Cross-Project Software Defect Prediction Based on SMOTE and Deep Canonical Correlation Analysis

Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.

Estimation and Prediction of the Condition of the Vehicle Engine Based on the Correlation Dimension

This paper applies the fractal dimension as a characteristic to describe the engine抯 operating condition and its developmental trend. A correlation dimension is one of the quantities that are usually used to characterize a strange attractor. With the operation of the phase space reconstruction, respective correlation dimensions of a series of vibration signals obtained under different conditions are calculated to find the intrinsic relationship between the indicator and the operating condition. The experiment result shows that the correlation dimension is sensitive to the condition evolution and convenient for the identification of abnormal operational states. In advanced prognostic algorithm based on the BP neural network is then applied on the correlation dimensions to predict the short-term running conditions in order to avoid severe faults and realize in-time maintenance. Experimental results are presented to illustrate the proposed methodology.

CORRELATION AND PREDICTION OF LIQUID DIFFUSION COEFFICIENTS IN BINARY SYSTEMS

A theoretical model to correlate and predict the liquid diffusion coefficients in binary sys-tems has been developed.Based on this mode1 the diffusion coefficient of 73 binary systems have beencorrelated,the overall average deviation of the correlation for diffusion coefficients is 0.009.Forbinary systems the diffusion coefficients have been predicted from vapor liquid phase equilibrium(VLE)and vice versa.

Temporal-spatial Distribution and Short-range Prediction Indicators of Hail Weather in East Central Haixi Prefecture of Qinghai Province

[ Objective] The study aimed to discuss the temporal-spatial distribution and short-range prediction indicators of hail weather in east central Haixi Prefecture of Qinghai Province. [Method] Using hail data of six stations in east central Haixi Prefecture from 1960 to 2010, the temporal and spatial distribution of hail weather was analyzed firstly. Afterwards, based on the high-altitude factual data of 30 case studies of hail during 2006 -2010, its high-altitude and ground weather situation and physical quantity field were studied to summarize short-term circulation pattern and shod- range prediction characteristics of hail weather. [ Result] In east central Haixi, hail appeared from April to September, and it was most frequently from May to August. Meanwhile, hail was frequent from 14：00 to 20：00. Among the six stations, hail was most frequent in Tianjun but least frequent in Wulan. Moreover, hail disaster mainly occurred in Wulan and Tianjun. In addition, there were three typos of circulation pattern of hail weather at 500 hPa. Hail mainly occurred under the effect of northwest airflow, and it had shortwave trough, cold center or trough, jet stream core or one of the three. Hail appeared frequently under the situation of upper-level divergence and low-level convergence, and abundant water vapor and water vapor flux convergence at low levels were important conditions for hailing. [ Conclusion] The research could provide scientific references for improving the accuracy of hail forecast.

Sensory Data Prediction Using Spatiotemporal Correlation and LSTM Recurrent Neural Network

The Wireless Sensor Networks(WSNs)are widely utilized in various industrial and environmental monitoring applications.The process of data gathering within the WSN is significant in terms of reporting the environmental data.However,it might occur that certain sensor node malfunctions due to the energy draining out or unexpected damage.Therefore,the collected data may become inaccurate or incomplete.Focusing on the spatiotemporal correlation among sensor nodes,this paper proposes a novel algorithm to predict the value of the missing or inaccurate data and predict the future data in replacement of certain nonfunctional sensor nodes.The Long-Short-Term-Memory Recurrent Neural Network(LSTM RNN)helps to more accurately derive the time-series data corresponding to the sets of past collected data,making the prediction results more reliable.It is observed from the simulation results that the proposed algorithm provides an outstanding data gathering efficiency while ensuring the data accuracy.

Improved Correlations for Prediction of Viscosity of Iranian Crude Oils

Empirical equations for predicting the viscosity of Iranian crude oils above, at and below the bub-ble-point pressure were developed based on pressure-volume-temperature(PVT) data of 57 bottom hole samples collected from central, southern and offshore oil fields of Iran. Both statistical and graphical techniques were employed to evaluate these equations compared with other empirical correlations. The results show that the developed correlations present better accuracy and performance for predicting the viscosity of Iranian crude oils than those correlations in literature.

Correlation and Prediction of the Solubility of Solid Solutes in Chemically Diverse Supercritical Fluids Based on the Expanded Liquid Theory

For the proper design of any extraction procedure based on supercritical solvents, it is essential to have a sound knowledge of the solubility data of different compounds and the accurate way to represent it. The solute’s solubility in a supercritical solvent is dependent on the solute, the solvent, and the operating conditions (temperature and pressure). Developing a comprehensive experimental data set is an onerous task and time consuming and, thus, the incentive to develop predictive tools is substantial. In this paper, a technique is presented and tested to correlate and predict solute’s solubility in different supercritical fluids with a methodology based on the expanded liquid theory, in which the solid-fluid equilibrium is modeled using the local composition model of UNIQUAC in which the interaction parameters are related to the solvent reduced density with empiric equations. The most advantages of this model include: it does not require the knowledge of critical properties and sublimation pressure of solid solutes and does take into account the binary interaction between solid solute and solvent. The evaluation of the proposed model capabilities is done by testing it on a large data base consisting of experimental solubility data taken from literature of 33 binary systems solid-SC fluid. The results obtained for both correlation and prediction show good agreement with the experimental data used. For the comparison we have considered some literature models that account for effect of the system conditions (temperature and pressure) in addition to the sublimation pressure of the solute through their introduction of the enhancement factor and a model based on a modified Peng-Robinson equation of state.

The Meteorological Prediction Model of Lemon Production in Anyue County Based on Correlation

Using the meteorological data during 1971- 2013 and lemon growth and yield data during 2003- 2013 in Anyue,the suitability problem of lemon growth and correlation problem between meteorological factors and lemon growth in Anyue area were studied. According to relevance between the selected meteorological factors and yield of lemon,meteorological prediction model of lemon yield was established in Anyue,and the prediction accuracy was higher. The research had certain guiding significance for management work of lemon production in Anyue area.

Spatiotemporal Prediction of Urban Traffics Based on Deep GNN

Traffic prediction already plays a significant role in applications like traffic planning and urban management,but it is still difficult to capture the highly non-linear and complicated spatiotemporal correlations of traffic data.As well as to fulfil both long-termand short-termprediction objectives,a better representation of the temporal dependency and global spatial correlation of traffic data is needed.In order to do this,the Spatiotemporal Graph Neural Network(S-GNN)is proposed in this research as amethod for traffic prediction.The S-GNN simultaneously accepts various traffic data as inputs and investigates the non-linear correlations between the variables.In terms of modelling,the road network is initially represented as a spatiotemporal directed graph,with the features of the samples at the time step being captured by a convolution module.In order to assign varying attention weights to various adjacent area nodes of the target node,the adjacent areas information of nodes in the road network is then aggregated using a graph network.The data is output using a fully connected layer at the end.The findings show that S-GNN can improve short-and long-term traffic prediction accuracy to a greater extent;in comparison to the control model,the RMSE of S-GNN is reduced by about 0.571 to 9.288 and the MAE(Mean Absolute Error)by about 0.314 to 7.678.The experimental results on two real datasets,Pe MSD7(M)and PEMS-BAY,also support this claim.

Preliminary research on the relationship between long-range correlations and predictability

By establishing the Markov model for a long-range correlated time series （LRCS） and analysing its evolutionary characteristics, this paper defines a physical effective correlation length （ECL） T, which reflects the predictability of the LRCS. It also finds that the ECL has a better power law relation with the long-range correlated exponent γ of the LRCS： T = Kexp（-γ/0.3） ＋ Y, （0 〈 γ〈 1） the predictability of the LRCS decays exponentially with the increase of γ It is then applied to a daily maximum temperature series （DMTS） recorded at 740 stations in China between the years 1960-2005 and calculates the ECL of the DMTS. The results show the remarkable regional distributive feature that the ECL is about 10-14 days in west, northwest and northern China, and about 5-10 days in east, southeast and southern China. Namely, the predictability of the DMTS is higher in central-west China than in east and southeast China. In addition, the ECL is reduced by 1-8 days in most areas of China after subtracting the seasonal oscillation signal of the DMTS from its original DMTS; however, it is only slightly altered when the decadal linear trend is removed from the original DMTS. Therefore, it is shown that seasonal oscillation is a significant component of daily maximum temperature evolution and may provide a basis for predicting daily maximum temperatures. Seasonal oscillation is also significant for guiding general weather predictions, as well as seasonal weather predictions.

Adaptive spatial-temporal graph attention network for traffic speed prediction

Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.

Nonlinearly correlated failure analysis and autonomic prediction for distributed systems

In order to achieve failure prediction without manual intervention for distributed systems, a novel failure feature analysis and extraction approach to automate failure prediction is proposed. Compared with the traditional methods which focus on building heuristic rules or models, the autonomic prediction approach analyzes the nonlinear correlation of failure features by recognizing failure patterns. Failure data are sorted according to the nonlinear correlation and failure signature is proposed for autonomic prediction. In addition, the Manifold Learning algorithm named supervised locally linear embedding is applied to achieve feature extraction. Based on the runtime monitoring of failure metrics, the experimental results indicate that the proposed method has better performance in terms of both correlation recognition precision and feature extraction quality and thus it can be used to design efficient autonomic failure prediction for distributed systems.

Employment of predictive search algorithm in digital image correlation

A predictive search algorithm to estimate the size and direction of displacement vectors was presented.The algorithm decreased the time of calculating the displacement of each pixel.In addition,the updating reference image scheme was used to update the reference image and to decrease the computation time when the displacement was larger than a certain number.In this way,the search range and computational complexity were cut down,and less EMS memory was occupied.The capability of proposed search algorithm was then verified by the results of both computer simulation and experiments.The results showed that the algorithm could improve the efficiency of correlation method and satisfy the accuracy requirement for practical displacement measuring.

A Note on Some Methods Suitable for Verifying and Correcting the Prediction of Climatic Anomaly

The weighted correlation coefficient of the predicted and observed anomalies and the ratio of the weighted norm of predicted anomaly to the observed one, both together, are suggested to be suitable for the estimating of the correctness of climate prediction. The former shows the similarity of the two patterns, and the later indicates the correctness of the predicted intensity of the anomaly. The weighting function can be different for different emphasis, for example, a constant weight means that the correlation coefficient is the conventional one, but some non-uniform weight leads to the ratio of correct sign of the anomaly, the stepwise weight leads to the formulation of correctness of prediction represented by grades of the anomaly, and so on. Three methods for making correction to the prediction are given in this paper. After subtracting the mean error of the prediction, one method is developed for maximizing the similarity between the predicted and observed patterns, based on the transformation of the spatial coordinates. Another method is to minimize the mean difference between the two fields. This method can also be simplified as similar to the 'optimum interpolation' in the objective analysis of weather chart. The third method is based on the expansion of the anomaly into series of EOF, where the coefficients are the predicted but the EOFs are taken as the 'observed' calculated from historical samples.

Prediction of chlorophyll a concentration using HJ-1 satellite imagery for Xiangxi Bay in Three Gorges Reservoir

Since the impoundment of the Three Gorges Reservoir in 2003, algal blooms have frequently been observed in it. The chlorophyll a concentration is an important parameter for evaluating algal blooms. In this study, the chlorophyll a concentration in Xiangxi Bay, in the Three Gorges Reservoir, was predicted using HJ-1 satellite imagery. Several models were established based on a correlation analysis between in situ measurements of the chlorophyll a concentration and the values obtained from satellite images of the study area from January 2010 to December 2011. Chlorophyll a concentrations in Xiangxi Bay were predicted based on the established models. The results show that the maximum correlation is between the reflectance of the band combination of B4/（B2＋B3） and in situ measurements of chlorophyll a concentration. The root mean square errors of the predicted values using the linear and quadratic models are 18.49 mg/m3 and 18.52 mg/m3, respectively, and the average relative errors are 37.79% and 36.79%, respectively. The results provide a reference for water bloom prediction in typical tributaries of the Three Gorges Reservoir and contribute to large-scale remote sensing monitoring and water quality management.

A precise tidal prediction mechanism based on the combination of harmonic analysis and adaptive network-based fuzzy inference system model

An efficient and accurate prediction of a precise tidal level in estuaries and coastal areas is indispensable for the management and decision-making of human activity in the field wok of marine engineering. The variation of the tidal level is a time-varying process. The time-varying factors including interference from the external environment that cause the change of tides are fairly complicated. Furthermore, tidal variations are affected not only by periodic movement of celestial bodies but also by time-varying interference from the external environment. Consequently, for the efficient and precise tidal level prediction, a neuro-fuzzy hybrid technology based on the combination of harmonic analysis and adaptive network-based fuzzy inference system（ANFIS）model is utilized to construct a precise tidal level prediction system, which takes both advantages of the harmonic analysis method and the ANFIS network. The proposed prediction model is composed of two modules： the astronomical tide module caused by celestial bodies’ movement and the non-astronomical tide module caused by various meteorological and other environmental factors. To generate a fuzzy inference system（FIS） structure,three approaches which include grid partition（GP）, fuzzy c-means（FCM） and sub-clustering（SC） are used in the ANFIS network constructing process. Furthermore, to obtain the optimal ANFIS based prediction model, large numbers of simulation experiments are implemented for each FIS generating approach. In this tidal prediction study, the optimal ANFIS model is used to predict the non-astronomical tide module, while the conventional harmonic analysis model is used to predict the astronomical tide module. The final prediction result is performed by combining the estimation outputs of the harmonious analysis model and the optimal ANFIS model. To demonstrate the applicability and capability of the proposed novel prediction model, measured tidal level samples of Fort Pulaski tidal station are selected as the testing database. Simulation and experimental results confirm that the proposed prediction approach can achieve precise predictions for the tidal level with high accuracy, satisfactory convergence and stability.

Short-term Wind Speed Prediction with a Two-layer Attention-based LSTM

Wind speed prediction is of great importance because it affects the efficiency and stability of power systems with a high proportion of wind power.Temporal-spatial wind speed features contain rich information;however,their use to predict wind speed remains one of the most challenging and less studied areas.This paper investigates the problem of predicting wind speeds for multiple sites using temporal and spatial features and proposes a novel two-layer attentionbased long short-term memory(LSTM),termed 2Attn-LSTM,a unified framework of encoder and decoder mechanisms to handle temporal-spatial wind speed data.To eliminate the unevenness of the original wind speed,we initially decompose the preprocessing data into IMF components by variational mode decomposition(VMD).Then,it encodes the spatial features of IMF components at the bottom of the model and decodes the temporal features to obtain each component's predicted value on the second layer.Finally,we obtain the ultimate prediction value after denormalization and superposition.We have performed extensive experiments for short-term predictions on real-world data,demonstrating that 2Attn-LSTM outperforms the four baseline methods.It is worth pointing out that the presented 2Atts-LSTM is a general model suitable for other spatial-temporal features.

Statistical simulation analysis of the correlation between the annual estimated key regions with a certain seismic risk and the earthquakes in China

We have analyzed the correlation of the annual key regions with a certain seismic risk and the earthquakes in China from 1990-1997 by the statistical simulation analysis method. The statistical simulation analysis method is effective to deal with space-time heterogeneity of earthquakes and risk regions, the values of simulating random prediction probability have been got after 105 count, the objective results have been got by comparing average probability between the simulating prediction and the practical prediction. The results show: (1) average probability of the practical prediction for the annual seismic key risk regions in China from 1990-1997 is higher than that of the simulating prediction by 0.037 19 using the method of pure random simulating risk regions; (2) average probability of the practical prediction is higher than that of the simulation prediction by 0.021 83 using the method of simulating risk regions with the different probability based on the earthquake activity; (3) average probability of the practical prediction is much higher than that of the simulating prediction by 0.209 62 in West Xinjiang region using the method of dividing the Chinese Continent into the three regions: West Xinjiang region, Southwest region of China and the other region.

A Spectrum Prediction-Based Frequency Band Pre-Selection over Deteriorating HF Electromagnetic Environment

As the earliest invented and utilized communication approach, shortwave, known as high frequency(HF) communication now experience the deterioration of HF electromagnetic environment. Finding quality frequency in efficient manner becomes one of the key challenges in HF communication. Spectrum prediction infers the future spectrum status from history spectrum data by exploring the inherent correlations and regularities. The investigation of HF electromagnetic environment data reveals the correlations and predictability of HF frequency band in both time and frequency domain. To solve this problem, we develop a Spectrum Prediction-based Frequency Band Pre-selection(SP-FBP) for HF communications. The pre-selection of HF frequency band mainly incorporated in prediction of HF spectrum occupancy and prediction of HF usable frequency, which provide the frequency band ranking of spectrum occupancy and alternative frequency for spectrum sensing, respectively. Performance evaluation via real-world HF spectrum data shows that SP-FBP significantly improves the efficiency of finding quality frequency in HF communications.

A Correlation Tracking Algorithm Based on Template Partition Motion Estimation

A correlation tracking algorithm based on template partition motion estimation proposed for improving real time performance of the conventional correlation matching algorithms. The target trajectory fitted using the least square with equal space in whole interval and the target prediction point is found out. According to the requirements of block motion estimation(BME) algorithm,the template divided into some macro blocks. The searching process is conducted by using diamond search algorithm around the prediction point and the optimal motion vector of each block is calculated. A point corresponding to the motion vector with the best matching is taken as a rough matching point of the template. The relation of relative position between the block with matching point and the searching area determined to decide whether to conduct precise matching search or to construct a new search area in the gradient direction. The target tracking experiment results show that over 70% time cost can be reduced caompared with the conventional correlation matching algorithm based on full search method.