In the Cyberspace, most people are tailored to obtain intelligence from the World Wide Web. To endure and flourish, a Web site has to constantly encourage its overall layout and potentials while providing a variety of constructive information services to attract users. The Web Recommendation System prompts users to visit a Web site and browse at a deeper level. Using large browsing patterns don’t satisfy user’s dynamic need. The requirement for an adaptive recommendation system comes into the modern world to encourage the online users to get required details immediately. This paper proposes a novel Web recommendation framework, based on Page Classification Algorithm which can respond to new navigation trends and dynamically adapts recommendations for users with suitable suggestions through hyperlinks. This research enables Web sites with dynamic intelligence to effectively tailor users’ needs by means of personalization. User behavior is identified for the improvement of website design

The successful application of data mining in highly visible fields like e-business, marketing and retail has led to its application in other industries and sectors. Among these sectors just discovering is healthcare. The Healthcare industry is generally “information rich”, but unfortunately not all the data are mined which is required for discovering hidden frequent patterns & effective decision making. Discovery of hidden patterns and relationships often goes unexploited. Advanced data mining modeling techniques can help remedy this situation.Data mining is a process which finds useful patterns from large amount of data. Data items are frequent in itemset is to be organized in multilevel and multi dimensional way. Data mining is the process of discovering interesting knowledge such as Patterns and Associations.  The process of looking for patterns to document is called pattern mining. Pattern mining is a data mining method that involves finding existing patterns  in the data. Mining frequent patterns is probably one of the most important concepts in data mining. Graph transformation method is used for  mining of patterns in frequent itemset. An  itemset  is closed  if none of its immediate supersets has the same support as the itemset. Frequent itemsets are so important . This paper intends to  use data mining Classification Modeling Techniques, namely, Decision Trees, Naïve Bayes and Neural Network, along with weighted association Apriori algorithm  in Heart Disease Prediction.

In this Natural world scenario, everything is performed in computerized manner, but recently it is moving from Computer World to Mobile World for trading and commercial purpose. Many small applications are developed and executed via mobile. Likewise computer learning system is slowly moving down and changing into mobile learning system. In field of education, it would become next generation blackboard. It is very beneficial for Students to get knowledge in their desire field.  Usage of mobile is very flexible and cheaper too. This paper supports M-learning, at the same time this paper examines certain Main issues related with the effective implementation of Mobile phones in all levels of education (like primary, secondary, higher-level) as well as types of education (formal, informal). It provides suggestions to address certain challenges that would help in the implementation of Mobile Phones in education. Explains about influence of mobile App development in the field of education with some proposing future works.

The healthcare industry has large amounts of data, driven by record keeping, medicine details, new era of medical needs, compliance & regulatory requirements, other stakeholders in the healthcare delivery and patient care. While most data is stored in paper records, the digitization of these large amounts of data would be the first and foremost activity.

Bioinformatics is one of the emerging technologies which is played an important role in the field of biology. The molecular biology and Bioinformatics information are extracted from the protein data set which is used for analysing the different kind of biological information. The major challenges in the protein data set are larger in size, which increases the complexity during the further experimental process. The complexity of the system is reduced by hybridized Soft Computing techniques and Evolutionary Methods. Thus, in this paper proposed that optimal feature selection method for reducing the dimensionality of the protein feature set to improve the performance of the proposed system. Initially, the biological data are grouped into the clusters which is fall into the pre-processing step for removing the missing and unwanted data’s. The cluster formation is done by Ant Colony with Rough Set Theory (ACRST) based feature selection process. The performance of the system is evaluated with the help of the existing algorithms such as wrapper method, Greedy Forward Selection, Particle Swarm Optimization, Scatter Search and the comparison is analyzed with the help of the accuracy, sensitivity and specificity.