This paper presents findings of a study to predict the winners of an One Day International (ODI) cricket game, after the completion of the first inning of the game. We use Naive Bayes (NB) approach to make this prediction using the data collected with 15 features, comprised of variables related to batting, bowling, team composition, and other. Upon the construction of an initial model, our objective is to improve the accuracy of predicting the winner using some feature selection algorithms, namely univariate, recursive elimination, and principle component analysis (PCA). Furthermore, we examine the contribution of the appropriate ratios of training sample size to testing sample size on the accuracy of prediction. According to the experimental findings, the accuracy of winner-prediction can be improved with the use of feature selection algorithm. Moreover, the accuracy of winner prediction becomes the highest (85.71%) with the univariate feature selection method, compared to its counterparts. By selecting the appropriate ratio of the sample sizes of training sample to testing sample, the prediction accuracy can be further increased.

Display Omitted A scalable monitoring scheme for stealthy attacks on computer networks is presented.Bayesian fusion along with traffic sampling is used as a data reduction method.Stealthy activities can be detected using 10-20% size sampling rates.A tracing algorithm for anonymous stealthy activities to their sources is presented.The effect of network parameters on detection is investigated. Stealthy attackers move patiently through computer networks - taking days, weeks or months to accomplish their objectives in order to avoid detection. As networks scale up in size and speed, monitoring for such attack attempts is increasingly a challenge. This paper presents an efficient monitoring technique for stealthy attacks. It investigates the feasibility of proposed method under number of different test cases and examines how design of the network affects the detection. A methodological way for tracing anonymous stealthy activities to their approximate sources is also presented. The Bayesian fusion along with traffic sampling is employed as a data reduction method. The proposed method has the ability to monitor stealthy activities using 10-20% size sampling rates without degrading the quality of detection.

Elementary education is critical as it lays the foundation for learning, critical thinking, social and emotional development, individual growth, and self-confidence. Hence, studying the elementary students’ educational progress is immensely important. This manuscript aims to investigate the factors that impact elementary students’ academic performance, predict their academic performance, and use the above factors to identify the student’s appropriate skilled level group based on their academic performance. In this study, the Dynamic Indicators of Basic Early Literacy Skills (DIBELS) score, a measurement to assess students’ early literacy skills for K-6 graders, is used to quantify students' academic performance. A sample of 185 first and second graders and their features, including student’s BMI (body mass index), amount of time the student spends watching television, student’s gender, number of hours that a student sleeps each night, amount of time that the student spends reading books, student’s race, and amount of time that the student spends on physical activity are used. Based on the regression analysis, second graders’ academic performances are significantly impacted by their BMI values (β = − 4.002, p < 0.05) and the amount of time students spend reading books (β = 29.14, p < 0.05). The first graders’ academic performances are significantly impacted by the amount of sleeping time (β = 41.89, p < 0.01) and their gender (β = − 37.129, p < 0.05). Furthermore, the experimental findings indicate that machine-learning techniques accurately predict the students' appropriate academic group. In the naive Byers classifier, students in the lowest academic performance group can be identified successfully with a sensitivity of 92%, and the students in the highest academic group can be identified with a specificity value of 100%.