|Commenced in January 2007||Frequency: Monthly||Edition: International||Paper Count: 18|
Rough set theory is used to handle uncertainty and incomplete information by applying two accurate sets, Lower approximation and Upper approximation. In this paper, the rough clustering algorithms are improved by adopting the Similarity, Dissimilarity–Similarity and Entropy based initial centroids selection method on three different clustering algorithms namely Entropy based Rough K-Means (ERKM), Similarity based Rough K-Means (SRKM) and Dissimilarity-Similarity based Rough K-Means (DSRKM) were developed and executed by yeast dataset. The rough clustering algorithms are validated by cluster validity indexes namely Rand and Adjusted Rand indexes. An experimental result shows that the ERKM clustering algorithm perform effectively and delivers better results than other clustering methods. Outlier detection is an important task in data mining and very much different from the rest of the objects in the clusters. Entropy based Rough Outlier Factor (EROF) method is seemly to detect outlier effectively for yeast dataset. In rough K-Means method, by tuning the epsilon (ᶓ) value from 0.8 to 1.08 can detect outliers on boundary region and the RKM algorithm delivers better results, when choosing the value of epsilon (ᶓ) in the specified range. An experimental result shows that the EROF method on clustering algorithm performed very well and suitable for detecting outlier effectively for all datasets. Further, experimental readings show that the ERKM clustering method outperformed the other methods.
The research was conducted to empirically validate the proposed maturity model of e-Government implementation, composed of four dimensions, further specified by 54 success factors as attributes. To do so, there are two steps were performed. First, expert’s judgment was conducted to test its content validity. The second, reliability study was performed to evaluate inter-rater agreement by using Fleiss Kappa approach. The kappa statistic (kappa coefficient) is the most commonly used method for testing the consistency among raters. Fleiss Kappa was a generalization of Kappa in extensions to the case of more than two raters (multiple raters) with multi-categorical ratings. Our findings show that most attributes of the proposed model were related to their corresponding dimensions. According to our results, The percentage of agree answers given by the experts was 73.69% in dimension A, 89.76% in B, 81.5% in C and 60.37% in D. This means that more than half of the attributes of each dimensions were appropriate or relevant to the dimensions they were supposed to measure, while 85% of attributes were relevant enough to their corresponding dimensions. Inter-rater reliability coefficient also showed satisfactory result and interpreted as substantial agreement among raters. Therefore, the proposed model in this paper was valid and reliable to measure the maturity of e-Government implementation.
This study was conducted to generate empirical evidence on validity and reliability of the item of Competency Assessment Implementation (CAI) Instrument using Rasch Model for polythomous data aided by Winstep software version 3.68. The construct validity was examined by analyzing the point-measure correlation index (PTMEA), infit and outfit MNSQ values; meanwhile the reliability was examined by analyzing item reliability index. A survey technique was used as the major method with the CAI instrument on 156 teachers from vocational schools. The results have shown that the reliability of CAI Instrument items were between 0.80 and 0.98. PTMEA Correlation is in positive values, in which the item is able to distinguish between the ability of the respondent. Statistical data obtained show that out of 154 items, 12 items from the instrument suggested to be omitted. This study is hoped could bring a new direction to the process of data analysis in educational research.
An automatic moment-based texture segmentation approach is proposed in this paper. First, we describe the related work in this computer vision domain. Our texture feature extraction, the first part of the texture recognition process, produces a set of moment-based feature vectors. For each image pixel, a texture feature vector is computed as a sequence of area moments. Then, an automatic pixel classification approach is proposed. The feature vectors are clustered using an unsupervised classification algorithm, the optimal number of clusters being determined using a measure based on validation indexes. From the resulted pixel classes one determines easily the desired texture regions of the image.
The purpose of this study was to examine the reliability and validity of the Masculine Subordination-to-women Stress Scale (MSS) in the rural Bangladeshi population. The scale was validated using a sample of 342 Bangladeshi married men from 5 northwest villages of the country. Exploratory factor analysis revealed a single-factorial structure of the scale: masculine subordination-to-women stress. The MSS also showed adequate reliability and concurrent validity. It appears that the MSS is a reliable and valid instrument to measure masculine subordination-to-women stress for Bangladeshi men. However, further study of the scale is imperative.
In this paper we study the fuzzy c-mean clustering algorithm combined with principal components method. Demonstratively analysis indicate that the new clustering method is well rather than some clustering algorithms. We also consider the validity of clustering method.
This article investigated the validity of C-test and Cloze test which purport to measure general English proficiency. To provide empirical evidence pertaining to the validity of the interpretations based on the results of these integrative language tests, their criterion-related validity was investigated. In doing so, the test of English as a foreign language (TOEFL) which is an established, standardized, and internationally administered test of general English proficiency was used as the criterion measure. Some 90 Iranian English majors participated in this study. They were seniors studying English at a university in Tehran, Iran. The results of analyses showed that there is a statistically significant correlation among participants- scores on Cloze test, C-test, and the TOEFL. Building on the findings of the study and considering criterion-related validity as the evidential basis of the validity argument, it was cautiously deducted that these tests measure the same underlying trait. However, considering the limitations of using criterion measures to validate tests, no absolute claims can be made as to the construct validity of these integrative tests.
Validity is an overriding consideration in language testing. If a test score is intended for a particular purpose, this must be supported through empirical evidence. This article addresses the validity of a multiple-choice achievement test (MCT). The test is administered at the end of each semester to decide about students' mastery of a course in general English. To provide empirical evidence pertaining to the validity of this test, two criterion measures were used. In so doing, a Cloze test and a C-test which are reported to gauge general English proficiency were utilized. The results of analyses show that there is a statistically significant correlation among participants' scores on the MCT, Cloze, and Ctest. Drawing on the findings of the study, it can be cautiously deduced that these tests measure the same underlying trait. However, allowing for the limitations of using criterion measures to validate tests, we cannot make any absolute claim as to the validity of this MCT test.
In a particular case of behavioural model reduction by ANNs, a validity domain shortening has been found. In mechanics, as in other domains, the notion of validity domain allows the engineer to choose a valid model for a particular analysis or simulation. In the study of mechanical behaviour for a cantilever beam (using linear and non-linear models), Multi-Layer Perceptron (MLP) Backpropagation (BP) networks have been applied as model reduction technique. This reduced model is constructed to be more efficient than the non-reduced model. Within a less extended domain, the ANN reduced model estimates correctly the non-linear response, with a lower computational cost. It has been found that the neural network model is not able to approximate the linear behaviour while it does approximate the non-linear behaviour very well. The details of the case are provided with an example of the cantilever beam behaviour modelling.
We develop a three-step fuzzy logic-based algorithm for clustering categorical attributes, and we apply it to analyze cultural data. In the first step the algorithm employs an entropy-based clustering scheme, which initializes the cluster centers. In the second step we apply the fuzzy c-modes algorithm to obtain a fuzzy partition of the data set, and the third step introduces a novel cluster validity index, which decides the final number of clusters.