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

The immense pressure and tension has created in the worldwide healthcare systems by disease. Various existing system has defined drug prediction system based on current patient evaluation. In this research we proposed a drug prediction for COVID-19 patient based on protein to protein reactions and availability. In order to evaluate the protein-protein interactions (PPIs) between some of the virus and individual receptors that are also confirmed utilizing biomedical simulations, the framework also defines machine learning models. The classification techniques are consistent with the predictions of separate physical material sequence-based characteristics such as classification of amino acids, distribution of pseudo amino acids and conjoint triads. Finally we will evaluate the system with numerous machine learning algorithm and show the effectiveness of propose systems.

World University root node

Engineering and Technology

COMPUTING COMMUNICATION AND GREEN ENGINEERING-2021

Aspect-Level Drug Reviews Sentiment Analysis and COVID-19 Drug prediction using PPI &amp; Deep Learning

Over a past decade it has been observed that a good research is done in healthcare using Machine Learning(ML) and Deep Learning(DL). To carry on the research or implementation using ML or DL, the main concern is database fields or feature selection for the implementation to be done based on the disease or diagnosis method. This paper mainly focus on the two methodologies for feature selection, the first method is a survey based method with Modified Weighted Sum Method (MWSM) implemented on the data collected and second is the feature selection method using machine learning. The said methods are applied to the data collected from diabetic patients and doctors for finding the features useful for diagnosing Hypoglycemia state (lowering of blood glucose level(BGL) in diabetic patients. Comparative analysis is shown for these method and thus concluding for the features selected. Features considered for this work were superficial body features for hypoglycemia detection. The features which we selected from modified WSM were used for feature selection algorithm implementation using machine learning. Univariate Statistical Tests(UST), Recursive Feature Elimination(RFE), Principle Component Analysis(PCA) and Feature Importance(FI) algorithm were implemented on data thus obtained resulting in omitting or rethinking for features.

2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)

Feature selection for healthcare study: Modified WSM and Machine Learning approach

In recent years, Crowd Anomaly detection has become a field of critical importance, especially so after the recent surge in technological development in the modern era. An increasing number of situations or places require surveillance which is also required to detect anomalies so as to prevent unforeseen accidents. Crowd Anomaly detection usually works by analyzing the surveillance scene in real time using various concepts and techniques such as AI, ML, optical flow analysis, streak flow analysis etc. to identify anomalies in a crowd of people. If an anomaly is found, the relevant authorities are immediately alerted. In this survey paper, few of these methodologies are analyzed by comparing their merits and demerits. © 2021 IEEE.

Proceedings of the 3rd International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2021

A survey and analysis of crowd anomaly detection techniques

This paper introduces an algorithm, termed self-adaptive genetic grey wolf optimizer (self-adaptive genetic GWO), for privacy preservation using a C-mixture factor. The C-mixture factor improves the privacy of data, in which the data does not satisfy the privacy constraints, such as l-diversity, m-privacy and k-anonymity. Experimentation is carried out using the adult dataset and the effectiveness of the proposed self-adaptive genetic GWO is checked depending on the information loss and the average equivalence class metric values and is evaluated to be the best when compared to other existing techniques with low information loss value as 0.1724 and average equivalence class value as 0.71, respectively.

Advances in Intelligent Systems and Computing

An approach for collaborative data publishing using self-adaptive genetic grey wolf optimizer

The security of privacy is currently a field of critical importance in data mining. Organizations and corporations in this dynamic environment are constantly trying to somehow get the database of their competitors. A detailed review of such databases can be done to retrieve a variety of confidential and sensitive information, links, connections, inferences, and findings. It can implicitly or explicitly cause a major loss to the database owner. The owners of the database sell their data to third parties for money. If a database is not held until it is revealed to a third party, then the data owner can suffer disasters. We consider the issue of collective publication of data to anonymize horizontally separated data on multiple data providers. The proposed work discusses and contributes to this new challenge of data publishing. First, we introduce the notion of group-based classification, which guarantees that the anonymized data satisfies a given privacy constraint against any group of data providers. We present a collaborative data publishing model with privacy preservation for efficiently checking in a group of records. Privacy preservation can be used to identify abnormal behavior in data sharing. Many privacy-preserving data publishing techniques were developed but failed to consider the data set because of its complexity and domain specific nature. Various organizations release information about persons in public for resource sharing. But maintaining the confidentiality of individual information is a difficult task with various data releases from multiple organizations where coordinating before data publication. The proposed model is compared with traditional models and the results depicts that proposed model exhibits better performance. © 2022 Scrivener Publishing LLC.

Machine Learning Paradigm for Internet of Things Applications

A collaborative data publishing model with privacy preservation using group-based classification and anonymity

Resting-state fMRI (rsfMRI) was firstly characterized by Biswal et al [1] in the year 1995 and since then it is used for studying patients with various neurosurgical, neurologic, and other brain-related disorders. Various statistical methods are used to analyze the resting-state functional magnetic resonance imaging connectivity. This paper attempts to explore more on the learning of resting-state functional magnetic resonance imaging connectivity. This study will help to understand the usage of rsfMRI to evaluate functional connectivity in the human brain and its usage for surgical decision-making for drug-resistant epilepsy. This paper explains the significance of such connectivity analysis, the methods available for it, and the shortcomings associated with the data.

School of Electronics & Communication Engineering

2021 2nd International Conference for Emerging Technology, INCET 2021

Resting-State Functional Connectivity Analysis for diagnosis of Epilepsy patients

In this paper, artificial neural network model developed for the prediction of PM2.5 particulate matter is discussed. Along with artificial neural network, multiple linear regression model is developed for the prediction. Both the techniques are compared for the prediction of PM2.5. The data for the training and testing is collected from OpenAq platform. The result shows that observed and predicted values are in close agreement. Artificial neural network is proved to be better than multiple regression model for the proposed application. Proposed method can also be used for data imputation technique for pollutant dataset. © 2021 IEEE

School of Electrical Engineering

2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)

Artificial Neural Network for the Prediction of Particulate Matter (PM 2.5)

International Research Journal of Engineering and Technology

Survey paper on Traffic Management System using IOT for Emergency Vehicles

Recent statistics show that malware attacks have been increased by over 97% in the past two years. Among these, a large portion is due to Ransomware, a subset of malware. Ransomware codes are easily available as Ransomware as-a-service (RaaS). Because of it, there is a significant threat to the world, as this is a malware which generates high revenues and is creating a viable criminal business model. Because of this the systems of private companies, individuals, or public service providers are at stake and can suffer a severe disruption and financial loss. There are two methods for the detection and analysis to be done for the detection of ransomware. One is the Static detection approach and the other is the Dynamic detection approach. We have done the detection using the Dynamic approach. This paper focuses on detection of ransomware and benign applications using machine learning algorithms for dynamic detection of ransomware. Our experimentation results show that high accuracy is obtained using the KNN algorithm.

International Advanced Computing Conference

Detection of Ransomware on Windows System Using Machine Learning Technique: Experimental Results

Nowadays, the authenticity of the RFID tags cannot be assured in the supply chain since these can be easily duplicated in the public space. We propose a novel Product Ownership Management System (POMS) of products for anti-counterfeits that can be used in the post supply chain by using the QR code. With the projected POMS, a consumer can reject the buying of counterfeits by scanning a QR code, if the seller does not have their proprietorship. This paper gives an application of the system that will help to overcome the problems related with the presently functioning supply chain management system and runs the mechanism to show the ownership of the products.