心信息增益率模型进行简化改进,提高特征选择效率,并采用回缩损失对比的方法对决策树进行后剪枝处理,构建单一N_C4.5决策树模型;最后将多组N_C4.5模型进行组合叠加,采用加权处理的方法构建N_C4.5-IDC模型。消融实验数据结果表明:优化策略的叠加能显著提高模型性能指标。对比实验数据结果表明:与基线分类算法相比,所提算法准确率最高达96.81%,召回率提高了6.15%,综合性能上升了5.66%。综上,基于改进C4.5决策树构建的不平衡数据分类模型在平衡数据的同时,提高了分类的稳定性与准确性。

不同授粉方式对油用型牡丹结实性影响的研究

为提高油用牡丹产量,探索油用牡丹理想授粉方式,选择结实性良好、生长势强且自然花期相遇的常见油用型牡丹品种,开展自交、人工授粉、自然授粉等不同方式的授粉试验,调查其坐果率、结实率、种子千粒重等结实情况和蓇葖果单角大小、质量等果荚干物质性状。结果表明,油用型牡丹存在一定自花结实性,自交处理Ⅰ没有结实,处理Ⅱ3个品种结实,处理Ⅲ全部结实,其中‘凤丹白’结实最好,为每个果角0.54粒;将参试的牡丹品种进行4×4人工定向安全双列杂交,所有组合全部结实,平均坐果率高达92%,单果角结实率达到3.87粒,结实率最高的组合为‘凤丹白×景泰蓝’,单果角结实率达到6.96粒;田间自然授粉均有结实,‘凤丹白'结实率最高,3.19粒/个;‘景泰蓝’和‘凤丹白’杂交的种子千粒重较高,达到436.89 g;蓇葖果果荚大小和质量与杂交母本关系较密切,以‘景泰蓝’为母本时表现突出;通过不同授粉方式所对应的坐果率、结实率和复果荚重等指标综合分析,从高到低依次为:人工授粉>自然授粉>自交,母本是影响杂交成功率和果荚性状的重要因素;油用牡丹生产中可通过品种合理搭配间植、相互授粉,如‘景泰蓝’和‘凤丹白’,获得更高种子产量。

基于UMCS树的UML类图的混合相似性度量

软件重用是基于给定条件从存储库中检索以前开发的软件产品,检索基于相似性度量。UML(Unified Modeling Language)类图被广泛应用于软件设计,UML类图重用作为软件设计重用的核心而备受关注。因此,对UML类图的相似性开展研究。类图包含语义和结构信息。目前,UML类图的相似性研究主要集中在语义,也有个别讨论结构相似性,但没有考虑将语义和结构相结合。因此,提出一种结合语义和结构的混合相似性度量。鉴于UML类图的非形式化特征,将UML类图转换成图模型,搜索最大公共子图列表,构建了最大公共子图树,提出一个基于最大公共子图序列的混合相似性度量方法。针对概念公共子图和结构公共子图分别定义了语义匹配和结构匹配,并开展了相似性对比和基于相似性的分类质量比较实验,实验结果验证了所提出方法的优势。

基于多节点协同的电力网络靶场混合入侵识别方法

研究了基于多节点协同的电力网络靶场混合入侵识别方法,提升电力网络对混合入侵行为的防御能力。依据多节点协同的分层协作结构,设置电力网络靶场训练平台内的通信节点作为感知节点,利用感知节点感知混合入侵数据,将感知结果传送至电力网络靶场训练平台的中心节点,利用中心节点融合混合入侵感知数据形成聚合节点。协同融合层的聚合节点将协同融合结果传送至识别层,识别层利用混合入侵识别模块,依据K-means聚类算法对混合入侵数据的聚类结果,构建C4.5决策树,利用决策树输出电力网络靶场混合入侵识别结果。实验结果表明,该方法可以精准识别电力网络靶场混合入侵行为,识别精度高于98%。

基于GPU的HPGB+-Tree索引

索引作为加速数据库查询的一种成熟技术,始终受限于CPU的内存带宽与架构的发展,因此无法在性能上实现质的飞跃。所以使用GPU赋能索引技术来辅助数据库执行查询任务是势在必行的。因此,针对异构环境下索引结构的适应性以及现有GPU索引受限于显存容量导致扩展性不够等问题,提出了一种CPU与GPU协同处理的HPGB+-Tree索引算法。该算法以混合架构的方式重新构建索引结构,使其完全适应GPU的硬件特性,突破CPU内存带宽受限和GPU内存容量受限的双重难关。HPGB+-Tree索引不仅解决了索引异构问题,还充分利用两大硬件平台各自的优势加速基于索引的相关操作。在不同数据量与不同任务规模下对算法的性能进行了评估,实验结果表明,该算法在内核占用率与程序执行速度两个方面都极具优势,在性能上处于领先地位。

Decision tree and deep learning based probabilistic model for character recognition

One of the most important methods that finds usefulness in various applications, such as searching historical manuscripts, forensic search, bank check reading, mail sorting, book and handwritten notes transcription, is handwritten character recognition. The common issues in the character recognition are often due to different writing styles, orientation angle, size variation(regarding length and height), etc. This study presents a classification model using a hybrid classifier for the character recognition by combining holoentropy enabled decision tree(HDT) and deep neural network(DNN). In feature extraction, the local gradient features that include histogram oriented gabor feature and grid level feature, and grey level co-occurrence matrix(GLCM) features are extracted. Then, the extracted features are concatenated to encode shape, color, texture, local and statistical information, for the recognition of characters in the image by applying the extracted features to the hybrid classifier. In the experimental analysis, recognition accuracy of 96% is achieved. Thus, it can be suggested that the proposed model intends to provide more accurate character recognition rate compared to that of character recognition techniques used in the literature.

Predicting the Results of RNA Molecular Specific Hybridization Using Machine Learning

Ribonucleic acid(RNA)hybridization is widely used in popular RNA simulation software in bioinformatics.However limited by the exponential computational complexity of combin atorial problems,it is challenging to decide,within an acceptable time,whether a specific RNA hybridization is effective.We hereby introduce a machine learning based technique to address this problem.Sample machine learning(ML)models tested in the training phase include algorithms based on the boosted tree(BT)random forest(RF),decision tree(DT)and logistic regression(LR),and the corresponding models are obtained.Given the RNA molecular coding training and testing sets,the trained machine learning models are applied to predict the classification of RNA hybridization results.The experiment results show that the op timal predictive accuracies are 96.2%,96.6%,96.0%and 69.8%for the RF,BT,DT and LR-based approaches,respectively,un der the strong constraint condition,compared with traditiona representative methods.Furthermore,the average computation efficiency of the RF,BT,DT and LR-based approaches are208679,269756,184333 and 187458 times higher than that o existing approach,respectively.Given an RNA design,the BT based approach demonstrates high computational efficiency and better predictive accuracy in determining the biological effective ness of molecular hybridization.

Useful life prediction using a stochastic hybrid automata model for an ACS multi-gyro subsystem

A useful life prediction method based on the integration of the stochastic hybrid automata(SHA) model and the frame of the dynamic fault tree(DFT) is proposed. The SHA model can incorporate the orbit environment, work modes, system configuration, dynamic probabilities and degeneration of components,as well as spacecraft dynamics and kinematics. By introducing the frame of DFT, the system is classified into several layers, and the problem of state combination explosion is artfully overcome.An improved dynamic reliability model(DRM) based on the Nelson hypothesis is investigated to improve the defect of cumulative failure probability(CFP), which is used to address the failure probability of components in the SHA model. The simulation using the Monte-Carlo method is finally conducted on two satellites, which are deployed with the same multi-gyro subsystem but run on different orbits. The results show that the predicted useful life of the attitude control system(ACS) with consideration of abrupt failure,degradation, and running environment is quite different between the two satellites.

Multicast Routing Based on Hybrid Genetic Algorithm

A new multicast routing algorithm based on the hybrid genetic algorithm (HGA) is proposed. The coding pattern based on the number of routing paths is used. A fitness function that is computed easily and makes algorithm quickly convergent is proposed. A new approach that defines the HGA's parameters is provided. The simulation shows that the approach can increase largely the convergent ratio, and the fitting values of the parameters of this algorithm are different from that of the original algorithms. The optimal mutation probability of HGA equals 0.50 in HGA in the experiment, but that equals 0.07 in SGA. It has been concluded that the population size has a significant influence on the HGA's convergent ratio when it's mutation probability is bigger. The algorithm with a small population size has a high average convergent rate. The population size has little influence on HGA with the lower mutation probability.

Hybrid Cartesian Grid Method for Moving Boundary Problems

A hybrid Cartesian structured grid method is proposed for solving moving boundary unsteady problems. The near body region is discretized by using the body-fitted structured grids, while the remaining computational domain is tessellated with the generated Cartesian grids. As the body moves, the structured grids move with the body and the outer boundaries of inside grids are used to generate new holes in the outside adaptive Cartesian grid to facilitate data communication. By using the alternating digital tree （ADT） algorithm, the computational time of hole-cutting and identification of donor cells can be reduced significantly. A compressible solver for unsteady flow problems is developed. A cell-centered, second-order accurate finite volume method is employed in spatial discreti- zation and an implicit dual-time stepping low-upper symmetric Gauss-Seidei （LU-SGS） approach is employed in temporal discretization. Geometry-based adaptation is used during unsteady simulation time steps when boundary moves and the flow solution is interpolated from the old Cartesian grids to the new one with inverse distance weigh- ting interpolation formula. Both laminar and turbulent unsteady cases are tested to demonstrate the accuracy and efficiency of the proposed method. Then, a 2-D store separation problem is simulated. The result shows that the hybrid Cartesian grid method can handle the unsteady flow problems involving large-scale moving boundaries.

Construction and analysis of tree models for chromosomal classification of diffuse large B-cell lymphomas

AIM: To construct tree models for classification of diffuse large B-cell lymphomas (DLBCL) by chromosome copy numbers, to compare them with cDNA microarray classification, and to explore models of multi-gene, multi-step and multi-pathway processes of DLBCL tumorigenesis. METHODS: Maximum-weight branching and distancebased models were constructed based on the comparative genomic hybridization (CGH) data of 123 DLBCL samples using the established methods and software of Desper et al . A maximum likelihood tree model was also used to analyze the data. By comparing with the results reported in literature, values of tree models in the classification of DLBCL were elucidated. RESULTS: Both the branching and the distance-based trees classified DLBCL into three groups. We combined the classification methods of the two models and classified DLBCL into three categories according to their characteristics. The first group was marked by +Xq, +Xp, -17p and +13q; the second group by +3q, +18q and +18p; and the third group was marked by -6q and +6p. This chromosomal classification was consistent with cDNA classification. It indicated that -6q and +3q were two main events in the tumorigenesis of lymphoma. CONCLUSION: Tree models of lymphoma established from CGH data can be used in the classification of DLBCL. These models can suggest multi-gene, multistep and multi-pathway processes of tumorigenesis. Two pathways, -6q preceding +6q and +3q preceding+18q, may be important in understanding tumorigenesis of DLBCL. The pathway, -6q preceding +6q, may have a close relationship with the tumorigenesis of non-GCB DLBCL.