Aaron Rocha-Rocha, E. M. D. Cote, S. Hernández, E. Succar
Many real world applications demand solutions that are difficult to implement. It is common practice for system designers to recur to multiagent theory, where the problem at hand is broken in sub-problems and each is handled by an autonomous agent. Notwithstanding, new questions emerge, like How should a problem be broken? What the task of each agent should be? And What information should they need to process their task? In addition, conflicts between agents' partial solutions (actions) may arise as a consequence of their autonomy. In this spirit, another question would be how should conflicts be solved? In this paper we conduct a study to answer some of those questions under a multiagent learning framework. The proposed framework guarantees an optimal solution to the original problem, at the cost of a low learning speed, but can be tuned to balance learning speed and optimality. We present an experimental analysis that shows learning curves until convergence to optimality, illustrating the trade-offs between learning speeds and optimality.
{"title":"Conflict Resolution in Multiagent Systems: Balancing Optimality and Learning Speed","authors":"Aaron Rocha-Rocha, E. M. D. Cote, S. Hernández, E. Succar","doi":"10.1109/MICAI.2012.16","DOIUrl":"https://doi.org/10.1109/MICAI.2012.16","url":null,"abstract":"Many real world applications demand solutions that are difficult to implement. It is common practice for system designers to recur to multiagent theory, where the problem at hand is broken in sub-problems and each is handled by an autonomous agent. Notwithstanding, new questions emerge, like How should a problem be broken? What the task of each agent should be? And What information should they need to process their task? In addition, conflicts between agents' partial solutions (actions) may arise as a consequence of their autonomy. In this spirit, another question would be how should conflicts be solved? In this paper we conduct a study to answer some of those questions under a multiagent learning framework. The proposed framework guarantees an optimal solution to the original problem, at the cost of a low learning speed, but can be tuned to balance learning speed and optimality. We present an experimental analysis that shows learning curves until convergence to optimality, illustrating the trade-offs between learning speeds and optimality.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114817573","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}
A famous field in which it is very possible for each typical dataset to be imbalanced and hard is physician recognition. In such systems there are many customers where a few of them are patient and the others are healthy. So it is very common and possible for a dataset to emerge an imbalanced one. In such a system it is desired to distinguish a patient from a mixture of customers. In a breast cancer detection that is a special case of the mentioned systems, it is desired to discriminate the patient clients from healthy ones. This paper presents an algorithm which is well-suited for and applicable to the field of severe imbalanced datasets. It is efficient in terms of both of the speed and the efficacy of learning. The experimental results show that the performance of the proposed algorithm outperforms some of the best methods in the literature.
{"title":"Effective Diagnosis of Breast Cancer","authors":"H. Parvin, Sajad Parvin","doi":"10.1109/MICAI.2012.26","DOIUrl":"https://doi.org/10.1109/MICAI.2012.26","url":null,"abstract":"A famous field in which it is very possible for each typical dataset to be imbalanced and hard is physician recognition. In such systems there are many customers where a few of them are patient and the others are healthy. So it is very common and possible for a dataset to emerge an imbalanced one. In such a system it is desired to distinguish a patient from a mixture of customers. In a breast cancer detection that is a special case of the mentioned systems, it is desired to discriminate the patient clients from healthy ones. This paper presents an algorithm which is well-suited for and applicable to the field of severe imbalanced datasets. It is efficient in terms of both of the speed and the efficacy of learning. The experimental results show that the performance of the proposed algorithm outperforms some of the best methods in the literature.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126270276","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}
Usage of recognition systems has found many applications in almost all fields. Generally in design of multiple classifier systems, the more diverse the results of the classifiers, the more appropriate the aggregated result. While most of classification algorithms have obtained a good performance for specific problems they have not enough robustness for other problems. Combination of multiple classifiers can be considered as a general solution method for pattern recognition problems. It has been shown that combination of multiple classifiers can usually operate better than a single classifier system provided that its components are independent or their components have diverse outputs. It has been shown that the necessary diversity for the ensemble can be achieved by manipulation of dataset features, manipulation of data points in dataset, different sub-samplings of dataset, and usage of different classification algorithms. We also propose a new method of creating this diversity. We use Linear Discriminant Analysis to manipulate the data points in dataset. The ensemble created by proposed method may not always outperform any of its members, it always possesses the diversity needed for creation of an ensemble, and consequently it always outperforms the simple classifier systems.
{"title":"A Robust Classifier Ensemble for Improving the Performance of Classification","authors":"H. Parvin, Sajad Parvin","doi":"10.1109/MICAI.2012.25","DOIUrl":"https://doi.org/10.1109/MICAI.2012.25","url":null,"abstract":"Usage of recognition systems has found many applications in almost all fields. Generally in design of multiple classifier systems, the more diverse the results of the classifiers, the more appropriate the aggregated result. While most of classification algorithms have obtained a good performance for specific problems they have not enough robustness for other problems. Combination of multiple classifiers can be considered as a general solution method for pattern recognition problems. It has been shown that combination of multiple classifiers can usually operate better than a single classifier system provided that its components are independent or their components have diverse outputs. It has been shown that the necessary diversity for the ensemble can be achieved by manipulation of dataset features, manipulation of data points in dataset, different sub-samplings of dataset, and usage of different classification algorithms. We also propose a new method of creating this diversity. We use Linear Discriminant Analysis to manipulate the data points in dataset. The ensemble created by proposed method may not always outperform any of its members, it always possesses the diversity needed for creation of an ensemble, and consequently it always outperforms the simple classifier systems.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127241207","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}
Santiago Omar Caballero Morales, Yara Pérez Maldonado, F. Trujillo-Romero
In this paper we extend on previous work about the application of Genetic Algorithms (GAs) to optimize the transition structure of phoneme Hidden Markov Models (HMMs) for Automatic Speech Recognition (ASR). We focus on the development of a micro-GA where, in contrast to other GA approaches, each individual in the initial population consists of an element of the transition matrix of an HMM. Each individual's fitness is measured at the phoneme recognition level, which makes the execution of the algorithm faster. Evaluation of performance was performed with test speech data from the Wall Street Journal (WSJ) database. When measuring the performance of the optimized HMMs at the word recognition level, statistically significant improvements were obtained when compared with the performance of a standard speaker adaptation technique.
{"title":"Improvement on Automatic Speech Recognition Using Micro-genetic Algorithm","authors":"Santiago Omar Caballero Morales, Yara Pérez Maldonado, F. Trujillo-Romero","doi":"10.1109/MICAI.2012.14","DOIUrl":"https://doi.org/10.1109/MICAI.2012.14","url":null,"abstract":"In this paper we extend on previous work about the application of Genetic Algorithms (GAs) to optimize the transition structure of phoneme Hidden Markov Models (HMMs) for Automatic Speech Recognition (ASR). We focus on the development of a micro-GA where, in contrast to other GA approaches, each individual in the initial population consists of an element of the transition matrix of an HMM. Each individual's fitness is measured at the phoneme recognition level, which makes the execution of the algorithm faster. Evaluation of performance was performed with test speech data from the Wall Street Journal (WSJ) database. When measuring the performance of the optimized HMMs at the word recognition level, statistically significant improvements were obtained when compared with the performance of a standard speaker adaptation technique.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114864586","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}
Miguel Murguía‐Romero, R. Jiménez-Flores, R. Méndez-Cruz, R. Villalobos-Molina
The body mass index (BMI) is nowadays the most used tool to evaluate obesity, involving only two anthropometric measures easy to obtain, the weight and the height (BMI=weight/height2). The BMI is valuable because it evaluates obesity, classifying people into 'underweight', 'normal weight', and 'overweight' classes. The value of the BMI means that through a classification of the weight condition, it implicitly estimates the possible alteration in metabolic parameters, such as blood glucose, blood pressure, and cholesterol, among others. Because it is widely used, a little variation in the accuracy of the classification of the BMI may involve thousands of individuals misclassified. The aim of this work was to evaluate variations of the BMI formula searching for one which increases the specificity and sensitivity, respect to metabolic alterations. We applied heuristic search of algebraic and constant variation to the original BMI formula, for example, a rule to generate new variations of the BMI formula is increasing the exponent of the denominator by 0.1. The heuristic function used was the intersection of specificity and sensitivity of the particular formula evaluated, i.e., the maximum values of the two statistics. To evaluate the specificity and sensitivity a database of a sample of 4,308 young Mexicans (17-24 years old), including the parameters of the metabolic alterations evaluated, and weight and height was used. The heuristic search can be applied to adjust formulae that evaluate other clinical alterations, such as the atherogenic index. Also, we propose to use the variations of the BMI formula found in this study, with the high sensitivity and specificity when evaluate obesity of young Mexican as a risk to present metabolic alterations.
{"title":"Improving the Body Mass Index (BMI) Formula with Heuristic Search","authors":"Miguel Murguía‐Romero, R. Jiménez-Flores, R. Méndez-Cruz, R. Villalobos-Molina","doi":"10.1109/MICAI.2012.24","DOIUrl":"https://doi.org/10.1109/MICAI.2012.24","url":null,"abstract":"The body mass index (BMI) is nowadays the most used tool to evaluate obesity, involving only two anthropometric measures easy to obtain, the weight and the height (BMI=weight/height2). The BMI is valuable because it evaluates obesity, classifying people into 'underweight', 'normal weight', and 'overweight' classes. The value of the BMI means that through a classification of the weight condition, it implicitly estimates the possible alteration in metabolic parameters, such as blood glucose, blood pressure, and cholesterol, among others. Because it is widely used, a little variation in the accuracy of the classification of the BMI may involve thousands of individuals misclassified. The aim of this work was to evaluate variations of the BMI formula searching for one which increases the specificity and sensitivity, respect to metabolic alterations. We applied heuristic search of algebraic and constant variation to the original BMI formula, for example, a rule to generate new variations of the BMI formula is increasing the exponent of the denominator by 0.1. The heuristic function used was the intersection of specificity and sensitivity of the particular formula evaluated, i.e., the maximum values of the two statistics. To evaluate the specificity and sensitivity a database of a sample of 4,308 young Mexicans (17-24 years old), including the parameters of the metabolic alterations evaluated, and weight and height was used. The heuristic search can be applied to adjust formulae that evaluate other clinical alterations, such as the atherogenic index. Also, we propose to use the variations of the BMI formula found in this study, with the high sensitivity and specificity when evaluate obesity of young Mexican as a risk to present metabolic alterations.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127325636","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}
The control of the power flow in a vehicle is a preponderant task for the correct vehicle performance. Therefore in this paper is developed the implementation of a fuzzy indirect vector control for the energy management of an EV powertrain. The main energy propulsion unit is a squirrel cage induction motor and the powertrain is simulated as the connections among motor, gear box, energy storage unit and wheels. Add to this it is taking into account for the simulation all the forces involved in the vehicle movement. Finally, simulations for a standard driving cycle.
{"title":"Electric Vehicle Powertrain Control with Fuzzy Indirect Vector Control","authors":"Joycer Osorio, P. Ponce, A. Molina","doi":"10.1109/MICAI.2012.33","DOIUrl":"https://doi.org/10.1109/MICAI.2012.33","url":null,"abstract":"The control of the power flow in a vehicle is a preponderant task for the correct vehicle performance. Therefore in this paper is developed the implementation of a fuzzy indirect vector control for the energy management of an EV powertrain. The main energy propulsion unit is a squirrel cage induction motor and the powertrain is simulated as the connections among motor, gear box, energy storage unit and wheels. Add to this it is taking into account for the simulation all the forces involved in the vehicle movement. Finally, simulations for a standard driving cycle.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134421523","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}
DC motors have been leading the field of adjustable speed drives for a long time due to its excellent control characteristics. This paper addresses a novel speed control application for DC motors gathering the features of Sliding Mode Control (SMC), Fuzzy Inference System (FIS), Neural Networks (NNs) and Genetic Algorithms (GAs). The main goal about combining these techniques is to create a robust speed controller avoiding the main disadvantage of SMC, the chattering. The design of the controller is implemented on a FPGA (Field Programmable Gate Array) and the steps for carrying out the implementation are described in detail. Finally, the results show a comparison between three different schemes of the designed controller.
{"title":"A Novel Speed Control for DC Motors: Sliding Mode Control, Fuzzy Inference System, Neural Networks and Genetic Algorithms","authors":"P. Cepeda, P. Ponce, A. Molina","doi":"10.1109/MICAI.2012.32","DOIUrl":"https://doi.org/10.1109/MICAI.2012.32","url":null,"abstract":"DC motors have been leading the field of adjustable speed drives for a long time due to its excellent control characteristics. This paper addresses a novel speed control application for DC motors gathering the features of Sliding Mode Control (SMC), Fuzzy Inference System (FIS), Neural Networks (NNs) and Genetic Algorithms (GAs). The main goal about combining these techniques is to create a robust speed controller avoiding the main disadvantage of SMC, the chattering. The design of the controller is implemented on a FPGA (Field Programmable Gate Array) and the steps for carrying out the implementation are described in detail. Finally, the results show a comparison between three different schemes of the designed controller.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115793984","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}
Ameni Azzouz, M. Ennigrou, Jlifi Boutheina, K. Ghédira
The Flexible Job Shop problem (FJSP) is an important extension of the classical job shop scheduling problem, in that each operation can be processed by a set of resources and has a processing time depending on the resource used. The objective is to minimize the make span, i.e., the time needed to complete all the jobs. This works aims to propose a new promising approach using multi-agent systems in order to solve the FJSP. Our model combines a local optimization approach based on Tabu Search (TS) meta-heuristic and a global optimization approach based on genetic algorithm (GA).
{"title":"Combining Tabu Search and Genetic Algorithm in a Multi-agent System for Solving Flexible Job Shop Problem","authors":"Ameni Azzouz, M. Ennigrou, Jlifi Boutheina, K. Ghédira","doi":"10.1109/MICAI.2012.12","DOIUrl":"https://doi.org/10.1109/MICAI.2012.12","url":null,"abstract":"The Flexible Job Shop problem (FJSP) is an important extension of the classical job shop scheduling problem, in that each operation can be processed by a set of resources and has a processing time depending on the resource used. The objective is to minimize the make span, i.e., the time needed to complete all the jobs. This works aims to propose a new promising approach using multi-agent systems in order to solve the FJSP. Our model combines a local optimization approach based on Tabu Search (TS) meta-heuristic and a global optimization approach based on genetic algorithm (GA).","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124659249","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}
J. Guadarrama, J. R. Marcial-Romero, Marcelo Romero, Jorge Hernandez Camacho
Knowledge representation is an important topic in common-sense reasoning and Artificial Intelligence, and one of the earliest techniques to represent it is by means of knowledge bases encoded into logic clauses. Encoding knowledge, however, is prone to typos and other kinds of consistency mistakes, which may yield incorrect results or even internal contradictions with conflicting information from other parts of the same code. In order to overcome such situations, we propose a logic-programming system to debug knowledge bases. The system has a strong theoretical framework on knowledge representation and reasoning, and a suggested on-line prototype where one can test logic programs. Such logic programs may have, of course, conflicting information and the system shall prompt the user where the possible source of conflict is. Besides, the system can be employed to identify conflicts of the knowledge base itself and upcoming new information, it can also be used to locate the source of conflict from a given inherently inconsistent static knowledge base. This paper describes an implementation of a declarative version of the system that has been characterised to debug knowledge bases in a semantical formalism. Some of the key components of such implementation are existing solvers, so this paper focuses on how to use them and why they work, towards an implemented a fully-fledged system.
{"title":"Implementing a Knowledge Bases Debugger","authors":"J. Guadarrama, J. R. Marcial-Romero, Marcelo Romero, Jorge Hernandez Camacho","doi":"10.1109/MICAI.2012.20","DOIUrl":"https://doi.org/10.1109/MICAI.2012.20","url":null,"abstract":"Knowledge representation is an important topic in common-sense reasoning and Artificial Intelligence, and one of the earliest techniques to represent it is by means of knowledge bases encoded into logic clauses. Encoding knowledge, however, is prone to typos and other kinds of consistency mistakes, which may yield incorrect results or even internal contradictions with conflicting information from other parts of the same code. In order to overcome such situations, we propose a logic-programming system to debug knowledge bases. The system has a strong theoretical framework on knowledge representation and reasoning, and a suggested on-line prototype where one can test logic programs. Such logic programs may have, of course, conflicting information and the system shall prompt the user where the possible source of conflict is. Besides, the system can be employed to identify conflicts of the knowledge base itself and upcoming new information, it can also be used to locate the source of conflict from a given inherently inconsistent static knowledge base. This paper describes an implementation of a declarative version of the system that has been characterised to debug knowledge bases in a semantical formalism. Some of the key components of such implementation are existing solvers, so this paper focuses on how to use them and why they work, towards an implemented a fully-fledged system.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129565486","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 a stochastic local search classifier combined with the fuzzy logic concepts for intrusion detection. The proposed classifier works on knowledge base modeled as a fuzzy rule "if-then" and improved by using a stochastic local search. The method is tested on the Benchmark KDD'99 intrusion dataset and compared with other existing techniques for intrusion detection. The results are encouraging and demonstrate the benefit of the proposed approach.
{"title":"Intrusion Detection Using Fuzzy Stochastic Local Search Classifier","authors":"B. Bahamida, D. Boughaci","doi":"10.1109/MICAI.2012.17","DOIUrl":"https://doi.org/10.1109/MICAI.2012.17","url":null,"abstract":"This paper proposes a stochastic local search classifier combined with the fuzzy logic concepts for intrusion detection. The proposed classifier works on knowledge base modeled as a fuzzy rule \"if-then\" and improved by using a stochastic local search. The method is tested on the Benchmark KDD'99 intrusion dataset and compared with other existing techniques for intrusion detection. The results are encouraging and demonstrate the benefit of the proposed approach.","PeriodicalId":348369,"journal":{"name":"2012 11th Mexican International Conference on Artificial Intelligence","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123772169","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：