DNA Methylation Data Analytics in Cancer Research
Many studies demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different subtypes of the tumor[1]. However, the conventional statistical methods are not suitable for analyzing the highly dimensional DNA methylation data with bounded support. DNA methylation is one of the most extensively studied epigenetic marks, and is known to be implicated in a wide range of biological processes, including chromosome instability, X-chromosome inactivation, cell differentiation, cancer progression and gene regulation[4]. Identification of cancer subtypes plays an important role in revealing useful insights into disease pathogenesis and advancing personalized therapy. In order to explicitly capture the properties of the data, a deep neural network is used, which composes of several stacked binary restricted Boltzmann machines, to learn the low-dimensional deep features of the DNA methylation data.
Published by: Apoorva Patil, Rashmi A. Rane
Author: Apoorva Patil
Paper ID: V4I1-1161
Paper Status: published
Published: January 8, 2018
A Study on the Volatility and Return with Reference to Stocks of Bank Nifty
Study on stock market trends has been an area of vast interest both for who wish to make a profit by trading stock in the stock market. India is one of the emerging economies, which has witnessed significant developments in the stock markets during the liberalization policy initiated by the government. However, investing in banking shares include high risks which can be guided but not controlled. The banking sector is the backbone of country’s economy. This sector has given very good return to the investors in the past. But the recent financial crisis has proved, that the Banking stocks tend to be more volatile than other stocks. This paper is a humble attempt to measure the volatility of the Bank index stocks and compare it with that of the volatility of NIFTY. Stock markets, in general, are considered volatile and volatility plays a key role in measuring the risk-return trade-offs. Estimating volatility enables the pricing of securities and, understanding stock market volatility or individual stock price volatility enables good decisions on the part of investors. Investors who are risk-averse would not be happy to invest in a highly fluctuating stock, whereas those with a thirst for riskiness would happily invest in a highly volatile market. The study evaluates the performance of banking stocks mainly to identify the required rate of return and risk of a particular stock based upon different risk elements prevailing in the market and other economic factors.
Published by: Rohith U J
Author: Rohith U J
Paper ID: V4I1-1150
Paper Status: published
Published: January 8, 2018
A Literature Survey on Intrusion Detection and Protection System using Data Mining
In the modern world of security many researchers have proposed various new approaches; among those techniques application of data mining for Intrusion detection is one of the best suitable approaches.The system proposes a security system, name the Intrusion Detection and Protection System (IDPS) at system call level, which creates the personal profile for the user to keep track of user usage habits as the forensic features. The IDP uses a local computational grid to detect malicious behavior in a real-time manner. In this paper, a security system, named the IDPS is proposed to detect insider attacker at SC level by using data mining and forensic techniques.
Published by: Chaitali Choure , Leena H. Patil
Author: Chaitali Choure
Paper ID: V4I1-1144
Paper Status: published
Published: January 8, 2018
Big Data Classification of Users Navigation and Behavior Using Web Server Logs
Users for online shopping are increasing day by day because of easy to get and time-saving property of online shopping. Having a proper understanding of users interest for certain type of product or different products for online shopping becomes important to create personalized service for a target market. An important property of successful e-commerce website is the ability to provide useful content at the right time to users. And because of all this, personalization techniques are introduced to create adaptive shopping application in which user interfaces change according to users interest. User’s behavior information is stored in web log files, and to get the information data mining techniques are used in which they use statistical characters to model users behavior and not considering the sequence of action performed by uses. It becomes helpful if we follow user’s session to understand complex user behavior. Therefore to eliminates all these issues this paper proposes a linear-temporal logic model checking approach for the analysis of structured e-commerce weblogs. If we consider a common way of mapping log records according to e-commerce structure, weblogs can be easily converted into event logs by which behavior of the user is captured. After getting users behavior by performing different predefine queries to identify different behavioral patterns that consider the different actions performed by a user during a session.
Published by: Prajakta Ghavare, Prashant Ahire
Author: Prajakta Ghavare
Paper ID: V4I1-1172
Paper Status: published
Published: January 8, 2018
Application of the Hash Function on Secret Message and Provide it Security with the Help of Invisible ASCII Character Replacement Technology
Most widely used technique over the internet for communication is the text-document exchange. This text document may contain valuable data or some general information of any kind. If this text document contains some important information and if gets hacked then they may change information about it or may misuse that information. Because of all these reasons we need some technique for information hiding within a text document while communication over the internet. Although there are lots of text-based information hiding techniques present and proposed by many authors but these techniques have some drawbacks such as poor robustness, lower embedding rate, and semantic clutter. Due to all these flaws in the existing system many time the information is hacked or extracted by the interceptors. To mitigates all these drawbacks of existing system or techniques we proposed a new technique based on the hash function and the invisible ASCII character replacement method. In this approach, we first find the binary formatted information which is added by even numbers of 1’s for even parity, after that the space character in every carrier is replaced by SOH with the help of some replacement algorithm. In the third stage, a hash value is generated. At last the hash value is compared with the encoded secret information.
Published by: Swati Dandekar, Dr. Jyoti Rao
Author: Swati Dandekar
Paper ID: V4I1-1171
Paper Status: published
Published: January 8, 2018
Sliding Window Control Based High Utility Pattern Mining For Industrial Use
Value of the item set is considered as an utility of that item set and find out the high utility of the item set is the aim of utility mining .Some time database parameters are considered to find out high utility pattern eg. Profit, cost etc. In day to day life high utility pattern mining play important role in applications. Its current hot topic in today’s research area. Different existing algorithms are present in this area .It first of all identify the candidate itemsets by using their utilities, and simultaneously identify the exact utility of that candidate pattern. Problem of using this algorithm is large number of candidate itemsets are generated. But after computing exact utility it’s clear that most of the candidate having no high utility. For generating profitable product manufacturing plan its very important to understanding the customer preferences in industrial area. One of the approach in pattern mining, by considering the quantity, quality and cost of each product for generating high profitable product set, which employed to find out high utility pattern. For establishing highly profitable manufacturing plan which allow corporation to maximize its revenue, high utility pattern mining is important aspect. Large amount of stream data related to customer purchase behavior used for establishing manufacturing plan. Recent preference of the customers also helps in generating manufacturing plans. This survey work contains a list structure and a novel algorithm for generating high utility pattern over large data, on the basis of Sliding Window Control Mode. This approach avoid the generation of candidate pattern. Due to that algorithm not required large amount of memory space as well as computational resources for verifying candidate patterns. Due to this it’s very efficient approach.
Published by: Swapnali Londhe, Rupesh Mahajan
Author: Swapnali Londhe
Paper ID: V4I1-1170
Paper Status: published
Published: January 8, 2018
