Pokpong Songmuang

Bees Algorithm for Construction of Multiple Test Forms in E-Testing

The purpose of this research is to automatically construct multiple equivalent test forms that have equivalent qualities indicated by test information functions based on item response theory. There has been a trade-off in previous studies between the computational costs and the equivalent qualities of test forms. To alleviate this problem, we propose an automated system of test construction based on the Bees Algorithm in parallel computing. We demonstrate the effectiveness of the proposed system through various experiments.

Maximum Clique Algorithm and ItsApproximation for UniformTest Form Assembly

Educational assessments occasionally require uniform test forms for which each test form comprises a different set of items, but the forms meet equivalent test specifications (i.e., qualities indicated by test information functions based on item response theory). We propose two maximum clique algorithms (MCA) for uniform test form assembly. The proposed methods can assemble uniform test forms with allowance of overlapping items among uniform test forms. First, we propose an exact method that maximizes the number of uniform test forms from an item pool. However, the exact method presents computational cost problems. To relax those problems, we propose an approximate method that maximizes the number of uniform test forms asymptotically. Accordingly, the proposed methods can use the item pool more efficiently than traditional methods can. We demonstrate the efficiency of the proposed methods using simulated and actual data.

Maximum Clique Algorithm for Uniform Test Forms Assembly

Educational assessments occasionally require “uniform test forms” for which each test form consists of a different set of items, but the forms meet equivalent test specifications (i.e., qualities indicated by test information functions based on item response theory). We propose two maximum clique algorithms (MCA) for uniform test forms assembly. The proposed methods can assemble uniform test forms with allowance of overlapping items among uniform test forms. First, we propose an exact method that maximizes the number of uniform test forms from an item pool. However, the exact method presents computational cost problems. To relax those problems, we propose an approximate method that maximizes the number of uniform test forms asymptotically. Accordingly, the proposed methods can use the item pool more efficiently than traditional methods can. We demonstrate the efficiency of the proposed methods using simulated and actual data.

Reducing waiting time in automatic captioned relay service using short pause in voice activity detection

The Automatic Captioned Relay Service is crucial for hearing disabilities or hard-of-hearing to communicate with others in real life. This service uses an Automatic Speech Recognition (ASR) to transcribe speech to a caption. If can reduce waiting time from non-streaming speech recognition, the relay service will support more users. In this paper, we proposed a method for improving a voice activity detection (VAD) using a short pause as endpoint based on dual-threshold method. This method reduces waiting time of the captions results. The experimental results show that the propose method reduces 19.10% of waiting time without losing the accuracy of captions when compare with traditional VAD.

Automated Test Assembly with Minimum Redundant Questions Based on Bee Algorithm

An ideal test form should contain questions with different level of difficulties and non-redundant questions. This paper proposed an automated test assembly algorithm to minimize the redundant question in a test form based on Bee algorithm. A neighborhood search in Bee algorithm is improved by using a new technique, called Min-SumDistance (MSD). The MSD is the distance of considered question compared to others in the test form. The sum of question pairs distance indicates to the redundant question in the test form. A question content is represented in two forms as an unigram with TF and TF-IDF scores. The experiments using 200 questions from Information Technology Professional Examination(ITPE). To evaluate the performance of MSD method, we count a number of enemy pairs of the test form and compared to the random method. The experimental results show that our proposed algorithm yields the significant numbers of redundant questions.

Comparison of Document Clustering Methods Based on Bees Algorithm and Firefly Algorithm Using Thai Documents

Several researches performed experiments to compare performances of data clustering methods based on nature-inspired algorithms using various data types including text document dataset. According to the results, although Firefly algorithm showed high performance to cluster text document over several nature-inspired algorithms but Bees algorithm had better performance to solve complex problems than several nature-inspired algorithms. However, none of the experiments compared the performances of the both algorithms to cluster text documents. Therefore, we compare the document clustering performances of the clustering methods based on Firefly algorithm and Bees algorithm.