Risk Analysis Using Multi-Source Data for Distribution Networks Facing Extreme Natural Disasters

Distribution networks denote important public infrastructure necessary for people’s livelihoods.However,extreme natural disasters,such as earthquakes,typhoons,and mudslides,severely threaten the safe and stable operation of distribution networks and power supplies needed for daily life.Therefore,considering the requirements for distribution network disaster prevention and mitigation,there is an urgent need for in-depth research on risk assessment methods of distribution networks under extreme natural disaster conditions.This paper accessesmultisource data,presents the data quality improvement methods of distribution networks,and conducts data-driven active fault diagnosis and disaster damage analysis and evaluation using data-driven theory.Furthermore,the paper realizes real-time,accurate access to distribution network disaster information.The proposed approach performs an accurate and rapid assessment of cross-sectional risk through case study.The minimal average annual outage time can be reduced to 3 h/a in the ring network through case study.The approach proposed in this paper can provide technical support to the further improvement of the ability of distribution networks to cope with extreme natural disasters.

Feature Fusion Multi-View Hashing Based on Random Kernel Canonical Correlation Analysis

Hashing technology has the advantages of reducing data storage and improving the efficiency of the learning system,making it more and more widely used in image retrieval.Multi-view data describes image information more comprehensively than traditional methods using a single-view.How to use hashing to combine multi-view data for image retrieval is still a challenge.In this paper,a multi-view fusion hashing method based on RKCCA(Random Kernel Canonical Correlation Analysis)is proposed.In order to describe image content more accurately,we use deep learning dense convolutional network feature DenseNet to construct multi-view by combining GIST feature or BoW_SIFT(Bag-of-Words model+SIFT feature)feature.This algorithm uses RKCCA method to fuse multi-view features to construct association features and apply them to image retrieval.The algorithm generates binary hash code with minimal distortion error by designing quantization regularization terms.A large number of experiments on benchmark datasets show that this method is superior to other multi-view hashing methods.

Evolutionary Algorithm Based Feature Subset Selection for Students Academic Performance Analysis

Educational Data Mining(EDM)is an emergent discipline that concen-trates on the design of self-learning and adaptive approaches.Higher education institutions have started to utilize analytical tools to improve students’grades and retention.Prediction of students’performance is a difficult process owing to the massive quantity of educational data.Therefore,Artificial Intelligence(AI)techniques can be used for educational data mining in a big data environ-ment.At the same time,in EDM,the feature selection process becomes necessary in creation of feature subsets.Since the feature selection performance affects the predictive performance of any model,it is important to elaborately investigate the outcome of students’performance model related to the feature selection techni-ques.With this motivation,this paper presents a new Metaheuristic Optimiza-tion-based Feature Subset Selection with an Optimal Deep Learning model(MOFSS-ODL)for predicting students’performance.In addition,the proposed model uses an isolation forest-based outlier detection approach to eliminate the existence of outliers.Besides,the Chaotic Monarch Butterfly Optimization Algo-rithm(CBOA)is used for the selection of highly related features with low com-plexity and high performance.Then,a sailfish optimizer with stacked sparse autoencoder(SFO-SSAE)approach is utilized for the classification of educational data.The MOFSS-ODL model is tested against a benchmark student’s perfor-mance data set from the UCI repository.A wide-ranging simulation analysis por-trayed the improved predictive performance of the MOFSS-ODL technique over recent approaches in terms of different measures.Compared to other methods,experimental results prove that the proposed(MOFSS-ODL)classification model does a great job of predicting students’academic progress,with an accuracy of 96.49%.

An intelligent prediction model of epidemic characters based on multi-feature

The epidemic characters of Omicron(e.g.large-scale transmission)are significantly different from the initial variants of COVID-19.The data generated by large-scale transmission is important to predict the trend of epidemic characters.However,the re-sults of current prediction models are inaccurate since they are not closely combined with the actual situation of Omicron transmission.In consequence,these inaccurate results have negative impacts on the process of the manufacturing and the service industry,for example,the production of masks and the recovery of the tourism industry.The authors have studied the epidemic characters in two ways,that is,investigation and prediction.First,a large amount of data is collected by utilising the Baidu index and conduct questionnaire survey concerning epidemic characters.Second,theβ-SEIDR model is established,where the population is classified as Susceptible,Exposed,Infected,Dead andβ-Recovered persons,to intelligently predict the epidemic characters of COVID-19.Note thatβ-Recovered persons denote that the Recovered persons may become Sus-ceptible persons with probabilityβ.The simulation results show that the model can accurately predict the epidemic characters.

Curve Classification Based onMean-Variance Feature Weighting and Its Application

The classification of functional data has drawn much attention in recent years.The main challenge is representing infinite-dimensional functional data by finite-dimensional features while utilizing those features to achieve better classification accuracy.In this paper,we propose a mean-variance-based(MV)feature weighting method for classifying functional data or functional curves.In the feature extraction stage,each sample curve is approximated by B-splines to transfer features to the coefficients of the spline basis.After that,a feature weighting approach based on statistical principles is introduced by comprehensively considering the between-class differences and within-class variations of the coefficients.We also introduce a scaling parameter to adjust the gap between the weights of features.The new feature weighting approach can adaptively enhance noteworthy local features while mitigating the impact of confusing features.The algorithms for feature weighted K-nearest neighbor and support vector machine classifiers are both provided.Moreover,the new approach can be well integrated into existing functional data classifiers,such as the generalized functional linear model and functional linear discriminant analysis,resulting in a more accurate classification.The performance of the mean-variance-based classifiers is evaluated by simulation studies and real data.The results show that the newfeatureweighting approach significantly improves the classification accuracy for complex functional data.

Polarimetric Meteorological Satellite Data Processing Software Classification Based on Principal Component Analysis and Improved K-Means Algorithm

With the increasing variety of application software of meteorological satellite ground system, how to provide reasonable hardware resources and improve the efficiency of software is paid more and more attention. In this paper, a set of software classification method based on software operating characteristics is proposed. The method uses software run-time resource consumption to describe the software running characteristics. Firstly, principal component analysis (PCA) is used to reduce the dimension of software running feature data and to interpret software characteristic information. Then the modified K-means algorithm was used to classify the meteorological data processing software. Finally, it combined with the results of principal component analysis to explain the significance of various types of integrated software operating characteristics. And it is used as the basis for optimizing the allocation of software hardware resources and improving the efficiency of software operation.

Second Language Data Analysis——From three pieces of Chinese students’ writing

Through analyzing the collected samples which are from three Chinese-English learners in ICLE project(Portsmouth Chinese-English learner corpus),this analysis project aims to describe the grammatical status of some non-native features in Chinese students’ writing and answer the following two questions:①Do these features seem to be performance mistakes(i.e.are they random) or is there evidence that they reflect an interlanguage grammar(ILG)(i.e.where they appear to be systematic errors)?②In the case of systematic errors,do they seem to be errors transferred from the L1(first language of the students) or do they seem to be developmental errors(shared by learners from other L1 backgrounds)?

Analysis of A Heavy Rainstorm Process during Main Flood Season of 2009 in Hunan Province

Conventional observation data,precipitation data from regional automatic stations,1°×1° NCEP reanalysis data and TBB pictures of FY-2C geostationary meteorological satellite as well as Doppler radar,etc.were utilized to analyzing the heavy precipitation process in Hunan Province from June 8 to 10.The results indicated that this heavy precipitation process was caused under the condition of western Pacific subtropical high jumped northward and fell southward rapidly,maintained and swung the shear line of low and middle-level atmosphere over long periods,and configurated temperature-moisture energy.Through analysis we found that precipitation period and precipitation area had a good corresponding to radar product and satellite TBB image,the high potential pseudo-equivalent temperature(θse) of low level and high convergence available potential energy(CAPE) area as well as ascending area of strong convergence.With the extension of effective forecasted period,the forecast location of T639 and EC on the western ridge points of western Pacific subtropical high became more and more easterly and the intensity became weaker and weaker,which had some deviations for forecasting heavy precipitation area.

Energy Theft Detection in Smart Grids with Genetic Algorithm-Based Feature Selection

As big data,its technologies,and application continue to advance,the Smart Grid(SG)has become one of the most successful pervasive and fixed computing platforms that efficiently uses a data-driven approach and employs efficient information and communication technology(ICT)and cloud computing.As a result of the complicated architecture of cloud computing,the distinctive working of advanced metering infrastructures(AMI),and the use of sensitive data,it has become challenging tomake the SG secure.Faults of the SG are categorized into two main categories,Technical Losses(TLs)and Non-Technical Losses(NTLs).Hardware failure,communication issues,ohmic losses,and energy burnout during transmission and propagation of energy are TLs.NTL’s are human-induced errors for malicious purposes such as attacking sensitive data and electricity theft,along with tampering with AMI for bill reduction by fraudulent customers.This research proposes a data-driven methodology based on principles of computational intelligence as well as big data analysis to identify fraudulent customers based on their load profile.In our proposed methodology,a hybrid Genetic Algorithm and Support Vector Machine(GA-SVM)model has been used to extract the relevant subset of feature data from a large and unsupervised public smart grid project dataset in London,UK,for theft detection.A subset of 26 out of 71 features is obtained with a classification accuracy of 96.6%,compared to studies conducted on small and limited datasets.

Sentiment Analysis on the Social Networks Using Stream Algorithms

The rising popularity of online social networks (OSNs), such as Twitter, Facebook, MySpace, and LinkedIn, in recent years has sparked great interest in sentiment analysis on their data. While many methods exist for identifying sentiment in OSNs such as communication pattern mining and classification based on emoticon and parts of speech, the majority of them utilize a suboptimal batch mode learning approach when analyzing a large amount of real time data. As an alternative we present a stream algorithm using Modified Balanced Winnow for sentiment analysis on OSNs. Tested on three real-world network datasets, the performance of our sentiment predictions is close to that of batch learning with the ability to detect important features dynamically for sentiment analysis in data streams. These top features reveal key words important to the analysis of sentiment.

Reduction of distortion and improvement of efficiency for gridding of scattered gravity and magnetic data

This paper presents a reasonable gridding-parameters extraction method for setting the optimal interpolation nodes in the gridding of scattered observed data. The method can extract optimized gridding parameters based on the distribution of features in raw data. Modeling analysis proves that distortion caused by gridding can be greatly reduced when using such parameters. We also present some improved technical measures that use human- machine interaction and multi-thread parallel technology to solve inadequacies in traditional gridding software. On the basis of these methods, we have developed software that can be used to grid scattered data using a graphic interface. Finally, a comparison of different gridding parameters on field magnetic data from Ji Lin Province, North China demonstrates the superiority of the proposed method in eliminating the distortions and enhancing gridding efficiency.

An Integrated Framework for Road Detection in Dense Urban Area from High-Resolution Satellite Imagery and Lidar Data

Automatic road detection, in dense urban areas, is a challenging application in the remote sensing community. This is mainly because of physical and geometrical variations of road pixels, their spectral similarity to other features such as buildings, parking lots and sidewalks, and the obstruction by vehicles and trees. These problems are real obstacles in precise detection and identification of urban roads from high-resolution satellite imagery. One of the promising strategies to deal with this problem is using multi-sensors data to reduce the uncertainties of detection. In this paper, an integrated object-based analysis framework was developed for detecting and extracting various types of urban roads from high-resolution optical images and Lidar data. The proposed method is designed and implemented using a rule-oriented approach based on a masking strategy. The overall accuracy (OA) of the final road map was 89.2%, and the kappa coefficient of agreement was 0.83, which show the efficiency and performance of the method in different conditions and interclass noises. The results also demonstrate the high capability of this object-based method in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite images and Lidar data.

基于大数据分析的可见光图像融合质量评价研究

在复杂可见光图像下图像融合质量受到遮挡和重叠等因素影响,需要进行图像融合质量评价优化设计,提出基于大数据分析的可见光图像融合质量评价模型,采用相应图像块之间的视觉特征提取方法建立可见光图像的深度立体匹配模型,将不同光照强下采集的图像像素值显示映射到嵌入特征空间中,完成预处理,构建可见光图像的动态像素大数据融合模型,通过端到端的视差融合估计实现对可见光图像的动态融合,采用超分辨重建方法获得真实配对图像,分析SR结果与LR图像中的相似内容,以特征级别的图像分布域反映可见光图像融合质量评价,实现可见光图像融合质量评价。仿真结果表明,采用该方法进行可见图像融合的匹配性能较好,图像的对比度、饱和度高,提高了可见光的成像质量,耗时为0.012 s,平均迭代次数为1.569,并且均方误差仅为1.071,总误差仅为4.646,该方法有效提高了图像融合质量的同时,提高了评估效果。

基于计算智能的电力数据智能分析及应用研究

为了提升智能电网负荷预测准确率,提出了一种基于深度学习的短期电力负荷预测模型。在长短时记忆网络和卷积神经网络基础上,构建混合CNN-LSTM预测模型结构。利用基于叠加卷积降噪自动编码器对电力数据进行特征提取,提出包含2个堆叠的LSTM层和1个线性输出层的负荷预测模型。24 h短期负荷预测结果表明,所提模型MAE、RMSE、MAPE和R2指标分别为232.08、292.19、0.0322、0.909,与XGBoost模型相比,性能分别提升74.8%、73.8%、70.8%和10.9%。

基于多维特征的通信网络异常数据识别算法

为解决现有方法存在的异常数据识别精度较低的问题,提出一种基于多维特征的通信网络异常数据识别算法。调整粒子群优化算法中粒子的当前速度和位置,获取通信网络多维数据样本;通过数据挖掘中的聚类分析法提取数据特征,确定密度指标,获取数据多维特征;将提取的多维特征引入深度信念网络中进行识别,根据特征频谱幅值变化,实现对通信网络数据异常识别。实验结果表明,该算法能有效识别通信网络异常数据特征,具有较高的识别准确性。

基于典型气象数据分析的南北方 供暖特性研究

针对南、北方供暖的需求差异,基于历年气象数据,综合考虑累年最冷月平均温度、供暖度日数HDD18、供暖期天数等多种因素,分析了中国南、北方8个典型城市的气候特征;同时结合需求调研和温度分布、波动差异对比情况,讨论了不同地区热负荷动态特性及负荷求解宜使用的方法;分析总结了南、北方地区的系统运行特征情况,给出了关于供暖系统设计、系统形式、运行策略的建议;并通过实际案例具体分析了供暖系统设置的适宜性问题,为后续供暖设计方法、参数确定,供暖方式选择和系统设置提供基础。

宁夏定点形变观测自然环境干扰分析

选取宁夏地区2015—2018年定点形变观测数据进行跟踪分析,初步探索自然环境典型干扰事件在形变观测数据中的特征表现形式,旨在丰富宁夏地震前兆数据服务产品,为形变观测数据的干扰识别提供参考依据,为深入研究等提供基础数据。

纸张生产质量检测系统的数值模拟与工业部署

为实现针对纸张生产质量的实时监测,提出了一种基于特征选择方案的在线软测量系统。该系统搭载有纸张生产质量软测量模型。软测量模型以托辊瞬时流量、毛布排放泵出口流量、断尾纤维百分比等纸张生产实时数据为基础建立运行参数体系。为验证该模型的有效性,通过数值模拟的方式对模型精度进行测试,最后提出了整个系统的部署思路并以参数设置功能模块为例展示了该操作界面的设计效果。经试验研究发现,纸张生产质量检测系统各项精度测试指标较为理想,操作界面设计友好直观,具有一定的应用价值。

基于近邻元分析的风电机组状态监测特征选择方法

针对现有特征选择方法难以从大量的SCADA参量中挑选出重要变量的问题,基于近邻元分析算法提出一种专门适用于风电机组状态监测的特征变量选择方法。所提方法根据每个待选变量对回归精度的贡献率为各变量赋予相应的重要度权值,从而挑选出最重要的特征变量。通过分析SCADA数据中冗余变量的特点,针对性地提出了基于相关系数矩阵的去除冗余方法。采用Pearson相关系数、互信息和随机森林三种方法作为对比,以门控循环神经网络作为模型预测齿轮箱油池温度,用预测精度指标和残差控制图对各特征选择方法的选择结果进行评价和对比,结果表明所提方法的特征选择结果更加直观、冗余变量更少、预测精度更高。

基于特征构建及CAE-LSTM的短期电量预测方法

线损率能够反映企业的管理水平和经济效益,而供售电不同期会导致线损统计存在误差,因此需要进行短期电量预测。针对现有方法未能充分挖掘电量影响因素的问题,提出基于特征构建及CAE-LSTM的短期电量预测方法。通过数据分析构建特征,并使用MIC进行筛选;使用ARIMA预测电量值,并与特征进行数据重构;通过CAE-LSTM对数据进行特征提取,得到预测结果。实验结果表明,提出的方法能够更有效地提取数据特征,实现更高的预测精度。