EESHAN MUNDHE | New York University (original) (raw)

Software Engineer, Cryptography Enthusiast.

less

Uploads

Papers by EESHAN MUNDHE

Research paper thumbnail of Live Cricket Score Prediction Web Application using Machine Learning

2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)

Research paper thumbnail of Web Application for Machine Learning based Music Genre Classification

2021 International Conference on Advances in Computing, Communication, and Control (ICAC3), 2021

With the tremendous increase in the number of songs produced, categorizing them has become a diff... more With the tremendous increase in the number of songs produced, categorizing them has become a difficult process. It's a good idea to categorize them according to their genre. To resolve this quandary, this paper introduces a web application that uses Machine Learning techniques to automatically classify a music file into its genre. Any .wav audio file can be uploaded to the application, which will accurately assess its genre and classify it accordingly. Django is used to create the web application, and three algorithms are tested for accuracy and performance. Of these three methods, the Support Vector Machine approach has the highest accuracy – Deep Neural Network (Keras library), Support Vector Machine, K Nearest Neighbors – and is thus chosen for the web application.

Research paper thumbnail of A Contactless IoT based Intelligent Parking Solution for Smart Cities

International Journal of Computer Applications, 2020

Research paper thumbnail of A Novel Encryption Algorithm Using Random Number Generation for Ciphertext Expansion

ICT with Intelligent Applications, 2021

Information security has a major role to play in this ever-increasing digital world. One of the m... more Information security has a major role to play in this ever-increasing digital world. One of the many important aspects in information security is cryptography, which is used to encrypt and decrypt information thereby protecting it from eavesdroppers. The modern cryptographic techniques make it difficult to decipher a message for even the most powerful computers. With advances in supercomputing, it is getting easier to break down these complex codes within minutes. This paper introduces a new algorithm for symmetric key encryption which will increase the length of the ciphertext as per the requirement and make it harder to decode back the original plaintext without knowing the secret key. The proposed algorithm in this paper generates a large random private key by using two relatively small random numbers: A natural number and a binary number, which is then used to encrypt the plaintext message.

Research paper thumbnail of A Solution for Finding Composite Numbers in an Unending Sequence Starting with Prime Numbers

viXra, 2020

A non-terminating sequence like 31, 331, 3331, 33331, … starts with first seven terms as prime nu... more A non-terminating sequence like 31, 331, 3331, 33331, … starts with first seven terms as prime numbers, while the 8th term, which is 333333331, can be expressed as 17 x 19607843. Using Fermat’s Little Theorem, it can be easily proved that there are many more terms in this sequence that are not prime numbers. This paper puts forward a solution to find factors of composite numbers in all such sequences without using Fermat’s Little theorem or divisibility tests. The solution uses a prime number only once to scan all the terms of the unending sequence together, to check if any term is divisible by that prime number instead of checking every term separately, hence reduces the computational complexity. The solution finds the smallest number of the sequence which is divisible by a particular prime number and also proves that it cannot be assumed that all the terms of such sequences will be prime numbers.

Research paper thumbnail of Live Cricket Score Prediction Web Application using Machine Learning

2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)

Research paper thumbnail of Web Application for Machine Learning based Music Genre Classification

2021 International Conference on Advances in Computing, Communication, and Control (ICAC3), 2021

With the tremendous increase in the number of songs produced, categorizing them has become a diff... more With the tremendous increase in the number of songs produced, categorizing them has become a difficult process. It's a good idea to categorize them according to their genre. To resolve this quandary, this paper introduces a web application that uses Machine Learning techniques to automatically classify a music file into its genre. Any .wav audio file can be uploaded to the application, which will accurately assess its genre and classify it accordingly. Django is used to create the web application, and three algorithms are tested for accuracy and performance. Of these three methods, the Support Vector Machine approach has the highest accuracy – Deep Neural Network (Keras library), Support Vector Machine, K Nearest Neighbors – and is thus chosen for the web application.

Research paper thumbnail of A Contactless IoT based Intelligent Parking Solution for Smart Cities

International Journal of Computer Applications, 2020

Research paper thumbnail of A Novel Encryption Algorithm Using Random Number Generation for Ciphertext Expansion

ICT with Intelligent Applications, 2021

Information security has a major role to play in this ever-increasing digital world. One of the m... more Information security has a major role to play in this ever-increasing digital world. One of the many important aspects in information security is cryptography, which is used to encrypt and decrypt information thereby protecting it from eavesdroppers. The modern cryptographic techniques make it difficult to decipher a message for even the most powerful computers. With advances in supercomputing, it is getting easier to break down these complex codes within minutes. This paper introduces a new algorithm for symmetric key encryption which will increase the length of the ciphertext as per the requirement and make it harder to decode back the original plaintext without knowing the secret key. The proposed algorithm in this paper generates a large random private key by using two relatively small random numbers: A natural number and a binary number, which is then used to encrypt the plaintext message.

Research paper thumbnail of A Solution for Finding Composite Numbers in an Unending Sequence Starting with Prime Numbers

viXra, 2020

A non-terminating sequence like 31, 331, 3331, 33331, … starts with first seven terms as prime nu... more A non-terminating sequence like 31, 331, 3331, 33331, … starts with first seven terms as prime numbers, while the 8th term, which is 333333331, can be expressed as 17 x 19607843. Using Fermat’s Little Theorem, it can be easily proved that there are many more terms in this sequence that are not prime numbers. This paper puts forward a solution to find factors of composite numbers in all such sequences without using Fermat’s Little theorem or divisibility tests. The solution uses a prime number only once to scan all the terms of the unending sequence together, to check if any term is divisible by that prime number instead of checking every term separately, hence reduces the computational complexity. The solution finds the smallest number of the sequence which is divisible by a particular prime number and also proves that it cannot be assumed that all the terms of such sequences will be prime numbers.

Log In