Search

In the real world, most of the entities are involved with space and time, from any starting point to the end point of the space. The conventional data mining process is extended to the mining knowledge of the spatiotemporal databases. The major knowledge is to mine the association rules in the spatiotemporal databases; the traditional approaches are not sufficient to do mining in the spatiotemporal databases. While mining the association rules, the privacy is the main concern. This paper proposed privacy preserved data mining technique for spatiotemporal databases based on the mining negative association rules and cryptography with low storage and communication cost. In the proposed approach first, the partial support for all the distributed sites is calculated, and then finally, the actual support was calculated to achieve privacy preserve data mining. The mathematical calculation was done and proved that this approach is best for mining association rules for spatiotemporal databases.

With the growth in the present digital era, the Internet is the prime source of knowledge. This situation is depleted by phishers and they have drafted various websites which steals user’s information and misuse it. Though it is hard to locate a phishing site, various features of the phishing site helps in uncovering its mask. This paper discusses several features to identify a phishing site. Using data mining techniques like classification and association rule mining many explorations are performed to prove the notion. Similarly, the impact of various features considered for analysis is studied too.

Data mining is the process of examining large databases to extract patterns, knowledge and to establish relationships to provide solution for the complex problems. Researchers have shown their interest in different areas particularly in identifying outliers. An object which significantly deviates from other objects or by their normal behaviour is termed as outliers. Real-world data have vagueness and uncertainty which can be handled by rough set theory. Research works that have been carried so far were focussed only on single universal set to detect outliers. By using intuitionistic fuzzy soft set relation, this paper proposes an idea for detecting outliers in two universal sets in which the attribute-based and object-based weighted density values are determined to detect outliers. The hiring dataset has taken for example and shown the validity of the proposed approach for outlier detection.

The ever-increasing fame of wireless technologies and their purposefulness of usage in the communication scenario is fascinating the interest of customers day by day. As we all know that this is the recent technology within the mobile telecommunications is the 4G architecture. Long term evolution (LTE) is said to be the nominee of the next generation in the direction of 4G in mobile broadband technology, which offers a data rate of 100 Mbps and works with IP. It is recently an emerging technology and it offers enhanced speed, capacity and coverage for present mobility networks. LTE, which is considered to be an IP based network, is said to eradicate the issues present in the communication systems such as lack of resources and distributed services to the users in their day to day life. It increases the speed and capacity with improvements in core network deployment and different radio interfaces all together. In order to provide a seamless and high speed communication, customization of channel is needed for each individual user. For channel allocation, there are several methods to predict available channel and optimal usage of channel to users. By the optimal selection of channel and customized scheduling, we can manage the data transmission to users. For this process, LTE system was used to schedule the channel. However, in LTE scheduling, the scheduler has to verify the channel information, user availability and hand off status in the network. The above mentioned criterions might create some limitation during scheduling of the channel. In order to overcome this limitation, we propose a novel feature extraction method and classification method for data mining process to retrieve the information about a network for LTE scheduling. In addition to this here in this paper we have analyzed the dataset and with the help of MATLAB.