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.

Correlation analysis between fault frequency and service time of underground fluid instruments

In this paper, we make a statistical analysis of the fault information of the underground fluid instruments of 12 models in China from January 2021 to May 2022 based on the Pearson correlation coefficient, and compare the fault statistics of the meteorological three-element instruments of 3 models during the study period. The results show that:(1) The numbers of faults of the underground fluid instruments of 12models with different service times are basically positively correlated with the numbers of the corresponding instruments, with good consistency. Moreover, the automatic observation instruments(8models) with more than 30 units are significantly correlated at a 0.05 significance level(95% confidence level). Even at a 0.01 significance level(99% confidence level), there are 7 models(7/8) with significant correlation.(2) The positive and negative correlations between the monthly average number of faults and the corresponding service times of the underground fluid instruments of 12 models with different service times are random, and there are 9 models(75%) with no significant correlation at a 0.05 significance level(95% confidence level), while 12 models(100%) with no significant correlation at a 0.01significance level(99% confidence level).(3) The monthly average numbers of faults of the underground fluid instruments of 12 models are basically 0.02-0.05 times/(unit·month), and the overall fault frequency is low.(4) The fault statistics results of the meteorological three-element instruments of 3 models are consistent with the characteristics of the underground fluid instruments of 12 models. In general,there is no significant correlation between the fault frequency and the service time of underground fluid instruments.(5) The results of this paper demonstrate that the service time of underground fluid instruments cannot be taken as the main reason for whether to update the instruments. Similarly, the fault frequency of the instruments cannot be taken as the main reason for the service life of the instruments in the process of formulating the service life standards of underground fluid instruments.

Correlation Analysis of Turbidity and Total Phosphorus in Water Quality Monitoring Data

At present,water pollution has become an important factor affecting and restricting national and regional economic development.Total phosphorus is one of the main sources of water pollution and eutrophication,so the prediction of total phosphorus in water quality has good research significance.This paper selects the total phosphorus and turbidity data for analysis by crawling the data of the water quality monitoring platform.By constructing the attribute object mapping relationship,the correlation between the two indicators was analyzed and used to predict the future data.Firstly,the monthly mean and daily mean concentrations of total phosphorus and turbidity outliers were calculated after cleaning,and the correlation between them was analyzed.Secondly,the correlation coefficients of different times and frequencies were used to predict the values for the next five days,and the data trend was predicted by python visualization.Finally,the real value was compared with the predicted value data,and the results showed that the correlation between total phosphorus and turbidity was useful in predicting the water quality.

Correlation analysis of mental health conditions and personality of patients with alcohol addiction

BACKGROUND Alcohol addiction,or alcohol dependence,refers to a psychological state of strong craving for alcohol caused by drinking when both the drinking times and alcohol consumption reach a certain level.Alcohol addiction can cause irreversible damage,leading to mental illness or mental disorders,negative changes in their original personality,and a tendency to safety incidents such as committing suicide or violent attacks on others.Significant attention needs to be given to the mental health of alcohol addicts,which could reflect their abnormal personality traits.However,only a few papers on this issue have been reported in China.AIM To investigate the correlation between mental health and personality in patients with alcohol addiction.METHODS In this single-center observational study,we selected 80 patients with alcohol addiction as the research subjects,according to the criteria of the K10 scale to evaluate the mental health of patients with alcohol addiction,and divided these patients into four groups based on the evaluation results:Good,average,relatively poor and bad.And then analyzed the correlation between mental health conditions and personality characteristics from these four groups of patients.RESULTS The average score of the K10 scale(Kessler 10 Simple Psychological Status Assessment Scale)in 80 patients with alcohol addiction was 25.45 points,the median score was 25 points,the highest score was 50 points,and the lowest score was 11 points.Pearson's analysis showed that the K10 score was positively correlated with the scores of these two subscales,such as the P-subscale and the N-subscale(P<0.05).In contrast,the K10 score had no significant correlation with the scores from the E-subscale and the L-subscale(P>0.05).CONCLUSION The mental health conditions of patients with alcohol addiction are positively correlated with their personality characteristics.

Prediction of land subsidence caused by groundwater exploitation in Hanoi, Vietnam, using multifactorial correlation analysis

Multifactorial correlation analysis is a new method used to predict the land subsidence caused by groundwater exploitation This article introduces and applies the method to establish the function of the surface settlement rate （Vs） and the function of the time-dependent surface settlement （St） caused by groundwater exploitation, based on data acquired at three land subsidence monitoring stations in the Hanoi area of Vietnam. Comparison with actual monitoring data indicates that the prediction results are relatively close to the monitoring data. From this, we conclude that multifactorial correlation analysis is a reliable method and can be used to predict future land subsidence caused by groundwater exploitation in Hanoi.

Reliability assessment and correlation analysis of evaluating orthodontic treatment outcome in Chinese patients

This study aimed to assess the reliability of experienced Chinese orthodontists in evaluating treatment outcome and to determine the correlations between three diagnostic information sources. Sixty-nine experienced Chinese orthodontic specialists each evaluated the outcome of orthodontic treatment of 108 Chinese patients. Three different information sources： study casts （SC）, lateral cephalometric X-ray images （LX） and facial photographs （PH） were generated at the end of treatment for 108 patients selected randomly from six orthodontic treatment centers throughout China. Six different assessments of treatment outcome were made by each orthodontist using data from the three information sources separately and in combination. Each assessment included both ranking and grading for each patient. The rankings of each of the 69 judges for the 108 patients were correlated with the rankings of each of the other judges yielding 13 873 Spearman rs values, ranging from -0.08 to ＋0.85. Of these, 90% were greater than 0.4, showing moderate-to-high consistency among the 69 orthodontists. In the combined evaluations, study casts were the most significant predictive component （R2=0.86, P〈0.000 1）, while the inclusion of lateral cephalometric films and facial photographs also contributed to a more comprehensive assessment （R2=0.96, P〈0.000 1）. Grading scores for SC＋LX and SC＋PH were highly significantly correlated with those for SC＋LX＋PH （r（SC＋LX）vs.（SC＋LX＋PH）=0.96, r（SC＋PH）vs.（SC＋LX＋PH）=0.97）, showing that either SC＋LX or SC＋PH is an excellent substitute for all three combined assessment,

Correlation analysis of the North Equatorial Current bifurcation and the Indonesian Throughflow

Based on monthly mean Simple Ocean Data Assimilation （SODA） products from 1958 to 2007, this study analyzes the seasonal and interannual variability of the North Equatorial Current （NEC） bifurcation latitude and the Indonesian Throughflow （ITF） volume transport. Further, Empirical Mode Decomposition （EMD） method and lag-correlation analysis are employed to reveal the relationships between the NEC bifurcation location, NEC and ITF volume transport and ENSO events. The analysis results of the seasonal variability show that the annual mean location of NEC bifurcation in upper layer occurs at 14.33°N and ITF volume transport has a maximum value in summer, a minimum value in winter and an annual mean transport of 7.75×10^6 m^3/s. The interannual variability analysis indicates that the variability of NEC bifurcation location can be treated as a precursor of El Nino. The correlation coefficient between the two reaches the maximum of 0.53 with a time lag of 2 months. The ITF volume transport is positively related with E1 Nifio events with a maximum coefficient of 0.60 by 3 months. The NEC bifurcation location is positively correlated with the ITF volume transport with a correlation coefficient of 0.43.

Genetic Variation Analysis, Correlation Analysis and Principal Component Analysis on Agronomic Traits of Summer Sowing Soybean (Glycine max Merr.) in Huang-Huai-Hai Region

Genetic variation analysis, correlation analysis and principal component analysis were conducted to investigate the relationship between 12 yield-related agronomic traits of 87 summer sowing soybean eultivars in Huang-Huai-Hai region. According to the experimental results, effective branch number showed the maxi- mum variation coefficient and growth duration showed the minimum variation coefficient. The variation coefficient of bottom pod height, pod number per plant, grain number per plant, grain weight per plant and 100-grain weight of semi-determinate summer sowing soybean ranged between 18.38% -27.56. The variation coeffi- eient of plant height, bottom pod height, pod number per plant, grain number per plant and grain weight per plant of determinate summer sowing soybean ranged from 21.02% to 8.04%. In semi-determinate summer sowing soybean, yield showed extremely significantly positive correlation with grain number per pod, grain weight per plant and 100-grain weight, but extremely significantly negative correlation with effective branch number and significantly negative correlation with growth duration. In determinate summer sowing soybean, yidd showed extremely significantly positive correlation with stem diameter but significantly positive correlation with bottom pod height, while it showed no significant correlation with other agronomic traits. Principal component analysis of yield-rdated agronomic traits showed that cumulative contribution rates of the former four principal components to the variation of seml-determinate and determinate summer sowing soybean were 79.92% and 79.50%, respectively. Agronomic traits with the greatest variation should be selected first. Semi-determinate and determinate summer sowing soybean individu- als in Huang-Hnai-Hai region should be selected according to different podding habits. In addition, semi-determlnate soybean varieties with moderate plant height and growth duration, fewer effective branches, more grains per pod and greater 100-grain weight should be selected; determinate soybean varieties with thicker stem diameter, higher plant height and bottom pod height, more nodes on main stem, fewer grains per pod, more pods per plant and grains per plant should be selected.

The Grey Correlation Analysis on the Relationship between the Rural Finance and the Rural Economical Growth in Sichuan Province

This paper analyzes the relationship between rural finance and the rural economy of Sichuan Province from 1999 to 2009 by using the sequential growth rate of the gross value of farming, forestry, animal husbandry and fishery and the sequential growth rate of the per capital total income of rural households as the indicators of rural economic development; and taking the volume of deposit, volume of credit, volume of agricultural credit and the credit volume of township enterprises as the indicators of rural financial development; as well as the method of grey correlation analysis. The results show that there is an obvious positive correlation between them, and the development of country finance has the closest connection with the sequential growth rate of farming, forestry, animal husbandry, sideline production and fishery. The loan scale of township enterprises has the biggest influence on the increase of the rural economy. The countermeasures are put forward, covering optimizing investment structure; supporting the development of township enterprises; encouraging loan; actively lightening the financial difficulties in the process of developing rural economy; innovating and exploring; and promoting the diversified development of rural finance.

Study on soil water characteristics of tobacco fields based on canonical correlation analysis

In order to identify the principal factors influencing soil water characteristics （SWC） and evaluate SWC effectively, the multivariate-statistical canonical correlation analysis （CCA） method was used to study and analyze the correlation between SWC and soil physical and chemical properties. Twenty-two soil samples were taken from 11 main tobacco-growing areas in Guizhou Province in China and the soil water characteristic curves （SWCC） and basic physical and chemical properties of the soil samples were determined. The results show that： （1） The soil bulk density, soil total porosity and soil capillary porosity have significant effects on SWC of tobacco fiels. Bulk density and total porosity are positively correlated with soil water retention characteristics （SWRC）, and soil capillary porosity is positively correlated with soil water supply characteristics （SWSC）. （2） Soil samples from different soil layers at the same soil sampling point show similarity or consistency in SWC. Inadequate soil water supply capability and imbalance between SWRC and SWSC are problems of tobacco soil. （3） The SWC of loamy clay are generally superior to those of silty clay loam.

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.

Correlation analysis of national elite Chinese male table tennis players’ shoulder proprioception and muscle strength

BACKGROUND Shoulder is the most injured part in table tennis players,and it takes multiple roles in transmitting power and striking the center of the ball during the stroke.Proprioception is strongly correlated with high level of athletic performance.It is customary to assume that there is a correlation between proprioception and muscle strength and therefore proprioceptive assessment and rehabilitation is often neglected.AIM To investigate the correlation between isokinetic muscle strength and proprioception in the internal and external rotation muscle groups of elite Chinese male table tennis players,to provide reference for physical training and rehabilitation of elite table tennis players.METHODS A total of 19 national elite table tennis players from the Chinese National Table Tennis Team were recruited in this research.All of them had more than 10 years training experience and had participated major competitions such as the National Games and World Youth Championships.IsoMed 2000 was used to test the peak torque of internal and external rotation isokinetic concentric contraction of the athletes'bilateral shoulder joints at low speed(60°/s)and high speed(180°/s)respectively;IsoMed 2000 was used to conduct the Joint Position Reproduction test to evaluate the athletes'proprioceptive ability capacity at low speed(60°/s)and high speed(180°/s)respectively.If the data satisfied the normal distribution,the correlation between the differences in peak torque s and angles in different directions was analyzed using a Pearson simple linear model;otherwise,Spearman correlation analysis was used.The comparison of proprioceptive ability between the table tennis racket-holding hand and non-racket-holding hands was performed using independent samples t-test if the data satisfied a normal distribution;otherwise,the Mann-Whitney U test was used.RESULTS There was no direct linear correlation between the strength and proprioceptive correlation analysis at slow speed(60°/s)and fast speed(180°/s)in the racket-holding hand;At the slow speed(60°/s)and fast speed(180°/s),there was no correlation between muscle strength and proprioception in the non-racket-holding hand except for the internal rotation variable error(VE)and external rotation relative peak torque,which showed a moderate positive correlation(r=0.477,P<0.05),(r=0.554,P<0.05).The internal rotation’s constant error(CE)and VE were 1.06±3.99 and 2.94±2.16,respectively,for the racket-holding hand,and-3.36±2.39 and 1.22±0.93,respectively,for the non-racket-holding hand;the internal rotation’s CE,VE of the racket-holding hand was lower than that of the non-racket-holding hand,and there was a highly significant difference(P<0.01).CONCLUSION There was no correlation between muscle strength and proprioceptive function in the internal and external rotation of the racket-holding hand’s shoulder in elite Chinese male table tennis players.These results may be useful for interventions for shoulder injuries and for the inclusion of proprioceptive training in rehabilitation programs.

Novel DDoS Feature Representation Model Combining Deep Belief Network and Canonical Correlation Analysis

Distributed denial of service(DDoS)attacks launch more and more frequently and are more destructive.Feature representation as an important part of DDoS defense technology directly affects the efficiency of defense.Most DDoS feature extraction methods cannot fully utilize the information of the original data,resulting in the extracted features losing useful features.In this paper,a DDoS feature representation method based on deep belief network(DBN)is proposed.We quantify the original data by the size of the network flows,the distribution of IP addresses and ports,and the diversity of packet sizes of different protocols and train the DBN in an unsupervised manner by these quantified values.Two feedforward neural networks(FFNN)are initialized by the trained deep belief network,and one of the feedforward neural networks continues to be trained in a supervised manner.The canonical correlation analysis(CCA)method is used to fuse the features extracted by two feedforward neural networks per layer.Experiments show that compared with other methods,the proposed method can extract better features.

Comprehensive Evaluation of Flood and Flood in the Yellow River Basin Based on Gray Correlation Analysis

Due to the concentrated rainfall and serious soil erosion in July and August in the Yellow River Basin, the flood discharge is not timely leading to serious floods. Therefore, a reasonable assessment of the flood-affected areas, advance arrangements for the deployment of the Yellow River basin flood disaster prevention and control plays a decisive role. For this purpose, this paper proposes a level assessment method based on the flood which analyzes three factors related to flooding disaster (disaster impact range, social index, and property index) through the gray correlation analysis method, to evaluate the level of flood disaster. Different from the traditional assessment method, which evaluates the nature of flood from the perspective of indicators such as frequency, duration, and magnitude, or indirect factors such as rainfall and soil loss, this paper conducts qualitative calculation of macro-scale indicators from the perspective of post-disaster losses in previous years. This study provides a new way of thinking and method for the classification of the flood disaster, which has certain practical application value under the condition of conforming to its own use.

Dual-parameter Correlation Analysis of the Fluorescence Data of 1-Methyl-2-formyl-5-substituted Pyrrole(4-nitrophenyl)hydrazones

By using 1-methyl-2-formyl-5 -Y-substituted pyrrole (4-nitrophenyl)hydrazones as a model for nitrogen-containing heterocyclic aromatic compounds, the emission wavelength [lambda(max(em))] values df their fluorescence spectra have been measured. Correlation results show that the Delta E-em values are mainly affected by polar effects, but spin-delocalizatin effects also exist.

Dual-parameter Correlation Analysis of the Redox Potential Data of 1-Methyl-2-formyl-5-substituted Pyrroles and their Hydrazones

By using 1-methyl-2-formyl-5-substituted pyrroles (1-Y), 1-methyl-2-formyl-5-substituted pyrrole phenylhydrazones (2-Y) and 1-methyl-2-formyl-5-substituted pyrrole (4-nitrophenyl)-hydrazones (3-Y) as model structures for nitrogen-containing heterocyclic aromatic compounds, correlation analysis of their redox potential data show that the transition states (TS) of the polarographic process are mainly affected by the polar effects, but spin-delocalizatin effects also exist.

Average Incremental Correlation Analysis Model and Its Application in Fault Diagnosis

The concept of average incremental correlation degree is put forward.It has been proved that the average incremental correlation model has such properties as parallelism,consistency,affine,affine transformation isotonicity and interference factors independence,and it will not lead to changes of the sequence order relation because of the data transformation.Therefore,the new model keeps good stability.Finally,the incremental average correlation model is applied to failure model analysis of equipment,and an ideal diagnostic effect is obtained.

Identification the Motion Error of Machine Tool Based on the Correlation Analysis

Machine tool has been widely used in the production of the military and civilian.The machining precision of the workpiece is the direct reflection for the machining performance of machine tool.With the improvement for requirement of the machining precision,improving the accuracy of machining is becoming important.Guideway and spindle are the key motion components that decided the shape,the relative position and the surface roughness of the workpiece.In order to adapt to the requirements of the workpiece machining,this paper analyzes the errors of guideway and spindle that affect the accuracy of the processing,establishes the motion relations for every errors of guideway in machining process,identifies the regular for the straightness,bending of the guideway and rotating error of spindle that influences the workpiece surface.Finally,according to the correlation analysis of the measured and the simulation results,the motion error of machine tool is identified,which lays the foundation for improving the accuracy of machine tool in next step.

SPATIAL REGULARIZATION OF CANONICAL CORRELATION ANALYSIS FOR LOW-RESOLUTION FACE RECOGNITION

Canonical correlation analysis ( CCA ) based methods for low-resolution ( LR ) face recognition involve face images with different resolutions ( or multi-resolutions ), i.e.LR and high-resolution ( HR ) .For single-resolution face recognition , researchers have shown that utilizing spatial information is beneficial to improving the recognition accuracy , mainly because the pixels of each face are not independent but spatially correlated.However , for a multi-resolution scenario , there are no related works.Therefore , a method named spatial regularization of canonical correlation analysis ( SRCCA ) is developed for LR face recognition to improve the performance of CCA by the regularization utilizing spatial information of different resolution faces.Furthermore , the impact of LR and HR spatial regularization terms on LR face recognition is analyzed through experiments.

Correlation Analysis of Energy Consumption of Agricultural Rotorcraft

With the rapid development of unmanned aerial vehicle technology,unmanned aerial vehicles(UAVs)have been widely used in the field of agricultural plant protection.Compared with fuel-driven UAVs,electrically driven rotorcrafts have many advantages such as lower cost,simpler operation,good maneuverability and cleaner power,which them popular in the plant protection.However,electrical rotorcrafts still face battery problems in actual operation,which limits its working time and application.Aiming at this issue,this paper studied the influence of rotorcraft flight parameters on energy consumption through series of carefully designed flight experiments.First of all,the linear motion experiments have been designed that the rotorcraft was made to perform speed tests and acceleration test with the speed varied from 2∼9 m/s.Secondly,the turning maneuver experiments are carried out under the different circular routes,a rotorcraft was made to conduct successive steering maneuvers at a certain speed of 2 m/s.With the collected tests data,the relation of the energy consumption and the flight dynamic parameter are analyzed through correlation analysis,and the test results of different pairs of experiments have been compared.The research results of this paper would encourage the agricultural rotorcraft to make less maneuvers during operation,which can also provide practical experience and data support for subsequent optimization of flight parameters and reduction of energy consumption.