Semantic interoperability represents the ability of two or more systems to automatically interpret the information exchanged meaningfully in order to produce useful results. Currently, the best recognized technology for achieving a specification of meaning is represented by ontologies. However, the variety of ways that a domain can be conceptualized results in the creation of different ontologies with discrepancies and heterogeneities. As a consequence, an ontology alignment process is necessary for bridging this gap and achieving a full communication understanding across different software components. This paper uses a synergetic approach, based on the integration of collaborative agents and parallel memetic algorithms, for efficiently aligning ontologies and, consequently, solving the semantic heterogeneity problem. As shown by a statistical procedure, our approach yields high performance in terms of the ratio between alignment quality and computational effort with respect to conventional evolutionary approaches for ontology alignment.
{"title":"Collaborative memetic agents for enabling semantic interoperability","authors":"G. Acampora, A. Vitiello","doi":"10.1109/IA.2013.6595185","DOIUrl":"https://doi.org/10.1109/IA.2013.6595185","url":null,"abstract":"Semantic interoperability represents the ability of two or more systems to automatically interpret the information exchanged meaningfully in order to produce useful results. Currently, the best recognized technology for achieving a specification of meaning is represented by ontologies. However, the variety of ways that a domain can be conceptualized results in the creation of different ontologies with discrepancies and heterogeneities. As a consequence, an ontology alignment process is necessary for bridging this gap and achieving a full communication understanding across different software components. This paper uses a synergetic approach, based on the integration of collaborative agents and parallel memetic algorithms, for efficiently aligning ontologies and, consequently, solving the semantic heterogeneity problem. As shown by a statistical procedure, our approach yields high performance in terms of the ratio between alignment quality and computational effort with respect to conventional evolutionary approaches for ontology alignment.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127882221","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}
Currently many problems related to data mining and knowledge discovery have two relevant characteristics: they produce data that is distributed over several locations, while also generating large volumes of data that need to be classified in an online fashion. Examples of such applications are related to bioinformatics, e-commerce, and sensor data. Regarding classification by means of decision trees, some efficient approaches have been proposed, which are centralized and based on restructuring the decision tree using new instances. However, there are some issues. First, most proposed approaches require that new instances are fully labeled. Second, in some environments, the agent in charge of the classification task cannot re-induce the classifier or restructure the decision tree each time it observes a new instance. Moreover, because this agent does not see the whole dataset, the induced classifier is not likely to be very accurate unless information is exchanged among the agents that are, each, in charge of pieces of the data. Thus, a decrease in accuracy may occur because attributes and classes may be misrepresented in the training dataset used so far. Instead of re-inducing the classification model with arbitrary frequency in a centralized way, this paper proposes an approach based on reinforcement learning that allows agents to go on using the existing classifier as basis for some exploration in the space of possible classifications. We use a quality assessment of the learned model in order to let each agent decide when it is time to get a new model, either by borrowing it from another agent, or by inducing a new classifier. Results using UCI datasets with various characteristics show that this method can be used as a compromise between costly methods for re-inducing the classifier at all times, and using only a static and centralized classification model.
{"title":"Cooperative induction of decision trees","authors":"A. Bazzan","doi":"10.1109/IA.2013.6595190","DOIUrl":"https://doi.org/10.1109/IA.2013.6595190","url":null,"abstract":"Currently many problems related to data mining and knowledge discovery have two relevant characteristics: they produce data that is distributed over several locations, while also generating large volumes of data that need to be classified in an online fashion. Examples of such applications are related to bioinformatics, e-commerce, and sensor data. Regarding classification by means of decision trees, some efficient approaches have been proposed, which are centralized and based on restructuring the decision tree using new instances. However, there are some issues. First, most proposed approaches require that new instances are fully labeled. Second, in some environments, the agent in charge of the classification task cannot re-induce the classifier or restructure the decision tree each time it observes a new instance. Moreover, because this agent does not see the whole dataset, the induced classifier is not likely to be very accurate unless information is exchanged among the agents that are, each, in charge of pieces of the data. Thus, a decrease in accuracy may occur because attributes and classes may be misrepresented in the training dataset used so far. Instead of re-inducing the classification model with arbitrary frequency in a centralized way, this paper proposes an approach based on reinforcement learning that allows agents to go on using the existing classifier as basis for some exploration in the space of possible classifications. We use a quality assessment of the learned model in order to let each agent decide when it is time to get a new model, either by borrowing it from another agent, or by inducing a new classifier. Results using UCI datasets with various characteristics show that this method can be used as a compromise between costly methods for re-inducing the classifier at all times, and using only a static and centralized classification model.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128891587","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}
Equilibrium-based traffic assignment models do not consider traffic movement. In particular the functions that are used to estimate delay from volume of vehicles do not allow the representation of the phenomenon of congestion spillback. In some cases one needs to understand and analyze microscopic properties associated to how travelers adjust to the conditions they encounter. This, on its turn, leads to dynamic environments that are difficult to analyze with conventional tools. This paper presents an agent-based simulation of route choice under different conditions of demand generation, number, and types of driver agents. We consider more sophisticated drivers' behaviors such as en-route decision-making. Besides, they may be equipped with vehicle-to-vehicle communication. We discuss the effects of the use of: various ratio demand/capacity, demand generation, information exchange, and re-planning strategies. The use of an agent-based approach allows the analysis of different classes of agents, thus departing from the investigation of population-wide metrics only. The main conclusion is that for travelers whose trips are long, there is a benefit of using communication and replan en-route, depending on the demand. However, in general, having imperfect information is advantageous, especially from the whole system perspective.
{"title":"Benefits of routing and replanning with imperfect information","authors":"Maicon de Brito do Amarante, A. Bazzan","doi":"10.1109/IA.2013.6595189","DOIUrl":"https://doi.org/10.1109/IA.2013.6595189","url":null,"abstract":"Equilibrium-based traffic assignment models do not consider traffic movement. In particular the functions that are used to estimate delay from volume of vehicles do not allow the representation of the phenomenon of congestion spillback. In some cases one needs to understand and analyze microscopic properties associated to how travelers adjust to the conditions they encounter. This, on its turn, leads to dynamic environments that are difficult to analyze with conventional tools. This paper presents an agent-based simulation of route choice under different conditions of demand generation, number, and types of driver agents. We consider more sophisticated drivers' behaviors such as en-route decision-making. Besides, they may be equipped with vehicle-to-vehicle communication. We discuss the effects of the use of: various ratio demand/capacity, demand generation, information exchange, and re-planning strategies. The use of an agent-based approach allows the analysis of different classes of agents, thus departing from the investigation of population-wide metrics only. The main conclusion is that for travelers whose trips are long, there is a benefit of using communication and replan en-route, depending on the demand. However, in general, having imperfect information is advantageous, especially from the whole system perspective.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132125595","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}
Being able to acquire knowledge and form concepts by observing, exploring, and interacting with the environment and then applying the knowledge thus gained for problem solving to satisfy its goals and needs is the hallmark of an adaptive autonomous intelligent agent. However, for an intelligent agent to be fully autonomous and adaptive, all aspects of intelligent processing from perception to action must be engaged and integrated. To build such an all-encompassing system is a formidable task. We propose that a good approach is to first identify the necessary intelligent computational structures and processes for dealing with a suitably designed micro-environment so that they are tractable. The challenge for computational intelligence is then to uncover general principles leading to general computational structures and processes that can deal with the micro-environment and that are also scalable to deal with more complex and real-world environments. Neuroscience research revealed that there are indeed such scalable general mechanisms in the brain and this is reviewed to provide inspirations for the building of artificial systems. A suitable micro-environment for this purpose must consist of a minimal set of features necessary to engage the various intelligent processes from that of the perceptual to that of the attentional, memory, affective, conceptual, planning, action, and learning. The micro-environment benchmark we propose here consists of an internal environment including the affective states of the intelligent agent as well as an external environment that is dynamic and in which activities of and interactions between objects can take place to engage the intelligent agent in all the intelligent processes described above.
{"title":"A grand challenge for computational intelligence a micro-environment benchmark for adaptive autonomous intelligent agents","authors":"Seng-Beng Ho","doi":"10.1109/IA.2013.6595188","DOIUrl":"https://doi.org/10.1109/IA.2013.6595188","url":null,"abstract":"Being able to acquire knowledge and form concepts by observing, exploring, and interacting with the environment and then applying the knowledge thus gained for problem solving to satisfy its goals and needs is the hallmark of an adaptive autonomous intelligent agent. However, for an intelligent agent to be fully autonomous and adaptive, all aspects of intelligent processing from perception to action must be engaged and integrated. To build such an all-encompassing system is a formidable task. We propose that a good approach is to first identify the necessary intelligent computational structures and processes for dealing with a suitably designed micro-environment so that they are tractable. The challenge for computational intelligence is then to uncover general principles leading to general computational structures and processes that can deal with the micro-environment and that are also scalable to deal with more complex and real-world environments. Neuroscience research revealed that there are indeed such scalable general mechanisms in the brain and this is reviewed to provide inspirations for the building of artificial systems. A suitable micro-environment for this purpose must consist of a minimal set of features necessary to engage the various intelligent processes from that of the perceptual to that of the attentional, memory, affective, conceptual, planning, action, and learning. The micro-environment benchmark we propose here consists of an internal environment including the affective states of the intelligent agent as well as an external environment that is dynamic and in which activities of and interactions between objects can take place to engage the intelligent agent in all the intelligent processes described above.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487355","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}
Marissa Milne, Richard Leibbrandt, P. Raghavendra, M. Luerssen, T. Lewis, D. Powers
Educators continually strive to provide learning materials that are specifically adapted to their students' unique learning preferences and needs. Software use continues to grow in classrooms however typical educational programs cannot be modified to suit individual learners. The Thinking Head Whiteboard is a lesson authoring tool that provides such a capability, allowing educators without a computer programming background to create their own interactive lessons. The Thinking Head Whiteboard also supports the use of virtual human `tutors' and `peers' within these lessons, making it uniquely suited to assist in areas such as social skills education. Further, the software currently being developed incorporates a basic level of automated assessment, allowing it to adapt on the fly to learner needs, providing repetition of content for struggling learners and fast-tracking those who are proficient. Ultimately, it is hoped that the Thinking Head Whiteboard will become an engaging and useful tool for educators and learners alike.
{"title":"Lesson authoring system for creating interactive activities involving virtual humans the thinking head whiteboard","authors":"Marissa Milne, Richard Leibbrandt, P. Raghavendra, M. Luerssen, T. Lewis, D. Powers","doi":"10.1109/IA.2013.6595184","DOIUrl":"https://doi.org/10.1109/IA.2013.6595184","url":null,"abstract":"Educators continually strive to provide learning materials that are specifically adapted to their students' unique learning preferences and needs. Software use continues to grow in classrooms however typical educational programs cannot be modified to suit individual learners. The Thinking Head Whiteboard is a lesson authoring tool that provides such a capability, allowing educators without a computer programming background to create their own interactive lessons. The Thinking Head Whiteboard also supports the use of virtual human `tutors' and `peers' within these lessons, making it uniquely suited to assist in areas such as social skills education. Further, the software currently being developed incorporates a basic level of automated assessment, allowing it to adapt on the fly to learner needs, providing repetition of content for struggling learners and fast-tracking those who are proficient. Ultimately, it is hoped that the Thinking Head Whiteboard will become an engaging and useful tool for educators and learners alike.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128095881","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 many real-world systems, multiple independent entities (or agents) repeatedly interact. Such repeated interactions, in which agents may or may not share the same preferences over outcomes, provide opportunities for the agents to adapt to each other to become more successful. Successful agents must be able to reason and learn given the dynamic behavior of others. This is challenging for artificial agents since the non-stationarity of the environment does not lend itself well to straight-forward application of traditional machine learning methods. In this paper, we study the performance of genetic algorithms (GAs) in repeated matrix games (RMGs) played against other learning agents. In so doing, we consider how particular variations in the GA affect its performance. Our results show the potential of using GAs to learn and adapt in RMGs, and highlight important characteristics of successful GAs in these games. However, the GAs we consider do not always perform effectively in RMGs. Thus, we also discuss and analyze how human input could potentially be used to improve their performance in RMGs.
{"title":"Genetic algorithms in repeated matrix games: the effects of algorithmic modifications and human input with various associates","authors":"Y. Hassan, J. Crandall","doi":"10.1109/IA.2013.6595186","DOIUrl":"https://doi.org/10.1109/IA.2013.6595186","url":null,"abstract":"In many real-world systems, multiple independent entities (or agents) repeatedly interact. Such repeated interactions, in which agents may or may not share the same preferences over outcomes, provide opportunities for the agents to adapt to each other to become more successful. Successful agents must be able to reason and learn given the dynamic behavior of others. This is challenging for artificial agents since the non-stationarity of the environment does not lend itself well to straight-forward application of traditional machine learning methods. In this paper, we study the performance of genetic algorithms (GAs) in repeated matrix games (RMGs) played against other learning agents. In so doing, we consider how particular variations in the GA affect its performance. Our results show the potential of using GAs to learn and adapt in RMGs, and highlight important characteristics of successful GAs in these games. However, the GAs we consider do not always perform effectively in RMGs. Thus, we also discuss and analyze how human input could potentially be used to improve their performance in RMGs.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132018194","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}
Gabriel Santos, Isabel Praça, T. Pinto, S. Ramos, Z. Vale
This document presents a tool able to automatically gather data provided by real energy markets and to generate scenarios, capture and improve market players' profiles and strategies by using knowledge discovery processes in databases supported by artificial intelligence techniques, data mining algorithms and machine learning methods. It provides the means for generating scenarios with different dimensions and characteristics, ensuring the representation of real and adapted markets, and their participating entities. The scenarios generator module enhances the MASCEM (Multi-Agent Simulator of Competitive Electricity Markets) simulator, endowing a more effective tool for decision support. The achievements from the implementation of the proposed module enables researchers and electricity markets' participating entities to analyze data, create real scenarios and make experiments with them. On the other hand, applying knowledge discovery techniques to real data also allows the improvement of MASCEM agents' profiles and strategies resulting in a better representation of real market players' behavior. This work aims to improve the comprehension of electricity markets and the interactions among the involved entities through adequate multi-agent simulation.
{"title":"Scenarios generation for multi-agent simulation of electricity markets based on intelligent data analysis","authors":"Gabriel Santos, Isabel Praça, T. Pinto, S. Ramos, Z. Vale","doi":"10.1109/IA.2013.6595183","DOIUrl":"https://doi.org/10.1109/IA.2013.6595183","url":null,"abstract":"This document presents a tool able to automatically gather data provided by real energy markets and to generate scenarios, capture and improve market players' profiles and strategies by using knowledge discovery processes in databases supported by artificial intelligence techniques, data mining algorithms and machine learning methods. It provides the means for generating scenarios with different dimensions and characteristics, ensuring the representation of real and adapted markets, and their participating entities. The scenarios generator module enhances the MASCEM (Multi-Agent Simulator of Competitive Electricity Markets) simulator, endowing a more effective tool for decision support. The achievements from the implementation of the proposed module enables researchers and electricity markets' participating entities to analyze data, create real scenarios and make experiments with them. On the other hand, applying knowledge discovery techniques to real data also allows the improvement of MASCEM agents' profiles and strategies resulting in a better representation of real market players' behavior. This work aims to improve the comprehension of electricity markets and the interactions among the involved entities through adequate multi-agent simulation.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128076521","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 ensemble application of intention awareness and sentic computing techniques is hereby examined for sensemaking in joint-cognitive systems, particularly in symbiotic systems that incorporate human and associate systems. The developed framework, in particular, exploits not only situational information of the operating environment, but also causal and temporal dimensions, together with circumstantial semantics and sentics, that is, the conceptual and affective information associated with objects and actors of such an environment. The work also highlights the effects of synchronized sensemaking processes in enabling associate systems to recognize the state of human activity. Studying the phenomenon of sensemaking, in fact, has direct implications for the development of more tightly coupled <;human reasoner - associate system> pairs. Specifically, the military doctrine is examined as a family of relevant case studies to demonstrate the role and potential applications of such joint cognitive systems.
{"title":"Application of intention awareness and sentic computing for sensemaking in joint-cognitive systems","authors":"N. Howard","doi":"10.1109/IA.2013.6595182","DOIUrl":"https://doi.org/10.1109/IA.2013.6595182","url":null,"abstract":"The ensemble application of intention awareness and sentic computing techniques is hereby examined for sensemaking in joint-cognitive systems, particularly in symbiotic systems that incorporate human and associate systems. The developed framework, in particular, exploits not only situational information of the operating environment, but also causal and temporal dimensions, together with circumstantial semantics and sentics, that is, the conceptual and affective information associated with objects and actors of such an environment. The work also highlights the effects of synchronized sensemaking processes in enabling associate systems to recognize the state of human activity. Studying the phenomenon of sensemaking, in fact, has direct implications for the development of more tightly coupled <;human reasoner - associate system> pairs. Specifically, the military doctrine is examined as a family of relevant case studies to demonstrate the role and potential applications of such joint cognitive systems.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127261661","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}
Nowadays, a multitude of users benefits from social interactions, blogging, wiki in order to share their own contents with each other (i.e., user-generated content). In fact, both Web 2.0 and Enterprise 2.0 applications have changed the knowledge sharing paradigm, and have introduced enabling features to foster information flow among users. Nevertheless, the availability of large amount of information targeted to human employment highlights reusing, reasoning and exploitation of available knowledge. Emerging Semantic Web technologies enable to codify information in a machine understandable way. Therefore, the latest web development trend is devoted to combine Web 2.0 features with semantic technologies (e.g. semantic tagging, semantic wiki). This scenario raises new requirements in terms of knowledge base extraction, update and maintenance. To this end, this work defines an ontology-based knowledge management platform that integrates methodologies aimed at supporting the life cycle of large and heterogeneous enterprise's knowledge bases. In particular, the defined architecture relies on hybrid methodologies which apply computational intelligence techniques and Semantic Web technologies to support Knowledge Extraction, Ontology Matching and Ontology Merging.
{"title":"Hybrid methodologies to foster ontology-based knowledge management platform","authors":"V. Loia, G. Fenza, C. D. Maio, S. Salerno","doi":"10.1109/IA.2013.6595187","DOIUrl":"https://doi.org/10.1109/IA.2013.6595187","url":null,"abstract":"Nowadays, a multitude of users benefits from social interactions, blogging, wiki in order to share their own contents with each other (i.e., user-generated content). In fact, both Web 2.0 and Enterprise 2.0 applications have changed the knowledge sharing paradigm, and have introduced enabling features to foster information flow among users. Nevertheless, the availability of large amount of information targeted to human employment highlights reusing, reasoning and exploitation of available knowledge. Emerging Semantic Web technologies enable to codify information in a machine understandable way. Therefore, the latest web development trend is devoted to combine Web 2.0 features with semantic technologies (e.g. semantic tagging, semantic wiki). This scenario raises new requirements in terms of knowledge base extraction, update and maintenance. To this end, this work defines an ontology-based knowledge management platform that integrates methodologies aimed at supporting the life cycle of large and heterogeneous enterprise's knowledge bases. In particular, the defined architecture relies on hybrid methodologies which apply computational intelligence techniques and Semantic Web technologies to support Knowledge Extraction, Ontology Matching and Ontology Merging.","PeriodicalId":114295,"journal":{"name":"2013 IEEE Symposium on Intelligent Agents (IA)","volume":"162 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126414959","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：