Prajakta Dhamanskar CRCE - Academia.edu (original) (raw)

Uploads

Papers by Prajakta Dhamanskar CRCE

Research paper thumbnail of Performance Evaluation and Statistical Analysis of MANET routing Protocols for RPGM and MG

International Journal of Advanced Computer Science and Applications, 2013

Research paper thumbnail of Diabetes and Liver Detection Using Machine Learning Algorithms

SSRN Electronic Journal

The medical sphere of any nation is always under a lot of stress especially in these tough times ... more The medical sphere of any nation is always under a lot of stress especially in these tough times of the pandemic. We have come up with a one stop website that can test the presence of various diseases like Liver and Diabetes using Machine Learning algorithms like Random Forest for Diabetes detection and Logistic Regression for Liver Disease detection. We wish to minimise the efforts and the human contact required in the entire process of getting oneself tested so that the presence of diseases can be detected at the comfort of your home, without spending money and time, physical effort and by avoiding human touch.

Research paper thumbnail of Performance evaluation of On Demand MANET protocols for different mobility models

MANET (Mobile Ad hoc Network) is collection of independent mobile nodes that communicate with eac... more MANET (Mobile Ad hoc Network) is collection of independent mobile nodes that communicate with each other via radio waves. There is no infrastructure support for this network so each mobile node acts as a router to forward data packets to other mobile nodes. As the nodes are frequently moving the topology of the network changes dynamically. This paper presents the performance of ondemand routing protocols such as AODV, DSR and TORA for mobile nodes following four mobility models such as Random Waypoint (RWP), Random Walk (RW), Manhattan Grid and Reference Point Group mobility model (RPGM). The work describes their performance with respect to three performance metrics such as End-to-End delay, Packet Delivery ratio and Normalized Routing Load in simulation environment by increasing the number of nodes in the network in first scenario and by increasing the speed of mobile nodes and keeping the number of nodes constant in second scenario. The results help in the basic understanding of t...

Research paper thumbnail of Human Computer Interaction using Hand Gestures and Voice

2019 International Conference on Advances in Computing, Communication and Control (ICAC3)

Research paper thumbnail of Performance Evaluation and Comparative Analysis of Reactive MANET Routing Protocols for RPGM and MG

Ad Hoc Network is a collection of mobile nodes forming temporary network. In MANET routing protoc... more Ad Hoc Network is a collection of mobile nodes forming temporary network. In MANET routing protocols are classified as Proactive, Reactive and Hybrid. The work presented here evaluates performance of three Reactive routing protocols such as AODV, DSR and TORA under six performance metrics such as packet delivery ratio, routing overhead, packet loss, normalized routing load, throughput and end to end delay. The nodes follow Reference Point Group Mobility model (RPGM) and Manhattan Grid (MG) model. The simulations are carried out using NS2. From the simulation results comparison of these three protocols is presented in a table and represented using KIVIAT diagrams. Contribution in this work is beneficial in deciding which protocol to choose for better QoS. KeywordsAODV, DSR, TORA, RPGM, MG.

Research paper thumbnail of Implementation and Analysis of Advanced Clustering Algorithms

International Journal for Research in Applied Science and Engineering Technology, May 31, 2018

Machine learning-based (IDS) have become a critical component of safeguarding our economic and na... more Machine learning-based (IDS) have become a critical component of safeguarding our economic and national security because of the massive quantities of data produced each day and the growing interconnection of the world's Internet infrastructures. The existing machine Learning Model technique may have difficulty comprehending the ever-increasingly complex distribution of data invasion patterns. With a small number of data points, a single deep learning algorithm may be ineffective at capturing different patterns for intrusive attacks. We presented CNN-LSTM Novel Intrusion Detection Model for Big Data to improve the efficiency of IDS-based CNN-LSTM even further (NIDM). NIDM uses behavioural traits and content functions to understand the characteristics when compared to earlier single learning model tactics, this strategy can improve the rate of intrusive attack detection.

Research paper thumbnail of The Influence of Emotions on Keystroke Patterns in Android Platform using Auditory Stimuli - An Experimental Study

International Journal of Computer Applications, Jul 17, 2017

Keystroke Dynamics or typing dynamics refers to the method of identifying or confirming the ident... more Keystroke Dynamics or typing dynamics refers to the method of identifying or confirming the identity of a person based on the typing pattern by checking the various timing information obtained when a key is pressed and released. It has been hypothesized that a user's keystroke patterns change according to his/her emotions. However, there were only limited investigations about the phenomenon itself in previous studies. The work in this paper is based on the use of auditory stimuli to check the influence of keystroke patterns and its variations according to the emotions of an individual. The advantages of using this method are that the data collected through this approach is non-intrusive and easy to obtain. The proposed system is of a controlled experiment to collect keystroke data from multiple subjects in a variety of emotional states induced by International Affective Digitized Sounds (IADS) using an Android Application. To examine the data collected, Two-way Valence (3) x Arousal (3) ANOVAs is applied. The work in this paper aims to prove that keystroke duration and latency are influenced by valence and arousal.

Research paper thumbnail of Pneumonia and Diabetic Retinopathy Detection Using Deep Learning Algorithm

Advances in Intelligent Systems and Computing

Research paper thumbnail of Program Similarity Detection Tool

International Journal of Engineering Research and

Plagiarism is copying another's work. Copying source code frequently happens in programming assig... more Plagiarism is copying another's work. Copying source code frequently happens in programming assignments in colleges. Direct copying does constitute academic dishonesty. So the student should be motivated to gain more understanding by typing independently than by copying code directly. The work in this paper presents a tool which would be used for detecting plagiarism in the programs performed by students. Also this would be used to detect whether the source code is copied from internet. Input to the tool would be the programs that need to be checked for plagiarism. The tool would give output as percentage of plagiarism detected between each pairs.

Research paper thumbnail of Performance Evaluation and Statistical Analysis of MANET routing Protocols for RPGM and MG

International Journal of Advanced Computer Science and Applications, 2013

Research paper thumbnail of Diabetes and Liver Detection Using Machine Learning Algorithms

SSRN Electronic Journal

The medical sphere of any nation is always under a lot of stress especially in these tough times ... more The medical sphere of any nation is always under a lot of stress especially in these tough times of the pandemic. We have come up with a one stop website that can test the presence of various diseases like Liver and Diabetes using Machine Learning algorithms like Random Forest for Diabetes detection and Logistic Regression for Liver Disease detection. We wish to minimise the efforts and the human contact required in the entire process of getting oneself tested so that the presence of diseases can be detected at the comfort of your home, without spending money and time, physical effort and by avoiding human touch.

Research paper thumbnail of Performance evaluation of On Demand MANET protocols for different mobility models

MANET (Mobile Ad hoc Network) is collection of independent mobile nodes that communicate with eac... more MANET (Mobile Ad hoc Network) is collection of independent mobile nodes that communicate with each other via radio waves. There is no infrastructure support for this network so each mobile node acts as a router to forward data packets to other mobile nodes. As the nodes are frequently moving the topology of the network changes dynamically. This paper presents the performance of ondemand routing protocols such as AODV, DSR and TORA for mobile nodes following four mobility models such as Random Waypoint (RWP), Random Walk (RW), Manhattan Grid and Reference Point Group mobility model (RPGM). The work describes their performance with respect to three performance metrics such as End-to-End delay, Packet Delivery ratio and Normalized Routing Load in simulation environment by increasing the number of nodes in the network in first scenario and by increasing the speed of mobile nodes and keeping the number of nodes constant in second scenario. The results help in the basic understanding of t...

Research paper thumbnail of Human Computer Interaction using Hand Gestures and Voice

2019 International Conference on Advances in Computing, Communication and Control (ICAC3)

Research paper thumbnail of Performance Evaluation and Comparative Analysis of Reactive MANET Routing Protocols for RPGM and MG

Ad Hoc Network is a collection of mobile nodes forming temporary network. In MANET routing protoc... more Ad Hoc Network is a collection of mobile nodes forming temporary network. In MANET routing protocols are classified as Proactive, Reactive and Hybrid. The work presented here evaluates performance of three Reactive routing protocols such as AODV, DSR and TORA under six performance metrics such as packet delivery ratio, routing overhead, packet loss, normalized routing load, throughput and end to end delay. The nodes follow Reference Point Group Mobility model (RPGM) and Manhattan Grid (MG) model. The simulations are carried out using NS2. From the simulation results comparison of these three protocols is presented in a table and represented using KIVIAT diagrams. Contribution in this work is beneficial in deciding which protocol to choose for better QoS. KeywordsAODV, DSR, TORA, RPGM, MG.

Research paper thumbnail of Implementation and Analysis of Advanced Clustering Algorithms

International Journal for Research in Applied Science and Engineering Technology, May 31, 2018

Machine learning-based (IDS) have become a critical component of safeguarding our economic and na... more Machine learning-based (IDS) have become a critical component of safeguarding our economic and national security because of the massive quantities of data produced each day and the growing interconnection of the world's Internet infrastructures. The existing machine Learning Model technique may have difficulty comprehending the ever-increasingly complex distribution of data invasion patterns. With a small number of data points, a single deep learning algorithm may be ineffective at capturing different patterns for intrusive attacks. We presented CNN-LSTM Novel Intrusion Detection Model for Big Data to improve the efficiency of IDS-based CNN-LSTM even further (NIDM). NIDM uses behavioural traits and content functions to understand the characteristics when compared to earlier single learning model tactics, this strategy can improve the rate of intrusive attack detection.

Research paper thumbnail of The Influence of Emotions on Keystroke Patterns in Android Platform using Auditory Stimuli - An Experimental Study

International Journal of Computer Applications, Jul 17, 2017

Keystroke Dynamics or typing dynamics refers to the method of identifying or confirming the ident... more Keystroke Dynamics or typing dynamics refers to the method of identifying or confirming the identity of a person based on the typing pattern by checking the various timing information obtained when a key is pressed and released. It has been hypothesized that a user's keystroke patterns change according to his/her emotions. However, there were only limited investigations about the phenomenon itself in previous studies. The work in this paper is based on the use of auditory stimuli to check the influence of keystroke patterns and its variations according to the emotions of an individual. The advantages of using this method are that the data collected through this approach is non-intrusive and easy to obtain. The proposed system is of a controlled experiment to collect keystroke data from multiple subjects in a variety of emotional states induced by International Affective Digitized Sounds (IADS) using an Android Application. To examine the data collected, Two-way Valence (3) x Arousal (3) ANOVAs is applied. The work in this paper aims to prove that keystroke duration and latency are influenced by valence and arousal.

Research paper thumbnail of Pneumonia and Diabetic Retinopathy Detection Using Deep Learning Algorithm

Advances in Intelligent Systems and Computing

Research paper thumbnail of Program Similarity Detection Tool

International Journal of Engineering Research and

Plagiarism is copying another's work. Copying source code frequently happens in programming assig... more Plagiarism is copying another's work. Copying source code frequently happens in programming assignments in colleges. Direct copying does constitute academic dishonesty. So the student should be motivated to gain more understanding by typing independently than by copying code directly. The work in this paper presents a tool which would be used for detecting plagiarism in the programs performed by students. Also this would be used to detect whether the source code is copied from internet. Input to the tool would be the programs that need to be checked for plagiarism. The tool would give output as percentage of plagiarism detected between each pairs.