• <tr id="yyy80"></tr>
  • <sup id="yyy80"></sup>
  • <tfoot id="yyy80"><noscript id="yyy80"></noscript></tfoot>
  • 99热精品在线国产_美女午夜性视频免费_国产精品国产高清国产av_av欧美777_自拍偷自拍亚洲精品老妇_亚洲熟女精品中文字幕_www日本黄色视频网_国产精品野战在线观看 ?

    Modeling of Artificial Intelligence Based Traffic Flow Prediction with Weather Conditions

    2022-08-24 03:31:30MesferAlDuhayyimAmaniAbdulrahmanAlbraikanFahdAlWesabiHibaBurburMohammadAlamgeerAnwerMustafaHilalManarAhmedHamzaandMohammedRizwanullah
    Computers Materials&Continua 2022年5期

    Mesfer Al Duhayyim,Amani Abdulrahman Albraikan,F(xiàn)ahd N.Al-Wesabi,Hiba M.Burbur,Mohammad Alamgeer,Anwer Mustafa Hilal,Manar Ahmed Hamza,*and Mohammed Rizwanullah

    1Department of Natural and Applied Sciences,College of Community-Aflaj,Prince Sattam Bin Abdulaziz University,Al-Kharj,16278,Saudi Arabia

    2Department of Information Systems,College of Computer and Information Sciences,Princess Nourah Bint Abdulrahman University,Riyadh,11564,Saudi Arabia

    3Department of Computer Science,College of Science&Arts at Mahayil,King Khalid University,Muhayel Aseer,62529,Saudi Arabia

    4Faculty of Computer and IT,Sana’a University,Sana’a,61101,Yemen

    5Department of Computer Science,College of Science and Arts in Al-Bukairiyah,Qassim University,Al-Bukairiyah,52571,Saudi Arabia

    6Department of Information Systems,College of Science&Arts at Mahayil,King Khalid University,Muhayel Aseer,62529,Saudi Arabia

    7Department of Computer and Self Development,Preparatory Year Deanship,Prince Sattam Bin Abdulaziz University,Al-Kharj,16278,Saudi Arabia

    Abstract: Short-term traffic flow prediction (TFP) is an important area in intelligent transportation system (ITS), which is used to reduce traffic congestion.But the avail of traffic flow data with temporal features and periodic features are susceptible to weather conditions, making TFP a challenging issue.TFP process are significantly influenced by several factors like accident and weather.Particularly, the inclement weather conditions may have an extreme impact on travel time and traffic flow.Since most of the existing TFP techniques do not consider the impact of weather conditions on the TF,it is needed to develop effective TFP with the consideration of extreme weather conditions.In this view,this paper designs an artificial intelligence based TFP with weather conditions(AITFP-WC)for smart cities.The goal of the AITFPWC model is to enhance the performance of the TFP model with the inclusion of weather related conditions.The proposed AITFP-WC technique includes Elman neural network (ENN) model to predict the flow of traffic in smart cities.Besides, tunicate swarm algorithm with feed forward neural networks(TSA-FFNN)model is employed for the weather and periodicity analysis.At last,a fusion of TFP and WPA processes takes place using the FFNN model to determine the final prediction output.In order to assess the enhanced predictive outcome of the AITFP-WC model,an extensive simulation analysis is carried out.The experimental values highlighted the enhanced performance of the AITFP-WC technique over the recent state of art methods.

    Keywords: Smart cities; artificial intelligence; urban transportation; deep learning;weather condition;TFP

    1 Introduction

    A survey reported that, in 2050, the global urban population is expected to attain 66% or 70%correspondingly.This upsurge in urbanization would have severe impact on cities’management,security, and the environment.To effectively manage the meteoric growth in urbanization, several countries have projected the idea of smart cities to efficiently handle the resources and enhance energy utilization.The smart cities project could accurately handle the green environment by adopting and developing lower carbon emission techniques.Several countries(like Japan,US,EU,and so on.)all over the world have projected and realized the smart cities project for definitively accomplishing the future problems.For meeting the needs of a smart city, effective usage of information and communication technologies(ICTs)are essential[1]for sufficiently manage the data communications,data analyses,and efficient execution of complicated approaches for ensuring the secure and smooth operations of a smart city.

    The IoT is the most significant and important component of the smart city applications that are accountable for producing large number of data [2].In the existence of amount of complex and big data,it is complex to accurately determine the most effective and accurate performances.The optimum analyses of the big data could be executed by an innovative method such as Deep Reinforcement Learning(DRL),Artificial intelligence(AI),and Machine learning(ML),for reaching an optimum decision.The previous technique considers a long-term objective and could lead to an optimal or near optimum control decision[3].The precision and accuracy of the above-mentioned methods could be enhanced further by increasing the number of training data to reinforce their learning abilities and thus the automatic decision efficacies.In [4], the researchers have displayed that the idea of smart cities realization and the utilization of innovative data analyses techniques for Big Data has increased nearly in the same years.The idea of IoT,smart cities,unmanned aerial vehicles(UAVs),Blockchain,and the utilization of DRL,AI,&ML based methods in several applications are yet in the evolution stage and eventually will provide better chances.

    The growth of intelligent transportation systems(ITS)needs a higher degree of carrying capacity as an assurance [5].Due to their high capacity and flexibility, vehicles are the main resources of transportation.Assuring traffic performance would have a significant effect on operation of the city.But,with the constant surge of vehicle ownership,the inadequate carrying capability of urban roads has slowed down the traffic performance of vehicles.Timely and accurate predictions of traffic flow(TF)give consistent basis of traffic control for governors and provide suitable travel guidance for the tourists thus enhancing road network and decrease traffic congestion[6].But,traffic prediction is a nonlinear and sophisticated challenge.In reality, TF has clear periodicity and temporal correlation,however,it might develop in an irregular manner under the disturbance of weather modifications that creates this problem more complex.The present short-term TFP methods could be generally separated into three classifications:DL,statistical modules,and conventional ML methods.

    Related to the statistical models, conventional ML approaches such as SVM and SVR shows powerful function fitting capability in nonlinear and complex TFP problem.The fundamental concept of this type of technique is to convert lower dimension and linearly inseparable traffic data to higher dimension and linearly separable expression via kernel function.With the development of traffic big data [7], short-term traffic prediction has to turn into more complex and challenging that propose higher needs for modelling data.DL modules,with the efficiency for higher dimension space modelling and the capability for extracting features of variables via hierarchical depiction, have turn into the popular technology of TFP.[8] proposed a short-term multistep freeway TFP method using RBF where center position of hidden layer is established by the fuzzy c-means clustering.[9]initially utilized SAE for learning the depiction of TF features for predicting.

    This paper introduces a novel artificial intelligence (AI) based TFP with weather conditions(AITFP-WC) for smart cities.The AITFP-WC model focuses on the improvement of the predictive performance of the TF with the consideration of weather related conditions.The proposed AITFPWC technique involves Elman neural network (ENN) model for TFP in smart cities.In addition,tunicate swarm algorithm with feed forward neural networks(TSA-FFNN)model is utilized for the weather and periodicity analysis.Furthermore,a fusion of TFP and WPA processes takes place using the FFNN model to determine the final prediction output.For examining the increased prediction performance of the AITFP-WC model,a series of experiments were carried out on TF and weather data.

    2 Existing Traffic Flow Prediction Models

    Lu et al.[10],proposed an integrated predictive technique for short term TF that relies on LSTMNN and ARIMA.This technique can create short-term predictions of upcoming TF depends on the past traffic data.Initially,the LR feature of traffic data was taken by the rolling regression ARIMA module;later,BP was utilized for training the LSTM network to take nonlinear features of traffic data;and lastly,relies on the dynamic weighting of sliding window integrated the predictive influences of this 2 methods.Kong et al.[11]take RBM as the technique for predicting TF that is a usual process relies on DL framework.RBM creates the long-term module of polymorphic for chaotic time sequence,with phase space recreation for recognizing the data.

    Hou et al.[12] proposed an integrated structure of SAE and RBF NN for predicting TF that could efficiently capture the disturbance of weather factors and periodicity of TF and data temporal correlation.Initially,SAE is utilized for processing the TF data in many time slices for acquiring early predictions.Later, RBF is utilized for capturing the relation among periodicity of TF and weather disturbance thus gaining other predictions.Lastly,alternative RBF is utilized for combining the above 2 predictions on decision level,obtain a recreated prediction with high precision.

    Zheng et al.[13]focused on the short term TF predictive problems on the basis of real time traffic data as one crucial module of a smart cities.In contradiction of long term traffic prediction,precise prediction of short term TF facilitate rapid response and timely traffic management.They developed and studied a new EM on the basis of LSTM, DAE, and CNN modules.This method considered spatial&temporal features of the traffic condition.In Rajendran et al.[14],the structural patterns of TF could be pinched from freeway toll data accordingly,a novel predictive module has been projected.Locally weighted learning is utilized for predicting the subsequent sample TF of current sector and the succeeding station entrance flow.This learning module places nonlinear and linear modules for fitting the adjacent points and later employs this value for predicting query point values.

    Kang et al.[15],proposed a hybrid module for spatio temporal feature extraction and prediction of urban road network travel time that integrates EDM and CN with an XGBoost predictive module.Because of the dynamic nature and high nonlinear travel time sequence,it is essential for considering time reliance and spatial dependence of travel time sequence to predict the travel time of road network.The dynamic feature of travel time sequence could be exposed through the EDM technique, a nonlinear technique is depending upon Chaos concept.In Raza et al.[16], GA is utilized for designing ANN and LWR modules.This proposed method is based on the integration of GA,NN,and LWR for achieving optimum predictive efficiency in several traffic and input conditions.The GA aimed ANN(GA-ANN)and GA aimed LWR(GA-LWR)disaggregate and aggregate modules are utilized for predicting short term traffic(five minutes)for 4 lanes of urban road in Beijing,China.

    3 Problem Statement and Data Used

    This section offers the detailed problem statement of this study and also explained the data(including traffic and weather data)employed for validation.

    3.1 Problem Statement

    TFP model makes use of existing traffic and weather-related parameters to estimate the output flow in any succeeding time slices.The outcomeyof the predictive technique is defined using Eq.(1):

    It is considered that the TF data is not limited only to the regularity and again affected by other weather conditions, the input variables of the model want to comprise external weather conditions.Here,Xidenotes the dataset on the time slicei, counting flow, time expression, vector depiction of embeddingxembedding,and weather variables;Xiis defined by

    whereyflowsignifies the flow prediction depending upon the traffic series data andyweather×ignifies the flow prediction depending upon the weather as well as time periodicity[17].By the view of decision level data fusion, the end flow prediction value is the fusion value of two decisions, therefore the outcomeyof the integrated model can be defined using Eq.(3):

    For multistep prediction,ycan be defined asyi,andiindicates the step size.

    3.2 Traffic and Weather Data

    The traffic dataset of metro freeway in the Twin Cities is used[17].The actual dataset is gathered at a 30 s duration of at least 4,500 loop detectors.During the preprocessing level, the data gets preprocessed in the form of table with 5 mts duration.In addition, time similarity measure is used to correct the errors and omissions.For revealing the periodicity of traffic data under weather disturbances,a time-flow correlation is derived.Besides,the training data gets partitioned into working and non-working days,and the average flow in each time slice is calculated.The time flow correlation for the time slices can be represented in Eq.(4):

    wheresignifies the flow of time sliceion dayj.

    Next, the weather dataset [17] is collected and used 1-hot coding technique to handle the nonnumerical parameters.Besides,an embedding element is employed for extracting the expression of high dimensional data of weather type.In addition, the embedding vector of weather type is represented using Eq.(5):

    wherexembeddingdenotes the trained embedded vector of weather types, whereasxonerepresents 1-hot expression.For variable selection related to TF,Pearson correlation coefficientρis determined using Eq.(6)is calculated,whereXandYdenotes a set of 2 target parameters.

    To extract the additional weather variables,the PCA technique can be employed for the data fusion process at the feature level.The actual matrixAof weather variables can be denoted as follows:

    wherexDB,xRH,xVis,xWB,andxWSare the designated variables.Once the PCA is employed,the resultant matrixPcan be produced as shown below.

    wherexpcais the fusion value of the elected weather variables examined by PCA.

    4 The Proposed Model

    The overall framework of the proposed AITFP-WC technique encompasses three major levels namely ENN based TFP,TSA-FFNN based WSA,and fusion process.Fig.1 demonstrates the overall process of TFP process.The detailed working of every level is offered in the next subsections.

    Figure 1:Systematic framework of TFP in smart cities

    4.1 Level I:TFP

    At the first level, the AITFP-WC technique exploits the ENN model to forecast TF.The ENN model is employed for the extraction of temporal correlation exist in the TF.Fig.2 shows a simple structure of an ENN.The ENN model comprises four major layers namely input,context,hidden,and output layers.The major configuration of the ENN model is similar to the FFNN in such a way that the connections except context layer are identical to MLP.The context layer receives the input from the output of the hidden layer to store the earlier values of the hidden layer.The external input,context weight,and output weight matrices can be represented asWhi,Whc,Wh0,respectively.The dimensions of the input and output layers aren,i.e.,,y(t)=[y1(t),y2(t),...,yn(t)]Tand the dimension of the context layer ism.

    Figure 2:Structure of ENN

    The input layer of the ENN model is defined in Eq.(9):

    whereldemonstrates the input and the output layers in roundl.Afterward,the kth hidden layer in the network can be represented using Eq.(10):

    where,xcj(l)defines the signal which is passed from the kth context layer node,(l)designates the ith and jth weights of the hidden layers directed fromothnode[18].At last,the outcome of the hidden layer can be fed into the context layer is given below:

    represents the normalized value of the hidden layer.

    The following layer is the context layer,which can be defined as follows.

    where,Wkpointed out the gain of self linked feedback among 0 and 1.Lastly,the output layer at the network can be represented below.

    where,defines the weights of the connections from the kth layer into theothlayer.

    4.2 Level II:Weather and Periodicity Analysis

    In the second level,the WPA is performed using the TSA-FFNN technique,which makes use of processed variables comprising xembedding,xtimecode,and xpca,therefore,the TSA-FFNN function is denoted as follows.

    The FFNN is an easier type of ANN that includes many processing modules called “neurons”.In FFNN,the data takes stimulated in single way,forwards from the input to output through hidden layer.It doesn’t comprise some loop or cycle[19].All individual neurons define the entire input weight and approved the sum through activation functions and so the result is obtained.It can be determined as Eqs.(16)and(17):

    where iwj,irepresents the weights related amongst the weight neuronsi= (1,2,...,R) andj= (1,2,...,N), hbjimplies the bias in hidden layers,Rindicates the neuron count in the input layers,andxjdenotes the respective input data.During this case,the S shaped curved sigmoid functions are utilized as activation functions as determined in Eq.(17):

    Therefore,the result of neurons in the hidden layers are determined as:

    In the final layer,the result of neurons are signified as:

    where hwj,irefers the weights interconnected amongst neuronsj= (1,2,...,N)andk= (1,2,...,S),obkstands for bias in final layer,Nrefers the neuron quantity in hidden layers,andSdefines the neuron quantity in hidden layers.Usually,the training technique is carried out for modifying the weight and bias values till the maximal classification accuracy was gained.

    In order to effectually adjust the parameters involved in the FFNN model,the TSA is employed.The motivation and scientific modeling of presented TSA technique are explained in detail.Tunicate has capability for finding the place of feed source in sea.But there is no knowledge about the feed source in the provided search space.In TSA, 2 performances of tunicates are utilized to determine the feed source and they are jet propulsion and SI.In order to scientifically process the jet propulsion performance, the tunicate can fulfill 3 situations such as avoid the fights amongst searching agents,movement near the place of optimum searching agents,and remained nearby the optimum searching agents.While the swarm performance upgrades the places of another search agent on the optimum solution[20].The mathematical process of the performance is explained in the following.

    For avoiding the fights amongst searching agents (for instance, another tunicate), vector →Ais utilized for the computation of novel search agent place as given below.

    wherePminandPmaxsignifies the primary and subordinate speeds for making social interface.In this work,of values ofPminandPmaxare considered as 1 and 4,correspondingly.

    Afterward,in order to avoid the fight amongst neighboring ones,the searching agents are travel near the direction of optimum neighbor.

    For mathematically simulating the swarm performance of tunicate, initial 2 optimum solutions are stored and upgraded the places of other searching agents based on the place of an optimum search agent.The subsequent equation is presented for defining the swarm performance of tunicate:

    The steps and flowchart presented are provided under.

    i.Initialization of the tunicate population

    ii.Select the primary variables and maximal iteration count.

    iii.Compute the fitness value of all searching agents.

    iv.Afterward calculating the fitness value, the optimum searching agent is traveled in provided searching area.

    v.Upgrade the place of all searching agents utilizing Eq.(26).

    vi.Alter the upgraded searching agent that drives away from the boundary in provided search space.

    vii.Calculate the upgraded searching agent fitness values.When there is an optimum solution compared to the preceding optimum solution,next upgradePp.

    viii.When the termination condition is fulfilled,next the TSA gets stopped.Then,repeat Steps 5–8.

    ix.Obtain optimum solutions.

    4.3 Level III:Decision Level Data Fusion Model

    The data fusion process takes place using FFNN model which aims to tune the features outcomes offered from the previous two modules.Since FFNN is a type of NN with easier architecture, it is not required to treat the hierarchical structure during modeling,and it could satisfy the need for data fusion in features as well as decision levels.The outcome of the fusion model is the end predictive results of the AITFP-WC model and it can be represented as follows.

    5 Results and Discussion

    This section validates the TFP performance of the AITFP-WC technique over other existing techniques.Tab.1 and Fig.3 demonstrates the results analysis of the AITFP-WC technique with other techniques on weather data.From the obtained results, it is evident that the AITFP-WC technique has attained improved predictive outcomes on the weather data.The experimental results ensured that the AITFP-WC technique has outperformed the existing techniques with the MAPE of 17.326%,MSE of 313.417, and RMSE of 17.704.At the same time, the least performance is obtained by the RBF+PCC+PCA+BP with the MAPE of 21.446%,MSE of 517.261,and RMSE of 22.743.

    Table 1:Performance comparison of recent methods with proposed methods on weather data

    Figure 3:MAPE and RMSE analysis of AITFP-WC technique on weather data

    Another comparison study of the AITFP-WC technique with baseline techniques is made in Tab.2 and Fig.4.From the obtained values, it is evident that the LSTM and GRU techniques have showcased inferior outcomes with the maximum MAPE of 11.341% and 11.896%.Followed by,the S.LSTM,S.GRU,SAE,and Fusion-ANN models have demonstrated moderate MAPE of 10.574%,10.628%,10.558%,and 10.537%respectively.In line with,the SAERBF technique has exhibited near optimal performance with the MAPE of 10.378%.However,the proposed AITFP-WC technique has demonstrated superior outcomes with the minimal MAPE of 10.280%.

    Table 2:Comparison study of AITFP-WC method with existing techniques

    Figure 4:Comparative MAPE and RMSE analysis of AITFP-WC technique with existing methods

    A brief TFP predictive performance of the AITFP-WC technique interms of MAPE take place in Tab.3 and Fig.5.The experimental results depicted that the AITFP-WC technique has offered effectual TFP outcomes under varying time intervals.For instance,with 5 min interval,the AITFP-WC technique has attained a lower MAPE of 10.28%whereas the LSTM,GRU,S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF techniques have depicted a higher MAPE of 11.34%,11.89%,10.57%,10.62%,10.55%,10.53%,and 10.37%respectively.Eventually,with 15 min interval,the AITFP-WC approach has attained a lesser MAPE of 12.64%whereas the LSTM,GRU,S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF manners have showcased a higher MAPE of 15.07%,15.29%,13.92%,13.75%,13.82%,13.26%,and 12.92%respectively.Meanwhile,with 30 min interval,the AITFP-WC technique has attained a minimum MAPE of 16.12% whereas the LSTM, GRU, S.LSTM, S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF algorithms have depicted a superior MAPE of 19.75%,19.62%,17.93%,17.64%,17.85%,16.20%and 16.12%correspondingly.

    Table 3:Result analysis of AITFP-WC model interms of MAPE

    Figure 5:MAPE analysis of AITFP-WC model with existing techniques

    A detailed TFP predictive performance of the AITFP-WC technique with respect to MSEtakes place in Tab.4 and Fig.6.The experimental outcomes showcased that the AITFP-WC approach has offered effective TFP outcomes under varying time intervals.For instance, with 5 min interval,the AITFP-WC manner has gained the least MSE of 149.25% whereas the LSTM, GRU, S.LSTM,S.GRU, SAE, FUSION-ANN, and SAERBF techniques have depicted a higher MSE of 166.77%,167.20%,155.60%,158.47%,162.25%,151.19%,and 151.15%respectively.Also,with 15 min interval,the AITFP-WC technique has attained a lower MSE of 207.48%whereas the LSTM,GRU,S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF methodologies have exhibited a higher MSE of 264.90%,263.18%,234.77%,236.78%,258.00%,213.09%,and 211.28%respectively.In the meantime,with 30 min interval, the AITFP-WC technique has attained a lower MSE of 328.43% whereas the LSTM,GRU,S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF methods have outperformed a higher MSE of 434.19%,434.89%,370.32%,369.00%,441.44%,326.71%,and 331.33%respectively.

    Table 4:Result analysis of AITFP-WC model interms of MSE

    Figure 6:MSE analysis of AITFP-WC model with existing techniques

    A brief TFP predictive performance of the AITFP-WC method interms of RMSE take place in Tab.5 and Fig.7.The experimental results outperformed that the AITFP-WC algorithm has offered effectual TFP outcomes under varying time intervals.For instance,with 5 min interval,the AITFPWC method has attained a minimum RMSE of 12.22%whereas the LSTM,GRU,S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF techniques have depicted a maximal RMSE of 12.91%,12.93%,12.47%, 12.59%, 12.74%, 12.30% and 12.29% correspondingly.Besides, with 15 min interval, the AITFP-WC approach has attained a lower RMSE of 14.40% whereas the LSTM, GRU, S.LSTM,S.GRU,SAE,F(xiàn)USION-ANN,and SAERBF techniques have depicted a superior RMSE of 16.28%,16.22%,15.32%,15.39%,16.06%,14.60%and 14.54%correspondingly.Likewise,with 30 min interval,the AITFP-WC manner has gained a lower RMSE of 18.12% whereas the LSTM, GRU, S.LSTM,S.GRU, SAE, FUSION-ANN, and SAERBF techniques have demonstrated a maximum RMSE of 20.84%,20.85%,19.24%,19.21%,21.01%,18.08%and 18.12%correspondingly.

    Table 5:Result analysis of AITFP-WC model interms of RMSE

    Figure 7:RMSE analysis of AITFP-WC model with existing techniques

    6 Conclusion

    In this study,a new AITFP-WC technique is designed to predict the flow of traffic with weather conditions in smart cities.The proposed AITFP-WC technique encompasses ENN based TFP,TSAFFNN based WSA,and FFNN based data fusion processes.In TSA-FFNN model,the TSA is used to optimally tune the parameters involved in the FFNN model and thereby raises the predictive performance to a maximum extent.For examining the increased prediction performance of the AITFP-WC model,a series of experiments were carried out on TF and weather data.The experimental values pointed out the supremacy of the AITFP-WC technique over the recent state of art methods.Therefore,the AITFP-WC technique can be used in real time smart city environment to predict the flow of traffic under extreme weather conditions.In future scope, the efficacy of the AITFP-WC technique can be boosted by the use of advanced DL architectures with learning rate scheduling approaches.

    Funding Statement:The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under grant number (RGP1/53/42), www.kku.e du.sa.This research was funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University through the Fast-track Research Funding Program.

    Conflicts of Interest:The authors declare that they have no conflicts of interest to report regarding the present study.

    欧美日本视频| 久久久久亚洲av毛片大全| av欧美777| 人人妻,人人澡人人爽秒播| 不卡一级毛片| 婷婷精品国产亚洲av| 午夜久久久久精精品| 国产精品美女特级片免费视频播放器 | 国产精品亚洲美女久久久| 三级男女做爰猛烈吃奶摸视频| 亚洲精品在线观看二区| or卡值多少钱| 三级毛片av免费| 亚洲人成网站高清观看| 婷婷精品国产亚洲av| 97人妻精品一区二区三区麻豆| 亚洲熟妇中文字幕五十中出| 成人午夜高清在线视频| x7x7x7水蜜桃| 人妻丰满熟妇av一区二区三区| 白带黄色成豆腐渣| 美女午夜性视频免费| 久久久精品欧美日韩精品| 给我免费播放毛片高清在线观看| 精品久久久久久久久久久久久| 国产伦在线观看视频一区| 亚洲电影在线观看av| 国产又色又爽无遮挡免费看| 欧美zozozo另类| 桃色一区二区三区在线观看| 中文资源天堂在线| 日韩欧美国产一区二区入口| av天堂在线播放| 日本三级黄在线观看| 免费看十八禁软件| 国产成人影院久久av| 国产高清有码在线观看视频| 国产精品久久视频播放| 日韩欧美在线二视频| 国产精品99久久久久久久久| 日韩精品青青久久久久久| 99精品欧美一区二区三区四区| 中亚洲国语对白在线视频| 99久久精品国产亚洲精品| 淫妇啪啪啪对白视频| 国产精品亚洲一级av第二区| 欧美黄色片欧美黄色片| 午夜福利视频1000在线观看| 国产精品一区二区免费欧美| 黄色成人免费大全| 日韩欧美一区二区三区在线观看| 日韩高清综合在线| 欧美另类亚洲清纯唯美| 色老头精品视频在线观看| 日韩成人在线观看一区二区三区| 亚洲av第一区精品v没综合| 欧美色欧美亚洲另类二区| 国产激情欧美一区二区| 麻豆久久精品国产亚洲av| 欧美黑人欧美精品刺激| 两性夫妻黄色片| 中文在线观看免费www的网站| 一二三四在线观看免费中文在| 村上凉子中文字幕在线| 狠狠狠狠99中文字幕| 国产单亲对白刺激| 黄色成人免费大全| 国产精品一区二区三区四区久久| 在线观看免费午夜福利视频| 一级毛片精品| 精品国产超薄肉色丝袜足j| 色老头精品视频在线观看| 亚洲欧美一区二区三区黑人| 黄频高清免费视频| 亚洲国产精品成人综合色| 在线观看午夜福利视频| 国产精品 国内视频| 真人一进一出gif抽搐免费| 日日干狠狠操夜夜爽| 午夜a级毛片| 国产野战对白在线观看| 在线观看一区二区三区| 色吧在线观看| 色综合站精品国产| 精品免费久久久久久久清纯| 最近最新免费中文字幕在线| 好男人在线观看高清免费视频| 国内精品久久久久久久电影| 校园春色视频在线观看| 国产高清三级在线| 国产熟女xx| 又黄又粗又硬又大视频| 色噜噜av男人的天堂激情| 欧美zozozo另类| 亚洲第一电影网av| 悠悠久久av| 国产一区二区激情短视频| 精品一区二区三区四区五区乱码| 岛国在线观看网站| 在线免费观看的www视频| 久久性视频一级片| 亚洲中文日韩欧美视频| 亚洲国产精品sss在线观看| 香蕉丝袜av| 波多野结衣巨乳人妻| 88av欧美| 久久久久久国产a免费观看| 我要搜黄色片| 久久久久国内视频| 亚洲国产色片| www国产在线视频色| 色综合欧美亚洲国产小说| 久久热在线av| 在线观看舔阴道视频| h日本视频在线播放| 此物有八面人人有两片| 黄色女人牲交| 偷拍熟女少妇极品色| 国产单亲对白刺激| 黑人巨大精品欧美一区二区mp4| 中文字幕人妻丝袜一区二区| 久久精品91无色码中文字幕| 国产精品电影一区二区三区| 91av网一区二区| 两个人视频免费观看高清| 99热这里只有精品一区 | av欧美777| 黄片大片在线免费观看| 久久久久久久久中文| 国产成人系列免费观看| 亚洲成av人片免费观看| 欧美日韩国产亚洲二区| 少妇丰满av| 久久精品91无色码中文字幕| 99久久99久久久精品蜜桃| www日本黄色视频网| 亚洲五月天丁香| 真实男女啪啪啪动态图| 欧美一区二区精品小视频在线| 午夜福利免费观看在线| 蜜桃久久精品国产亚洲av| 午夜两性在线视频| 最近视频中文字幕2019在线8| 久久久国产成人精品二区| 免费在线观看视频国产中文字幕亚洲| 99热只有精品国产| 久久精品91无色码中文字幕| 久久精品91蜜桃| 黄色 视频免费看| 国产精品九九99| 69av精品久久久久久| 国产高清videossex| 亚洲成av人片在线播放无| 国产三级在线视频| 久久中文字幕一级| 日本三级黄在线观看| 国产毛片a区久久久久| 久久天堂一区二区三区四区| 久久久久九九精品影院| 在线国产一区二区在线| 最好的美女福利视频网| 欧美在线一区亚洲| 日韩欧美在线二视频| 午夜福利在线观看免费完整高清在 | 国产成人精品无人区| 丝袜人妻中文字幕| 美女被艹到高潮喷水动态| 女同久久另类99精品国产91| 99国产综合亚洲精品| 国产美女午夜福利| 国产亚洲av高清不卡| 亚洲片人在线观看| 操出白浆在线播放| 校园春色视频在线观看| 又黄又爽又免费观看的视频| 精品国产美女av久久久久小说| 国产蜜桃级精品一区二区三区| 国产高清有码在线观看视频| 伦理电影免费视频| 亚洲真实伦在线观看| 亚洲狠狠婷婷综合久久图片| www.熟女人妻精品国产| 精品福利观看| av在线天堂中文字幕| 成年免费大片在线观看| 成年女人看的毛片在线观看| 床上黄色一级片| 精品午夜福利视频在线观看一区| 老司机在亚洲福利影院| 十八禁网站免费在线| 日韩高清综合在线| av片东京热男人的天堂| 高清在线国产一区| svipshipincom国产片| 欧美午夜高清在线| 亚洲九九香蕉| 成年女人毛片免费观看观看9| 久久草成人影院| 精品国内亚洲2022精品成人| 亚洲国产高清在线一区二区三| 麻豆久久精品国产亚洲av| 国产高潮美女av| 免费电影在线观看免费观看| 成人特级av手机在线观看| 亚洲七黄色美女视频| 日本撒尿小便嘘嘘汇集6| 国产精品永久免费网站| 国产精品电影一区二区三区| 午夜两性在线视频| 亚洲成人精品中文字幕电影| a级毛片a级免费在线| 久久久久国内视频| 国产成人欧美在线观看| 亚洲一区二区三区不卡视频| 全区人妻精品视频| 日本免费一区二区三区高清不卡| 国产不卡一卡二| 99精品欧美一区二区三区四区| 我要搜黄色片| 亚洲欧美日韩高清专用| 久久这里只有精品19| aaaaa片日本免费| www日本在线高清视频| 亚洲专区国产一区二区| 国内少妇人妻偷人精品xxx网站 | 97超视频在线观看视频| 欧美色视频一区免费| 在线十欧美十亚洲十日本专区| 午夜福利欧美成人| 热99re8久久精品国产| 国产1区2区3区精品| 午夜福利欧美成人| 桃红色精品国产亚洲av| 日韩精品中文字幕看吧| 黄片小视频在线播放| 国内精品久久久久久久电影| h日本视频在线播放| a级毛片a级免费在线| 国产亚洲欧美98| 亚洲成人免费电影在线观看| 一个人免费在线观看的高清视频| 级片在线观看| 日韩精品青青久久久久久| 一边摸一边抽搐一进一小说| 成人一区二区视频在线观看| 色噜噜av男人的天堂激情| 麻豆av在线久日| 亚洲av成人一区二区三| 美女免费视频网站| 国产成人av教育| 国产免费男女视频| 午夜福利免费观看在线| 亚洲avbb在线观看| 亚洲真实伦在线观看| 香蕉丝袜av| 脱女人内裤的视频| av天堂在线播放| 欧美成狂野欧美在线观看| 高清在线国产一区| 亚洲国产精品sss在线观看| 免费观看人在逋| www.熟女人妻精品国产| 999久久久精品免费观看国产| 成年女人永久免费观看视频| 精品久久久久久久久久免费视频| 婷婷精品国产亚洲av在线| a在线观看视频网站| 免费观看精品视频网站| 国产蜜桃级精品一区二区三区| 久久久国产成人免费| 亚洲精品一卡2卡三卡4卡5卡| 国产精品,欧美在线| 欧美成人免费av一区二区三区| 免费在线观看视频国产中文字幕亚洲| 亚洲国产欧美人成| 麻豆成人午夜福利视频| 国产精品乱码一区二三区的特点| 免费电影在线观看免费观看| 高清在线国产一区| 美女免费视频网站| 1024手机看黄色片| 亚洲熟女毛片儿| av中文乱码字幕在线| 国产淫片久久久久久久久 | 国产精品爽爽va在线观看网站| 欧美中文综合在线视频| 成人av一区二区三区在线看| 亚洲精品久久国产高清桃花| 成人欧美大片| 99热只有精品国产| 99精品久久久久人妻精品| 亚洲精品一卡2卡三卡4卡5卡| 99国产综合亚洲精品| av黄色大香蕉| 久久婷婷人人爽人人干人人爱| 免费人成视频x8x8入口观看| 国产精品98久久久久久宅男小说| 999久久久国产精品视频| 国产精品日韩av在线免费观看| 久久精品国产99精品国产亚洲性色| 真人做人爱边吃奶动态| 欧美+亚洲+日韩+国产| 精品免费久久久久久久清纯| 免费在线观看亚洲国产| 麻豆成人av在线观看| www.999成人在线观看| 狂野欧美白嫩少妇大欣赏| 老司机在亚洲福利影院| 午夜福利免费观看在线| 成人18禁在线播放| 亚洲专区中文字幕在线| 国产精品久久久久久人妻精品电影| 99久久精品一区二区三区| 欧美在线黄色| 日韩高清综合在线| 一区二区三区国产精品乱码| 国产不卡一卡二| 精品一区二区三区四区五区乱码| av福利片在线观看| 国产一区二区在线av高清观看| 欧美3d第一页| 国内少妇人妻偷人精品xxx网站 | 欧美中文日本在线观看视频| 国产av麻豆久久久久久久| 成年女人看的毛片在线观看| 国产高清激情床上av| 久久久久九九精品影院| 91九色精品人成在线观看| 人人妻人人澡欧美一区二区| 高清毛片免费观看视频网站| 日韩有码中文字幕| 久久久久久久久中文| 18禁观看日本| 又大又爽又粗| www.熟女人妻精品国产| 一个人看视频在线观看www免费 | 久久热在线av| 天天躁狠狠躁夜夜躁狠狠躁| 叶爱在线成人免费视频播放| 国产成人欧美在线观看| 手机成人av网站| 亚洲美女视频黄频| bbb黄色大片| 亚洲国产欧美网| 亚洲欧美日韩无卡精品| 床上黄色一级片| 久久久色成人| 国产伦一二天堂av在线观看| 人人妻,人人澡人人爽秒播| 99国产精品一区二区蜜桃av| 少妇的丰满在线观看| 中文资源天堂在线| 在线永久观看黄色视频| 亚洲精华国产精华精| 午夜精品一区二区三区免费看| 国产亚洲av高清不卡| 国产高清激情床上av| 可以在线观看的亚洲视频| 亚洲国产欧美网| 色综合亚洲欧美另类图片| 天天躁日日操中文字幕| 欧美日韩国产亚洲二区| 国产黄a三级三级三级人| 91老司机精品| 男人舔女人下体高潮全视频| 成人亚洲精品av一区二区| 国产高清视频在线播放一区| 国产麻豆成人av免费视频| 熟女电影av网| 毛片女人毛片| 欧美激情久久久久久爽电影| 色播亚洲综合网| 白带黄色成豆腐渣| 久久中文字幕一级| 欧美激情久久久久久爽电影| 舔av片在线| 国产亚洲精品综合一区在线观看| 国产一区二区在线观看日韩 | 一个人免费在线观看电影 | 九九在线视频观看精品| 美女cb高潮喷水在线观看 | 欧美性猛交╳xxx乱大交人| 欧美日本视频| 亚洲精品粉嫩美女一区| 波多野结衣巨乳人妻| 国产一区二区激情短视频| 国产人伦9x9x在线观看| 国产精品久久久久久精品电影| 成年免费大片在线观看| 少妇人妻一区二区三区视频| 在线观看日韩欧美| 波多野结衣高清无吗| 欧美日韩乱码在线| 757午夜福利合集在线观看| 最近最新中文字幕大全免费视频| 国产欧美日韩精品一区二区| 欧美一区二区国产精品久久精品| 男女那种视频在线观看| 19禁男女啪啪无遮挡网站| 成年女人毛片免费观看观看9| 国产精品久久久av美女十八| 国产美女午夜福利| 91字幕亚洲| 老司机午夜十八禁免费视频| 日韩免费av在线播放| 中文字幕精品亚洲无线码一区| 黄色成人免费大全| 久久九九热精品免费| 精品不卡国产一区二区三区| 岛国视频午夜一区免费看| 欧美国产日韩亚洲一区| 欧美av亚洲av综合av国产av| 亚洲人与动物交配视频| 搞女人的毛片| 国产精品爽爽va在线观看网站| 韩国av一区二区三区四区| 制服丝袜大香蕉在线| 精品久久久久久久人妻蜜臀av| 成人特级av手机在线观看| 国产伦精品一区二区三区四那| 久久亚洲精品不卡| 国产高清三级在线| 日本 av在线| 伦理电影免费视频| 欧美黄色片欧美黄色片| av黄色大香蕉| 变态另类丝袜制服| 精品久久久久久久久久免费视频| 国产精品日韩av在线免费观看| 99国产精品99久久久久| 天堂动漫精品| 9191精品国产免费久久| 中文字幕人妻丝袜一区二区| 国产成人精品久久二区二区免费| 最近视频中文字幕2019在线8| 成人欧美大片| 日韩欧美免费精品| 久久久精品大字幕| 国产亚洲欧美在线一区二区| 久久久久久久久中文| 天堂√8在线中文| 国产精品野战在线观看| 国产成年人精品一区二区| 国产1区2区3区精品| 国产一区二区三区在线臀色熟女| 精品久久久久久久人妻蜜臀av| 亚洲九九香蕉| 91九色精品人成在线观看| 最近最新中文字幕大全免费视频| 婷婷精品国产亚洲av| 岛国在线免费视频观看| 黑人巨大精品欧美一区二区mp4| 69av精品久久久久久| 美女午夜性视频免费| 国内精品久久久久久久电影| 99re在线观看精品视频| 国产v大片淫在线免费观看| 色噜噜av男人的天堂激情| 国产久久久一区二区三区| 成人三级黄色视频| 亚洲第一电影网av| 91麻豆精品激情在线观看国产| 啦啦啦观看免费观看视频高清| 久久精品夜夜夜夜夜久久蜜豆| 久久热在线av| 欧美日韩中文字幕国产精品一区二区三区| 成人一区二区视频在线观看| 午夜亚洲福利在线播放| 久久久久久久久中文| 久久精品影院6| 9191精品国产免费久久| 国产午夜精品久久久久久| 99久久99久久久精品蜜桃| 国产成人精品久久二区二区91| 国产免费男女视频| www.www免费av| 老熟妇仑乱视频hdxx| 精品欧美国产一区二区三| 女人高潮潮喷娇喘18禁视频| 精品一区二区三区视频在线 | 国产精品久久久久久久电影 | 五月玫瑰六月丁香| 亚洲avbb在线观看| 1000部很黄的大片| 给我免费播放毛片高清在线观看| 在线观看66精品国产| 久久精品影院6| 中文字幕av在线有码专区| 成人特级av手机在线观看| 日日摸夜夜添夜夜添小说| 九九久久精品国产亚洲av麻豆 | 母亲3免费完整高清在线观看| 欧美高清成人免费视频www| 日本a在线网址| 国产精品久久久久久久电影 | 久久午夜综合久久蜜桃| 在线观看一区二区三区| 久久国产精品人妻蜜桃| 美女黄网站色视频| 成人18禁在线播放| 日韩精品青青久久久久久| 亚洲欧美精品综合久久99| 国产私拍福利视频在线观看| 法律面前人人平等表现在哪些方面| 黄片小视频在线播放| 国产精品久久电影中文字幕| 岛国视频午夜一区免费看| 久久精品国产综合久久久| 亚洲中文av在线| 国产毛片a区久久久久| 亚洲欧美日韩高清专用| 12—13女人毛片做爰片一| 国产精品亚洲av一区麻豆| 午夜福利高清视频| 亚洲国产色片| 一a级毛片在线观看| 欧美另类亚洲清纯唯美| 国产午夜精品久久久久久| 特级一级黄色大片| 国产成人精品久久二区二区91| 色哟哟哟哟哟哟| a在线观看视频网站| 人人妻,人人澡人人爽秒播| 丰满人妻熟妇乱又伦精品不卡| 久久亚洲精品不卡| 小蜜桃在线观看免费完整版高清| 丰满的人妻完整版| www.熟女人妻精品国产| 噜噜噜噜噜久久久久久91| 看黄色毛片网站| 最近最新免费中文字幕在线| 日韩精品青青久久久久久| 亚洲人成伊人成综合网2020| 香蕉av资源在线| 窝窝影院91人妻| 国产精品爽爽va在线观看网站| av天堂中文字幕网| 亚洲欧美日韩高清专用| 成人国产一区最新在线观看| 高清在线国产一区| 国产精品久久久久久精品电影| 人人妻人人看人人澡| 欧美黑人巨大hd| 亚洲中文字幕日韩| 国产单亲对白刺激| 亚洲熟妇中文字幕五十中出| 国产精品野战在线观看| 亚洲精华国产精华精| 757午夜福利合集在线观看| cao死你这个sao货| 又粗又爽又猛毛片免费看| 观看美女的网站| 亚洲 欧美 日韩 在线 免费| 欧美丝袜亚洲另类 | 亚洲七黄色美女视频| 亚洲一区二区三区不卡视频| 成年人黄色毛片网站| 天天躁狠狠躁夜夜躁狠狠躁| 老司机福利观看| 国产欧美日韩精品亚洲av| 99国产精品一区二区三区| 欧美在线一区亚洲| 嫩草影视91久久| 欧美中文综合在线视频| 亚洲av美国av| 在线十欧美十亚洲十日本专区| 天天添夜夜摸| 午夜两性在线视频| 狂野欧美激情性xxxx| 亚洲成人精品中文字幕电影| 啦啦啦观看免费观看视频高清| 69av精品久久久久久| 又黄又爽又免费观看的视频| bbb黄色大片| 色哟哟哟哟哟哟| 91麻豆av在线| 久久精品综合一区二区三区| 国产1区2区3区精品| 在线观看午夜福利视频| 国内少妇人妻偷人精品xxx网站 | 亚洲中文字幕一区二区三区有码在线看 | 高潮久久久久久久久久久不卡| 亚洲精品中文字幕一二三四区| 天天一区二区日本电影三级| 亚洲成av人片免费观看| 国内揄拍国产精品人妻在线| 国产aⅴ精品一区二区三区波| 一夜夜www| 每晚都被弄得嗷嗷叫到高潮| 国产成人av教育| 精品乱码久久久久久99久播| 久久久久国产精品人妻aⅴ院| 欧美性猛交黑人性爽| 欧美日韩综合久久久久久 | 非洲黑人性xxxx精品又粗又长| 久久天堂一区二区三区四区| 真人做人爱边吃奶动态| 精品免费久久久久久久清纯| 精品电影一区二区在线| 欧美大码av| 国产精品,欧美在线| www日本在线高清视频| 一进一出抽搐动态| 国产乱人视频| 成人三级做爰电影| 亚洲中文av在线| 国产亚洲av高清不卡| av女优亚洲男人天堂 | 亚洲五月婷婷丁香| 亚洲成人中文字幕在线播放| 中文字幕高清在线视频| 亚洲精品国产精品久久久不卡| 国产午夜精品论理片| 在线观看免费午夜福利视频| 色在线成人网|