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

Malaria is a fatal disease. It is transmitted from one person to another by the bite of female Anopheles Mosquitoes. The estimated cost of detection of malaria in India is 11,640 crore per year. There are various techniques to diagnose malaria of which manual microscopy is considered to be the gold standard but it takes more time. The proposed method not only improved the degree of accuracy of the analysis but it provides double checked to verify the correct results. The proposed work used various image processing techniques like image acquisition, image pre-processing, segmentation, feature extraction using regional descriptor, feature detection using edge detector and then classification using particle swarm optimization support vector machine. The classification work in two levels, the first level is applicable for checking the presence of malaria parasite in red blood corpuscles and the second level is detect the type of malaria parasite using particle swarm optimization support vector machine. This proposed work is mainly focus on detection accuracy, false match rate, computational time, less estimation time for parasite detection and complexity. In this way, the detection of malaria parasite may be give faster and accurate results. Keywords: Malaria parasite, image processing, Image pre-processing segmentation, Feature extraction, classification.&nbsp;

Engineering and Technology

International Journal of Computer Engineering and Applications

TO DEVELOP AN AUTOMATED MALARIA DETECTION USING REGIONAL DESCRIPTER AND PSO SVM CLASSIFIER

In this paper, we propose a two-factor data security protection mechanism forpathology laboratory system. Our system allows a pathologist (sender) to upload anencrypted information of patient on cloud storage server. The pathologist (receiver)needs to possess two things in order to decrypt the cipher text. The first thing ishis/her secret key stored in the computer. The second thing is a unique personalsecurity device which connects to the computer. There are two types of storages in thesystem. First one is private data storage and second is public data storage. We have toupload and download data on private storage with the help of security device and inpublic data storage we can download data using secret key via e-mail. This process iscompletely transparent to the third party (admin). The security and efficiencyanalysis show that our system is not only secure but also practical.

World University root node

International Engineering Research Journal (IERJ)

Securing Information of Pathology Lab using Two-Factor Data Security Mechanism in Cloud

Depression is a mental disorder that affects not only the thoughts but also the body and behavior of the person suffering from it. Depression detection, as of today, is limited to analysis of the patient by the psychologist, which is prone to subjective bias. Although depression is a mental disorder, it affects various physical attributes like eye movements, voice modulation, urine, saliva, etc. These effects, if observed and analyzed, can be used for designing tests wherein the physiological parameters are observed and depression is detected objectively, thus reducing the burden on psychologists. This paper gives a systematic review of the studies undertaken for analyzing the effects of depression on different physical attributes.

International Journal of New Technology and Research (IJNTR)

Different Parameters for Computational DepressionAnalysis: A Review

Nowadays, we find students having ‘n’ abilities. It is difficult to predict, if a person is a good speaker, is he good at studies? If a student is good in academics, is he/she good at communication skills? There are many machine learning techniques identified as a paradigm is modeling of student’s academic performance. This work is aimed at predicting student’s performance on the basis of various factors and him/her his/her area of weaknesses to be handled and strengths to be enhanced. This system will predict student’s academic performance, behavior, personality, and mental ability.

Recommendation System for Performance Enhancement of Students

In recent time World Wide Web or web is collection of billions of web pages growing exponentially by the means of public transport, social media, online shopping, blogs etc. This highly generated data is stored, for a large duration of time results into big data. Big data can be in structured, unstructured or semi structured format. This exponential growth of web pages generates huge data which is beyond the capability of relational database. Analysis of such large data cannot be handled easily using traditional data mining tool. Thus Data mining is being researched intensively and combined with soft computing domain, which uses mathematical algorithms to segment data and analyze the probability of future events. In the paper we mention about the evolutionary clustering technique Particle Swarm Optimization (PSO) algorithm on web data, fetched with the help of crawler and preprocessed by removing stop words and stemming. Then an improved numerical statistic method, Term Frequency Inverse Document Frequency is applied on the preprocessed data to derive the importance of a word with respect to a set of documents and overcome traditional TDIDF issue of inter class consideration. A parallel PSO clustering technique is applied on this data to get optimized clusters with higher accuracy and minimize computational time by preserving compactness of intermolecular distance between particles.

International Journal of Pure and Applied Mathematics

Clustering with tag for web data by using parallel PSO

In present scenario, internet is very important part of our life. On web user searches a queryaccording to his requirement. There are large numbers of web resources are present oninternet as well as its nature is dynamic, so providing better result, relevant to topic is achallenging issue. To solve this problem we propose a two-stage framework of crawler. Firstphase, Smart crawler performs “Reverse searching” that match user query with URL. In thesecond phase “Incremental-site prioritizing” performed and matches the query content within form. Then according to match frequency crawler classifies relevant and irrelevant pagesand rank this page. Result page displays high rank web pages. Our proposed crawlerrelevantly retrieves web interfaces from large sites. We develop searching throughpersonalized searching which is based on profession profile of user for searching data in yourwork field efficiently. We are maintaining log file by considering a time. We are usingLevenshtein distance algorithm to calculate word frequency in incremental-site prioritizing.User will get pre-query result based on past search results while entering cursor in searchbox. Our objective is to design a Focused Crawler to efficiently search the site database andprovide better result to the user.

International Journal of Computer Engineering and Applications (IJCEA), ISSN (Online): 2321-3469

Smart Approach to crawl Web Interfaces with Personalized Search and Domain Classification Concept

In the cloud, to keep data confidential and to achieve access control, the data owners can use attribute-based encryption to encrypt data. At the time of encryption, the access policies are not flexible. To achieve the strongest form of access control, so for construction of circuit’s cipher text we are using circuit cipher text-policy attribute-based encryption in our work. We also propose Division and Replication of Data in the Cloud for Optimal Performance and Security (DROPS) which provides solution for performance and security problems. In this methodology, file is separated into fragments and then encrypted and replicated fragments data stored on the nodes in cloud storage. Each node can stores only one fragment of data file that gives surety that even in case of a successful attack attacker will not get meaningful information. Third Party Auditor will check integrity of stored data and replace the tempered data with original one.

CIRCUIT-CIPHERTEXT POLICY ATTRIBUTEBASED ENCRYPTION AND DATA INTEGRITY ON CLOUD STORAGE

International Journal of Innovative Research in Computerand Communication Engineering

Production Improvement using Predictive Planning

Emotions play a very important role in our lives. The behavioral expressions help to analyze the state of the individual with respect to their minds. This paper aims at providing a Machine Learning Approach in detecting the likelihood of an individual to commit suicide. Suicide is a very serious issue which is increasing rapidly in the society due to various reasons of which most are mental ones. There is a lot of brain drain that is happening due to individuals opting for suicide instead of facing life with societal challenges. Hence, it needs to be tackled and any attempt of suicide must be prevented. The behavioral pattern of an individual is analyzed using text and audio typed/spoken by the individual. Then classify the data based on emotions present in the input and thereby conclude how likely will the individual commit suicide. Appropriate predictions will help create a healthy society.

International Journal of Computer Engineering And Applications

A Novel Approach for Suicide Prediction in a Healthy Society

Now a days Wireless sensor networks are used for number of real time applications such as computation cost, memory utilization, and communication and energy resources. As the network consist of number of nodes, these nodes comprises of batteries. One of the main issue in WSN is that these batteries are not easily recharged or replaced. Moreover decreasing these energy reduction reduce the network lifetime, therefore increasing the network lifetime is an important issue in front of researcher. This paper proposes the clustering based routing protocol, in which sensor nodes are divided into number of clusters. Then a cluster head is selected from each cluster called as super cluster head. Data is sent to base station by super cluster head, which is selected among all cluster heads. For selection of Super cluster head (SCH) a fuzzy logic approach is used, which considers the factors such as the remaining battery power of modem mobility, route of base station etc. In the existing system, researcher does not focus on security of network. Hence in the proposed system we are securing data in the network by using ECC algorithm. Proposed system also detects the attack found in the network. Therefore it improves the network lifetime, providing security to the network.