No abstract

No abstract

No abstract

The prediction of burn patient survivability is a difficult problem to investigate till present times. In present study a prediction Model for patients with burns was built, and its capability to accurately predict the survivability was assessed. We have compared different data mining techniques to asses the performance of various algorithms based on the different measures used in the analysis of information pertaining to medical domain. Obtained results were evaluated for correctness with the help of registered medical practitioners. The dataset was collected from SRT (Swami Ramanand Tirth) Hospital in India, which is one of the Asia's largest rural hospitals. Dataset contains records of 180 patients mainly suffering from burn injuries collected during period from the year 2002 to 2006. Features contain patients' age, sex and percentage of burn received for eight different parts of the body. Prediction models have been developed through rigorous comparative study of important and relevant data mining classification techniques namely, navie bayes, decision tree, support vector machine and back propagation. Performance comparison was also carried out for measuring unbiased estimate of the prediction models using 10-fold cross-validation method. Using the analysis of obtained results, we show that Navie bayes is the best predictor with an accuracy of 97.78% on the holdout samples, further, both the decision tree and support vector machine (SVM) techniques demonstrated an accuracy of 96.12%, and back propagation technique resulted in achieving accuracy of 95%.

The use of data mining approaches in the domain of predict the survival of a particular patient. Automated tools for medicine is increasing rapidly. The effectiveness of these storage and retrieval of large volume of medical data have approaches to classification and prediction has improved the become possible with the increase in the computing power. performance of their systems. These are particularly useful to This large amount of data is made available to the medical medical practioners in decision making. In this paper, we research community which is interested in developing present an analysis of prediction of the survivability of the burn prediction models for survivability. New research avenues such patients. The machine learning algorithm c4.5 is used to classify as knowledge discovery in databases (KDD) have become the patients using WEKA tool. The performance of the algorithm ... popular and medical researchers are mining the data, so that is examined by using the classification accuracy, sensitivity, they can identify and exploit patterns and relationships among specificity and confusion matrix. The dataset was collected from . .Swami Ramanand Tirth Hospital, Ambajogai, Maharashtra, l ut mer of f eate t aoh India and is used retroactively from data records of the burn outcome of a disease [5]. patients. The results are found to be precise and accurate by This paper is organized as follows: The next section comparing with actual information on survivability or death.introduces the WEKA tool. Section 3 gives the methodology used to conduct the prediction analysis on the burn patient.

No abstract

This paper deals with improvement of swelling characteristics of clayey soil by adding industrial waste and RBI Grade 81. The construction of road in clayey soil is challenging due to its more swelling and more shrinkage characteristics. To overcome this problem there are two solutions one is replace the clayey soil by good quality granular material. The second is stabilizing the subgrade clayey soil by using various industrial wastes. Generally pond ash, fly ash and stone dust are use for soil stabilization. The swelling and shrinkage characteristics of clayey soil are considerably improved if it treated with industrial wastes and RBI Grade 81. The RBI Grade 81 is chemical soil stabilizer. The differential free swell index (DFS) test was carried out on different mix of soil, industrial waste and RBI Grade 81. The result shows that the DFS index of untreated soil obtained is 65% reduces to 35% by addition of 20% fly ash and 4% RBI Grade 81. This reduction in DFS index helps to reduce the effect of moisture variation in clayey soil.

No abstract