ANFIS BASED MODELS FOR ACCESSING QUALITY OF WIKIPEDIA ARTICLES

Wikipedia is a free, web-based, collaborative, multilingual encyclopedia project supported by the non-profit Wikimedia Foundation. Due to the free nature of Wikipedia and allowing open access to everyone to edit articles the quality of articles may be affected. As all people don’t have equal level of knowledge and also different people have different opinions about a topic so there may be difference between the contributions made by different authors. To overcome this situation it is very important to classify the articles so that the articles of good quality can be separated from the poor quality articles and should be removed from the database. The aim of this study is to classify the articles of Wikipedia into two classes class 0 (poor quality) and class 1(good quality) using the Adaptive Neuro Fuzzy Inference System (ANFIS) and data mining techniques. Two ANFIS are built using the Fuzzy Logic Toolbox [1] available in Matlab. The first ANFIS is based on the rules obtained from J48 classifier in WEKA while the other one was built by using the expert’s knowledge. The data used for this research work contains 226 article’s records taken from the German version of Wikipedia. The dataset consists of 19 inputs and one output. The data was preprocessed to remove any similar attributes. The input variables are related to the editors, contributors, length of articles and the lifecycle of articles. In the end analysis of different methods implemented in this research is made to analyze the performance of each classification method used.

Estimation of Parameters in Random Effect Models with Incidence Matrix Uncertainty

Random effect models have been widely applied in many fields of research. However, models with uncertain design matrices for random effects have been little investigated before. In some applications with such problems, an expectation method has been used for simplicity. This method does not include the extra information of uncertainty in the design matrix is not included. The closed solution for this problem is generally difficult to attain. We therefore propose an two-step algorithm for estimating the parameters, especially the variance components in the model. The implementation is based on Monte Carlo approximation and a Newton-Raphson-based EM algorithm. As an example, a simulated genetics dataset was analyzed. The results showed that the proportion of the total variance explained by the random effects was accurately estimated, which was highly underestimated by the expectation method. By introducing heuristic search and optimization methods, the algorithm can possibly be developed to infer the 'model-based' best design matrix and the corresponding best estimates.

Depicting the interplay between organisational tiers in the use of a national quality registry to develop quality of care in Sweden

BACKGROUND: With a pending need to identify potential means to improved quality of care, national quality registries (NQRs) are identified as a promising route. Yet, there is limited evidence with regards to what hinders and facilitates the NQR innovation, what signifies the contexts in which NQRs are applied and drive quality improvement. Supposedly, barriers and facilitators to NQR-driven quality improvement may be found in the healthcare context, in the politico-administrative context, as well as with an NQR itself. In this study, we investigated the potential variation with regards to if and how an NQR was applied by decision-makers and users in regions and clinical settings. The aim was to depict the interplay between the clinical and the politico-administrative tiers in the use of NQRs to develop quality of care, examining an established registry on stroke care as a case study. METHODS: We interviewed 44 individuals representing the clinical and the politico-administrative settings of 4 out of 21 regions strategically chosen for including stroke units representing a variety of outcomes in the NQR on stroke (Riksstroke) and a variety of settings. The transcribed interviews were analysed by applying The Consolidated Framework for Implementation Research (CFIR). RESULTS: In two regions, decision-makers and/or administrators had initiated healthcare process projects for stroke, engaging the health professionals in the local stroke units who contributed with, for example, local data from Riksstroke. The Riksstroke data was used for identifying improvement issues, for setting goals, and asserting that the stroke units achieved an equivalent standard of care and a certain level of quality of stroke care. Meanwhile, one region had more recently initiated such a project and the fourth region had no similar collaboration across tiers. Apart from these projects, there was limited joint communication across tiers and none that included all individuals and functions engaged in quality improvement with regards to stroke care. CONCLUSIONS: If NQRs are to provide for quality improvement and learning opportunities, advances must be made in the links between the structures and processes across all organisational tiers, including decision-makers, administrators and health professionals engaged in a particular healthcare process.

Local politico-administrative perspectives on quality improvement based on national registry data in Sweden : a qualitative study using the Consolidated Framework for Implementation Research.

Background. Through a national policy agreement, over 167 million Euros will be invested in the Swedish National Quality Registries (NQRs) between 2012 and 2016. One of the policy agreement¿s intentions is to increase the use of NQR data for quality improvement (QI). However, the evidence is fragmented as to how the use of medical registries and the like lead to quality improvement, and little is known about non-clinical use. The aim was therefore to investigate the perspectives of Swedish politicians and administrators on quality improvement based on national registry data. Methods. Politicians and administrators from four county councils were interviewed. A qualitative content analysis guided by the Consolidated Framework for Implementation Research (CFIR) was performed. Results. The politicians and administrators perspectives on the use of NQR data for quality improvement were mainly assigned to three of the five CFIR domains. In the domain of intervention characteristics, data reliability and access in reasonable time were not considered entirely satisfactory, making it difficult for the politico-administrative leaderships to initiate, monitor, and support timely QI efforts. Still, politicians and administrators trusted the idea of using the NQRs as a base for quality improvement. In the domain of inner setting, the organizational structures were not sufficiently developed to utilize the advantages of the NQRs, and readiness for implementation appeared to be inadequate for two reasons. Firstly, the resources for data analysis and quality improvement were not considered sufficient at politico-administrative or clinical level. Secondly, deficiencies in leadership engagement at multiple levels were described and there was a lack of consensus on the politicians¿ role and level of involvement. Regarding the domain of outer setting, there was a lack of communication and cooperation between the county councils and the national NQR organizations. Conclusions. The Swedish experiences show that a government-supported national system of well-funded, well-managed, and reputable national quality registries needs favorable local politico-administrative conditions to be used for quality improvement; such conditions are not yet in place according to local politicians and administrators.

Nurses' research utilization two years after graduation : a national survey ofassociated individual, organizational, and educational factors

Background. Nurses' research utilization (RU) as part of evidence-based practice is strongly emphasized in today's nursing education and clinical practice. The primary aim of RU is to provide high-quality nursing care to patients. Data on newly graduated nurses' RU are scarce, but a predominance of low use has been reported in recent studies. Factors associated with nurses' RU have previously been identified among individual and organizational/contextual factors, but there is a lack of knowledge about how these factors, including educational ones, interact with each other and with RU, particularly in nurses during the first years after graduation. The purpose of this study was therefore to identify factors that predict the probability for low RU among registered nurses two years after graduation. Methods. Data were collected as part of the LANE study (Longitudinal Analysis of Nursing Education), a Swedish national survey of nursing students and registered nurses. Data on nurses' instrumental, conceptual, and persuasive RU were collected two years after graduation (2007, n = 845), together with data on work contextual factors. Data on individual and educational factors were collected in the first year (2002) and last term of education (2004). Guided by an analytic schedule, bivariate analyses, followed by logistic regression modeling, were applied. Results. Of the variables associated with RU in the bivariate analyses, six were found to be significantly related to low RU in the final logistic regression model: work in the psychiatric setting, role ambiguity, sufficient staffing, low work challenge, being male, and low student activity. Conclusions. A number of factors associated with nurses' low extent of RU two years postgraduation were found, most of them potentially modifiable. These findings illustrate the multitude of factors related to low RU extent and take their interrelationships into account. This knowledge might serve as useful input in planning future studies aiming to improve nurses', specifically newly graduated nurses', RU.