The ability to extract state-estimates for each target of a multi-target posterior, referred to as multi-estimate extraction(MEE), is an essential requirement for a multi-target filter, whose key performance assessmen...The ability to extract state-estimates for each target of a multi-target posterior, referred to as multi-estimate extraction(MEE), is an essential requirement for a multi-target filter, whose key performance assessments are based on accuracy, computational efficiency and reliability. The probability hypothesis density(PHD) filter, implemented by the sequential Monte Carlo approach,affords a computationally efficient solution to general multi-target filtering for a time-varying number of targets, but leaves no clue for optimal MEE. In this paper, new data association techniques are proposed to distinguish real measurements of targets from clutter, as well as to associate particles with measurements. The MEE problem is then formulated as a family of parallel singleestimate extraction problems, facilitating the use of the classic expected a posteriori(EAP) estimator, namely the multi-EAP(MEAP) estimator. The resulting MEAP estimator is free of iterative clustering computation, computes quickly and yields accurate and reliable estimates. Typical simulation scenarios are employed to demonstrate the superiority of the MEAP estimator over existing methods in terms of faster processing speed and better estimation accuracy.展开更多
Educational innovation is a field that has been greatly enriched by using technology in its processes, resulting in a learning model where information comes from numerous sources and collaboration takes place among mu...Educational innovation is a field that has been greatly enriched by using technology in its processes, resulting in a learning model where information comes from numerous sources and collaboration takes place among multiple students. One attractive challenge within educational innovation is the design of collaborative learning activities from the social computing point of view, where collaboration is not limited to student-to-student relationships, but includes student-to-machine interactions. At the same time, there is a great lack of tools that give support to the whole learning process and are not restricted to specific aspects of the educational task. In this paper, we present and evaluate context-aware framework for collaborative learning applications(CAFCLA) as a solution to these problems. CAFCLA is a flexible framework that covers the entire process of developing collaborative learning activities, taking advantage of contextual information and social interactions. Its application in the experimental case study of a collaborative WebQuest within a museum has shown that, among other benefits, the use of social computing improves the learning process, fosters collaboration, enhances relationships, and increases engagement.展开更多
4:1!Google’s artificial intelligence(AI)program,Alpha Go,has won Go Master Lee Sedol in a best-of-five competition held in Korean March 9-15,2016.Seen by many as a landmark moment for AI,the outcome did not come as a...4:1!Google’s artificial intelligence(AI)program,Alpha Go,has won Go Master Lee Sedol in a best-of-five competition held in Korean March 9-15,2016.Seen by many as a landmark moment for AI,the outcome did not come as a surprise,considering the excellent combination of 1920 CPUs with so-展开更多
基金Project supported by the Marie Sk?odowska-Curie Individual Fellowship(H2020-MSCA-IF-2015)(No.709267)the Open Project Program of Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering,Southeast University,China(No.MCCSE2017A01)
基金partly supported by the Marie SklodowskaCurie Individual Fellowship (No. 709267)under the European Union’s Framework Programme for ResearchInnovation Horizon 2020 and National Natural Science Foundation of China (No. 51475383)
文摘The ability to extract state-estimates for each target of a multi-target posterior, referred to as multi-estimate extraction(MEE), is an essential requirement for a multi-target filter, whose key performance assessments are based on accuracy, computational efficiency and reliability. The probability hypothesis density(PHD) filter, implemented by the sequential Monte Carlo approach,affords a computationally efficient solution to general multi-target filtering for a time-varying number of targets, but leaves no clue for optimal MEE. In this paper, new data association techniques are proposed to distinguish real measurements of targets from clutter, as well as to associate particles with measurements. The MEE problem is then formulated as a family of parallel singleestimate extraction problems, facilitating the use of the classic expected a posteriori(EAP) estimator, namely the multi-EAP(MEAP) estimator. The resulting MEAP estimator is free of iterative clustering computation, computes quickly and yields accurate and reliable estimates. Typical simulation scenarios are employed to demonstrate the superiority of the MEAP estimator over existing methods in terms of faster processing speed and better estimation accuracy.
基金Project supported by the National Natural Science Foundation of China(No.51475383)European Commission MSCA-RISE-2014(No.641794)+1 种基金the Excellent Doctorate Foundation of Northwestern Polytechnical Universitythe Postdoctoral Fellowship of the University of Salamanca
基金Project supported by the Interreg V-A Spain-Portugal Program(PocTep)the European Regional Development Fund(ERDF) under the IOTEC project(No.0123_IOTEC_3_E)
文摘Educational innovation is a field that has been greatly enriched by using technology in its processes, resulting in a learning model where information comes from numerous sources and collaboration takes place among multiple students. One attractive challenge within educational innovation is the design of collaborative learning activities from the social computing point of view, where collaboration is not limited to student-to-student relationships, but includes student-to-machine interactions. At the same time, there is a great lack of tools that give support to the whole learning process and are not restricted to specific aspects of the educational task. In this paper, we present and evaluate context-aware framework for collaborative learning applications(CAFCLA) as a solution to these problems. CAFCLA is a flexible framework that covers the entire process of developing collaborative learning activities, taking advantage of contextual information and social interactions. Its application in the experimental case study of a collaborative WebQuest within a museum has shown that, among other benefits, the use of social computing improves the learning process, fosters collaboration, enhances relationships, and increases engagement.
文摘4:1!Google’s artificial intelligence(AI)program,Alpha Go,has won Go Master Lee Sedol in a best-of-five competition held in Korean March 9-15,2016.Seen by many as a landmark moment for AI,the outcome did not come as a surprise,considering the excellent combination of 1920 CPUs with so-