دانلود رایگان مقاله انگلیسی مدلسازی دانشجویی در آموزش جراحی ارتوپدی: بهره گیری از تعامل بین شبکه های بیزی زمانی و تحلیل تعلیمی ظریف به همراه ترجمه فارسی
عنوان فارسی مقاله | مدلسازی دانشجویی در آموزش جراحی ارتوپدی: بهره گیری از تعامل بین شبکه های بیزی زمانی و تحلیل تعلیمی ظریف |
عنوان انگلیسی مقاله | Student Modeling in Orthopedic Surgery Training: Exploiting Symbiosis between Temporal Bayesian Networks and Fine-grained Didactic Analysis |
رشته های مرتبط | علوم تربیتی و کامپیوتر، تکنولوژی آموزشی و هوش مصنوعی |
کلمات کلیدی | مدلسازی دانشجویی، شبکه های بیزی زمانی، پشتیبانی هوشمند ، مهندسی تعلیمی ، آموزش پزشکی، شبیهسازی های کامپیوتری |
فرمت مقالات رایگان |
مقالات انگلیسی و ترجمه های فارسی رایگان با فرمت PDF آماده دانلود رایگان میباشند همچنین ترجمه مقاله با فرمت ورد نیز قابل خریداری و دانلود میباشد |
کیفیت ترجمه | کیفیت ترجمه این مقاله متوسط میباشد |
توضیحات | ترجمه این مقاله به صورت خلاصه انجام شده است. |
سال انتشار | 2010 |
کد محصول | F673 |
مقاله انگلیسی رایگان (PDF) |
دانلود رایگان مقاله انگلیسی |
ترجمه فارسی رایگان (PDF) |
دانلود رایگان ترجمه مقاله |
خرید ترجمه با فرمت ورد |
خرید ترجمه مقاله با فرمت ورد |
جستجوی ترجمه مقالات | جستجوی ترجمه مقالات |
فهرست مقاله: چکیده |
بخشی از ترجمه فارسی مقاله: مقدمه |
بخشی از مقاله انگلیسی: INTRODUCTION Knowledge Modeling and Student Modeling In the past thirty years, research results in cognitive science have been exploited for student modeling in problem solving, as evidenced by a significant number of cognitive approaches (Webber, 2004; Mayo & Mitrovic, 2001; Murray, 1999). Many studies have been done within the context of teaching fundamental subjects, for example, geometry (Anderson, Boyle, & Yost, 1986), (Webber, 2004), algebra (Koedinger, Anderson, Hadley, & Mark, 1997), physics (Albacete & VanLehn, 2000), computer programming language (Anderson, Farrell, & Sauers, 1984). The nature of domain knowledge and the complexity of the learner’s cognitive behavior, especially in a number of specific subjects (e.g., in medical education), however, have not been considered carefully. Firstly, the tacit pragmatic knowledge (obtained by experience) plays an important role for both the expert teacher and the novice learner during a problem-solving process. This tacit knowledge refers to “work-related, practical know-how that typically is acquired informally as a result of on-the-job experience, as opposed to formal instruction.” (Wagner, Sujan, Sujan, Rashotte, & Sternberg, 1999, p. 157). While observing a number of medical interventions in a French hospital, we realized that sometimes the expert teacher and the novice student, when confronting a specific problem, used pragmatic knowledge to elaborate an original solution to the problem encountered, which could not have been defined before. Secondly, the student’s cognitive behavior we observed in those interventions is complex. A skillful learner, even a domain expert, often makes several attempts before arriving at an acceptable solution: he or she may make an error and then retry to correct the error several times. Thus, from an observer’s point of view, one may need to consider a sequence of actions from the learner to be able to diagnose his or her cognitive state and behavior accurately. A number of researchers (Kodaganallur, Weitz, & Rosenthal, 2005; Luengo, Mufti-Alchawafa, & Vadcard, 2004; Webber, 2004; Mitrovic & Ohlsson, 1999) have argued that it is important to check the consistency of the student’s solution with domain constraints (i.e., local consistency checks) rather than to compare the student’s solution with the domain expert’s a priori normative solution (Ohlsson, 1992). This idea is particularly useful for building tutoring systems for the kind of specific domains mentioned in the previous paragraph, because in those domains there may have many different solutions to a given problem, some of which being elaborated in action by the domain expert. So, the first question we address in this paper is concerned with exploiting and analyzing different kinds of domain knowledge, especially tacit pragmatic knowledge, in order to build a robust domain model, which is critical for student modeling and diagnosis (Weber & Brusilovsky, 2001). Tacit pragmatic knowledge is often not explicitly explained in theoretical courses or reference books (Vadcard & Luengo, 2005). To answer the first question, we argue for a fine-grained “didactic” analysis (Pastré, 1997). Didactic (an originally francophone term) designates the study of teaching and knowledge acquisition in different subject domains. Didactic is thus different from pedagogy by the central role of the subject domain contents and by its epistemological dimension (i.e., the nature of knowledge to be taught). To some extent, didactic analysis is similar to cognitive task analysis (Clark & Estes, 1996). Both of them seek to better understand the subject being taught, so as to better devise instructional situations for students. The major difference between them is the analysis protocol: cognitive task analysis is often done by observing highly skilled practitioners and describing the precise activities that are required to perform a complex task, whereas didactic analysis is often performed in instructional or apprenticeship settings in which, for example, a novice learner interacts with an expert teacher to solve problems. Unlike cognitive task analysis, which tries to describe the problem-solving process of domain experts as completely as possible and to seek pedagogical implications from that process, didactic analysis seeks different kinds of knowledge needed for successful teaching directly from observing instructional or apprenticeship settings. Hence, didactic analysis may reveal special kinds of knowledge such as pedagogical content knowledge (Shulman, 1986) that cognitive task analysis might not be able to produce because the domain experts might not have those kinds of knowledge in mind or not reveal them explicitly in the context of cognitive task analysis. Special kinds of knowledge such as pedagogical content knowledge are useful for the design of a learning environment (Shulman, 1986). The second question is concerned with exploiting suitable techniques in artificial intelligence to model and “diagnose” the student’s knowledge or cognitive state at a given time and his or her cognitive behavior over time. The first diagnosis is important and very common in many traditional ITSs (Wenger, 1987). We believe that the second diagnosis about cognitive behavior could be also important, because it may help generate better feedback for the student. A way to do those kinds of diagnosis is to analyze the student’s interactions with the interface of the learning system such as a computerbased simulation (Luengo, Mufti-Alchawafa, & Vadcard, 2004). Diagnosing the student’s knowledge and cognitive behavior, however, is not easy because it is difficult to know what happens exactly in the mind of an individual when he or she is learning a concept or solving a problem (Sasse, 1991). Bayesian networks offer a useful technique for modeling under uncertainty (e.g., about students’ cognitive state), and according to Mayo and Mitrovic (2001) it has been adopted in many applications, including ITSs. Considering the complexity of the learner’s cognitive behavior over time (e.g., the learner’s correction process while he or she is constructing a solution) in specific domains, as mentioned previously, temporal (or dynamic) Bayesian networks (Russell & Norvig, 2009; Ghahramani, 1998) could be an effective means. |