Pub Date : 2018-10-01DOI: 10.1109/BRACIS.2018.00091
E. Ebermam, G. D. Angelo, H. Knidel, R. Krohling
The use of models that combine empirical mode decomposition (EMD) and artificial neural networks (ANN) to time series prediction has been attracted much research interest in several areas of great relevance. However, the way the two methods are combined can vary. Thus, a comparison between different combinations of models is presented in this work. The first objective is to verify if the use of EMD improves the prediction results. The second objective is to compare whether it is better to group the intrinsic mode function (IMFs) and then perform the prediction, or predict each IMF separately and then aggregate the results. The methods were tested for six different time series and the results show that EMD improves the prediction for the most of the investigated series, especially if one predictor is used for each IMF separately.
{"title":"Empirical Mode Decomposition, Extreme Learning Machine and Long Short-Term Memory for Time Series Prediction: A Comparative Study","authors":"E. Ebermam, G. D. Angelo, H. Knidel, R. Krohling","doi":"10.1109/BRACIS.2018.00091","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00091","url":null,"abstract":"The use of models that combine empirical mode decomposition (EMD) and artificial neural networks (ANN) to time series prediction has been attracted much research interest in several areas of great relevance. However, the way the two methods are combined can vary. Thus, a comparison between different combinations of models is presented in this work. The first objective is to verify if the use of EMD improves the prediction results. The second objective is to compare whether it is better to group the intrinsic mode function (IMFs) and then perform the prediction, or predict each IMF separately and then aggregate the results. The methods were tested for six different time series and the results show that EMD improves the prediction for the most of the investigated series, especially if one predictor is used for each IMF separately.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131682725","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00009
J. P. Schmitt, F. Baldo, R. S. Parpinelli
Real-world transportation systems should deal with dynamism and asymmetry to find good solutions for logistics companies. In this scenario, the inefficiency of exact methods to solve complex optimization problems like Travelling Salesman Problem (TSP) and Vehicle Routing Problem (VRP) rise the opportunity to use methods like those provided by meta-heuristics as ant-based systems. Despite the improvements reached by adopting meta-heuristics in TSP and VRP, due to its intrinsically complex and time-consuming solutions, there are still opportunities to improve the problem-solving performance by adding some extra characteristics in the ant-based system solution. Therefore, this study proposes the use of short-term memory in the MAX-MIN Ant System algorithm, named MMAS-MEM, applied in the asymmetric and dynamic traveling salesman problem (ADTSP) with moving vehicle. To evaluate the proposed method, a comparison is made with the EIACO and with the canonical MMAS algorithms in benchmarks and real-world instances. Results pointed out that MMAS-MEM is better than EIACO and MMAS to solve such complex problems. Hence, it can be considered the most suitable for moving vehicle scenarios.
{"title":"A MAX-MIN Ant System with Short-Term Memory Applied to the Dynamic and Asymmetric Traveling Salesman Problem","authors":"J. P. Schmitt, F. Baldo, R. S. Parpinelli","doi":"10.1109/BRACIS.2018.00009","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00009","url":null,"abstract":"Real-world transportation systems should deal with dynamism and asymmetry to find good solutions for logistics companies. In this scenario, the inefficiency of exact methods to solve complex optimization problems like Travelling Salesman Problem (TSP) and Vehicle Routing Problem (VRP) rise the opportunity to use methods like those provided by meta-heuristics as ant-based systems. Despite the improvements reached by adopting meta-heuristics in TSP and VRP, due to its intrinsically complex and time-consuming solutions, there are still opportunities to improve the problem-solving performance by adding some extra characteristics in the ant-based system solution. Therefore, this study proposes the use of short-term memory in the MAX-MIN Ant System algorithm, named MMAS-MEM, applied in the asymmetric and dynamic traveling salesman problem (ADTSP) with moving vehicle. To evaluate the proposed method, a comparison is made with the EIACO and with the canonical MMAS algorithms in benchmarks and real-world instances. Results pointed out that MMAS-MEM is better than EIACO and MMAS to solve such complex problems. Hence, it can be considered the most suitable for moving vehicle scenarios.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134028037","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00060
Augusto Victor Martins Gomides, Lucas Josino de Paula Goncalves, L. R. Silva, A. Backes
This paper presents a study on the correlation between lacunarity and morphological characteristics of urban areas. In remote sensing images, morphological features of urban areas are represented by complex interactions of different types of surface, where each surface results in a different type of texture which depends on its physical properties (such as color, bright, reflectance etc). In this work, we estimate lacunarity from images of urban areas in order to estimate the complexity of the image textures and, consequently, to obtain a measure of the morphological characteristics of the urban areas.
{"title":"Lacunarity as a Tool for Analyzing Satellite Images of Urban Areas","authors":"Augusto Victor Martins Gomides, Lucas Josino de Paula Goncalves, L. R. Silva, A. Backes","doi":"10.1109/BRACIS.2018.00060","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00060","url":null,"abstract":"This paper presents a study on the correlation between lacunarity and morphological characteristics of urban areas. In remote sensing images, morphological features of urban areas are represented by complex interactions of different types of surface, where each surface results in a different type of texture which depends on its physical properties (such as color, bright, reflectance etc). In this work, we estimate lacunarity from images of urban areas in order to estimate the complexity of the image textures and, consequently, to obtain a measure of the morphological characteristics of the urban areas.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478379","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 : 2018-10-01DOI: 10.1109/bracis.2018.00040
Diêgo Farias de Oliveira, Nykolas Mayko Maia Barbosa, Alisson Sampaio Carvalho de Alencar, João Paulo Pordeus Gomes, Leonardo Ramos Rodrigues
Solving regression problems with interval-valued datasets is a challenging task that may arise in many real world applications. Motivated by that fact, many researchers have proposed nonlinear regression methods to handle interval-valued data in recent years. In this paper, we propose two variants of the Minimal Learning Machine (MLM) for interval-valued data. The choice of MLM is explained by its remarkable performance in many applications and the need of a single hyperparameter definition. We present a performance comparison between our methods and five benchmark nonlinear regression methods. The proposed methods presented competitive results.
{"title":"Minimal Learning Machine for Interval-Valued Data","authors":"Diêgo Farias de Oliveira, Nykolas Mayko Maia Barbosa, Alisson Sampaio Carvalho de Alencar, João Paulo Pordeus Gomes, Leonardo Ramos Rodrigues","doi":"10.1109/bracis.2018.00040","DOIUrl":"https://doi.org/10.1109/bracis.2018.00040","url":null,"abstract":"Solving regression problems with interval-valued datasets is a challenging task that may arise in many real world applications. Motivated by that fact, many researchers have proposed nonlinear regression methods to handle interval-valued data in recent years. In this paper, we propose two variants of the Minimal Learning Machine (MLM) for interval-valued data. The choice of MLM is explained by its remarkable performance in many applications and the need of a single hyperparameter definition. We present a performance comparison between our methods and five benchmark nonlinear regression methods. The proposed methods presented competitive results.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116529430","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00069
J. P. A. Neto, D. Pianto, C. Ralha
Cloud computing providers have started offering their idle resources as transient servers. Spot instances are transient servers offered by Amazon, whose prices dynamically change over time based on supply and demand. By using appropriate strategies and fault-tolerant mechanisms, users can effectively use spot instances to run applications at a lower price. This paper presents a resilient agent-based fog computing architecture that combines machine learning and a statistical model to predict time to instance revocation and helps to refine fault tolerance parameters and reduce total execution time. The experiments demonstrate that our model predicts with high levels of accuracy reaching 94% success rate what indicates the model is effective under realistic working conditions.
{"title":"An Agent-Based Fog Computing Architecture for Resilience on Amazon EC2 Spot Instances","authors":"J. P. A. Neto, D. Pianto, C. Ralha","doi":"10.1109/BRACIS.2018.00069","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00069","url":null,"abstract":"Cloud computing providers have started offering their idle resources as transient servers. Spot instances are transient servers offered by Amazon, whose prices dynamically change over time based on supply and demand. By using appropriate strategies and fault-tolerant mechanisms, users can effectively use spot instances to run applications at a lower price. This paper presents a resilient agent-based fog computing architecture that combines machine learning and a statistical model to predict time to instance revocation and helps to refine fault tolerance parameters and reduce total execution time. The experiments demonstrate that our model predicts with high levels of accuracy reaching 94% success rate what indicates the model is effective under realistic working conditions.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122910665","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00074
M. Carneiro, Liang Zhao
Graph-based methods have attracted a lot of attention in recent years, especially due to its inherent ability to capture properties of the networked data (e.g., structural and dynamical). Clustering, semi-supervised label propagation and, more recently, data classification are examples of tasks in which graph-based learning methods have obtained relevant results. In any of these tasks, the common approach is (i) to transform the feature vector data in a graph and then (ii) exploit some property uncovered by the network structure. However, most works have focused on the development of models to exploit the graph, while the graph construction step has been little explored. In this article, we conduct a preliminary study to evaluate supervised graph construction methods based on k-nearest neighbors (kNN) and ϵ-radius neighborhood (ϵN) criteria by employing a recently proposed classification technique based on the importance concept of complex networks. Experiments were conducted on artificial and real-world data sets, including the problem of invariant pattern recognition in images. The results show that the graph construction methods under study are able to deal with different configuration of problems (e.g., domain, features, etc). They also suggest that the combination between selective kNN and ϵN is more suitable in data sets with low level of mixture among the classes, while kNN seems slightly better in problems with higher noise levels.
{"title":"Analysis of Graph Construction Methods in Supervised Data Classification","authors":"M. Carneiro, Liang Zhao","doi":"10.1109/BRACIS.2018.00074","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00074","url":null,"abstract":"Graph-based methods have attracted a lot of attention in recent years, especially due to its inherent ability to capture properties of the networked data (e.g., structural and dynamical). Clustering, semi-supervised label propagation and, more recently, data classification are examples of tasks in which graph-based learning methods have obtained relevant results. In any of these tasks, the common approach is (i) to transform the feature vector data in a graph and then (ii) exploit some property uncovered by the network structure. However, most works have focused on the development of models to exploit the graph, while the graph construction step has been little explored. In this article, we conduct a preliminary study to evaluate supervised graph construction methods based on k-nearest neighbors (kNN) and ϵ-radius neighborhood (ϵN) criteria by employing a recently proposed classification technique based on the importance concept of complex networks. Experiments were conducted on artificial and real-world data sets, including the problem of invariant pattern recognition in images. The results show that the graph construction methods under study are able to deal with different configuration of problems (e.g., domain, features, etc). They also suggest that the combination between selective kNN and ϵN is more suitable in data sets with low level of mixture among the classes, while kNN seems slightly better in problems with higher noise levels.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127829111","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00027
R. Bonini, Felipe Leno da Silva, R. Glatt, Edison Spina, Anna Helena Reali Costa
Reinforcement Learning is a successful yet slow technique to train autonomous agents. Option-based solutions can be used to accelerate learning and to transfer learned behaviors across tasks by encapsulating a partial policy. However, commonly these options are specific for a single task, do not take in account similar features between tasks and may not correspond exactly to an optimal behavior when transferred to another task. Therefore, unprincipled transfer might provide bad options to the agent, hampering the learning process. We here propose a way to discover and reuse learned object-oriented options in aprobabilistic way in order to enable better actuation choices to the agent in multiple different tasks. Our experimental evaluation show that our proposal is able to learn and successfully reuse options across different tasks.
{"title":"A Framework to Discover and Reuse Object-Oriented Options in Reinforcement Learning","authors":"R. Bonini, Felipe Leno da Silva, R. Glatt, Edison Spina, Anna Helena Reali Costa","doi":"10.1109/BRACIS.2018.00027","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00027","url":null,"abstract":"Reinforcement Learning is a successful yet slow technique to train autonomous agents. Option-based solutions can be used to accelerate learning and to transfer learned behaviors across tasks by encapsulating a partial policy. However, commonly these options are specific for a single task, do not take in account similar features between tasks and may not correspond exactly to an optimal behavior when transferred to another task. Therefore, unprincipled transfer might provide bad options to the agent, hampering the learning process. We here propose a way to discover and reuse learned object-oriented options in aprobabilistic way in order to enable better actuation choices to the agent in multiple different tasks. Our experimental evaluation show that our proposal is able to learn and successfully reuse options across different tasks.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132447132","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00019
R. Martins, Marco Gomes, J. J. Almeida, P. Novais, P. Henriques
In this paper, we examine methods to classify hate speech in social media. We aim to establish lexical baselines for this task by applying classification methods using a dataset annotated for this purpose. As features, our system uses Natural Language Processing (NLP) techniques in order to expand the original dataset with emotional information and provide it for machine learning classification. We obtain results of 80.56% accuracy in hate speech identification, which represents an increase of almost 100% from the original analysis used as a reference.
{"title":"Hate Speech Classification in Social Media Using Emotional Analysis","authors":"R. Martins, Marco Gomes, J. J. Almeida, P. Novais, P. Henriques","doi":"10.1109/BRACIS.2018.00019","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00019","url":null,"abstract":"In this paper, we examine methods to classify hate speech in social media. We aim to establish lexical baselines for this task by applying classification methods using a dataset annotated for this purpose. As features, our system uses Natural Language Processing (NLP) techniques in order to expand the original dataset with emotional information and provide it for machine learning classification. We obtain results of 80.56% accuracy in hate speech identification, which represents an increase of almost 100% from the original analysis used as a reference.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125397226","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00028
Matheus R. F. Mendonça, A. Ziviani, André Barreto
Skill acquisition methods for Reinforcement Learning (RL) are focused on solving problems by breaking them into smaller sub-problems, allowing the learning agent to reuse tasks for other similar problems. Many of these skill acquisition methods use a State Transition Graph (STG). Nevertheless, the problem is that STGs are only available for simple RL problems, given that, for complex problems, the resulting STG becomes too large to be handled in practice. In this paper, we propose a method for creating Abstract State Transition Graphs (ASTGs) that fuse structurally similar states into a single abstract state. We show that an ASTG is capable of: (i) efficiently identifying similar states; (ii) greatly reducing the number of states of a STG; and (iii) detecting temporal features, thus enabling the differentiation of states based on their predecessors. This allows the ASTG to be (i) more accurate, since it succeeds at creating abstract states by merging similar states with similar previous steps; as well as (ii) manageable with respect to its size.
{"title":"Abstract State Transition Graphs for Model-Based Reinforcement Learning","authors":"Matheus R. F. Mendonça, A. Ziviani, André Barreto","doi":"10.1109/BRACIS.2018.00028","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00028","url":null,"abstract":"Skill acquisition methods for Reinforcement Learning (RL) are focused on solving problems by breaking them into smaller sub-problems, allowing the learning agent to reuse tasks for other similar problems. Many of these skill acquisition methods use a State Transition Graph (STG). Nevertheless, the problem is that STGs are only available for simple RL problems, given that, for complex problems, the resulting STG becomes too large to be handled in practice. In this paper, we propose a method for creating Abstract State Transition Graphs (ASTGs) that fuse structurally similar states into a single abstract state. We show that an ASTG is capable of: (i) efficiently identifying similar states; (ii) greatly reducing the number of states of a STG; and (iii) detecting temporal features, thus enabling the differentiation of states based on their predecessors. This allows the ASTG to be (i) more accurate, since it succeeds at creating abstract states by merging similar states with similar previous steps; as well as (ii) manageable with respect to its size.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126728340","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 : 2018-10-01DOI: 10.1109/BRACIS.2018.00073
Artur Maia, Jaime Simão Sichman
Organizations are key elements in a multi-agent system, since they promote cooperation between agents by constraining their possible behaviours. However, constraining behaviour means diminishing the agents autonomy. In human organizations, agents have different degrees of autonomy: autonomous and more adaptable agents coexist with non-autonomous agents that just follow organizational rules. This work will propose an explicit representation for planning-autonomy in agents organizations, particularly using the MOISE organizational model. We propose the use of a domain specification, based on the planning formalism and on goal types. We implemented our representation using the JaCaMo framework in a proof-of-concept scenario showing how a planning autonomous agent can use the SHOP planner to achieve an organizational goal.
{"title":"Explicit Representation of Planning Autonomy in MOISE Organizational Model","authors":"Artur Maia, Jaime Simão Sichman","doi":"10.1109/BRACIS.2018.00073","DOIUrl":"https://doi.org/10.1109/BRACIS.2018.00073","url":null,"abstract":"Organizations are key elements in a multi-agent system, since they promote cooperation between agents by constraining their possible behaviours. However, constraining behaviour means diminishing the agents autonomy. In human organizations, agents have different degrees of autonomy: autonomous and more adaptable agents coexist with non-autonomous agents that just follow organizational rules. This work will propose an explicit representation for planning-autonomy in agents organizations, particularly using the MOISE organizational model. We propose the use of a domain specification, based on the planning formalism and on goal types. We implemented our representation using the JaCaMo framework in a proof-of-concept scenario showing how a planning autonomous agent can use the SHOP planner to achieve an organizational goal.","PeriodicalId":405190,"journal":{"name":"2018 7th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127111614","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：