A Machine Learning Based Funding Project Evaluation Decision Prediction

Traditional linear statistical methods cannot provide effective prediction results due to the complexity of human mind.In this paper,we apply machine learning to the field of funding allocation decision making,and try to explore whether personal characteristics of evaluators help predict the outcome of the evaluation decision?and how to improve the accuracy rate of machine learning methods on the imbalanced dataset of grant funding?Since funding data is characterized by imbalanced data distribution,we propose a slacked weighted entropy decision tree(SWE-DT).We assign weight to each class with the help of slacked factor.The experimental results show that the SWE decision tree performs well with sensitivity of 0.87,specificity of 0.85 and average accuracy of 0.75.It also provides a satisfied classification accuracy with Area Under Curve(AUC)=0.87.This implies that the proposed method accurately classified minority class instances and suitable to imbalanced datasets.By adding evaluator factors into the model,sensitivity is improved by over 9%,specificity improved by nearly 8%and the average accuracy also increased by 7%.It proves the feasibility of using evaluators’characteristics as predictors.And by innovatively using machine learning method to predict evaluation decisions based on the personal characteristics of evaluators,it enriches the literature in the field of decision making and machine learning field.

Estimating Usable-Security Through Hesitant Fuzzy Linguistic Term Sets Based Technique

The apparent contradiction between usability and security has been discussed in the literature for several years.This continuous trade-off requires be acknowledging and handling whenever security solutions are introduced.However,some progressive analysts point out that present security solutions are usually very difficult for several users,and they have expressed a willingness to simplify the security product user experience.Usable security is still mostly unexplored territory in computer science.Which we are all aware with security and usability on many levels,usable security has received little operational attention.Companies have recently focused primarily on usable security.As consumers prefer to discard unsatisfactory solutions,attaining well-balanced degrees of both is a prerequisite for adequate security.Usability should be examined from the viewpoint of security to be properly assessed.The aim of this research study is to explore and discuss universally accepted and solutionindependent factors influencing the perceived usable-security of institutional websites.An integrated Hesitant Fuzzy Linguistic term sets based technique was chosen as the methodology,and the experts and academicians opinion were collected.The use of predetermined selection criteria resulted in the compilation of statistical findings and were used to determine the usable-security of five different instituational websites.

Gearbox Device Failure Mode Criticality Analysis Based on Support Vector Machine

A method which integrates expert evaluation method and support vector machine(SVM) method is introduced for failure mode criticality analysis(FMCA) about the gearbox device. An expert evaluation standard is built by using expert evaluation method. The experts make scores about the gearbox failure mode. In order to overcome the subjectivity of expert evaluation method, we use SVM method to make a comprehensive prediction about the scores. According to the comprehensive prediction evaluation results, the FMCA of the gearbox device can be obtained. The analysis shows that the method used in this paper not only can effectively solve the problem which is unable to get specific failure rate in the qualitative analysis, but also can solve the problem which needs lots of data in the quantitative analysis.