Nitasha Soni - Academia.edu (original) (raw)

Papers by Nitasha Soni

Comparative Study on Image Detection using Variants of CNN and YOLO

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON)

Procedia Computer Science, 2018

This paper avails an in-depth analysis of the field of crowdsourcing and its impacts when used in... more This paper avails an in-depth analysis of the field of crowdsourcing and its impacts when used in the world of machine learning. It comprises of various contributions that crowdsourcing can make to improvise the techniques that employ machine learning like-producing data, debugging and checking of models, hybrid smart machines to reduce the human intervention required to facilitate high quality performance by artificial intelligence and developmental experimentation to improve human-computer interaction. A discussion regarding the nature of crowd-workers follows next which focuses on various factors like their reaction to different forms of motivation, their behaviour towards each other and deceit among them. The takeaways of this paper inclu de a few tips and routines to be followed to achieve success through crowdsourcing.

International Journal of Recent Technology and Engineering (IJRTE), 2019

In an IOT based smart city, the most astonishing and, the most reflective component would be a mu... more In an IOT based smart city, the most astonishing and, the most reflective component would be a much more efficient water supply. This kind of water supply treatment plant that would be established will be a much more advanced version of the already existing kinds. This water supply would help many people across the globe to get access to clean, drinking water and sanitation. Also, in such a city there would be provided an innovative solution to the huge traffic congestion being faced these days that leads to delays in reaching to work, rash driving and results in huge chaos and accidents. Thus, it would be great to kept in mind to provide a mid-way out to deal with these traffic issues in a more reliable and efficient way. We would provide a more reliable public transportation. Public transportation these days are the most relied means of conveyance for people living in all parts of the world. Thus, we would build up a more reliable public transport structure that would be effortles...

IOSR Journal of Engineering, 2012

It has been observed that 80% of development time and a lots of memory space is spend over handli... more It has been observed that 80% of development time and a lots of memory space is spend over handling the abnormal conditions and exceptions in any programming Environment. It also affects the cost factor of program development also. The support for precise exceptions in optimizing Java program states, combined with frequent checks for runtime exceptions, leads to severe limitations on the compiler's ability to perform program optimizations that involve reordering of instructions. This paper presents a basic framework that allows the application programmers to recognise the constraints of application programs in instruction scheduling. We first present a formulated way for analysing the problem caused in coded program and its related Exception-handling constructs, and a methodology, to identify the subset of program state that needs to be preserved if an exception is thrown. This allows many spurious dependence constraints between potentially excepting instructions (PEIs) and writes into variables to be eliminated. Our planned methodology is particularly suitable for dynamically dispatched methods in object-oriented languages, where static analysis may be quite conservative. We then present the first software-only solution that allows dependence constraints among PEIs to be completely ignored while applying program optimizations, with no need to execute any additional instructions if an exception is not thrown. With a preliminary implementation, by this we observe that for many benchmark programs, a large percentage of methods can be optimized (while honouring the precise exception requirement) without any constraints imposed by frequent runtime exceptions. Finally, we show that relaxing these reordering constraints can lead to substantial improvements (up to a factor of 7 out of 10 for small codes) in the performance of programs

International Journal of Engineering and Advanced Technology, 2020

This research paper looks into the world of how-to of cloud services and the ways through which i... more This research paper looks into the world of how-to of cloud services and the ways through which it is threatened by various elements that regularly disrupt the functioning of these services. We will see how different models are being implemented across different fields. These various models are adopted by different users and organizations according to their needs. As there is almost no service with its specific problems, we delve into the discussion about various threats that loom over this expanded service step by step. These problems may be related to networking or authentication problems or security breach. Then we will look into how these problems are overcome by cloud service experts.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Performance of genetic algorithms mainly depends on type of genetic operators – Selection, Crossover, Mutation and Replacement used in it. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different crossover operators that help in solving the problem.

Machine Learning Based Movie Recommendation System

2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

Database Security: Threats and Security Techniques

Data security is an emerging concern proved by an increase in the number of reported cases of los... more Data security is an emerging concern proved by an increase in the number of reported cases of loss of or exposure to sensitive data by some unauthorized sources. Security is a composed part in which it protects and secures the sensitive data or database management software from some unauthorized user or from malicious attacks. In this paper we will be presenting some of the common security techniques for the data that can be implemented in fortifying and strengthening the databases.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different mutation operators that help in solving the problem. Keywords— Genetic Algorithm; Mutation; crossover; Selection; travelling salesman problem.

OPTIMIZING PROGRAM-STATES USING EXCEPTION-HANDLING CONSTRUCTS IN JAVA ( During Analysis and Testing of Programs )

The support for precise exceptions in optimizing Java program states, combined with frequent chec... more The support for precise exceptions in optimizing Java program states, combined with frequent checks for runtime exceptions, leads to severe limitations on the compiler’s ability to perform program optimizations that involve reordering of instructions. This paper presents a basic framework that allows the application programmers to recognise the constraints of application programs in instruction scheduling. We first present a formulated way for analysing the problem caused in coded program and its related Exception-handling constructs, and a methodology, to identify the subset of program state that needs to be preserved if an exception is thrown. This allows many spurious dependence constraints between potentially excepting instructions (PEIs) and writes into variables to be eliminated. Our planned methodology is particularly suitable for dynamically dispatched methods in object-oriented languages, where static analysis may be quite conservative. We then present the first software-on...

Object Detection in Image Using Components of Convolutional Neural Network and YOLO

Sentiment Analysis on Customer Feedback Data: Amazon Product Reviews

2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon)

Sentiment analysis is one of the fastest spreading research areas in computer science, making it ... more Sentiment analysis is one of the fastest spreading research areas in computer science, making it challenging to keep track of all the activities in the area. We present a customer feedback reviews on product, where we utilize opinion mining, text mining and sentiments, which has affected the surrounded world by changing their opinion on a specific product. Data used in this study are online product reviews collected from http://Amazon.com. We performed a comparative sentiment analysis of retrieved reviews. This research paper provides you with sentimental analysis of various smart phone opinions on smart phones dividing them Positive, Negative and Neutral Behaviour.

This paper surveys recent literature in the area of stock market forecasting using advanced engin... more This paper surveys recent literature in the area of stock market forecasting using advanced engineering based methods like Neural Network, fractal theory, Data Mining, Hidden Markov Model and Neuro-Fuzzy system. Neural Networks and Neuro-Fuzzy systems are emerging as an effective tool to be used in the forecasting of stock market especially in machine learning techniques. Due to chaotic behavior of the market, traditional techniques are insufficient to cover all the possible relation of the stock price fluctuations. Neural Network and Markov Model is being used exclusively in the forecasting of finance markets but in third world countries. In this paper, we will discuss the relevance of existing methods based on neural network and discussed gaps between these methods. We also propose a forecasting method to provide better an accuracy rather traditional method.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Performance of genetic algorithms mainly depends on type of genetic operators – Selection, Crossover, Mutation and Replacement used in it. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different crossover operators that help in solving the problem.

Comparative Study on Image Detection using Variants of CNN and YOLO

2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON)

Procedia Computer Science, 2018

This paper avails an in-depth analysis of the field of crowdsourcing and its impacts when used in... more This paper avails an in-depth analysis of the field of crowdsourcing and its impacts when used in the world of machine learning. It comprises of various contributions that crowdsourcing can make to improvise the techniques that employ machine learning like-producing data, debugging and checking of models, hybrid smart machines to reduce the human intervention required to facilitate high quality performance by artificial intelligence and developmental experimentation to improve human-computer interaction. A discussion regarding the nature of crowd-workers follows next which focuses on various factors like their reaction to different forms of motivation, their behaviour towards each other and deceit among them. The takeaways of this paper inclu de a few tips and routines to be followed to achieve success through crowdsourcing.

International Journal of Recent Technology and Engineering (IJRTE), 2019

In an IOT based smart city, the most astonishing and, the most reflective component would be a mu... more In an IOT based smart city, the most astonishing and, the most reflective component would be a much more efficient water supply. This kind of water supply treatment plant that would be established will be a much more advanced version of the already existing kinds. This water supply would help many people across the globe to get access to clean, drinking water and sanitation. Also, in such a city there would be provided an innovative solution to the huge traffic congestion being faced these days that leads to delays in reaching to work, rash driving and results in huge chaos and accidents. Thus, it would be great to kept in mind to provide a mid-way out to deal with these traffic issues in a more reliable and efficient way. We would provide a more reliable public transportation. Public transportation these days are the most relied means of conveyance for people living in all parts of the world. Thus, we would build up a more reliable public transport structure that would be effortles...

IOSR Journal of Engineering, 2012

It has been observed that 80% of development time and a lots of memory space is spend over handli... more It has been observed that 80% of development time and a lots of memory space is spend over handling the abnormal conditions and exceptions in any programming Environment. It also affects the cost factor of program development also. The support for precise exceptions in optimizing Java program states, combined with frequent checks for runtime exceptions, leads to severe limitations on the compiler's ability to perform program optimizations that involve reordering of instructions. This paper presents a basic framework that allows the application programmers to recognise the constraints of application programs in instruction scheduling. We first present a formulated way for analysing the problem caused in coded program and its related Exception-handling constructs, and a methodology, to identify the subset of program state that needs to be preserved if an exception is thrown. This allows many spurious dependence constraints between potentially excepting instructions (PEIs) and writes into variables to be eliminated. Our planned methodology is particularly suitable for dynamically dispatched methods in object-oriented languages, where static analysis may be quite conservative. We then present the first software-only solution that allows dependence constraints among PEIs to be completely ignored while applying program optimizations, with no need to execute any additional instructions if an exception is not thrown. With a preliminary implementation, by this we observe that for many benchmark programs, a large percentage of methods can be optimized (while honouring the precise exception requirement) without any constraints imposed by frequent runtime exceptions. Finally, we show that relaxing these reordering constraints can lead to substantial improvements (up to a factor of 7 out of 10 for small codes) in the performance of programs

International Journal of Engineering and Advanced Technology, 2020

This research paper looks into the world of how-to of cloud services and the ways through which i... more This research paper looks into the world of how-to of cloud services and the ways through which it is threatened by various elements that regularly disrupt the functioning of these services. We will see how different models are being implemented across different fields. These various models are adopted by different users and organizations according to their needs. As there is almost no service with its specific problems, we delve into the discussion about various threats that loom over this expanded service step by step. These problems may be related to networking or authentication problems or security breach. Then we will look into how these problems are overcome by cloud service experts.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Performance of genetic algorithms mainly depends on type of genetic operators – Selection, Crossover, Mutation and Replacement used in it. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different crossover operators that help in solving the problem.

Machine Learning Based Movie Recommendation System

2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)

Database Security: Threats and Security Techniques

Data security is an emerging concern proved by an increase in the number of reported cases of los... more Data security is an emerging concern proved by an increase in the number of reported cases of loss of or exposure to sensitive data by some unauthorized sources. Security is a composed part in which it protects and secures the sensitive data or database management software from some unauthorized user or from malicious attacks. In this paper we will be presenting some of the common security techniques for the data that can be implemented in fortifying and strengthening the databases.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different mutation operators that help in solving the problem. Keywords— Genetic Algorithm; Mutation; crossover; Selection; travelling salesman problem.

OPTIMIZING PROGRAM-STATES USING EXCEPTION-HANDLING CONSTRUCTS IN JAVA ( During Analysis and Testing of Programs )

The support for precise exceptions in optimizing Java program states, combined with frequent chec... more The support for precise exceptions in optimizing Java program states, combined with frequent checks for runtime exceptions, leads to severe limitations on the compiler’s ability to perform program optimizations that involve reordering of instructions. This paper presents a basic framework that allows the application programmers to recognise the constraints of application programs in instruction scheduling. We first present a formulated way for analysing the problem caused in coded program and its related Exception-handling constructs, and a methodology, to identify the subset of program state that needs to be preserved if an exception is thrown. This allows many spurious dependence constraints between potentially excepting instructions (PEIs) and writes into variables to be eliminated. Our planned methodology is particularly suitable for dynamically dispatched methods in object-oriented languages, where static analysis may be quite conservative. We then present the first software-on...

Object Detection in Image Using Components of Convolutional Neural Network and YOLO

Sentiment Analysis on Customer Feedback Data: Amazon Product Reviews

2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon)

Sentiment analysis is one of the fastest spreading research areas in computer science, making it ... more Sentiment analysis is one of the fastest spreading research areas in computer science, making it challenging to keep track of all the activities in the area. We present a customer feedback reviews on product, where we utilize opinion mining, text mining and sentiments, which has affected the surrounded world by changing their opinion on a specific product. Data used in this study are online product reviews collected from http://Amazon.com. We performed a comparative sentiment analysis of retrieved reviews. This research paper provides you with sentimental analysis of various smart phone opinions on smart phones dividing them Positive, Negative and Neutral Behaviour.

This paper surveys recent literature in the area of stock market forecasting using advanced engin... more This paper surveys recent literature in the area of stock market forecasting using advanced engineering based methods like Neural Network, fractal theory, Data Mining, Hidden Markov Model and Neuro-Fuzzy system. Neural Networks and Neuro-Fuzzy systems are emerging as an effective tool to be used in the forecasting of stock market especially in machine learning techniques. Due to chaotic behavior of the market, traditional techniques are insufficient to cover all the possible relation of the stock price fluctuations. Neural Network and Markov Model is being used exclusively in the forecasting of finance markets but in third world countries. In this paper, we will discuss the relevance of existing methods based on neural network and discussed gaps between these methods. We also propose a forecasting method to provide better an accuracy rather traditional method.

Genetic Algorithms are the population based search and optimization technique that mimic the proc... more Genetic Algorithms are the population based search and optimization technique that mimic the process of natural evolution. Performance of genetic algorithms mainly depends on type of genetic operators – Selection, Crossover, Mutation and Replacement used in it. Different crossover and mutation operators exist to solve the problem that involves large population size. Example of such a problem is travelling sales man problem, which is having a large set of solution. In this paper we will discuss different crossover operators that help in solving the problem.