The Research on Web-Based Testing Environment Using Simulated Annealing Algorithm

Abstract

The computerized evaluation is now one of the most important methods to diagnose learning; with the application of artificial intelligence techniques in the field of evaluation, the computerized adaptive testing gradually becomes one of the most important evaluation methods. In this test, the computer dynamic updates the learner's ability level and selects tailored items from the item pool. In order to meet the needs of the test it requires that the system has a relatively high efficiency of the implementation. To solve this problem, we proposed a novel method of web-based testing environment based on simulated annealing algorithm. In the development of the system, through a series of experiments, we compared the simulated annealing method and other methods of the efficiency and efficacy. The experimental results show that this method ensures choosing nearly optimal items from the item bank for learners, meeting a variety of assessment needs, being reliable, and having valid judgment in the ability of learners. In addition, using simulated annealing algorithm to solve the computing complexity of the system greatly improves the efficiency of select items from system and near-optimal solutions.

Diagnostic Accuracy Comparison of Artificial Immune Algorithms for Primary Headaches

“…These applications [ 17 – 19 ] provide quick and easy information to physicians. This is especially the case with web-based applications [ 20 ], which have enabled people to become more connected to each other. Hence, in this study we developed an expert web-based headache-diagnosis system to collect and share patients' data from different cities and used artificial immune system algorithms to classify their headache types.…”

Multi-Swarm Optimization for Extracting Multiple-Choice Tests From Question Banks

“…In this paper, we present an approach to extract the abundance of tests with equivalent levels of difficulty and approximate the specific difficulty level requirement given by the user based on question banks and parallel multiswarm migration in PSO algorithm. Our approach performs better than the other techniques, such as Simulate Annealing [7], Random [4], etc., in terms of the execution time and quality of the tests. The experimental results are compared with those from PSO methods such as sequential PSO, parallel PSO and parallel migration PSO and assessed in light of several essential criteria, including number of successful solutions, accuracy, standard deviation, search speed, and number of questions overlapping between the exam questions, as well as for changing the search space (large and small question banks), changing the number of individuals, changing the number of groups (number of questions), and changing the difficulty requirements of the test.…”

“…However, it can be seen that generating many tests with the same level of difficulty is an extremely hard task, even in the case of manually choosing questions from a question bank, and so the success rate of generating multiple-choice tests satisfying a given difficulty is low and timeconsuming. Therefore, to speed up the process and improve the quality of the results, some authors apply local search algorithms such as Tabu Search (TS) [9] and Simulated Annealing (SA) [7] to generate tests with the use of computers and approximate the resulting difficulties to the required ones. Some authors also apply GA [12][13] to solve the problem of extracting tests, and the experimental results showed that such approaches can reach approximately a 100% success rate, and GA is also faster than SA for this task.…”

“…This problem is important when extracting multiple tests with similar difficulty for multiple students at the same time. We compare the efficiency of algorithms such as PSO following sequential, parallel and parallel migration; Simulate Annealing Algorithm [7]; and Random Algorithm [4], using the same criteria for the experiments. Based on the average statistical method after 10 runs, we examine the number of successful solutions, accuracy, standard deviation, search speed, and number of questions overlapping between the exam questions, as well as changing the search space (large and small question banks), changing the number of individuals, changing the number of groups (number of questions), and changing the difficulty requirements of the test.…”

“…We have proven the effectiveness of the PSO in parallel migration in the problem of extracting multiplechoice tests with a difficulty level predefined by the user. Besides, we have evaluated and compared the efficiency of the proposed algorithm and other algorithms from previous works, such as Random [4] and SA [7]. Our proposed algorithms are always highly effective based on the evaluation criteria for the change in the number of individuals in the swarm, change in the number of swarms, and change in the difficulty of the test.…”