In large classes, teachers find it difficult to care about the personality and ability of individual students. One of the ways to grasp the learning state of students is to conduct a number of short tests during every class. If a system can automatically give the appropriate instructions and teaching materials to individual students based on the test results of each student, students in the large classes will be able to obtain the same advantages as those that can be obtained in tutorial classes. We have developed automatic marking systems and have been able to conduct a number of short tests. In this paper, we discuss the development of an integrated e-learning system for realizing large classes that enhance students' academic motivation by recognizing each student's state of learning.
All students (about 1000) at Sapporo Gakuin University are required to take a Computer Literacy course. At Hokkaido University, we teach courses, such as AI Programming, with approximately 100 students. By using automatic marking systems of our own design we can check student work and obtain the results immediately. It reduces our labor, enables us to grasp individual students' learning states, and allows us to tailor our instruction to each student's needs. Automatic marking is a key technology for determining the current individual learning state of each student in a large class. By using automatic marking we can conduct short tests many times, mark the tests automatically, and collect detailed information about the learning states of students from the test results. However, developing reliable and efficient marking systems is a difficult and time-consuming job using conventional methods. In this paper, we introduce our automatic marking systems, share our experiences developing and using the systems in our classes, and discuss the possibility of expanding its use to object-oriented programming language courses.
This paper proposes a framework for time-efficiently finding multiple answers that meet multiple logical constraints and are Pareto-optimal for multiple objective functions. The proposed framework determines a set of optimal answers by iteratively replacing a set of definite clauses. Clause replacement is performed using a SAT solver consisting of equivalent transformation rules (ETRs). An ETR replaces a definite clause with one or more clauses while preserving the declarative meaning of the union of the original clause and problem clauses. To efficiently find optimal answers, in this paper, we define a new class of ETRs that are generated based on the evaluation results of a multi-objective genetic algorithm (MOGA), and propose a method for generating ETRs that belong to the new class. ETRs belonging to the new class help to replace definite clauses according to user objectives such as cost-benefit performance, reliability, and financial constraints. Thus, a SAT solver that uses the new ETR class in addition to extant ETR classes can preferentially replace definite clauses that produce the optimal answer for user objectives. Experimental results indicate that the proposed framework can significantly reduce the computation time and memory usage necessary to determine a set of optimal answers for user objectives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.