International Journal of Advanced Networking and Applications

4509-4518

Authors: Gajendra Sharma, UmeshHengaju

In Data mining, Classification and prediction are the two very essential forms of data analysis. They are widely used for extracting models for describing important data classes. This paper aims in designing classifier models based on five different classification algorithms namely, Decision Tree, K-Nearest Neighbors (KNN), Naive Bayes, Random Forest and Support Vector Machines (SVM), to classify and predict patients with diabetes. These classifiers are experimented with 10 fold Cross Validation and their performances are evaluated by computing Accuracy, Precision, F-Score, Recall and ROC measure. The test experiment shows that the accuracy given by classifier models developed by using Decision Tree, KNN, Naïve Bayes, SVM and Random Forest are 73.82%, 71.65%, 76.30%, 65.10% and 68.74 % respectively. Similarly, their precisions and recall are 0.705, 0.552, 0.759, 0.424, 0.538 and 0.738, 0.763, 0.82, 0.651, 0.804 respectively. Thus, this study shows that the Naïve Bayes algorithm provides the better accuracy in predicting diabetes as compared to other techniques. And, the data set chosen for this study is “Pima Indian Diabetic Dataset” taken from University of California, Irvine (UCI) Repository of Machine Learning databases.

4528-4531

Authors: Pshwang Wang, Zecheng Wang

In order to protect mobile social network users' privacy information, and promote the healthy development of the mobile social industry, This paper studies the types and ways of user privacy disclosure in mobile social networks, and proposes the privacy protection strategies for users in mobile social networks from the aspects of formulating national laws and regulations, building and managing mobile platforms, improving privacy protection technologies and enhancing personal protection awareness. It also briefly introduces the development trend and future research of access control policies in mobile social network.

4537-4541

Authors: Dr.K.R.R.MOHAN RAO, Dr K.KIRAN KUMAR, Prof. P.SUBBA RAO

In the fund world stock exchanging is one of the most significant exercises. Securities exchange expectation is a demonstration of attempting to decide the future estimation of a stock other money related instrument exchanged on a monetary trade. This paper clarifies the expectation of a stock utilizing Machine Learning[6]. The specialized and central or the time arrangement examination is utilized by the a large portion of the stockbrokers while making the stock forecasts. The programming language is utilized to anticipate the securities exchange utilizing AI is Python. Right now propose a Machine Learning[10] (ML) approach that will be prepared from the accessible stocks information and increase insight and afterward utilizes the gained information for a precise forecast. Right now study utilizes an AI system called Support Vector Machine (SVM)[1] to anticipate stock costs for the enormous and little capitalizations and in the three distinct markets, utilizing costs with both every day and regularly updated frequencies.