- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Cloud Data Security Solutions
- Network Security and Intrusion Detection
- Big Data and Business Intelligence
- Smart Parking Systems Research
- Video Surveillance and Tracking Methods
- Evolutionary Algorithms and Applications
- Anomaly Detection Techniques and Applications
- Handwritten Text Recognition Techniques
- Artificial Intelligence in Healthcare
- Metaheuristic Optimization Algorithms Research
- Energy Efficient Wireless Sensor Networks
- Access Control and Trust
- COVID-19 epidemiological studies
- Autonomous Vehicle Technology and Safety
- Noise Effects and Management
- Manufacturing Process and Optimization
- Cryptography and Data Security
- Advanced Data Storage Technologies
- Online and Blended Learning
- Embedded Systems Design Techniques
- Advanced Multi-Objective Optimization Algorithms
- Rough Sets and Fuzzy Logic
- Vehicle License Plate Recognition
International Institute of Information Technology
2016-2025
Smt. Kashibai Navale Medical College and General hospital
2023
Savitribai Phule Pune University
2016
The emergence of the latest technologies gives rise to usage noninvasive techniques for assisting health-care systems. Amongst four major cardiovascular diseases, stroke is one most dangerous and life-threatening disease, but life a patient can be saved if detected during early stage. literature reveals that patients always experience ministrokes which are also known as transient ischemic attacks (TIA) before experiencing actual attack stroke. Most work based on MRI CT scan images...
Many researchers are getting attracted in the field of object tracking video surveillance, which is an important application and emerging research area image processing. Video process locating a moving or multiple objects over time using camera. Due to key features it has variety uses like human-computer interactions, security communication, traffic control, public areas such as airports, underground stations, mass events, etc. Tracking target cluttered premise still one challenging problems...
An affective state of a learner in E-learning has gained enormous interest. The prediction the emotional can enhance outcome learning by including designated mediation. Many techniques are developed for anticipating states using video, audio, and bio-sensors. Still, examining audio will not confirm secretiveness is exposed to security issues. Here creator devises fusion technique, be specific Squirrel Search Rider optimization-grounded Deep LSTM affect prediction. trained exercise new...
This foreword is related to the sixteen papers published in this issue, which were presented at IC2ST-2021 - International Conference on Convergence of Smart Technologies. The Aspire Research Foundation organized conference Pune, India, January 9-10, 2021. These have not and will be anywhere else.
The Internet of Things (IoT) facilitates connections between people and things at any time, anywhere, with anything, anybody through the use network, service, or application. IoT is a system actual physical objects commonly referred to as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">things</i> . contain sensors, software, other technologies that connect systems devices over allow data exchange. Identity management (IDM) involves managing...
Wireless Sensor Network solve the problem of various applications like military, nuclear power plant. This type application required continuous monitoring, hence security is for such network. WSN affected by many attacks, wormhole and selective forwarding attacks are them. In attack, attacker may refuse or forward certain messages simply drop one more receive packets from location them into another different location. this paper, we discuss countermeasures attack.
With the increasing prevalence of Internet Things (IoT), there is a growing need for effective access control methods to secure IoT systems and data. Traditional models often prove inadequate when dealing with specific challenges presented by IoT, characterized variety heterogeneous devices, ever-changing network structures, diverse contextual elements. Managing devices effectively complex task in maintaining security.This study introduces context-driven approach Device Classification...
Classification is important task of data mining used to extract knowledge from huge volume data. By nature, classification multi-objective problem, as it required optimization multiple objectives simultaneously like accuracy, sensitivity, squared error, precision etc. Traditionally, evolutionary algorithms were solve problem by considering single-objective but this approach gives single solution problem. Therefore, are In paper, we have Pareto optimize neural network Non-dominated sorting...
Cloud computing has given a large scope of improvement in processing, storage and retrieval data that is generated huge amount from devices users. Heterogenous users generates the multidisciplinary needs to take care for easy efficient fast by maintaining quality service level agreements. By just storing cloud will not full fill user requirements, management techniques be applied so adaptiveness proactiveness characteristics are upheld. To manage effectiveness entire eco system middleware...
Online platforms' integrity and security are seriously threatened by the growth of automated bot attacks, necessitating development effective methods for telling harmful bots apart from legitimate users. In order to successfully combat this project investigates creation application CAPTCHA (Completely Automated Public Turing test tell Computers Humans Apart) utilising deep learning techniques. study, we employ create apply complex CAPTCHA-problems that help us distinguish between real users...
In this paper novel technique for CPU scheduling in real time operating systems by using genetic algorithm (GA) is proposed.Proposed adaptive a combination of existing dynamic priority driven i.e.Earliest Deadline First (EDF) and new based algorithm.First we have developed GA tested it during both under loaded overloaded condition.Initially, underloaded condition EDF used system will change to .Thus our Adaptive uses the strong features algorithms overcome their drawbacks.We simulated,...
Feature selection is an essential method in which we identify a subset of most useful ones from the original set features. On comparing results with and identified subset, observe that are compatible. The feature algorithm evaluated based on components efficiency effectiveness, where time required optimality considered. Based this, modifying fast clustering algorithm, to check impact entropy correlation coefficient it this paper. In between features calculated using instead symmetric...
Due to rise in number of vehicles the traffic management has become a major problem. Manual system is not efficient. This paper presents adaptive using Internet Things (IoT) and Image processing. The proposed capability analyze real time data image Using cameras, different lanes are monitored constantly. obtained from examined. Detection counting each lane done by count sent central processing unit. According algorithm calculates waiting for lane, then signal lights will be decided. reduces...
Today, data mining is used in every area. In mining, huge quantity of can be store. Now education very powerful field. this field, suggests many techniques, tools and research plan for extracting large generated by learning activities educational system. The main aim paper, we create a system which giving rank to teacher as per subject or domain. It will help assign teaching load the teacher. This paper introduces i.e. decide on base rank. assigned based various parameters such how time...
Feature selection is an important data processing step where irrelevant and redundant attributes are removed for shorter learning time, better accuracy comprehensibility. It involves identifying optimal subset of the most useful features from original set features. The efficiency feature algorithm concerns time required to find a effectiveness related quality feature. This paper focuses on study different models, techniques evaluation measures used their merits limitations.Then we talk about...