• <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 ?

    Deep Reinforcement Learning Enabled Smart City Recycling Waste Object Classification

    2022-08-23 02:21:00MesferAlDuhayyimTaiseerAbdallaElfadilEisaFahdAlWesabiAbdelzahirAbdelmaboudManarAhmedHamzaAbuSarwarZamaniMohammedRizwanullahandRadwaMarzouk
    Computers Materials&Continua 2022年6期

    Mesfer Al Duhayyim,Taiseer Abdalla Elfadil Eisa,Fahd N.Al-Wesabi,Abdelzahir Abdelmaboud,Manar Ahmed Hamza,Abu Sarwar ZamaniMohammed Rizwanullah and Radwa Marzouk

    1Department of Natural and Applied Sciences,College of Community-Aflaj,Prince Sattam bin Abdulaziz University,Saudi Arabia

    2Department of Information Systems-Girls Section,King Khalid University,Mahayil,62529,Saudi Arabia

    3Department of Computer Science,King Khalid University,Muhayel Aseer,Saudi Arabia

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

    5Department of Information Systems,King Khalid University,Muhayel Aseer,62529,Saudi Arabia

    6Department of Computer and Self Development,Preparatory Year Deanship,Prince Sattam bin Abdulaziz University,AlKharj,Saudi Arabia

    7Department of Information Systems,College of Computer and Information Sciences,Princess Nourah Bint Abdulrahman University,Saudi Arabia

    8Department of Mathematics,Faculty of Science,Cairo University,Giza,12613,Egypt

    Abstract: The Smart City concept revolves around gathering real time data from citizen, personal vehicle, public transports, building, and other urban infrastructures like power grid and waste disposal system.The understandings obtained from the data can assist municipal authorities handle assets and services effectually.At the same time, the massive increase in environmental pollution and degradation leads to ecological imbalance is a hot research topic.Besides, the progressive development of smart cities over the globe requires the design of intelligent waste management systems to properly categorize the waste depending upon the nature of biodegradability.Few of the commonly available wastes are paper, paper boxes, food, glass, etc.In order to classify the waste objects, computer vision based solutions are cost effective to separate out the waste from the huge dump of garbage and trash.Due to the recent developments of deep learning (DL) and deep reinforcement learning (DRL), waste object classification becomes possible by the identification and detection of wastes.In this aspect,this paper designs an intelligence DRL based recycling waste object detection and classification (IDRL-RWODC) model for smart cities.The goal of the IDRLRWODC technique is to detect and classify waste objects using the DL and DRL techniques.The IDRL-RWODC technique encompasses a twostage process namely Mask Regional Convolutional Neural Network(Mask RCNN) based object detection and DRL based object classification.In addition, DenseNet model is applied as a baseline model for the Mask RCNN model, and a deep Q-learning network (DQLN) is employed as a classifier.Moreover, a dragonfly algorithm (DFA) based hyperparameter optimizer is derived for improving the efficiency of the DenseNet model.In order to ensure the enhanced waste classification performance of the IDRL-RWODC technique, a series of simulations take place on benchmark dataset and the experimental results pointed out the better performance over the recent techniques with maximal accuracy of 0.993.

    Keywords:Smart cities;deep reinforcement learning;computer vision;image classification;object detection;waste management

    1 Introduction

    In smart cities,the design of intelligent waste management is a new borderline for local authorities aiming to minimize municipal solid waste and improve community recycling rate.Since cities spent high cost for managing waste in public places, smart city waste management programs result in enhanced performance.The rapid explosion in urbanization,global population rate,and industrialization have gained more consideration,pertain to environment degradation.With the global population growing at an alarming rate,there has been dreadful degradation of the environments,result in terrific conditions.According to the reports(2019),India yearly generates over 62 million tons(MT)of solid waste[1].The concern has been increased toward the necessity of segregation of waste on the basis of non-biodegradable and biodegradable behaviors.Generally, in the Indian context, waste consists of plastic, paper, metal, rubber, textiles, glass, sanitary products, organics, infectious materials (clinical and hospital),electrical and electronics,hazardous substances(chemical,paint,and spray)are widely categorized as non-biodegradable (NBD) and biodegradable (BD) wastes with their corresponding shares of 48%&52%[2].Furthermore,as per the current Indian government report,the most common thing which has been disposed of in the garbage’s are food,glass,paper and paper boxes[3].This thing constitutes over 99.5%of overall garbage gathered,that defines clearly that peoples dispose of wet and dry waste together.

    Effective waste segregation will support the appropriate recycling and disposal of this waste according to its biodegradability.Therefore,modern times dictate the development of a smart waste segregation scheme for alluding to the above-mentioned cause of ecological ruins.The segregation of wastes is subsequently, seeking consideration from several academicians and researchers around the world.Recycling systems could produce more effective results by keeping up with industrial development.In this system, the decomposition of waste is yet based on human factors [4].But,the developments of deep learning architecture and artificial intelligence technology might lead to enhancing system productivity than human factors in the following days.Specifically, human brain control system could be successfully and quickly transmitted to the machine with AI model.In these developments, it can be unavoidable that recycling systems depending on DL frameworks could be employed in the waste classification[5].

    The conventional waste classification is based largely on manual selections, however, the disadvantages are inefficacy.Even though the present waste classification driven by Machine Learning(ML)methods could operate effectively,but still the classification performance need to be enhanced.By analyzing the present waste classification method depends on deep learning method, 2 potential reason leads to the complexity of enhancing the classification performance[6].Initially,because of the distinct frameworks of DL methods,they act in a different way on many datasets.Next,there is only a low number of waste image dataset accessible for training model, absence of large scale databases such as ImageNet7.As well,it consists of various kinds of garbage,the absence of accurate and clear classification would result in lower classification performance.As plastic bags and plastic bottles have distinct characteristics and shapes, even though they are made up of plastic, the disposal ways are distinct.

    Deep Reinforcement Learning (DRL) is a subfield of ML which amalgamates Reinforcement Learning (RL) and Deep Learning (DL).A variety of algorithms exist in literature to deal with the underlying concept of iteratively learning[7],illustrating and improving data in order to foresee better outcomes and apply them to provide improved decisions.DL is largely are trained by the scientific community employing Graphical Processing Units(GPU)to accelerate their research and application,bringing them to the point where they exceed the performance of most traditional ML algorithms in video analytics.DRL techniques are extended to 3-dimensional for unveiling spatio-temporal features from the video feed which could distinguish the objects from one another

    This paper designs an intelligence DRL based recycling waste object detection and classification(IDRL-RWODC) model.The IDRL-RWODC technique encompasses a two-stage process namely Mask Regional Convolutional Neural Network(Mask RCNN)based object detection and DRL based object classification.Moreover, DenseNet model is used as a baseline model for the Mask RCNN model and a deep Q-learning network(DQLN)is employed as a classifier.For ensuring the improved waste classification outcomes of the IDRL-RWODC technique, an extensive experimental analysis takes place to investigate the efficacy in terms of different measures.

    2 Literature Review

    Ziouzios et al.[8] proposed a cloud based classification approach for automatic machines in recycling factories with ML algorithm.They trained an effective MobileNet method, capable of classifying 5 distinct kinds of waste.The inference could be implemented in real time on a cloud server.Different methods were used and described for improving the classification performances like hyperparameter tuning and data augmentation.Adedeji et al.[9] proposed a smart waste material classification algorithm,i.e.,established with the fifty layers residual net pretrain(ResNet-50)CNN method, i.e., ML algorithm and serves as the extractor, and SVM i.e., employed for classifying the waste to distinct types or groups like metal,glass,plastic,paper and so on.

    Chu et al.[10] propose an MHS DL approach for manually sorting the waste disposed of by individual perosn in the urban public area.Such systems deploy a higher resolution camera for capturing unwanted images and sensor nodes for detecting another beneficial feature data.The MHS employs CNN based method for extracting image features and MLP model for consolidating image features and other features data for classifying waste is recyclable.Gan et al.[11]propose an approach of MSW recycling and classification depends on DL technique and employs CNN for building classification algorithm and garbage intelligence simultaneous interpreting, that enhances the speed and accuracy of the garbage image detection.Narayan[12]proposed DeepWaste,an easy to use mobile app,which uses greatly improved DL model for providing users instantaneous waste classification to recycling,compost,and trash.Research using various CNN frameworks for detecting and classifying waste materials.Huang et al.[13]proposed a novel combinational classification algorithm depending on 3 pretrained CNN methods(NASNetLarge,VGG19,and DenseNet169)to process the ImageNet database and attain higher classification performance.In this presented method, the TL method depends on every pretrained method is made as candidate classifiers, and the optimum output of 3 candidate classifications are elected as the concluding classifier results.

    Zhang et al.[14]aim are to enhance the performance of waste sorting via DL model for providing a chance to smart waste classifications depending on mobile phone or computer vision terminal.A self-monitoring model is included in the residual network module that is capable of integrating the appropriate features of each channel graph,compresses the spatial dimensional feature,and has global receptive fields.In To?ga?ar et al.[15],the dataset applied to the classification of waste has been recreated using the AE network.Then,the feature set is extracted by 2 datasets using CNN frameworks and the feature set is integrated.The RR model implemented on the integrated feature set decreased the amount of features and also exposed the effective features.The SVM model has been employed as a classifier in each experiment.

    Wang et al.[16]explore the applications of DL in the area of environmental protections,the CNN VGG16 models are applied for solving the problems of classification and identification of domestic garbage.Such solutions are initially employed the Open CV library for locating and selecting the recognized object and pre-processed the image to 224×224 pixel RGB images recognized as the VGG16 network.Next,data augmentation,a VGG16 CNN depending on the TensorFlow frameworks are constructed, with the RELU activation function and including BN layer for accelerating the model’s convergence speed,when safeguarding detection performance.In Hasan et al.[17],automated waste classification systems are presented with DL approach for classifying the wastes like paper,metal, non-recyclable and plastic waste.The classification was executed by this CV model with the aid of AlexNet CNN framework in realtime thus the waste could be dropped to the proper chamber since it is thrown to dustbin.

    Kumar et al.[18] investigate a new method for waste segregation to its efficient disposal and recycling by using a DL approach.The YOLOv3 model was used in the Darknet NN architecture for training self-made datasets.The network was trained for six objects classes(such as glass,cardboard,paper,metal,organic and plastic waste).Sousa et al.[19]proposed a hierarchical DL model for waste classification and detection in food trays.The proposed 2 phase method maintains the benefits of current object detectors(as Faster RCNN)and permits the classification process to be assisted in high resolution bounding box.As well, they annotate, collect and provide to the research novel datasets,called Labeled Waste in the Wild.

    3 The Proposed Model

    In this study, a new IDRL-RWODC technique has been presented for recycling waste object detection and classification.The IDRL-RWODC technique derives a Mask RCNN with DenseNet model for the detection and masking of waste objects in the scene.In addition,the DRL based DQLN technique is employed to classify the detected objects into distinct class labels.The detailed working of these processes is given in the succeeding sections.

    3.1 Problem Formulation

    Given a waste object image datasetwhereasXirepresent theithtraining samples andndenotes the amount of the training samples.The labeled set of the training sample is given asc= {ci}, ?ci∈ {1,...,C}, in whichCdenotes the waste class image count.They determineRejectas the set of labeled training samples, while XLiindicates the ith labelled training sample,yLi= {1, 2,...,C} denote its label, andnLmeans the amount of labelled training samples inJL.Likewise,denotes the unlabelled training set aswhereasXU irepresents the ith unlabelled training sample,nUsignifies the amount of unlabelled training samples inJU.For every input imageXi,they determine the output of final layer of a DRL method usingf(Xi),i.e.,the predictive score ofXi[20].For every input imageXi,they determine the output of penultimate layer of a DRL method asxi,and considerxias the object detected by the Mask RCNN model.

    3.2 Mask RCNN Based Object Detection Model

    At the initial stage,the Mask RCNN model is used for the detection of waste objects in the image.Mask RCNN is an easy, flexible, and usual structure for object recognition, exposure, and sample segmentation that capably detects objects in an image,but creating a great quality segmentation mask for all instances.The RPN,the 2nd piece of Mask R-CNN,and share complete images convolution features with recognition networks,therefore supporting approximately cost-free region proposal.The RPN is implemented to Mask R-CNN rather than elective search and so RPN shares the convolutional feature of complete map with recognition networks.It is forecast combined boundaries place as well as to object score at all places,and it can be also fully convolutional network(FCN).

    For Mask R-CNN achieves 3 tasks: target recognition, detection, and segmentation.At the input, the images are passed to the FPN.Then, a 5 group of feature maps of distinct sizes were created and candidate frame region has been created by RPN[21].Then the candidate area has been both the feature map, the model attained the recognition, classifier, and mask of target.In order to additional enhance the calculating speed of technique,it is adjusted to real time necessities of quick drive anti-collision warning scheme.During this case,FPN framework,and RPN parameter settings were enhanced.An enhanced technique presented during this case is to appreciate the recognition,detection,and segmentation of target simultaneously.Fig.1 illustrates the structure of Mask RCNN for waste object detection.

    Figure 1:Structure of mask RCNN for waste object detection

    In the multi-task loss,function is implemented during trained Mask R CNN with three portions such as classifier loss of bounding box, place regression loss of bounding box, and loss of mask as showcased by the provided functions.

    wherepirefers the noticed probabilities for ROI in classifier lossLclsandutilized for ground truth as one of the ROI has been considered as foreground or zero otherwise.tiimplies the vector of accurate controls for detecting bound box(Eq.(3))andrepresents the ground truth in place regression loss where r indicates the robust loss function for estimating the regression error.All the ROI detecting the outcome ofK*m2dimensional by utilizing mask branch as well as encodedKbinary mask together with resolution of m*m.

    In this study,DenseNet method is employed as the baseline model for the Mask RCNN.DenseNet[22] is a DL framework where each layer is directly connected, thus attaining efficient data flow amongst other.Every layer is connected to each subsequent layer of the network, and they are represented as DenseNets.Assume an input imagex0, i.e., passed by the presented convolution networks.The network containsNlayer, and all the layers execute nonlinear transformationsFn(.).Suppose that layernconsists of feature map of each previous convolution layer.The input feature map of layer 0 ton-1 are concatenated and represented asx0,...,xn-1.Therefore,this algorithm has N(N+1)/2 connection on a N-layer network.The output of the nth layers are expressed as

    wherexnis the present nth layer,[x0, ...,xn-1]is a concatenation of feature map obtained from 0 ton-1 layers,andFn(.)is the composite functions of BN and ReLU.Fig.2 depicts the framework of DenseNet.

    Figure 2:Structure of DenseNet

    All the convolutional layers corresponding to the BN-ReLU-Conv sequences.Afterward the convolution is implemented on the image,ReLU is employed to the output feature map.This function presents nonlinearity in CNN models.The ReLU function can be expressed as

    Average pooling splits the input to the pooling area and calculates the average value of all the areas.GAP compute the average of all the feature maps,and the resultant vector is taken to the softmax layer.In this case,DenseNet-169 model is utilized,which depends upon the basic DenseNet framework and the DenseNet has L(L+1)/2 direct connections.

    In order to boost the object detection outcomes of the DenseNet model, a hyperparameter optimization using dragonfly algorithm (DFA).The DFA is established by Mirjalili in 2016 [23].It is a metaheuristic technique simulated by the static as well as dynamic performances of dragonflies in nature.There are 2 important phases of optimization:exploration as well as exploitation.These 2 stages are modeled by dragonflies,also dynamic/static searching to food or avoided the enemy.

    There are 2 analysis where SI appears in dragonflies:fooding and migration.The feeding has been demonstrated as a statically swarm in optimized;migration is displayed as dynamically swarm.Based on the swarms are 3 particular performances:separation,alignment,and cohesion.At this point,the model of separation implies which separate in swarm avoid statically collision with neighbor(Eq.(7)).Alignment mentions the speed at that the agents were corresponding with adjacent individuals(Eq.(8)).Lastly, the model of cohesion illustrates the tendency of individuals nearby centre of herd(Eq.(9)).Two other performances are added to these 3 fundamental performances in DA:moving near food and avoid the enemy.The reason to add these performances to this technique is that important drive of all swarms is for surviving.So,if every individual is moving near food source(Eq.(10)),it can avoid the enemy in similar time period(Eq.(11)).

    In the above cases,Ximplies the instantaneous place of individuals,butXjrefers the instantaneous place ofjthindividuals.Nsignifies the amount of adjacent individuals[24],howeverVjdemonstrates the speed ofjthadjacent individuals.X+andX-stands for the place of food as well as enemy sources correspondingly.Afterward computing the step vector,the place vector is upgraded(Eq.(13)):

    where the values ofs,a,andcin Eq.(12)signify the separate,alignment,and cohesion coefficients correspondingly,andf,e,w,andtvalues demonstrate the food factor,enemy factor,inertia coefficients,and iteration number correspondingly.These coefficients and stated factors allow for performing exploratory as well as exploitative performances in the optimization.During this dynamic swarm,dragonfly incline for alignment its flight.During the static motion,the alignment has been extremely lower,but the fits for attacking the enemy were extremely superior.So,the coefficient of alignment has been maximum and the cohesion coefficient was minimum during the exploration procedure;during the exploitation model, the coefficient of alignment was minimum and co-efficient of cohesion was maximum.

    3.3 DRL Based Waste Classification Model

    Once the waste objects are detected in the image, the next step involves the waste object classification process by the use of DQLN technique.The DRL incorporates three components namely state,action,and reward.The DRL agent intends in learning the map function from the state to action space.Then,the DRL agent receives an award.The goal of the DRL agent is the maximization of total rewards.The classifier strategy of DQLN model is a function that receives the instance and returns the probability of every label.

    The aim of classification agent is to appropriately identify the instances in the trained data more feasible.Since the classification agents obtain a positive reward if it correctly identifies instances, it attains their aim by maximizing the cumulative rewardgt:

    In reinforcement learning,there is function which computes the quality of state-action combination named asQfunction:

    Based on the Bellman formula,theQfunction is written as:

    The classification agents are maximizing the cumulative reward by resolving the optimumQ*function[25],and the greedy approach in an optimumQ*function is the better classifier approachπ*for DQLN.

    In the low-dimension finite state space,Qfunction is recording by table.But, in the high dimensional continuous state space,Qfunctions could not be solved still deepQ-learning technique is presented that fits theQfunction with DNN.In deepQ-learning technique,the communication data(s,a,r,s′)achieved from (19) are saved in the experience replay memoryM.The agent arbitrarily instances a mini-batch of transitionBfromMand carries out the gradient descent step on DeepQnetwork based on the loss function as:

    whereyimplies the target evaluation ofQfunction,the written ofyis:

    wheres′implies the next state ofs,a′represents the act carried out by agent in states′,t= 1 ifterminal=True;thent=0.The derivative of loss function(20)in terms ofθis:

    At this point,optimumQ*function can be obtained by minimizing the loss function(20),and the greedy policy in the optimumQ*function get the maximal cumulative reward.Therefore,the optimum classifier approachπ*:S→Afor DQLN has been obtained.

    4 Performance Validation

    The proposed model is simulated using Python 3.6.5 tool on a benchmark Garbage[26]classification dataset from Kaggle repository.The dataset includes six waste classes.It has 403 images under cardboard,137 images under Thrash,501 images under Glass,482 images under Plastic,504 images under Paper,and 410 images under Metal.Fig.3 showcases some of the sample test images from the Kaggle datasets.

    Figure 3:Sample images

    Fig.4 demonstrates the sample object detection results of the Mask RCNN model.The figures displayed that the Mask RCNN model has effectually detected and masked the objects.

    Fig.5 offers the confusion matrices of the IDRL-RWODC technique under varying sizes of testing and training information.On the applied training/testing(90:10)dataset,the IDRL-RWODC technique has identified 391 images into cardboard, 489 images into glass, 405 images into metal,496 images into Paper, 474 images into Plastic, and 130 images into Thrash.Also, on the applied training/testing (80:20) dataset, the IDRL-RWODC approach has identified 363 images into cardboard,470 images into glass,392 images into metal,477 images into Paper,446 images into Plastic,and 110 images into Thrash.Likewise, on the applied training/testing (70:30) dataset, the IDRLRWODC method has identified 354 images into cardboard, 461 images into glass, 382 images into metal,467 images into Paper,440 images into Plastic,and 104 images into Thrash.Similarly,on the applied training/testing(60:40)dataset,the IDRL-RWODC algorithm has identified 349 images into cardboard,461 images into glass,375 images into metal,461 images into Paper,438 images into Plastic,and 92 images into Thrash.

    Figure 4:Sample object detection results

    Tab.1 offers the waste object classification results of the IDRL-RWODC technique on the varying training/testing dataset.The table values showcased that the IDRL-RWODC technique has classified all the objects efficiently under each size of testing or training datasets.With training/testing(90:10),the IDRL-RWODC technique has attained an average recall of 0.975,precision of 0.978,F-score of 0.977,and accuracy of 0.993.Additionally,with training/testing(80:20),the IDRL-RWODC approach has gained an average accuracy of 0.976, precision of 0.925, recall of 0.912, and F-score of 0.918.Moreover,with training/testing(70:30),the IDRL-RWODC manner has reached an average recall of 0.888,precision of 0.900,F-score of 0.894,and accuracy of 0.969.Furthermore,with training/testing(60:40), the IDRL-RWODC methodology has gained an average recall of 0.866, precision of 0.884,F-score of 0.873 and accuracy of 0.964.

    Fig.6 showcases the accuracy analyses of the IDRL-RWODC method on the applied dataset.The figure demonstrated that the IDRL-RWODC approach has resulted in maximum accuracy on the training and validation dataset.The results demonstrated that the validation accuracy is found to be higher than the training accuracy.

    Fig.7 illustrates the loss analysis of the IDRL-RWODC approach on the applied dataset.The figure showcased that the IDRL-RWODC manner has resulted in a minimum loss on the training and validation dataset.The results outperformed that the validation loss is initiate to be lesser over the training loss.

    Figure 5:Confusion matrix of IDRL-RWODC model

    Table 1: Result analysis of IDRL-RWODC model with different measures

    Table 1:Continued

    Figure 6:Accuracy analysis of IDRL-RWODC model

    Figure 7:Loss analysis of IDRL-RWODC model

    Tab.2 and Fig.8 demonstrate the comparative results analysis of the IDRL-RWODC manner with existing approaches.The figure depicted that the Faster R-CNN+Inception V4+OID V4 has accomplished a comparative lower precision of 0.958,recall of 0.94,and F1 score of 0.951.Followed by, the SSD + MobileNetV2 + COCO technique has obtained certainly increased result with the precision of 0.961,recall of 0.958,and F1 score of 0.959.Moreover,the SSD+Inception V2+COCO technique has gained moderate results with the precision of 0.967,recall of 0.948,and F1 score of 0.957.Furthermore,the SSD+MobileNetV2+OID V4 technique has resulted in a competitive efficiency with precision of 0.976,recall of 0.944,and F1 score of 0.960.However,the IDRL-RWODC method has accomplished effective results with the recall of 0.975,precision of 0.978,and F1 score of 0.977.

    Table 2: Comparative analysis of IDRL-RWODC model with different measures

    Tab.3 and Fig.9 depict the accuracy analyses of the IDEL-RWODC technique with existing manners.The figure outperformed that the RecycleNetV4 and Faster R-CNN (Inception V2) algorithms have attained a lesser accuracy of 0.810 and 0.816 respectively.In line with,the ResNet50 and Inception-ResNetV2 approaches have achieved somewhat improved and same accuracy of 0.870.

    Figure 8:Comparative analysis of IDRL-RWODC model with existing techniques

    Table 3: Accuracy analysis of IDRL-RWODC model with existing methods

    Simultaneously, the MobileNetV2 and VGG-16 techniques have accomplished nearly nearer accuracy values of 0.880 and 0.884 correspondingly.Along with that, the DenseNet121 and SSD(MobileNetV2-OID V4) methods depicted that reached superior accuracy of 0.950, and 0.976 respectively.Finally, the IDRL-RWODC algorithm has resulted in a maximum performance with a maximal accuracy of 0.993.

    Figure 9:Accuracy analysis of IDRL-RWODC model with existing techniques

    5 Conclusion

    In this study, a new IDRL-RWODC technique has been presented for recycling waste object detection and classification for smart cities.The IDRL-RWODC technique derives a Mask RCNN with DenseNet model for the detection and masking of waste objects in the scene.In order to boost the object detection outcomes of the DenseNet model,a hyperparameter optimization using DFA.In addition,the DRL based DQLN technique is employed to classify the detected objects into distinct class labels.The IDRL-RWODC technique has the ability to recognize objects of varying scales and orientations.For ensuring the improved waste classification outcomes of the IDRL-RWODC technique,an extensive experimental analysis takes place to investigate the efficacy in terms of different measures.The experimental results pointed out the better performances of the IDRL-RWODC algorithm over the current techniques.In future, the IDRL-RWODC technique can be realized as a mobile application for smartphones to aid the waste object classification process in real time.

    Funding Statement:The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number (RGP 1/282/42).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.

    制服人妻中文乱码| 中文字幕精品免费在线观看视频| 两人在一起打扑克的视频| 在线观看免费日韩欧美大片| 一夜夜www| 女人久久www免费人成看片| 天堂动漫精品| 亚洲久久久国产精品| 国产欧美日韩一区二区三| 国产又色又爽无遮挡免费看| 久久久久久久大尺度免费视频| 一二三四在线观看免费中文在| 一级毛片女人18水好多| 午夜91福利影院| 中文字幕高清在线视频| 日日夜夜操网爽| 亚洲情色 制服丝袜| 正在播放国产对白刺激| 国产激情久久老熟女| 久久久久视频综合| 桃花免费在线播放| 国产精品亚洲av一区麻豆| 久久九九热精品免费| 亚洲天堂av无毛| 国产极品粉嫩免费观看在线| 男女下面插进去视频免费观看| videosex国产| 午夜福利一区二区在线看| 天天躁日日躁夜夜躁夜夜| 最黄视频免费看| 欧美日韩成人在线一区二区| 黄色视频,在线免费观看| 欧美午夜高清在线| 80岁老熟妇乱子伦牲交| 国产亚洲精品第一综合不卡| 日韩视频在线欧美| 亚洲国产成人一精品久久久| 在线观看免费视频日本深夜| 亚洲自偷自拍图片 自拍| 亚洲欧美日韩高清在线视频 | 热re99久久精品国产66热6| 夜夜骑夜夜射夜夜干| 亚洲精品成人av观看孕妇| 老司机靠b影院| 在线观看66精品国产| 美女国产高潮福利片在线看| 91精品国产国语对白视频| 美女扒开内裤让男人捅视频| 大片电影免费在线观看免费| 老司机午夜十八禁免费视频| 国产麻豆69| 如日韩欧美国产精品一区二区三区| 国产色视频综合| 天天操日日干夜夜撸| 欧美在线一区亚洲| 国产精品av久久久久免费| 极品教师在线免费播放| 日韩三级视频一区二区三区| 肉色欧美久久久久久久蜜桃| 精品人妻熟女毛片av久久网站| 午夜福利一区二区在线看| 久久精品aⅴ一区二区三区四区| 无遮挡黄片免费观看| 国产一区有黄有色的免费视频| videos熟女内射| 女人高潮潮喷娇喘18禁视频| 国产亚洲av高清不卡| 久久国产精品影院| 曰老女人黄片| 色婷婷久久久亚洲欧美| 久久国产亚洲av麻豆专区| 国产成人免费无遮挡视频| 成人18禁高潮啪啪吃奶动态图| 搡老乐熟女国产| 亚洲精品国产一区二区精华液| √禁漫天堂资源中文www| 99久久精品国产亚洲精品| 国产男女内射视频| 久久久久久亚洲精品国产蜜桃av| 亚洲人成伊人成综合网2020| 男人操女人黄网站| 无人区码免费观看不卡 | 老司机在亚洲福利影院| 757午夜福利合集在线观看| 高清欧美精品videossex| 王馨瑶露胸无遮挡在线观看| 黑人操中国人逼视频| netflix在线观看网站| 美国免费a级毛片| netflix在线观看网站| 免费在线观看视频国产中文字幕亚洲| 久久青草综合色| 99国产精品99久久久久| 亚洲中文日韩欧美视频| 亚洲av片天天在线观看| 91九色精品人成在线观看| 日日夜夜操网爽| 搡老熟女国产l中国老女人| 一区二区三区国产精品乱码| 中文字幕高清在线视频| 午夜日韩欧美国产| 日本av手机在线免费观看| 精品卡一卡二卡四卡免费| 亚洲欧美一区二区三区久久| 国产精品久久久久久精品电影小说| 国产深夜福利视频在线观看| 老熟女久久久| 国产精品麻豆人妻色哟哟久久| 在线观看免费视频网站a站| 亚洲第一av免费看| 免费在线观看完整版高清| 久久毛片免费看一区二区三区| 国产精品久久久人人做人人爽| 国产主播在线观看一区二区| kizo精华| 日本精品一区二区三区蜜桃| 久久精品人人爽人人爽视色| 露出奶头的视频| 肉色欧美久久久久久久蜜桃| 国产精品久久久久久人妻精品电影 | 欧美在线黄色| 国产精品香港三级国产av潘金莲| 久久国产精品男人的天堂亚洲| 精品一区二区三卡| 中文字幕人妻丝袜一区二区| 99国产精品99久久久久| a级毛片黄视频| 国产在线一区二区三区精| 国产不卡av网站在线观看| 欧美午夜高清在线| 成人亚洲精品一区在线观看| 99在线人妻在线中文字幕 | 国产欧美日韩一区二区三| 国产欧美日韩一区二区三| 亚洲av第一区精品v没综合| 久久亚洲真实| 菩萨蛮人人尽说江南好唐韦庄| 欧美黄色淫秽网站| 国产高清videossex| 青青草视频在线视频观看| 久久青草综合色| 欧美日韩国产mv在线观看视频| 咕卡用的链子| 黑人巨大精品欧美一区二区mp4| 久久久久久免费高清国产稀缺| 超碰97精品在线观看| 欧美日韩亚洲高清精品| 亚洲全国av大片| 深夜精品福利| 欧美日韩中文字幕国产精品一区二区三区 | 国产精品久久久久成人av| 麻豆乱淫一区二区| 好男人电影高清在线观看| 免费在线观看完整版高清| 99精品欧美一区二区三区四区| 51午夜福利影视在线观看| 老鸭窝网址在线观看| 一区在线观看完整版| aaaaa片日本免费| 午夜激情久久久久久久| 色婷婷久久久亚洲欧美| 黑人巨大精品欧美一区二区mp4| 飞空精品影院首页| 亚洲视频免费观看视频| 亚洲久久久国产精品| 久久人妻福利社区极品人妻图片| 丝袜美腿诱惑在线| 日韩精品免费视频一区二区三区| av天堂在线播放| 久久精品aⅴ一区二区三区四区| 91麻豆精品激情在线观看国产 | 色播在线永久视频| 一本大道久久a久久精品| 日韩免费av在线播放| 99re在线观看精品视频| 91麻豆精品激情在线观看国产 | 欧美精品啪啪一区二区三区| 久久婷婷成人综合色麻豆| 久久精品国产a三级三级三级| 好男人电影高清在线观看| 欧美av亚洲av综合av国产av| 日韩视频在线欧美| 男女无遮挡免费网站观看| 亚洲精品久久成人aⅴ小说| 深夜精品福利| 在线看a的网站| 青草久久国产| 免费观看a级毛片全部| 免费不卡黄色视频| 国产成人啪精品午夜网站| 日本av手机在线免费观看| 男男h啪啪无遮挡| 岛国在线观看网站| 一边摸一边做爽爽视频免费| 亚洲av成人不卡在线观看播放网| 丁香欧美五月| 久久天堂一区二区三区四区| 国产精品自产拍在线观看55亚洲 | 国产伦理片在线播放av一区| 大香蕉久久网| kizo精华| 国产三级黄色录像| 99在线人妻在线中文字幕 | 成人免费观看视频高清| 男女边摸边吃奶| 欧美日韩一级在线毛片| 老司机福利观看| 国产成人精品久久二区二区免费| 不卡av一区二区三区| 自线自在国产av| avwww免费| 中文字幕另类日韩欧美亚洲嫩草| 日韩人妻精品一区2区三区| 操美女的视频在线观看| 色视频在线一区二区三区| 国产精品免费视频内射| 久久亚洲精品不卡| 青草久久国产| 91老司机精品| 女人爽到高潮嗷嗷叫在线视频| 欧美+亚洲+日韩+国产| 欧美日韩中文字幕国产精品一区二区三区 | 久久亚洲精品不卡| 欧美国产精品一级二级三级| 国产成+人综合+亚洲专区| 大型黄色视频在线免费观看| 亚洲精品美女久久久久99蜜臀| 一级片免费观看大全| 色综合欧美亚洲国产小说| 怎么达到女性高潮| 国产无遮挡羞羞视频在线观看| 久久中文看片网| 99riav亚洲国产免费| 亚洲avbb在线观看| 国产在视频线精品| 自线自在国产av| 亚洲成av片中文字幕在线观看| 日韩人妻精品一区2区三区| 美女扒开内裤让男人捅视频| 成人永久免费在线观看视频 | 黄频高清免费视频| 在线观看免费午夜福利视频| 久久久久久久久免费视频了| 国产精品一区二区精品视频观看| 国产免费av片在线观看野外av| 国产精品 国内视频| 国产成人欧美在线观看 | 精品少妇久久久久久888优播| 国产精品一区二区精品视频观看| 女人高潮潮喷娇喘18禁视频| 国产精品自产拍在线观看55亚洲 | 在线观看免费日韩欧美大片| 亚洲综合色网址| 午夜福利影视在线免费观看| 久久久久久久国产电影| 另类亚洲欧美激情| 国产免费福利视频在线观看| 欧美精品一区二区免费开放| 国产精品 欧美亚洲| 动漫黄色视频在线观看| 久久精品aⅴ一区二区三区四区| 51午夜福利影视在线观看| 成人手机av| 欧美中文综合在线视频| 激情在线观看视频在线高清 | 国产又爽黄色视频| 久久精品国产亚洲av高清一级| 欧美黄色淫秽网站| 午夜福利影视在线免费观看| 国产亚洲精品第一综合不卡| 黄色视频,在线免费观看| 亚洲国产av新网站| 久久 成人 亚洲| 久久久久久免费高清国产稀缺| 热99久久久久精品小说推荐| 日韩人妻精品一区2区三区| 黑人猛操日本美女一级片| 亚洲专区国产一区二区| 国产不卡一卡二| 男女下面插进去视频免费观看| 自拍欧美九色日韩亚洲蝌蚪91| 色综合婷婷激情| 亚洲精品在线观看二区| 免费观看av网站的网址| 首页视频小说图片口味搜索| 亚洲av片天天在线观看| 黑人巨大精品欧美一区二区蜜桃| 久久中文字幕一级| 一本—道久久a久久精品蜜桃钙片| www日本在线高清视频| 精品一区二区三卡| 欧美精品一区二区大全| 午夜激情久久久久久久| 国产精品一区二区精品视频观看| 老汉色av国产亚洲站长工具| 成人国语在线视频| 国产在视频线精品| h视频一区二区三区| 欧美精品人与动牲交sv欧美| √禁漫天堂资源中文www| 一边摸一边做爽爽视频免费| 国产精品久久久人人做人人爽| 一级片免费观看大全| 久久ye,这里只有精品| 丰满饥渴人妻一区二区三| 亚洲久久久国产精品| 操出白浆在线播放| 午夜91福利影院| 精品一区二区三卡| 夜夜爽天天搞| av天堂久久9| 久久婷婷成人综合色麻豆| 黄色视频不卡| 午夜精品久久久久久毛片777| 午夜福利视频精品| 亚洲国产欧美日韩在线播放| 国产男女超爽视频在线观看| 亚洲国产av影院在线观看| 美女福利国产在线| 亚洲美女黄片视频| 久久久久国内视频| 我的亚洲天堂| 男人舔女人的私密视频| 99国产综合亚洲精品| 桃花免费在线播放| 亚洲成人免费电影在线观看| 欧美黑人欧美精品刺激| 汤姆久久久久久久影院中文字幕| 9色porny在线观看| 91字幕亚洲| 精品久久久久久久毛片微露脸| 精品欧美一区二区三区在线| 美女视频免费永久观看网站| 90打野战视频偷拍视频| 女警被强在线播放| 精品久久久精品久久久| 涩涩av久久男人的天堂| 久久99一区二区三区| 狂野欧美激情性xxxx| 亚洲精品一卡2卡三卡4卡5卡| 欧美变态另类bdsm刘玥| 在线观看免费午夜福利视频| 精品高清国产在线一区| 国产野战对白在线观看| 最近最新免费中文字幕在线| 在线观看免费高清a一片| 热re99久久精品国产66热6| 亚洲久久久国产精品| 精品国产一区二区久久| 在线观看舔阴道视频| 搡老岳熟女国产| 国产又爽黄色视频| 久久精品国产亚洲av高清一级| 久久久久视频综合| 欧美日韩av久久| 亚洲成人国产一区在线观看| 亚洲av国产av综合av卡| 人人澡人人妻人| 悠悠久久av| 国产精品一区二区在线观看99| 午夜激情久久久久久久| 一边摸一边抽搐一进一出视频| 99精品欧美一区二区三区四区| 99热国产这里只有精品6| 欧美乱码精品一区二区三区| 人妻 亚洲 视频| 亚洲色图 男人天堂 中文字幕| 在线观看舔阴道视频| 一区二区日韩欧美中文字幕| 国产成人一区二区三区免费视频网站| av不卡在线播放| 国产欧美日韩一区二区三| 两性夫妻黄色片| 午夜福利影视在线免费观看| 国产真人三级小视频在线观看| 中亚洲国语对白在线视频| av一本久久久久| 欧美日韩亚洲高清精品| 亚洲人成77777在线视频| 99久久精品国产亚洲精品| 757午夜福利合集在线观看| 久久天堂一区二区三区四区| 久久香蕉激情| 色婷婷久久久亚洲欧美| 国产一卡二卡三卡精品| 热99re8久久精品国产| www日本在线高清视频| 在线永久观看黄色视频| 欧美精品一区二区免费开放| 99久久99久久久精品蜜桃| 久久久精品免费免费高清| 超色免费av| 99国产精品99久久久久| 亚洲成人免费av在线播放| 久久免费观看电影| 日日夜夜操网爽| 国产不卡一卡二| 一级,二级,三级黄色视频| 日本av手机在线免费观看| 日韩欧美国产一区二区入口| 亚洲免费av在线视频| 丝袜美足系列| 国产真人三级小视频在线观看| 1024视频免费在线观看| 精品少妇久久久久久888优播| 久久国产精品男人的天堂亚洲| 亚洲精华国产精华精| 人人妻人人添人人爽欧美一区卜| 男人舔女人的私密视频| 肉色欧美久久久久久久蜜桃| 精品一区二区三区av网在线观看 | 捣出白浆h1v1| 久久午夜综合久久蜜桃| 99国产极品粉嫩在线观看| 久久久久久久久久久久大奶| 国产免费视频播放在线视频| 欧美午夜高清在线| 男人操女人黄网站| 成人永久免费在线观看视频 | 最新在线观看一区二区三区| 国产精品亚洲一级av第二区| 国产成人精品在线电影| 美女扒开内裤让男人捅视频| 人人妻,人人澡人人爽秒播| 久久久国产成人免费| 国产精品亚洲一级av第二区| 国产精品九九99| 精品欧美一区二区三区在线| 日本一区二区免费在线视频| 国产精品电影一区二区三区 | 蜜桃国产av成人99| 久久中文字幕人妻熟女| 成人18禁在线播放| 自线自在国产av| 在线看a的网站| 看免费av毛片| 国产淫语在线视频| 视频区图区小说| 国产精品1区2区在线观看. | 日本五十路高清| 亚洲精品自拍成人| 色综合婷婷激情| 两个人免费观看高清视频| bbb黄色大片| 国产精品一区二区精品视频观看| 岛国毛片在线播放| 午夜久久久在线观看| 女人被躁到高潮嗷嗷叫费观| 最近最新中文字幕大全免费视频| 亚洲欧美日韩高清在线视频 | 精品久久久久久电影网| 欧美 日韩 精品 国产| 十八禁人妻一区二区| 日韩免费高清中文字幕av| 国产一区二区三区在线臀色熟女 | 亚洲天堂av无毛| 欧美亚洲日本最大视频资源| tocl精华| 女人被躁到高潮嗷嗷叫费观| 国产色视频综合| 侵犯人妻中文字幕一二三四区| 日本a在线网址| 午夜福利影视在线免费观看| 丝袜美腿诱惑在线| 午夜福利影视在线免费观看| 精品久久久久久久毛片微露脸| 操出白浆在线播放| 老司机亚洲免费影院| 久久人妻福利社区极品人妻图片| 精品国内亚洲2022精品成人 | 少妇 在线观看| 中文字幕另类日韩欧美亚洲嫩草| 国产亚洲精品一区二区www | 亚洲综合色网址| 亚洲专区中文字幕在线| 最新的欧美精品一区二区| 夜夜骑夜夜射夜夜干| 女性生殖器流出的白浆| av一本久久久久| 无遮挡黄片免费观看| 欧美日韩福利视频一区二区| 欧美成人午夜精品| 亚洲七黄色美女视频| 成人精品一区二区免费| 欧美黄色片欧美黄色片| 亚洲欧洲日产国产| 国产在线观看jvid| 久久久精品国产亚洲av高清涩受| 黄色 视频免费看| 久久久国产成人免费| 12—13女人毛片做爰片一| 亚洲天堂av无毛| 精品福利观看| 精品国产乱码久久久久久男人| 我的亚洲天堂| 成年动漫av网址| 免费不卡黄色视频| 成人av一区二区三区在线看| 久久亚洲真实| 中文字幕精品免费在线观看视频| 国产午夜精品久久久久久| svipshipincom国产片| 在线观看人妻少妇| av福利片在线| 日韩一区二区三区影片| 国产免费福利视频在线观看| 国产1区2区3区精品| a级片在线免费高清观看视频| 亚洲成国产人片在线观看| 少妇粗大呻吟视频| 18在线观看网站| 国产精品国产高清国产av | 一本一本久久a久久精品综合妖精| 欧美成人免费av一区二区三区 | 日日爽夜夜爽网站| 亚洲第一青青草原| 国产精品 欧美亚洲| 天天躁狠狠躁夜夜躁狠狠躁| 制服诱惑二区| 在线观看66精品国产| 满18在线观看网站| 欧美日韩国产mv在线观看视频| 精品少妇黑人巨大在线播放| 色尼玛亚洲综合影院| 日韩视频在线欧美| 首页视频小说图片口味搜索| 涩涩av久久男人的天堂| 久久久久视频综合| 亚洲第一av免费看| 成年女人毛片免费观看观看9 | 欧美精品啪啪一区二区三区| 国产有黄有色有爽视频| 黑人操中国人逼视频| 人人妻人人澡人人爽人人夜夜| 午夜福利视频精品| 成年人免费黄色播放视频| 久久人人爽av亚洲精品天堂| 考比视频在线观看| 中文字幕色久视频| 丝袜喷水一区| 老司机午夜十八禁免费视频| 日韩制服丝袜自拍偷拍| 国产熟女午夜一区二区三区| 777久久人妻少妇嫩草av网站| 久久99一区二区三区| 欧美人与性动交α欧美软件| 狠狠婷婷综合久久久久久88av| 王馨瑶露胸无遮挡在线观看| 国产男女超爽视频在线观看| 热re99久久国产66热| 一个人免费在线观看的高清视频| 国产av国产精品国产| 性高湖久久久久久久久免费观看| 大片免费播放器 马上看| 99精国产麻豆久久婷婷| 精品久久久精品久久久| 精品国产一区二区三区久久久樱花| 一区二区三区国产精品乱码| 大香蕉久久网| 久久国产亚洲av麻豆专区| 五月开心婷婷网| 亚洲av成人一区二区三| 91成年电影在线观看| 欧美乱码精品一区二区三区| 免费观看人在逋| 我要看黄色一级片免费的| 欧美激情高清一区二区三区| 国产在视频线精品| 日本a在线网址| 成年版毛片免费区| 亚洲精品自拍成人| 国产老妇伦熟女老妇高清| a级毛片在线看网站| 中文亚洲av片在线观看爽 | 久久精品成人免费网站| 一边摸一边做爽爽视频免费| 大香蕉久久成人网| 成人av一区二区三区在线看| 亚洲国产av影院在线观看| 无遮挡黄片免费观看| 久久久久视频综合| 国产xxxxx性猛交| 国产亚洲午夜精品一区二区久久| 深夜精品福利| 午夜福利视频精品| 天堂中文最新版在线下载| 亚洲专区国产一区二区| 一区在线观看完整版| 国产亚洲精品第一综合不卡| 2018国产大陆天天弄谢| 国产不卡av网站在线观看| av天堂久久9| 男女床上黄色一级片免费看| 高潮久久久久久久久久久不卡| 国产三级黄色录像| 亚洲自偷自拍图片 自拍| 满18在线观看网站| 国产精品99久久99久久久不卡| 国产福利在线免费观看视频| 国产精品免费视频内射| a在线观看视频网站| 久久婷婷成人综合色麻豆| 精品国产一区二区久久| 亚洲成人免费av在线播放| 免费久久久久久久精品成人欧美视频| 亚洲成人国产一区在线观看| 久久青草综合色| 免费高清在线观看日韩| 成年人午夜在线观看视频| 在线观看免费日韩欧美大片| 亚洲av成人不卡在线观看播放网| 欧美另类亚洲清纯唯美| 人人妻人人爽人人添夜夜欢视频| 免费一级毛片在线播放高清视频 | av有码第一页|