Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492775
Ahmed Hafez, Hossam M. Zawbaa, E. Emary, Hamdi A. Mahmoud, A. Hassanien
In this paper, a system for feature selection based on chicken swarm optimization (CSO) algorithm is proposed. Datasets ordinarily includes a huge number of attributes, with irrelevant and redundant attribute. Commonly wrapper-based approaches are used for feature selection but it always requires an intelligent search technique as part of the evaluation function. Chicken swarm optimization (CSO)is a new bio-inspired algorithm mimicking the hierarchal order of the chicken swarm and the behaviors of chicken swarm, including roosters, hens and chicks, CSO can efficiently extract the chickens' swarm intelligence to optimize problems. Therefore, CSO was employed to feature selection in wrapper mode to search the feature space for optimal feature combination maximizing classification performance, while minimizing the number of selected features. The proposed system was benchmarked on 18 datasets drawn from the UCI repository and using different evaluation criteria and proves advance over particle swarm optimization (PSO) and genetic algorithms (GA) that commonly used in optimization problems.
{"title":"An innovative approach for feature selection based on chicken swarm optimization","authors":"Ahmed Hafez, Hossam M. Zawbaa, E. Emary, Hamdi A. Mahmoud, A. Hassanien","doi":"10.1109/SOCPAR.2015.7492775","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492775","url":null,"abstract":"In this paper, a system for feature selection based on chicken swarm optimization (CSO) algorithm is proposed. Datasets ordinarily includes a huge number of attributes, with irrelevant and redundant attribute. Commonly wrapper-based approaches are used for feature selection but it always requires an intelligent search technique as part of the evaluation function. Chicken swarm optimization (CSO)is a new bio-inspired algorithm mimicking the hierarchal order of the chicken swarm and the behaviors of chicken swarm, including roosters, hens and chicks, CSO can efficiently extract the chickens' swarm intelligence to optimize problems. Therefore, CSO was employed to feature selection in wrapper mode to search the feature space for optimal feature combination maximizing classification performance, while minimizing the number of selected features. The proposed system was benchmarked on 18 datasets drawn from the UCI repository and using different evaluation criteria and proves advance over particle swarm optimization (PSO) and genetic algorithms (GA) that commonly used in optimization problems.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114240138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492818
Qiuchen Cheng, Kun Ma, Bo Yang
As the load in the cloud environment is always changing, data migration become a key technology to realize the load balance of clusters. A good migration decision can make data migration more efficiency. To realize the migration decision rapidly, parallel Particle Swarm Optimization (PSO) based on stream computing technology is presented in this paper. We use PSO to get a migration plan with minimum overhead. Since the implementation of traditional PSO in serial is a huge waste of time in our scene, we design and accomplish Stream-based Particle Swarm Optimization (SPSO). SPSO utilizes stream computing technology to realize parallel PSO to make the process of data migration decision more rapidly and accurately, and realize real-time decisions on the basis of real-time status of nodes in the cloud. The average execution time of our SPSO is shorter than traditional serial PSO algorithm, and the migration cost of data migration decision result is lower.
{"title":"Stream-based Particle Swarm Optimization for data migration decision","authors":"Qiuchen Cheng, Kun Ma, Bo Yang","doi":"10.1109/SOCPAR.2015.7492818","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492818","url":null,"abstract":"As the load in the cloud environment is always changing, data migration become a key technology to realize the load balance of clusters. A good migration decision can make data migration more efficiency. To realize the migration decision rapidly, parallel Particle Swarm Optimization (PSO) based on stream computing technology is presented in this paper. We use PSO to get a migration plan with minimum overhead. Since the implementation of traditional PSO in serial is a huge waste of time in our scene, we design and accomplish Stream-based Particle Swarm Optimization (SPSO). SPSO utilizes stream computing technology to realize parallel PSO to make the process of data migration decision more rapidly and accurately, and realize real-time decisions on the basis of real-time status of nodes in the cloud. The average execution time of our SPSO is shorter than traditional serial PSO algorithm, and the migration cost of data migration decision result is lower.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124088801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492819
Munehiro Namba
There is a trend to introduce content caches as an inherent capacity of network device, such as routers, for improving the efficiency of content distribution and reducing network traffic. In this paper, we discuss the network state estimation in probabilistic caching based on a study with Bayesian inference, and propose a recursive estimation method for potentially improving the performance of adaptation to time-varying network state.
{"title":"A recursive estimation of network state for improving probabilistic caching","authors":"Munehiro Namba","doi":"10.1109/SOCPAR.2015.7492819","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492819","url":null,"abstract":"There is a trend to introduce content caches as an inherent capacity of network device, such as routers, for improving the efficiency of content distribution and reducing network traffic. In this paper, we discuss the network state estimation in probabilistic caching based on a study with Bayesian inference, and propose a recursive estimation method for potentially improving the performance of adaptation to time-varying network state.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"249 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122521034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492812
N. A. Mohamed, M. A. El-Azeim, Alaa Zaghloul, A. El-latif
In present time, in order to provide security of multimedia data while transmission and storage processes, the protection of image data can be accomplished using encryption. This paper presents a new image encryption scheme relaying on a chaotic 3D cat map and Turing machine in the form of dynamic random growth technique. The proposed technique composed of two processes of pixels' locations confusion using a chaotic 3D cat map, which is performed concurrently with substituting values swapping pixels' locations using Turing machine. The generated key is dependent on the plain image, to resist the chosen plaintext attack. Both experimental and security analysis show that the presented technique can achieve a large key space and resist the common against cipher attacks. These good cryptographic advantages make it suitable for image transmission over network.
{"title":"Image encryption scheme for secure digital images based on 3D cat map and Turing machine","authors":"N. A. Mohamed, M. A. El-Azeim, Alaa Zaghloul, A. El-latif","doi":"10.1109/SOCPAR.2015.7492812","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492812","url":null,"abstract":"In present time, in order to provide security of multimedia data while transmission and storage processes, the protection of image data can be accomplished using encryption. This paper presents a new image encryption scheme relaying on a chaotic 3D cat map and Turing machine in the form of dynamic random growth technique. The proposed technique composed of two processes of pixels' locations confusion using a chaotic 3D cat map, which is performed concurrently with substituting values swapping pixels' locations using Turing machine. The generated key is dependent on the plain image, to resist the chosen plaintext attack. Both experimental and security analysis show that the presented technique can achieve a large key space and resist the common against cipher attacks. These good cryptographic advantages make it suitable for image transmission over network.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124712189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492794
S. Yassen, T. Gaber, A. Hassanien
Thermal imaging is a technology with property of seeing objects in the darkness. Such property makes this technology very important tool for security and surveillance applications. In this paper, a thermal image authentication technique using hash function is proposed. In this technique, the thermal images are used as cover images and bits from secret data (i.e. messages or images) are then hidden in the cover images. This is achieved by using the hash function and Integer Wavelet Transform (IWT). 1, 2 and 3 bits per bytes have been hidden in both horizontal and vertical components of wavelet transform. The proposed technique has been evaluated based on mean square error (MSE), peak signal to noise ratio (PSNR), image fidelity (IF) and standard deviation (SD). The results have shown better performance of the proposed technique comparing with the most related work.
{"title":"Integer wavelet transform for thermal image authentication","authors":"S. Yassen, T. Gaber, A. Hassanien","doi":"10.1109/SOCPAR.2015.7492794","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492794","url":null,"abstract":"Thermal imaging is a technology with property of seeing objects in the darkness. Such property makes this technology very important tool for security and surveillance applications. In this paper, a thermal image authentication technique using hash function is proposed. In this technique, the thermal images are used as cover images and bits from secret data (i.e. messages or images) are then hidden in the cover images. This is achieved by using the hash function and Integer Wavelet Transform (IWT). 1, 2 and 3 bits per bytes have been hidden in both horizontal and vertical components of wavelet transform. The proposed technique has been evaluated based on mean square error (MSE), peak signal to noise ratio (PSNR), image fidelity (IF) and standard deviation (SD). The results have shown better performance of the proposed technique comparing with the most related work.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"440 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123425204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492814
Xiyan Chen, Q. Meng
Unmanned Aerial Vehicles have been used widely in the commercial and surveillance use in the recent year. Vehicle tracking from aerial video is one of commonly used application. In this paper, a self-learning mechanism has been proposed for the vehicle tracking in real time. The main contribution of this paper is that the proposed system can automatic detect and track multiple vehicles with a self-learning process leading to enhance the tracking and detection accuracy. Two detection methods have been used for the detection. The Features from Accelerated Segment Test (FAST) with Histograms of Oriented Gradient (HoG) method and the HSV colour feature with Grey Level Cooccurrence Matrix (GLCM) method have been proposed for the vehicle detection. A Forward and Backward Tracking (FBT) mechanism has been employed for the vehicle tracking. The main purpose of this research is to increase the vehicle detection accuracy by using the tracking results and the learning process, which can monitor the detection and tracking performance by using their outputs. Videos captured from UAVs have been used to evaluate the performance of the proposed method. According to the results, the proposed learning system can increase the detection performance.
{"title":"Robust vehicle tracking and detection from UAVs","authors":"Xiyan Chen, Q. Meng","doi":"10.1109/SOCPAR.2015.7492814","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492814","url":null,"abstract":"Unmanned Aerial Vehicles have been used widely in the commercial and surveillance use in the recent year. Vehicle tracking from aerial video is one of commonly used application. In this paper, a self-learning mechanism has been proposed for the vehicle tracking in real time. The main contribution of this paper is that the proposed system can automatic detect and track multiple vehicles with a self-learning process leading to enhance the tracking and detection accuracy. Two detection methods have been used for the detection. The Features from Accelerated Segment Test (FAST) with Histograms of Oriented Gradient (HoG) method and the HSV colour feature with Grey Level Cooccurrence Matrix (GLCM) method have been proposed for the vehicle detection. A Forward and Backward Tracking (FBT) mechanism has been employed for the vehicle tracking. The main purpose of this research is to increase the vehicle detection accuracy by using the tracking results and the learning process, which can monitor the detection and tracking performance by using their outputs. Videos captured from UAVs have been used to evaluate the performance of the proposed method. According to the results, the proposed learning system can increase the detection performance.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127665636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492815
M. Zsifkovits, M. S. Nistor, Silja Meyer-Nieberg
As recent attacks in trains and train stations show, the protections of such critical infrastructure plays a major role for public decision makers. Thereby, security installations in the railway network are a frequently discussed topic. Especially the need for an open system demands for technologies that do not influence or delay passenger flows. This also leads to the question of optimal placement of security installations such as smart camera systems or stand-off detectors. For answering this question we observed passenger flows in the Munich central station. The observation data was transferred into a quantitative network and analyzed using various measures. With its help, critical parameter constellations can be identified and investigated in detail. Furthermore we are able to identify special groups of passengers and the differences in their behavior.
{"title":"Quantitative network analysis for passenger pattern recognition: An analysis of railway stations","authors":"M. Zsifkovits, M. S. Nistor, Silja Meyer-Nieberg","doi":"10.1109/SOCPAR.2015.7492815","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492815","url":null,"abstract":"As recent attacks in trains and train stations show, the protections of such critical infrastructure plays a major role for public decision makers. Thereby, security installations in the railway network are a frequently discussed topic. Especially the need for an open system demands for technologies that do not influence or delay passenger flows. This also leads to the question of optimal placement of security installations such as smart camera systems or stand-off detectors. For answering this question we observed passenger flows in the Munich central station. The observation data was transferred into a quantitative network and analyzed using various measures. With its help, critical parameter constellations can be identified and investigated in detail. Furthermore we are able to identify special groups of passengers and the differences in their behavior.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126371151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492773
D. Nabil, Noussaiba Benadjimi, Meriem Romaissa Boubakeur, Layth Sliman, Fathelalem F. Ali
In the literature, several abscissae generation methods of chaff points in fingerprint fuzzy vault exist. In this paper, we make an experimental comparison between squares method and threshold methods. The experimental results show that the squares method is far better than methods based on threshold. But minutiae representation in squares method use 2D representation while threshold methods are represented by composite representation. We proposed to implements squares methods using composite representation and made same experiments which showed less gain of time.
{"title":"Fingerprint fuzzy vault chaff point generation by squares method","authors":"D. Nabil, Noussaiba Benadjimi, Meriem Romaissa Boubakeur, Layth Sliman, Fathelalem F. Ali","doi":"10.1109/SOCPAR.2015.7492773","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492773","url":null,"abstract":"In the literature, several abscissae generation methods of chaff points in fingerprint fuzzy vault exist. In this paper, we make an experimental comparison between squares method and threshold methods. The experimental results show that the squares method is far better than methods based on threshold. But minutiae representation in squares method use 2D representation while threshold methods are represented by composite representation. We proposed to implements squares methods using composite representation and made same experiments which showed less gain of time.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492802
Jun Yu, H. Takagi
We propose a method for clustering moving vectors oriented around two different local optima and some methods for improving the clustering performance. Evolutionary computation is an optimization method for finding the global optimum iteratively using multiple individuals; we propose a method for estimating the global optimum mathematically using the moving vectors between parent individuals and their offspring. Our proposed clustering method is the first to tackle the extension of the estimation method to multi-modal optimization. We describe the algorithm of the clustering method, the improvements made to the method, and the estimation performance for two local optima.
{"title":"Clustering of moving vectors for evolutionary computation","authors":"Jun Yu, H. Takagi","doi":"10.1109/SOCPAR.2015.7492802","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492802","url":null,"abstract":"We propose a method for clustering moving vectors oriented around two different local optima and some methods for improving the clustering performance. Evolutionary computation is an optimization method for finding the global optimum iteratively using multiple individuals; we propose a method for estimating the global optimum mathematically using the moving vectors between parent individuals and their offspring. Our proposed clustering method is the first to tackle the extension of the estimation method to multi-modal optimization. We describe the algorithm of the clustering method, the improvements made to the method, and the estimation performance for two local optima.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125224126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492800
Yuya Kaneda, Qiangfu Zhao, Yong Liu, Yan Pei
In this paper, we investigate proper strategies for determining the step size of the backpropagation (BP) algorithm for on-line learning. It is known that for off-line learning, the step size can be determined adaptively during learning. For on-line learning, since the same data may never appear again, we cannot use the same strategy proposed for off-line learning. If we do not update the neural network with a proper step size for on-line learning, the performance of the network may not be improved steadily. Here, we investigate four strategies for updating the step size. They are (1) constant, (2) random, (3) linearly decreasing, and (4) inversely proportional, respectively. The first strategy uses a constant step size during learning, the second strategy uses a random step size, the third strategy decreases the step size linearly, and the fourth strategy updates the step size inversely proportional to time. Experimental results show that, the third and the fourth strategies are more effective. In addition, compared with the third strategy, the fourth one is more stable, and usually can improve the performance steadily.
{"title":"Strategies for determining effective step size of the backpropagation algorithm for on-line learning","authors":"Yuya Kaneda, Qiangfu Zhao, Yong Liu, Yan Pei","doi":"10.1109/SOCPAR.2015.7492800","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492800","url":null,"abstract":"In this paper, we investigate proper strategies for determining the step size of the backpropagation (BP) algorithm for on-line learning. It is known that for off-line learning, the step size can be determined adaptively during learning. For on-line learning, since the same data may never appear again, we cannot use the same strategy proposed for off-line learning. If we do not update the neural network with a proper step size for on-line learning, the performance of the network may not be improved steadily. Here, we investigate four strategies for updating the step size. They are (1) constant, (2) random, (3) linearly decreasing, and (4) inversely proportional, respectively. The first strategy uses a constant step size during learning, the second strategy uses a random step size, the third strategy decreases the step size linearly, and the fourth strategy updates the step size inversely proportional to time. Experimental results show that, the third and the fourth strategies are more effective. In addition, compared with the third strategy, the fourth one is more stable, and usually can improve the performance steadily.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131732658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：