MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Heart Attacks are the major cause of death in the world today, particularlyin India. The need to predict this is a major necessity for improving the countrieshealthcare sector. Accurate and precise prediction of the heart disease mainly depends onElectrocardiogram (ECG) data. Heart disease is a major life threatening disease that causeto death and it has a serious long term disability. The time taken to recover from heartdisease depends on patient’s severity. Heart disease diagnosis is complex task whichrequires much experience and knowledge. Nowadays, health care industry contain hugeamount of health care data, which contain hidden information. Advanced data miningtechniques along with computer generated information are used for appropriate results.Neural Network is widely used tool for predicting heart attack. A Heart Attack PredictionSystem we are going to develop using Neural Network and Genetic Algorithm. Thissystem calculates the number of hidden nodes for neural network which train the networkwith proper selection of neural network architecture and uses the global optimization ofgenetic algorithm for initialization of neural network.

Engineering and Technology

World University root node

Fulltext

International Journal of Latest Trends in Engineering and Technology

A survey on ECG signal monitoring through sensor and prediction of heart attack with the help of optimized neural network using genetic algorithm

With enterprises collecting feedback down to every possible detail, data repositories are being over flooded with information. In-order to access valuable information, these data should be processed using sophisticated statistical analysis. Traditional analytical tools, existing statistical software and data management systems find it challenging to perform deep analysis upon large data libraries. Users demand a service platform that can store and handle large quantities of data with some features such as easy accessibility, fast performance, durable and secure. These features can be availed without having to spend too much on hardware, upgrading, configuring etc to perform analysis of big data. This project intends to overcome all these obstacles and built a user friendly SAAS platform. It is cloud based web application which stores data in Amazon S3. As this system supports dynamic and optimized cluster nodes size as per the desired time, user doesn't need to calculate and estimate the number of nodes. The system uses Amazon EMR and MapReduce paradigm using opensource R scripting language to perform analysis of bigdata analysis in desire time. © 2016 IEEE.

Proceedings of 2016 International Conference on Advanced Communication Control and Computing Technologies, ICACCCT 2016

High performance analytics of bigdata with dynamic and optimized hadoop cluster

Now a days, a lot of people and groups are using X.509 certificates to represent their identity, during online trade, so the level of purity and trustworthiness of these certificates becomes dubious. Hence, we have suggested a model which calculates the risk associated with X.509 certificates by evaluating Certificate Practice statement (CPS) document and by using certain trust criteria. For evaluating CPS document we have proposed a novel algorithm which locates certain attributes, in the CPS document. We are referring to these attributes from the prior paper of Omar and Lindsay. Our model categorizes risk in three levels-High, Medium and Low risk. It has application in detecting phishing websites which contain Https URL. © 2016 IEEE.

International Conference on Computing, Analytics and Security Trends, CAST 2016

Risk assessment of X.509 certificate by evaluating Certification Practice Statements

In collaborative environment (CE) multiple members work together to achieve a common goal. But to find person/source that has most relevant information is a challenging part as the information requirement varies from task to task. Today, people are working in a collaborative environment to explore the ever increasing data and have new insights for knowledge sharing. Analyzing these needs we have proposed a system that finds the most appropriate and relevant documents based on the search query. In this system relevancy of document is supported by expert search method. In expert search, various aspects such as author name, hit count (number of downloads) of document, time span of hit count and last hit to that document are considered and clustering of retrieved results with meaningful cluster labels are identified to find whether a search term is used in the intended sense in that document. In this system, documents uploaded by members are analyzed. After analysis, indexing of documents is done. Further based on search query documents are retrieved and labeled clusters of documents are formed. Finally expert search is applied over mined results. This system helps in getting exact knowledge with quick response and repeating efforts for finding same information can be avoided with efficient time utilization. The performance of proposed system is evaluated with respect to response time of system. Thus, the effective use of knowledge sharing (data/information) is achieved with the Expert Search for time efficient systems. © 2017 IEEE.

2017 International Conference on Emerging Trends Innovation in ICT (ICEI)

Expert search based knowledge sharing system for collaborative environment

Water scarcity has been a big issue for agriculture. This proposed idea is beneficial to the farmers to irrigate the farms efficiently using an automated irrigation system based on soil temperature, moisture and pH. Respective sensors are used to find the soil water content level and based on this microcontroller drives the servo motor and pump. Irrigation status is updated to the database using PC. This technique works by installing sensors in the field to monitor the soil temperature, moisture and type of soil, which transmits the data to the microcontroller for estimation of accurate quantity of water as per the requirements. The collected data is updated from time to time to the server and can be accessed via an Android app. The subsequent watering of plants can be controlled using the aforementioned app. Depending upon the type of soil and crop, the fertilizers are suggested by applying Naïve Bayes algorithm on the database. The estimated amount of rain is predicted using weather forecasting using Web scraper and the crops are watered accordingly, i.e., is a heavy rainfall is predicted then the system will automatically reduce the water supplied to the crops. © 2017 IEEE.

2017 2nd International Conference for Convergence in Technology, I2CT 2017

Smart water dripping system for agriculture/farming

With use of advanced image processing software's and tools, it becomes very easy to perform the tampering on original digital images with different intensions. Such kind of image tampering or manipulation is collectively called as image forgery. The main two types are 1) copy-move forgery and 2) image splicing forgery of image forgery. Copy-move tampering is most generally used by attackers in which object of another image is copy and paste in original image in nearly matching areas. Hence to identify such image threats, it is required to automatic computer vision based method which can classify whether input digital image is original or tampered. The image processing based methods are mainly three important phases like as image pre-processing, image features extraction and detection of forged area on image using features extracted. For copy-move forgery detection there are many methods introduced from last 15 years. This all methods are categorized in two main types is active and passive forgery detection methods. This paper scope is limited to study on passive forgery detection methods. In this paper, aim is to present the study on different old methods of image forgery detection using different approaches like DWT (Discrete Wavelet Transform), SIFT, LBP (Local Binary Pattern) etc. The outcome of this paper is to find the current research challenges based on study of different methods of image forgery detection through the comparative study of all recent methods studied. © 2017 IEEE.

Proceedings of the International Conference on IoT in Social, Mobile, Analytics and Cloud, I-SMAC 2017

Study and analysis of copy-move &amp; splicing image forgery detection techniques

Sentiment analysis is the process of analyzing the text about a topic written in a natural language and classify them as positive or negative based on the human sentiments, opinions expressed in it. Due to the increasing growth in use of social media (e.g. reviews, forum, blogs, Twitter and postings in social network sites) on the Web, users now have many opportunities to express their opinions about a product or topic. Users express their opinion through the reviews. These reviews are used by the individuals and organizations for decision making purpose. It is impossible to read and extract user opinions from such huge number of reviews manually. To solve such problem an automated opinion mining approach is required. It is difficult for a user to read and understand all the reviews. Relevant and important information about these establishments should be fetched from reviews and presented to user in a summarized manner. Current approaches for opinion mining, attempts to detect the polarity of a sentence, paragraph or text regardless of the aspects mentioned in it. In this paper we proposed an aspect based approach for opinion mining which uses aggregate score of opinion words and aspect table together for opinion mining process. The main motive of the system is to develop an opinion mining application with improved accuracy by following an implicit approach. © 2016 IEEE.

ISAR: Implicit sentiment analysis of user reviews

Delay Tolerant Networks is an emerging technique which supports for the intermittent connectivity. Previously, for transmission of bundles the end-To-end connection was required to carry out the transmission successfully. But now, using the store-carry-forward mechanism and the node mobility it is possible to transmit the data from the source to the destination even if there is no end to end connection between them. There are different routing strategies which are formed in a DTN environment to reduce the message overhead and for increasing the message delivery probability, but very few take the energy into a consideration while designing. DTN nodes have a very limited amount of energy resources which holds a great significance. To perform any kind of operation between various nodes, i.e. sending bundle, searching for the neighbor node, storing bundle, etc the energy is used. Hence, in this paper, we proposed a new energy efficient algorithm to improve the energy efficiency. This algorithm forwards the packet to the nearest neighbor node which also uses the probability distribution function to forward the bundle to the next best hop which requires the least energy for the transmission. It also narrows down the specific region for the transmission of data by using the angle based transmission. The freshly energized node is redeployed in the network. With the help of Opportunistic Network Simulator results, it is proven that the designed algorithm is more energy efficient than the previous distance based algorithm. © 2017 IEEE.

Implementation of energy efficient algorithm in delay tolerant networks

Image is a representation of visual information. Objects and its shape are important aspect as image contains information about various useful structures during information analysis. Segmentation of image is one of the necessary task in image processing. It involves generation of various useful parts called segments as set of selected pixels belong to image. One of the objective of such division is to provide an ability to have automation in identification of various objects in image and analyze relevant information image contains. During the process of object extraction there is a need to separate image background and foreground in efficient and accurate manner. Image segmentation provides easy and more meaningful way to represent an image. In this paper CIE L*a*b* Color Segmentation using Green and Yellow Colors was implemented which can be extended to any other dominant color in image. Boundary extraction along with color segmentation implemented in this paper aims towards identification of various objects and their region color.

International Journal Of Advances In Cloud Computing And Computer Science

Color Based Image Segmentation and Object Detection for Color Content Based Feature

Cloud computing technologies getting importance with a high level in security concern. In a domain of private, public or government organization. It shows new aspect for transparency. The main issue that Cloud computing provides transparency, but sharing of resources at different level in distributed scheme has severe implications. When at sensitive or privacy-relevant data is concerned for most secure challenging task. In cloud computing ensure the data security in data access control is an effective way. The problem with unsecured cloud servers or the untrusted cloud servers, data access control to various vendors becomes a challenging and most unsecured issue in cloud storage systems in these days. However after user's data or attribute revocation if we have to show the more security through re-encryption process. In the proposed method we uses certificate less encryption-based schemes by relying on a public cloud server. We have applied it as underlying techniques to design the data users and data access control scheme in process. We came to know that our certificate less encryption method can efficiently provide not only forward security but also backward security with more efficient way. © 2016 IEEE.