Pub Date : 2018-01-01DOI: 10.1109/CEC.2018.8477938
Pedro Henriquede Oliveira Santos, G. L. Soares, T. M. Machado-Coelho, Bernardo Augusto Godinho de Oliveira, P. Ekel, F. M. F. Ferreira, C. D. S. Martins
{"title":"Multi-Objective Genetic Algorithm Implemented on a STM32F Microcontroller","authors":"Pedro Henriquede Oliveira Santos, G. L. Soares, T. M. Machado-Coelho, Bernardo Augusto Godinho de Oliveira, P. Ekel, F. M. F. Ferreira, C. D. S. Martins","doi":"10.1109/CEC.2018.8477938","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477938","url":null,"abstract":"","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"40 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79049887","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 : 2018-01-01DOI: 10.1109/CEC.2018.8477936
T. P. Ferreira, L. F. Almeida, Juan G. Lazo Lazo
The majority of the countries use oil as the main source of their energetic matrices. Techniques of Enhanced Oil Recovery (EOR) have been widely used with the aim of increasing oil and gas recovery trapped in oil reservoir, as 011 as improving the sweep and displacement efficiency. The use of tertiary (or advanced) recovery techniques such as Water Alternating Gas (WAG) injection has been considered promising to attend the expectations of improving the oil recovery, at the same it contributes with changes in some chemical properties of the reservoir that facilitate its exploitation. This paper describes the optimization of a water alternating gas injection strategy in an oil reservoir taking into account techniques of Evolutionary Computing used for maximizing the Net Present Value (NPV) of the field in analysis. It was created a program, developed in JAVA, that performs the optimization through the use of the custom evolutionary algorithm implemented and also uses the commercial software $mathbf{GEM}^{bigcirc!!!text{R}}$ , which executes the numerical simulation and deliver important data to the optimizer.
{"title":"Optimization of the Water Alternating Gas Injection Strategy in an Oil Reservoir Using Evolutionary Algorithms","authors":"T. P. Ferreira, L. F. Almeida, Juan G. Lazo Lazo","doi":"10.1109/CEC.2018.8477936","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477936","url":null,"abstract":"The majority of the countries use oil as the main source of their energetic matrices. Techniques of Enhanced Oil Recovery (EOR) have been widely used with the aim of increasing oil and gas recovery trapped in oil reservoir, as 011 as improving the sweep and displacement efficiency. The use of tertiary (or advanced) recovery techniques such as Water Alternating Gas (WAG) injection has been considered promising to attend the expectations of improving the oil recovery, at the same it contributes with changes in some chemical properties of the reservoir that facilitate its exploitation. This paper describes the optimization of a water alternating gas injection strategy in an oil reservoir taking into account techniques of Evolutionary Computing used for maximizing the Net Present Value (NPV) of the field in analysis. It was created a program, developed in JAVA, that performs the optimization through the use of the custom evolutionary algorithm implemented and also uses the commercial software $mathbf{GEM}^{bigcirc!!!text{R}}$ , which executes the numerical simulation and deliver important data to the optimizer.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"47 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76876516","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 : 2018-01-01DOI: 10.1109/CEC.2018.8477957
Victor Henrique Alves Ribeiro, G. Reynoso-Meza
{"title":"Multi-objective PID Controller Tuning for an Industrial Gasifier","authors":"Victor Henrique Alves Ribeiro, G. Reynoso-Meza","doi":"10.1109/CEC.2018.8477957","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477957","url":null,"abstract":"","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"49 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90830837","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 : 2017-06-01DOI: 10.1109/CEC.2017.7969451
F. F. Vega
The four-part harmonization problem is a well known problem that has been studied in the last three centuries by music scholars. The goal is to build up three different voices, melodies, based on a previously provided one, being it a soprano melody or a bass instead, so that a complete soprano, alto, tenor and bass (SATB) score is completed.
{"title":"Revisiting the 4-part harmonization problem with GAs: A critical review and proposals for improving","authors":"F. F. Vega","doi":"10.1109/CEC.2017.7969451","DOIUrl":"https://doi.org/10.1109/CEC.2017.7969451","url":null,"abstract":"The four-part harmonization problem is a well known problem that has been studied in the last three centuries by music scholars. The goal is to build up three different voices, melodies, based on a previously provided one, being it a soprano melody or a bass instead, so that a complete soprano, alto, tenor and bass (SATB) score is completed.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"1 1","pages":"1271-1278"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79825438","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 : 2016-07-24DOI: 10.1109/CEC.2016.7743910
C. H. Antunes, D. Margarida
The distribution network is the most exposed part of water supply systems due to the large number and geographical dispersion of derivation nodes and access points. Therefore, a reliable monitoring and surveillance system based on a sensor network is necessary to timely detect contamination events. The sensor location problem in water distribution networks to detect (accidental or intentional) contamination events has been tackled by optimization approaches aimed to determine the best location for a set of sensors, thus allowing the management entity to detect those events in a short period of time and be able to minimize their impact on the population served. This paper presents a multiobjective evolutionary approach to determine the location of sensors in a water distribution network to detect a contamination event and minimize its potential consequences according to multiple, incommensurate and conflicting evaluation aspects of the merits of each solution. The objective functions are the expected time of detection, the expected population affected prior to detection, the expected consumption of contaminated water prior to detection, and the detection likelihood. A set of nondominated solutions representing the Pareto front is obtained, which have been validated with known solutions for the case studies. Further, this information enables to exploit tradeoffs and identify good compromise solutions according to the decision maker's preferences.
{"title":"Sensor location in water distribution networks to detect contamination events - A multiobjective approach based on NSGA-II","authors":"C. H. Antunes, D. Margarida","doi":"10.1109/CEC.2016.7743910","DOIUrl":"https://doi.org/10.1109/CEC.2016.7743910","url":null,"abstract":"The distribution network is the most exposed part of water supply systems due to the large number and geographical dispersion of derivation nodes and access points. Therefore, a reliable monitoring and surveillance system based on a sensor network is necessary to timely detect contamination events. The sensor location problem in water distribution networks to detect (accidental or intentional) contamination events has been tackled by optimization approaches aimed to determine the best location for a set of sensors, thus allowing the management entity to detect those events in a short period of time and be able to minimize their impact on the population served. This paper presents a multiobjective evolutionary approach to determine the location of sensors in a water distribution network to detect a contamination event and minimize its potential consequences according to multiple, incommensurate and conflicting evaluation aspects of the merits of each solution. The objective functions are the expected time of detection, the expected population affected prior to detection, the expected consumption of contaminated water prior to detection, and the detection likelihood. A set of nondominated solutions representing the Pareto front is obtained, which have been validated with known solutions for the case studies. Further, this information enables to exploit tradeoffs and identify good compromise solutions according to the decision maker's preferences.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"15 1","pages":"1093-1099"},"PeriodicalIF":0.0,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88462561","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 : 2016-07-01DOI: 10.1109/CEC.2016.7744058
M. L. D. Dias, A. Neto
A theoretical advantage of large margin classifiers such as Support Vector Machines (SVM) concerns the empirical and structural risk minimization which balances the model complexity against its success at fitting the training data. Metaheuristics have been used in order to select features, to tune hyperparameters or even to achieve a reduced-set of support vectors for SVM. Although these tasks are interesting, metaheuristics do not play an important role in the process of solving the dual quadratic optimization problem, which arises from Support Vector Machines. Well-known methods such as, Sequential Minimal Optimization, Kernel Adatron and classical mathematical methods have been applied with this goal. In this paper, we propose the use of Genetic Algorithms to solve such quadratic optimization problem. Our proposal is promising when compared with those aforementioned methods because it does not need complex mathematical calculations and, indeed, the problem is solved in an astonishingly straightforward way. To achieve this goal, we successfully model an instance of Genetic Algorithms to handle the dual optimization problem and its constraints in order to obtain the Lagrange multipliers as well as the bias for the decision function.
{"title":"Evolutionary support vector machines: A dual approach","authors":"M. L. D. Dias, A. Neto","doi":"10.1109/CEC.2016.7744058","DOIUrl":"https://doi.org/10.1109/CEC.2016.7744058","url":null,"abstract":"A theoretical advantage of large margin classifiers such as Support Vector Machines (SVM) concerns the empirical and structural risk minimization which balances the model complexity against its success at fitting the training data. Metaheuristics have been used in order to select features, to tune hyperparameters or even to achieve a reduced-set of support vectors for SVM. Although these tasks are interesting, metaheuristics do not play an important role in the process of solving the dual quadratic optimization problem, which arises from Support Vector Machines. Well-known methods such as, Sequential Minimal Optimization, Kernel Adatron and classical mathematical methods have been applied with this goal. In this paper, we propose the use of Genetic Algorithms to solve such quadratic optimization problem. Our proposal is promising when compared with those aforementioned methods because it does not need complex mathematical calculations and, indeed, the problem is solved in an astonishingly straightforward way. To achieve this goal, we successfully model an instance of Genetic Algorithms to handle the dual optimization problem and its constraints in order to obtain the Lagrange multipliers as well as the bias for the decision function.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"9 1","pages":"2185-2192"},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87452180","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 : 2016-07-01DOI: 10.1109/CEC.2016.7743866
B. Beirigo, A. G. Santos
In this paper we assess the performance of the classic NSGA-II algorithm when applied to a broad and realistic formulation of a bi-objective travel planning problem. Given a set of destinations and a travel time window, our goal is to find a Pareto set of detailed travel itineraries, which are both cost and time efficient. When the sequence of cities is fixed, the travel planning problem is commonly modeled in literature as a time-dependent network and the best itinerary is computed using shortest path algorithms. However, in our formulation, finding the order of cities that produces a good trade-off solution is also a goal. Additionally, a set of nondominated solutions must be provided to the tourist so that he/she can choose the best option based on his/her own preferences. Then, our formulation is built as a bi-objective Time Dependent Shortest Path Problem (TDSPP) embedded in a bi-objective Travel Salesman Problem (TSP). For managing the process of creation and evolving a population of routes, we apply a parallelized version of the NSGA-II framework. We present experimental results on 180 real-world instances, and show that, given 1 minute of execution, our approach is able to reach an approximated solution in average up to 10% divergent from an exact implementation.
{"title":"Application of NSGA-II framework to the travel planning problem using real-world travel data","authors":"B. Beirigo, A. G. Santos","doi":"10.1109/CEC.2016.7743866","DOIUrl":"https://doi.org/10.1109/CEC.2016.7743866","url":null,"abstract":"In this paper we assess the performance of the classic NSGA-II algorithm when applied to a broad and realistic formulation of a bi-objective travel planning problem. Given a set of destinations and a travel time window, our goal is to find a Pareto set of detailed travel itineraries, which are both cost and time efficient. When the sequence of cities is fixed, the travel planning problem is commonly modeled in literature as a time-dependent network and the best itinerary is computed using shortest path algorithms. However, in our formulation, finding the order of cities that produces a good trade-off solution is also a goal. Additionally, a set of nondominated solutions must be provided to the tourist so that he/she can choose the best option based on his/her own preferences. Then, our formulation is built as a bi-objective Time Dependent Shortest Path Problem (TDSPP) embedded in a bi-objective Travel Salesman Problem (TSP). For managing the process of creation and evolving a population of routes, we apply a parallelized version of the NSGA-II framework. We present experimental results on 180 real-world instances, and show that, given 1 minute of execution, our approach is able to reach an approximated solution in average up to 10% divergent from an exact implementation.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"33 suppl 1 1","pages":"746-753"},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89305548","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 : 2016-07-01DOI: 10.1109/CEC.2016.7743938
Karine da Silva Miras de Araújo, F. O. França
Computational Intelligence in Games comprises many challenges such as the procedural level generation, evolving adversary difficulty and the learning of autonomous playing agents. This last challenge has the objective of creating an autonomous playing agent capable of winning against an opponent on an specific game. Whereas a human being can learn a general winning strategy (i.e., avoid the obstacles and defeat the enemies), learning algorithms have a tendency to overspecialize for a given training scenario (i.e., perform an exact sequence of actions to win), not being able to face variations of the original scenario. To further study this problem, we have applied three variations of Neuroevolution algorithms to the EvoMan game playing learning framework with the main objective of developing an autonomous agent capable of playing in different scenarios than those observed during the training stages. This framework is based on the bosses fights of the well known game called Mega Man. The experiments show that the evolved agents are not capable of winning every challenge imposed to them but they are still capable of learning a generalized behavior.
{"title":"Evolving a generalized strategy for an action-platformer video game framework","authors":"Karine da Silva Miras de Araújo, F. O. França","doi":"10.1109/CEC.2016.7743938","DOIUrl":"https://doi.org/10.1109/CEC.2016.7743938","url":null,"abstract":"Computational Intelligence in Games comprises many challenges such as the procedural level generation, evolving adversary difficulty and the learning of autonomous playing agents. This last challenge has the objective of creating an autonomous playing agent capable of winning against an opponent on an specific game. Whereas a human being can learn a general winning strategy (i.e., avoid the obstacles and defeat the enemies), learning algorithms have a tendency to overspecialize for a given training scenario (i.e., perform an exact sequence of actions to win), not being able to face variations of the original scenario. To further study this problem, we have applied three variations of Neuroevolution algorithms to the EvoMan game playing learning framework with the main objective of developing an autonomous agent capable of playing in different scenarios than those observed during the training stages. This framework is based on the bosses fights of the well known game called Mega Man. The experiments show that the evolved agents are not capable of winning every challenge imposed to them but they are still capable of learning a generalized behavior.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"38 1","pages":"1303-1310"},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79938889","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 : 2016-07-01DOI: 10.1109/CEC.2016.7743898
Edgar Manoatl Lopez, C. Coello
In recent years, the design of selection mechanisms based on performance indicators has become a very popular trend in the development of new Multi-Objective Evolutionary Algorithms (MOEAs). The main motivation has been the well-known limitations of Pareto-based MOEAs when dealing with problems having four or more objectives (the so-called many-objective problems). The most commonly adopted indicator has been the hypervolume, mainly because of its nice mathematical properties (e.g., it is the only unary indicator which is known to be Pareto compliant). However, the hypervolume has a well-known disadvantage: its exact computation is very costly in high dimensionality, making it prohibitive for many-objective problems (this cost normally becomes unaffordable for problems with more than 5 objectives). Recently, a variation of the well-known inverse generational distance (IGD) was introduced. This indicator, which is called IGD+ was shown to be weakly Pareto compliant, and presents some evident advantages with respect to the original IGD. Here, we propose an indicator-based MOEA, which adopts IGD+. The proposed approach adopts a novel technique for building the reference set, which is used to assess the quality of the solutions obtained during the search. Our preliminary results indicate that our proposed approach is able to solve many-objective problems in an effective and efficient manner, being able to obtain solutions of a similar quality to those obtained by SMS-EMOA and MOEA/D, but at a much lower computational cost than required by the computation of exact hypervolume contributions (as adopted in SMS-EMOA).
{"title":"IGD+-EMOA: A multi-objective evolutionary algorithm based on IGD+","authors":"Edgar Manoatl Lopez, C. Coello","doi":"10.1109/CEC.2016.7743898","DOIUrl":"https://doi.org/10.1109/CEC.2016.7743898","url":null,"abstract":"In recent years, the design of selection mechanisms based on performance indicators has become a very popular trend in the development of new Multi-Objective Evolutionary Algorithms (MOEAs). The main motivation has been the well-known limitations of Pareto-based MOEAs when dealing with problems having four or more objectives (the so-called many-objective problems). The most commonly adopted indicator has been the hypervolume, mainly because of its nice mathematical properties (e.g., it is the only unary indicator which is known to be Pareto compliant). However, the hypervolume has a well-known disadvantage: its exact computation is very costly in high dimensionality, making it prohibitive for many-objective problems (this cost normally becomes unaffordable for problems with more than 5 objectives). Recently, a variation of the well-known inverse generational distance (IGD) was introduced. This indicator, which is called IGD+ was shown to be weakly Pareto compliant, and presents some evident advantages with respect to the original IGD. Here, we propose an indicator-based MOEA, which adopts IGD+. The proposed approach adopts a novel technique for building the reference set, which is used to assess the quality of the solutions obtained during the search. Our preliminary results indicate that our proposed approach is able to solve many-objective problems in an effective and efficient manner, being able to obtain solutions of a similar quality to those obtained by SMS-EMOA and MOEA/D, but at a much lower computational cost than required by the computation of exact hypervolume contributions (as adopted in SMS-EMOA).","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"44 1","pages":"999-1006"},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87768283","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 : 2016-07-01DOI: 10.1109/CEC.2016.7744370
A. Garza
We use an evolutionary algorithm in which we change the fitness function periodically to model the fact that objectives can change during creative problem solving. We performed an experiment to observe the behavior of the evolutionary algorithm regarding its response to these changes and its ability to successfully generate solutions for its creative task despite the changes. An analysis of the results of this experiment sheds some light into the conditions under which the evolutionary algorithm can respond with varying degrees of robustness to the changes.
{"title":"Modifying the fitness function during the use of an evolutionary algorithm for design","authors":"A. Garza","doi":"10.1109/CEC.2016.7744370","DOIUrl":"https://doi.org/10.1109/CEC.2016.7744370","url":null,"abstract":"We use an evolutionary algorithm in which we change the fitness function periodically to model the fact that objectives can change during creative problem solving. We performed an experiment to observe the behavior of the evolutionary algorithm regarding its response to these changes and its ability to successfully generate solutions for its creative task despite the changes. An analysis of the results of this experiment sheds some light into the conditions under which the evolutionary algorithm can respond with varying degrees of robustness to the changes.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"34 1","pages":"4555-4561"},"PeriodicalIF":0.0,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76608656","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：