Authors Mohammed J. Alhaddad
Authors Surjeet Kumar Yadav Saurabh Pal
Authors Husein Osman Abdullahi Abdirizaq said Jamaludin Bin Ibrahim 
Authors Ahmad Haboush Ahmad Momani Maryam Al-Zoubi Motassem Tarazi
Authors Aryaf Abdullah Aladwan Rufaida Muhammad Shamroukh Ana’am Abdullah Aladwan
Authors Rufaida Muhammad Shamroukh Aryaf Abdullah Aladwan Ana’am Abdullah Aladwan
Multiple Classifiers to verify the Online Signature Abstract: Nowadays biometric increasingly used in many applications that  has strong relation to our live; it's a reliable mean as an alternative to the  traditional methods of personal identification. As a behavioral biometric,  an online signature still has some shortcomings because of that nature.  Furthermore, features in online signature verification system can be either  global or local; the techniques that can be used also variety. In this paper  both global and local features were used. To classify the mentioned  features; the back-propagation neural network (BPNN) technique was used  to classify the local features, whereas, the global features was classified by  the probabilistic model.   Once the results obtained from the local  classifier and global classifier, the “AND” fusion was used to combine the  two classifiers for final decision. SVC2004 dataset was used to evaluate the  proposed method in term of False Rejection Rate (FRR) and False  Acceptance Rate (FAR).  The obtained results for FRR and FAR were 0.3%  and 0.5% respectively. These results are encouraging when compared with  related existing studies. Keywords : Online Signature; Probabilistic Modeling; Back-propagation  Neural Network (BPNN).  Data Mining: A Prediction for Performance Improvement of Engineering Students using Classification Abstract: Now-a-days the amount of data stored in educational database  increasing rapidly. These databases contain hidden information for  improvement of students’ performance. Educational data mining is used to  study the data available in the educational field and bring out the hidden  knowledge from it. Classification methods like decision trees, Bayesian  network etc can be applied on the educational data for predicting the  student’s performance in examination. This prediction will help to identify  the weak students and help them to score better marks. The C4.5, ID3 and  CART decision tree algorithms are applied on engineering student’s data to  predict their performance in the final exam. The outcome of the decision  tree predicted the number of students who are likely to pass, fail or  promoted to next year. The results provide steps to improve the  performance of the students who were predicted to fail or promoted. After  the declaration of the results in the final examination the marks obtained  by the students are fed into the system and the results were analyzed for  the next session. The comparative analysis of the results states that the  prediction has helped the weaker students to improve and brought out  betterment in the result.  Keywords : Prediction; Educational data mining; Decision tree; C4.5  algorithm; ID3 algorithm; CART algorithm. An Investigation into privacy and Security in Online Social Networking Sites among IIUM Students Abstract: The issues of privacy and security in online social networking sites have been the dual themes of utmost concern amongst many communities  and IIUM community in particular. This article highlights the importance of  online social networking sites such as:  Face book, Google+, and Twitter  and the issues of privacy and security in online interactions. The authors  also argue that the online social networks have played a significant role on  daily digital interaction for more than half billion users around the world  today are bedeviling with the issues of privacy and security. This study  employs a quantitative data analysis, a survey and a random sampling of  (n=160) IIUM students from different Kulliyah were conducted. The result  shows that the percentage responses of IIUM who seems to be actively  involved in online social network pages are not