A new scheme for adaptive neural networks for nonlinear dynamic system identification is proposed in this paper. The network of structure multi-layer perceptron with external recurrence is trained offline at first to get the initial network parameters. The parameters of the network are classified into short-term memory part and long-term memory part. The short-term memory part includes the parameters which are linear to the network output. In the implementation, the network is validated in each sampling time using a set of new measurement data. Training procedure will be executed if the model error exceeds a specified value and the short-term memory part will be adjusted. The application in modelling of room thermal behaviour demonstrates the performance of the proposed scheme.
{"title":"Adaptive Neural Networks for Nonlinear Dynamic Systems Identification","authors":"Erwin Sitompul","doi":"10.1109/CIMSIM.2013.10","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.10","url":null,"abstract":"A new scheme for adaptive neural networks for nonlinear dynamic system identification is proposed in this paper. The network of structure multi-layer perceptron with external recurrence is trained offline at first to get the initial network parameters. The parameters of the network are classified into short-term memory part and long-term memory part. The short-term memory part includes the parameters which are linear to the network output. In the implementation, the network is validated in each sampling time using a set of new measurement data. Training procedure will be executed if the model error exceeds a specified value and the short-term memory part will be adjusted. The application in modelling of room thermal behaviour demonstrates the performance of the proposed scheme.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115478295","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}
Said Kerrache, Hafida Benhidour, Sahar Al-Homaidhi
The effectiveness of crowd evacuation is an important public safety issue. Crowd related incidents are frequent and often result in serious material and human loss, hence the increasing interest in developing new techniques to assist in crowd evacuation. In this paper, we introduce a new crowd evacuation method, where the evacuation plan is computed based on optimal transport. The use of the optimal transport formulation results in the minimization of the kinetic energy necessary to perform the evacuation, thus reducing the effort exercised by the crowd members. To ensure the safety and the feasibility of the computed plan, a safety model is introduced as an additional factor in the optimization. The proposed model allows avoiding dangerous places, spreading out the crowd, limiting the crowd density and imposing one-way circulation. A numerical method adapted to the resulting optimization problem is presented. The efficiency of the proposed approach is evaluated through simulation. The experimental results show that the proposed method computes a solution that strikes a balance between the different considered factors.
{"title":"An Optimal Transport-Based Approach for Crowd Evacuation","authors":"Said Kerrache, Hafida Benhidour, Sahar Al-Homaidhi","doi":"10.1109/CIMSIM.2013.31","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.31","url":null,"abstract":"The effectiveness of crowd evacuation is an important public safety issue. Crowd related incidents are frequent and often result in serious material and human loss, hence the increasing interest in developing new techniques to assist in crowd evacuation. In this paper, we introduce a new crowd evacuation method, where the evacuation plan is computed based on optimal transport. The use of the optimal transport formulation results in the minimization of the kinetic energy necessary to perform the evacuation, thus reducing the effort exercised by the crowd members. To ensure the safety and the feasibility of the computed plan, a safety model is introduced as an additional factor in the optimization. The proposed model allows avoiding dangerous places, spreading out the crowd, limiting the crowd density and imposing one-way circulation. A numerical method adapted to the resulting optimization problem is presented. The efficiency of the proposed approach is evaluated through simulation. The experimental results show that the proposed method computes a solution that strikes a balance between the different considered factors.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125294994","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}
This paper presents the simulation study of magneto-rheological (MR) damper and hydraulic actuator for suspension system using intelligent PID controller with iterative learning algorithm. The MR damper is an intelligent damper filled with particle magnetic polarizable and suspended into a liquid form. This actuator was installed to the semi-active suspension system as a variable damper. The Bouc Wen model of MR damper was used to determine the required damper force based on the force-displacement and force velocity characteristic. For the purpose of comparison of performance, a hydraulic actuator, working as an additional damper, was installed within an active suspension system. Two different disturbances namely bump and random disturbances were introduced as the road profile. The performances of theproposed actuators were investigated in term of body displacement, velocity and acceleration. The results indicated the active system based on hydraulic actuator was better than semi-active based on MR damper and passive system in term of the body displacement, velocity and acceleration.
{"title":"Self-Tuning PID Controller with MR damper and Hydraulic Actuator for Suspension System","authors":"M. H. Ab Talib, I. Darus","doi":"10.1109/CIMSIM.2013.27","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.27","url":null,"abstract":"This paper presents the simulation study of magneto-rheological (MR) damper and hydraulic actuator for suspension system using intelligent PID controller with iterative learning algorithm. The MR damper is an intelligent damper filled with particle magnetic polarizable and suspended into a liquid form. This actuator was installed to the semi-active suspension system as a variable damper. The Bouc Wen model of MR damper was used to determine the required damper force based on the force-displacement and force velocity characteristic. For the purpose of comparison of performance, a hydraulic actuator, working as an additional damper, was installed within an active suspension system. Two different disturbances namely bump and random disturbances were introduced as the road profile. The performances of theproposed actuators were investigated in term of body displacement, velocity and acceleration. The results indicated the active system based on hydraulic actuator was better than semi-active based on MR damper and passive system in term of the body displacement, velocity and acceleration.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121665827","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}
This paper proposes an automated system for discrimination between melanocytic nevi and malignantmelanoma. The proposed system used a number of featuresextracted from histo-pathological images of skin lesionsthrough image processing techniques which consisted of aspatially adaptive color median filter for filtering and a Kmeansclustering for segmentation. The extracted featureswere reduced by using sequential feature selection and thenclassified by using support vector machine (SVM) to diagnoseskin biopsies from patients as either malignant melanoma orbenign nevi. The proposed system was able to achieve a goodresult with classification accuracy of 88.9%, sensitivity of87.5% and specificity of 100%.
{"title":"Classification of Malignant Melanoma and Benign Nevi from Skin Lesions Based on Support Vector Machine","authors":"M. A. Mahmoud, Adel Al-Jumaily, Y. Maali, K. Anam","doi":"10.1109/CIMSIM.2013.45","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.45","url":null,"abstract":"This paper proposes an automated system for discrimination between melanocytic nevi and malignantmelanoma. The proposed system used a number of featuresextracted from histo-pathological images of skin lesionsthrough image processing techniques which consisted of aspatially adaptive color median filter for filtering and a Kmeansclustering for segmentation. The extracted featureswere reduced by using sequential feature selection and thenclassified by using support vector machine (SVM) to diagnoseskin biopsies from patients as either malignant melanoma orbenign nevi. The proposed system was able to achieve a goodresult with classification accuracy of 88.9%, sensitivity of87.5% and specificity of 100%.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129022495","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}
Sayeed Islam, S. Rahman, Billal Hossain, Aliyu Ahmed
In this paper, a new and efficient approach for Orthogonal Frequency-Division Multiplexing (OFDM) timing offset error estimation has been presented without using pilot signal. The effect of timing offset on bit error rate (BER) has been analyzed using BPSK, QPSK, 8-PSK modulation scheme and an analytical expression has been derived using probabilistic equation to estimate timing offset. This will guide us to determine the best modulation scheme and also the actual length of CP which allows more spectral efficient OFDM system. Simulation results show that when SNR is decreased BER increases and BPSK shows superior performance among other modulation schemes, when SNR is lower and in presence and absence of timing offset. The analytically derived estimator is precise and useful.
{"title":"OFDM Timing Offset Estimation with Efficient Methodology and Observation of Different Modulation Schemes","authors":"Sayeed Islam, S. Rahman, Billal Hossain, Aliyu Ahmed","doi":"10.1109/CIMSIM.2013.64","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.64","url":null,"abstract":"In this paper, a new and efficient approach for Orthogonal Frequency-Division Multiplexing (OFDM) timing offset error estimation has been presented without using pilot signal. The effect of timing offset on bit error rate (BER) has been analyzed using BPSK, QPSK, 8-PSK modulation scheme and an analytical expression has been derived using probabilistic equation to estimate timing offset. This will guide us to determine the best modulation scheme and also the actual length of CP which allows more spectral efficient OFDM system. Simulation results show that when SNR is decreased BER increases and BPSK shows superior performance among other modulation schemes, when SNR is lower and in presence and absence of timing offset. The analytically derived estimator is precise and useful.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128083180","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}
In this paper we propose a methodology for investigating the impact of basic Network-on-Chip (NoC) parameters and self-adaptive scheme in the context of the Field Programmable Gate Array (FPGA). With our proposed methodology that is based on the Bayesian networking model we examined the effects of flit buffer depth, flit data width and virtual channel parameters through an extensive experimentation and simulation for scalable and adaptive NoC on Xilinx Virtex7 FPGA device. To demonstrate the flexibility and extensible design space coverage of our methodology, we design and present hardware synthesis results of 96 different NoCs configurations. We used a cycle accurate simulation system and drive the NoCs with four different traffic patterns and varying number of virtual channels (VCs) and show the resulting load-delay curves. Our results show that, for scalable and adaptive NoC, the flit data width and flit buffer depth parameters have the largest impact on FPGA area and clock frequency. We show that these parameters need to be properly adjusted for better run-time performance of the FPGA. Moreover, the neighbor traffic pattern with 4 VCs offer the best performance with 95% throughput, low latency and efficient silicon area in both Mesh and Torus networks.
{"title":"Examining the Performance Impact of NoC Parameters for Scalable and Adaptive FPGA-Based Network-on-Chips","authors":"S. Abba, Jeong-A Lee","doi":"10.1109/CIMSIM.2013.65","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.65","url":null,"abstract":"In this paper we propose a methodology for investigating the impact of basic Network-on-Chip (NoC) parameters and self-adaptive scheme in the context of the Field Programmable Gate Array (FPGA). With our proposed methodology that is based on the Bayesian networking model we examined the effects of flit buffer depth, flit data width and virtual channel parameters through an extensive experimentation and simulation for scalable and adaptive NoC on Xilinx Virtex7 FPGA device. To demonstrate the flexibility and extensible design space coverage of our methodology, we design and present hardware synthesis results of 96 different NoCs configurations. We used a cycle accurate simulation system and drive the NoCs with four different traffic patterns and varying number of virtual channels (VCs) and show the resulting load-delay curves. Our results show that, for scalable and adaptive NoC, the flit data width and flit buffer depth parameters have the largest impact on FPGA area and clock frequency. We show that these parameters need to be properly adjusted for better run-time performance of the FPGA. Moreover, the neighbor traffic pattern with 4 VCs offer the best performance with 95% throughput, low latency and efficient silicon area in both Mesh and Torus networks.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125225101","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}
For implementation of Cyber-Physical Systems (CPS) simulation, interoperability between physical and cyber system are required. IEEE High Level Architecture (HLA) is standard for distributed simulation interoperability, and ETSI Machine-to-Machine (M2M) is standard for integration between physical machines. In this paper, we propose M2MHLA adaptor to integrate HLA-based simulations and M2M physical machines. M2M-HLA adaptor is located between HLA simulation systems and M2M systems. This adaptor transforms HLA data to M2M data and M2M data to HLA data. We propose sequence structure between M2M-HLA APIs for interconnection, data type definition and transformation method and time management method for design and implementation M2M-HLA adaptor. Because of M2M-HLA adaptor allows interoperability between different cyber systems and physical systems, this would extend the scope of CPS simulation system and increase its utilization.
{"title":"Design and Implementation of M2M-HLA Adaptor for Integration of ETSI M2M Platform and IEEE HLA-Based Simulation System","authors":"Yunjung Park, D. Min","doi":"10.1109/CIMSIM.2013.57","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.57","url":null,"abstract":"For implementation of Cyber-Physical Systems (CPS) simulation, interoperability between physical and cyber system are required. IEEE High Level Architecture (HLA) is standard for distributed simulation interoperability, and ETSI Machine-to-Machine (M2M) is standard for integration between physical machines. In this paper, we propose M2MHLA adaptor to integrate HLA-based simulations and M2M physical machines. M2M-HLA adaptor is located between HLA simulation systems and M2M systems. This adaptor transforms HLA data to M2M data and M2M data to HLA data. We propose sequence structure between M2M-HLA APIs for interconnection, data type definition and transformation method and time management method for design and implementation M2M-HLA adaptor. Because of M2M-HLA adaptor allows interoperability between different cyber systems and physical systems, this would extend the scope of CPS simulation system and increase its utilization.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125534644","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}
Conventional sonar offers low-resolution imaging of a target region. Synthetic aperture sonar (SAS) modeling ischallenging than the conventional systems because the towfish path geometry is more complicated and the data are usually non stationary. This paper investigates the application of synthetic aperture technique to sonar image and develops a new model for two-dimensional (2-D) SAS target feature extraction. The technique is shown to be accurate at resolving. Time-domain algorithms can handle general sonar cases, but they are very inefficient; therefore, frequency-domain methods are preferred. In this paper, we discuss the chirp scaling algorithm (CSA) to handle SAS data. An attempt is then made to overcome some of the motion errors inherent in the current 2-D SAS. Simulations are implemented and the accuracy of the technique is assessed.
{"title":"Modelling and Enhancement of Stripmap Mode Coherent Sonar","authors":"R. Sathishkumar, P. J. A. Vignesh, H. R. Babu","doi":"10.1109/CIMSIM.2013.46","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.46","url":null,"abstract":"Conventional sonar offers low-resolution imaging of a target region. Synthetic aperture sonar (SAS) modeling ischallenging than the conventional systems because the towfish path geometry is more complicated and the data are usually non stationary. This paper investigates the application of synthetic aperture technique to sonar image and develops a new model for two-dimensional (2-D) SAS target feature extraction. The technique is shown to be accurate at resolving. Time-domain algorithms can handle general sonar cases, but they are very inefficient; therefore, frequency-domain methods are preferred. In this paper, we discuss the chirp scaling algorithm (CSA) to handle SAS data. An attempt is then made to overcome some of the motion errors inherent in the current 2-D SAS. Simulations are implemented and the accuracy of the technique is assessed.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126974956","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}
Don Buddhika Wijayantha Nettasinghe, T. A. Ratnayake, N. N. Pollwaththage, G. Godaliyadda, J. Wijayakulasooriya, M. Ekanayake
This paper proposes a subspace based classifier, which can separate highly correlated acoustic signals based on source material. In this method, the optimum set of Eigen-filters that form the subspace classifier are selected such that the cross correlation between different classes is minimized. The proposed method has high noise immunity as the noise subspace is eliminated at the subspace separation stage. Then the resolution of the subspace classifier is varied and its impact is analyzed for the given set of signals. Finally, robustness and the practicality of the proposed classifier is verified by applying it for two application scenarios, namely, "decision making in cricket" and "hidden information extraction from speech signals in order to reveal the speaker identity".
{"title":"A Robust Subspace Classification Method for Highly Correlated Acoustic Signals","authors":"Don Buddhika Wijayantha Nettasinghe, T. A. Ratnayake, N. N. Pollwaththage, G. Godaliyadda, J. Wijayakulasooriya, M. Ekanayake","doi":"10.1109/CIMSIM.2013.43","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.43","url":null,"abstract":"This paper proposes a subspace based classifier, which can separate highly correlated acoustic signals based on source material. In this method, the optimum set of Eigen-filters that form the subspace classifier are selected such that the cross correlation between different classes is minimized. The proposed method has high noise immunity as the noise subspace is eliminated at the subspace separation stage. Then the resolution of the subspace classifier is varied and its impact is analyzed for the given set of signals. Finally, robustness and the practicality of the proposed classifier is verified by applying it for two application scenarios, namely, \"decision making in cricket\" and \"hidden information extraction from speech signals in order to reveal the speaker identity\".","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123085877","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}
In this paper we compare the performance of back propagation and resilient propagation algorithms in training neural networks for spam classification. Back propagation algorithm is known to have issues such as slow convergence, and stagnation of neural network weights around local optima. Researchers have proposed resilient propagation as an alternative. Resilient propagation and back propagation are very much similar except for the weight update routine. Resilient propagation does not take into account the value of the partial derivative (error gradient), but rather considers only the sign of the error gradient to indicate the direction of the weight update. We show that resilient propagation yields faster convergence and higher accuracy on the UCI Spambase dataset.
{"title":"Comparison of Back Propagation and Resilient Propagation Algorithm for Spam Classification","authors":"Navneel Prasad, Rajeshni Singh, S. Lal","doi":"10.1109/CIMSIM.2013.14","DOIUrl":"https://doi.org/10.1109/CIMSIM.2013.14","url":null,"abstract":"In this paper we compare the performance of back propagation and resilient propagation algorithms in training neural networks for spam classification. Back propagation algorithm is known to have issues such as slow convergence, and stagnation of neural network weights around local optima. Researchers have proposed resilient propagation as an alternative. Resilient propagation and back propagation are very much similar except for the weight update routine. Resilient propagation does not take into account the value of the partial derivative (error gradient), but rather considers only the sign of the error gradient to indicate the direction of the weight update. We show that resilient propagation yields faster convergence and higher accuracy on the UCI Spambase dataset.","PeriodicalId":249355,"journal":{"name":"2013 Fifth International Conference on Computational Intelligence, Modelling and Simulation","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115172094","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：