Chip-scale spontaneous quasi-phase matched second harmonic generation in a micro-racetrack resonator

In this paper,we demonstrate efficient spontaneous quasi-phase matched(SQPM)second harmonic generation(SHG)in a microracetrack resonator on X-cut thin film lithium niobate.Our approach does not involve poling,but exploits the anisotropy of the crystals to allow the phase-matching condition to be fulfilled spontaneously as the TE-polarized light circulates in a specifically designed racetrack resonator.In experiment,normalized on-chip conversion efficiencies of 1.01×10-4/W and 0.43×10-4/W are achieved by 37th-order and 111th-order SQPM,respectively.The configurable SQPM will benefit the application of nonlinear frequency conversion and quantum source generation in chip-scale integrated photonics compatible with standard CMOS fabrication processes.

Heparin-binding protein as a predictor of mortality in patients with diabetes mellitus and community-acquired pneumonia in intensive care unit:a propensity score matched study

BACKGROUND:Patients with diabetes mellitus(DM)are vulnerable to community-acquired pneumonia(CAP),which have a high mortality rate.We aimed to investigate the value of heparin-binding protein(HBP)as a prognostic marker of mortality in patients with DM and CAP.METHODS:This retrospective study included CAP patients who were tested for HBP at intensive care unit(ICU)admission from January 2019 to April 2020.Patients were allocated to the DM or non-DM group and paired with propensity score matching.Baseline characteristics and clinical outcomes up to 90 days were evaluated.The primary outcome was the 10-day mortality.Receiver operating characteristic(ROC)curves,Kaplan-Meier analysis,and Cox regression were used for statistical analysis.RESULTS:Among 152 enrolled patients,60 pairs were successfully matched.There was no significant difference in 10-day mortality,while more patients in the DM group died within 28 d(P=0.024)and 90 d(P=0.008).In the DM group,HBP levels at ICU admission were higher in 10-day non-survivors than in 10-day survivors(median 182.21[IQR:55.43-300]ng/ml vs.median 66.40[IQR:34.13-107.85]ng/mL,P=0.019),and HBP levels could predict the 10-day mortality with an area under the ROC curve of 0.747.The cut-off value,sensitivity,and specificity were 160.6 ng/mL,66.7%,and 90.2%,respectively.Multivariate Cox regression analysis indicated that HBP was an independent prognostic factor for 10-day(HR 7.196,95%CI:1.596-32.455,P=0.01),28-day(HR 4.381,95%CI:1.449-13.245,P=0.009),and 90-day mortality(HR 4.581,95%CI:1.637-12.819,P=0.004)in patients with DM.CONCLUSION:Plasma HBP at ICU admission was associated with the 10-day,28-day,and 90-day mortality,and might be a prognostic factor in patients with DM and CAP.

Robotic versus laparoscopic distal pancreatectomy for pancreatic ductal adenocarcinoma: A propensity score-matched analysis

Background: Minimally invasive surgery is becoming increasingly popular in the field of pancreatic surgery. However, there are few studies of robotic distal pancreatectomy(RDP) for pancreatic ductal adenocarcinoma(PDAC). This study aimed to investigate the efficacy and feasibility of RDP for PDAC. Methods: Patients who underwent RDP or laparoscopic distal pancreatectomy(LDP) for PDAC between January 2015 and September 2020 were reviewed. Propensity score matching analyses were performed. Results: Of the 335 patients included in the study, 24 underwent RDP and 311 underwent LDP. A total of 21 RDP patients were matched 1:1 with LDP patients. RDP was associated with longer operative time(209.7 vs. 163.2 min;P = 0.003), lower open conversion rate(0% vs. 4.8%;P < 0.001), higher cost(15 722 vs. 12 699 dollars;P = 0.003), and a higher rate of achievement of an R0 resection margin(90.5% vs. 61.9%;P = 0.042). However, postoperative pancreatic fistula grade B or C showed no significant intergroup difference(9.5% vs. 9.5%). The median disease-free survival(34.5 vs. 17.3 months;P = 0.588) and overall survival(37.7 vs. 21.9 months;P = 0.171) were comparable between the groups. Conclusions: RDP is associated with longer operative time, a higher cost of surgery, and a higher likelihood of achieving R0 margins than LDP.

Laparoscopic liver resection for hepatocellular carcinoma complicated with significant portal hypertension:A propensity score-matched survival analysis

Background: Significant portal hypertension(SPH) is a relative contraindication for patients with resectable hepatocellular carcinoma(HCC). However, increasing evidence indicates that liver resection is feasible for HCC patients with SPH. Methods: HCC patients with cirrhosis who underwent laparoscopic liver resection(LLR) in two centers from January 2013 to April 2018 were included. Surgical and survival outcomes were analyzed to explore potential prognostic factors. Propensity score matching(PSM) analysis was performed to minimize bias. Results: A total of 165 patients were divided into two groups based on the presence(SPH, n = 76) or absence(non-SPH, n = 89) of SPH. Patients in the SPH group had longer operative time, more blood loss, and more advanced TNM stage than patients in the non-SPH group( P < 0.05). However, there were no significant differences in the postoperative 90-day mortality rate( n = 0), overall postoperative complications(47.4% vs. 41.6%, P = 0.455), Clavien-Dindo classification( P = 0.347), conversion to open surgery(9.2% vs. 6.7%, P = 0.557), or length of hospitalization(16 vs. 15 days, P = 0.203) between the SPH and non-SPH groups before PSM. Similar results were obtained after PSM. The 1-, 3-, and 5-year overall survival(OS) and recurrence-free survival rates in the SPH group were not significantly different from those in the non-SPH group both before and after PSM(log-rank P > 0.05). After PSM, alpha-fetoprotein(AFP) ≥ 400 μg/L [hazard ratio(HR) = 4.71, 95% confidence interval(CI): 2.69-8.25], ascites(HR = 2.18, 95% CI: 1.30-3.66), American Society of Anesthesiologists(ASA) classification(Ⅲ vs. Ⅱ)(HR = 2.13, 95% CI: 1.11-4.07) and tumor diameter > 5 cm(HR = 3.91, 95% CI: 2.02-7.56) independently predicted worse OS. Conclusions: LLR for patients with HCC complicated with SPH appears feasible at the price of increasing operative time and blood loss. AFP, ascites, ASA classification and tumor diameter may predict the prognosis of HCC complicated with SPH after LLR.

Sustainable Lignin-Derived Carbon as Capacity-Kinetics Matched Cathode and Anode towards 4.5 V High-Performance Lithium-Ion Capacitors

The Li-ion capacitors(LICs)develop rapidly due to their double-high features of high-energy density and high-power density.However,the relative low capacity of cathode and sluggish kinetics of anode seriously impede the development of LICs.Herein,the precisely pore-engineered and heteroatomtailored defective hierarchical porous carbons(DHPCs)as large-capacity cathode and high-rate anode to construct high-performance dual-carbon LICs have been developed.The DHPCs are prepared based on triple-activation mechanisms by direct pyrolysis of sustainable lignin with urea to generate the interconnected hierarchical porous structure and plentiful heteroatominduced defects.Benefiting from these advanced merits,DHPCs show the well-matched high capacity and fast kinetics of both cathode and anode,exhibiting large capacities,superior rate capability and long-term lifespan.Both experimental and computational results demonstrate the strong synergistic effect of pore and dopants for Li storage.Consequently,the assembled dual-carbon LIC exhibits high voltage of 4.5 V,high-energy density of 208 Wh kg^(−1),ultrahigh power density of 53.4 kW kg^(−1)and almost zerodecrement cycling lifetime.Impressively,the full device with high mass loading of 9.4 mg cm^(−2)on cathode still outputs high-energy density of 187 Wh kg^(−1),demonstrative of their potential as electrode materials for high-performance electrochemical devices.

A 15-year-Long catalog of seismicity in the Eastern Tennessee Seismic Zone(ETSZ)using matched filter detection

We present a detailed catalog of 13671 earthquakes in the Eastern Tennessee Seismic Zone(ETSZ)that spans January 1,2005 to July 31,2020.We apply a matched filter detection technique on over 15 years of continuous data,resulting in arguably the most complete catalog of seismicity in the ETSZ yet.The magnitudes of newly detected events are determined by computing the amplitude ratio between the detections and templates using a principal component fit.We also compute the b-value for the new catalog and comparatively relocate a subset of newly detected events using XCORLOC and hypoDD,which shows a more defined structure at depth.We find the greatest concentration along and to the east of the New York-Alabama Lineament,as defined by the magnetic anomaly,supporting the argument that this feature likely is related to the generation of seismicity in the ETSZ.We examine seismicity in the vicinity of the Watts Bar Reservoir,which is located about 5 km from the epicenter of the M_(W) 4.4 December 12,2018 Decatur,Tennessee earthquake,and find possible evidence for reservoir modulated seismicity in this region.We also examine seismicity in the entire ETSZ to search for a correlation between shallow earthquakes and seasonal hydrologic changes.Our results show limited evidence for hydrologicallydriven shallow seismicity due to seasonal groundwater levels in the ETSZ,which contradicts previous studies hypothesizing that most intraplate earthquakes are associated with the dynamics of hydrologic cycles.

Quasi-Phase Equilibrium Prediction of Multi-Element Alloys Based on Machine Learning and Deep Learning

In this study,a phase field model is established to simulate the microstructure formation during the solidification of dendrites by taking the Al-Cu-Mg ternary alloy as an example,and machine learning and deep learning methods are combined with the Kim-Kim-Suzuki(KKS)phase field model to predict the quasi-phase equilibrium.The paper first uses the least squares method to obtain the required data and then applies eight machine learning methods and five deep learning methods to train the quasi-phase equilibrium prediction models.After obtaining different models,this paper compares the reliability of the established models by using the test data and uses two evaluation criteria to analyze the performance of these models.This work find that the performance of the established deep learning models is generally better than that of the machine learning models,and the Multilayer Perceptron(MLP)based quasi-phase equilibrium prediction model achieves the best performance.Meanwhile the Convolutional Neural Network(CNN)based model also achieves competitive results.The experimental results show that the model proposed in this paper can predict the quasi-phase equilibrium of the KKS phase-field model accurately,which proves that it is feasible to combine machine learning and deep learning methods with phase-field model simulation.

Catheter ablation versus medical therapy for atrial fibrillation with prior stroke history:a prospective propensity score-matched cohort study

BACKGROUND Patients with atrial fibrillation(AF)and prior stroke history have a high risk of cardiovascular events despite anticoagulation therapy.It is unclear whether catheter ablation(CA)has further benefits in these patients.METHODS AF patients with a previous history of stroke or systemic embolism(SE)from the prospective Chinese Atrial Fibrillation Registry study between August 2011 and December 2020 were included in the analysis.Patients were matched in a 1:1 ratio to CA or medical treatment(MT)based on propensity score.The primary outcome was a composite of all-cause death or ischemic stroke(IS)/SE.RESULTS During a total of 4.1±2.3 years of follow-up,the primary outcome occurred in 111 patients in the CA group(3.3 per 100 person-years)and in 229 patients in the MT group(5.7 per 100 person-years).The CA group had a lower risk of the primary outcome compared to the MT group[hazard ratio(HR)=0.59,95%CI:0.47–0.74,P<0.001].There was a significant decreasing risk of all-cause mortality(HR=0.43,95%CI:0.31–0.61,P<0.001),IS/SE(HR=0.73,95%CI:0.54–0.97,P=0.033),cardiovascular mortality(HR=0.32,95%CI:0.19–0.54,P<0.001)and AF recurrence(HR=0.33,95%CI:0.30–0.37,P<0.001)in the CA group compared to that in the MT group.Sensitivity analysis generated consistent results when adjusting for time-dependent usage of anticoagulants.CONCLUSIONS In AF patients with a prior stroke history,CA was associated with a lower combined risk of all-cause death or IS/SE.Further clinical trials are warranted to confirm the benefits of CA in these patients.

Different roles of surfaces’ interaction on lattice mismatched/matched surfaces in facilitating ice nucleation

The freezing of water is one of the most common processes in nature and affects many aspects of human activity. Ice nucleation is a crucial part of the freezing process and usually occurs on material surfaces. There is still a lack of clear physical pictures about the central question how various features of material surfaces affect their capability in facilitating ice nucleation. Via molecular dynamics simulations, here we show that the detailed features of surfaces, such as atomic arrangements, lattice parameters, hydrophobicity, and function forms of surfaces’ interaction to water molecules, generally affect the ice nucleation through the average adsorption energy per unit-area surfaces to individual water molecules, when the lattice of surfaces mismatches that of ice. However, for the surfaces whose lattice matches ice, even the detailed function form of the surfaces’ interaction to water molecules can largely regulate the icing ability of these surfaces. This study provides new insights into understanding the diverse relationship between various microscopic features of different material surfaces and their nucleation efficacy.

Finite-difference modeling of Maxwell viscoelastic media developed from perfectly matched layer

In numerical simulation of wave propagation,both viscoelastic materials and perfectly matched layers(PMLs)attenuate waves.The wave equations for both the viscoelastic model and the PML contain convolution operators.However,convolution operator is intractable in finite-difference time-domain(FDTD)method.A great deal of progress has been made in using time stepping instead of convolution in FDTD.To incorporate PML into viscoelastic media,more memory variables need to be introduced,which increases the code complexity and computation costs.By modifying the nonsplitting PML formulation,I propose a viscoelastic model,which can be used as a viscoelastic material and/or a PML just by adjusting the parameters.The proposed viscoelastic model is essentially equivalent to a Maxwell model.Compared with existing PML methods,the proposed method requires less memory and its implementation in existing finite-difference codes is much easier.The attenuation and phase velocity of P-and S-waves are frequency independent in the viscoelastic model if the related quality factors(Q)are greater than 10.The numerical examples show that the method is stable for materials with high absorption(Q=1),and for heterogeneous media with large contrast of acoustic impedance and large contrast of viscosity.

Stability of Perfectly Matched Layers for Time Fractional Schrödinger Equation

It is an important issue to numerically solve the time fractional Schrödinger equation on unbounded domains, which models the dynamics of optical solitons propagating via optical fibers. The perfectly matched layer approach is applied to truncate the unbounded physical domain, and obtain an initial boundary value problem on a bounded computational domain, which can be efficiently solved by the finite difference method. The stability of the reduced initial boundary value problem is rigorously analyzed. Some numerical results are presented to illustrate the accuracy and feasibility of the perfectly matched layer approach. According to these examples, the absorption parameters and the width of the absorption layer will affect the absorption effect. The larger the absorption width, the better the absorption effect. There is an optimal absorption parameter, the absorption effect is the best.

Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features

Road traffic monitoring is an imperative topic widely discussed among researchers.Systems used to monitor traffic frequently rely on cameras mounted on bridges or roadsides.However,aerial images provide the flexibility to use mobile platforms to detect the location and motion of the vehicle over a larger area.To this end,different models have shown the ability to recognize and track vehicles.However,these methods are not mature enough to produce accurate results in complex road scenes.Therefore,this paper presents an algorithm that combines state-of-the-art techniques for identifying and tracking vehicles in conjunction with image bursts.The extracted frames were converted to grayscale,followed by the application of a georeferencing algorithm to embed coordinate information into the images.The masking technique eliminated irrelevant data and reduced the computational cost of the overall monitoring system.Next,Sobel edge detection combined with Canny edge detection and Hough line transform has been applied for noise reduction.After preprocessing,the blob detection algorithm helped detect the vehicles.Vehicles of varying sizes have been detected by implementing a dynamic thresholding scheme.Detection was done on the first image of every burst.Then,to track vehicles,the model of each vehicle was made to find its matches in the succeeding images using the template matching algorithm.To further improve the tracking accuracy by incorporating motion information,Scale Invariant Feature Transform(SIFT)features have been used to find the best possible match among multiple matches.An accuracy rate of 87%for detection and 80%accuracy for tracking in the A1 Motorway Netherland dataset has been achieved.For the Vehicle Aerial Imaging from Drone(VAID)dataset,an accuracy rate of 86%for detection and 78%accuracy for tracking has been achieved.

Histogram Matched Chest X-Rays Based Tuberculosis Detection Using CNN

Tuberculosis(TB)is a severe infection that mostly affects the lungs and kills millions of people’s lives every year.Tuberculosis can be diagnosed using chest X-rays(CXR)and data-driven deep learning(DL)approaches.Because of its better automated feature extraction capability,convolutional neural net-works(CNNs)trained on natural images are particularly effective in image cate-gorization.A combination of 3001 normal and 3001 TB CXR images was gathered for this study from different accessible public datasets.Ten different deep CNNs(Resnet50,Resnet101,Resnet152,InceptionV3,VGG16,VGG19,DenseNet121,DenseNet169,DenseNet201,MobileNet)are trained and tested for identifying TB and normal cases.This study presents a deep CNN approach based on histogram matched CXR images that does not require object segmenta-tion of interest,and this coupled methodology of histogram matching with the CXRs improves the accuracy and detection performance of CNN models for TB detection.Furthermore,this research contains two separate experiments that used CXR images with and without histogram matching to classify TB and non-TB CXRs using deep CNNs.It was able to accurately detect TB from CXR images using pre-processing,data augmentation,and deep CNN models.Without histogram matching the best accuracy,sensitivity,specificity,precision and F1-score in the detection of TB using CXR images among ten models are 99.25%,99.48%,99.52%,99.48%and 99.22%respectively.With histogram matching the best accuracy,sensitivity,specificity,precision and F1-score are 99.58%,99.82%,99.67%,99.65%and 99.56%respectively.The proposed meth-odology,which has cutting-edge performance,will be useful in computer-assisted TB diagnosis and aids in minimizing irregularities in TB detection in developing countries.

A Portfolio Selection Method Based on Pattern Matching with Dual Information of Direction and Distance

Pattern matching method is one of the classic classifications of existing online portfolio selection strategies. This article aims to study the key aspects of this method—measurement of similarity and selection of similarity sets, and proposes a Portfolio Selection Method based on Pattern Matching with Dual Information of Direction and Distance (PMDI). By studying different combination methods of indicators such as Euclidean distance, Chebyshev distance, and correlation coefficient, important information such as direction and distance in stock historical price information is extracted, thereby filtering out the similarity set required for pattern matching based investment portfolio selection algorithms. A large number of experiments conducted on two datasets of real stock markets have shown that PMDI outperforms other algorithms in balancing income and risk. Therefore, it is suitable for the financial environment in the real world.

Feature Matching via Topology-Aware Graph Interaction Model

Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.

Multiple Matching Attenuation Based on Curvelet Domain Extended Filtering

The paper develops a multiple matching attenuation method based on extended filtering in the curvelet domain,which combines the traditional Wiener filtering method with the matching attenuation method in curvelet domain.Firstly,the method uses the predicted multiple data to generate the Hilbert transform records,time derivative records and time derivative records of Hilbert transform.Then,the above records are transformed into the curvelet domain and multiple matching attenuation based on least squares extended filtering is performed.Finally,the attenuation results are transformed back into the time-space domain.Tests on the model data and field data show that the method proposed in the paper effectively suppress the multiples while preserving the primaries well.Furthermore,it has higher accuracy in eliminating multiple reflections,which is more suitable for the multiple attenuation tasks in the areas with complex structures compared to the time-space domain extended filtering method and the conventional curvelet transform method.

Perfect 1-k Matchings of Bipartite Graphs

Let k be a positive integer and G a bipartite graph with bipartition (X,Y). A perfect 1-k matching is an edge subset M of G such that each vertex in Y is incident with exactly one edge in M and each vertex in X is incident with exactly k edges in M. A perfect 1-k matching is an optimal semi-matching related to the load-balancing problem, where a semi-matching is an edge subset M such that each vertex in Y is incident with exactly one edge in M, and a vertex in X can be incident with an arbitrary number of edges in M. In this paper, we give three sufficient and necessary conditions for the existence of perfect 1-k matchings and for the existence of 1-k matchings covering | X |−dvertices in X, respectively, and characterize k-elementary bipartite graph which is a graph such that the subgraph induced by all k-allowed edges is connected, where an edge is k-allowed if it is contained in a perfect 1-k matching.

A Non-Parametric Scheme for Identifying Data Characteristic Based on Curve Similarity Matching

For accurately identifying the distribution charac-teristic of Gaussian-like noises in unmanned aerial vehicle(UAV)state estimation,this paper proposes a non-parametric scheme based on curve similarity matching.In the framework of the pro-posed scheme,a Parzen window(kernel density estimation,KDE)method on sliding window technology is applied for roughly esti-mating the sample probability density,a precise data probability density function(PDF)model is constructed with the least square method on K-fold cross validation,and the testing result based on evaluation method is obtained based on some data characteristic analyses of curve shape,abruptness and symmetry.Some com-parison simulations with classical methods and UAV flight exper-iment shows that the proposed scheme has higher recognition accuracy than classical methods for some kinds of Gaussian-like data,which provides better reference for the design of Kalman filter(KF)in complex water environment.

Distributed Matching Theory-Based Task Re-Allocating for Heterogeneous Multi-UAV Edge Computing

Many efforts have been devoted to efficient task scheduling in Multi-Unmanned Aerial Vehicle(UAV)edge computing.However,the heterogeneity of UAV computation resource,and the task re-allocating between UAVs have not been fully considered yet.Moreover,most existing works neglect the fact that a task can only be executed on the UAV equipped with its desired service function(SF).In this backdrop,this paper formulates the task scheduling problem as a multi-objective task scheduling problem,which aims at maximizing the task execution success ratio while minimizing the average weighted sum of all tasks’completion time and energy consumption.Optimizing three coupled goals in a realtime manner with the dynamic arrival of tasks hinders us from adopting existing methods,like machine learning-based solutions that require a long training time and tremendous pre-knowledge about the task arrival process,or heuristic-based ones that usually incur a long decision-making time.To tackle this problem in a distributed manner,we establish a matching theory framework,in which three conflicting goals are treated as the preferences of tasks,SFs and UAVs.Then,a Distributed Matching Theory-based Re-allocating(DiMaToRe)algorithm is put forward.We formally proved that a stable matching can be achieved by our proposal.Extensive simulation results show that Di Ma To Re algorithm outperforms benchmark algorithms under diverse parameter settings and has good robustness.

A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.