Informatics Publishing Limited

Satyendra Nath Mandal ¹

Affiliations
1 Department of Information Technology, Kalyani Government Engineering College, Kalyani- 741235, Dist. Nadia, West Bengal, IN

Abstract

The output of any physical problem is likely to be dependent on huge number of parameters. But, many of them are not significant and some are highly correlated with other parameters. Same result can be produced by fewer parameters in stead of considering all parameters. In this paper, an algorithm has been proposed to reduce parameters based on principal component analysis and factor analysis. The algorithm has been applied to reduce the environment parameters which are needed for the healthy growth of mustard plant. It has been observed that the growth of mustard plant has not been disturbed if the significant environment parameters have been supplied sufficiently.

Keywords

Physical Problem, Environmental Parameters, Principal Component Analysis, Factor Analysis, Significant Parameters, Plant Growth.

Full Text

   

Subhajit Das ¹, Satyendra Nath Mandal ²

Affiliations
1 Nayagram Bani Bidyapith, Nayagram, IN
2 Kalyani Government Engineering College, Dept.of Information Tech., Kalyani, Nadia, IN

Abstract

In this paper, a symmetric key image encryption algorithm has been proposed based on genetic algorithm. The algorithm has three steps, generation of random sequence, diffused image and image encryption. Key generation is based on a new integer sequence generation and a mixing process. The random integer sequence has been generated from 64 bits key and mixing. The input image has been diffused by genetic algorithm and parents have been selected from image folding. The encrypted image is formed after performing logical operation between diffused image and random sequenence. The effectiveness of the algorithm has been measured by applying number of statistical tests between plain and encrypted image.It has been observed that the proposed algorithm is giving satisfactory result in all cases.

Keywords

Symmetric Key, Genetic Algorithm, Horizontal and Vertical Folding, Remainder Set and Security Level.

Full Text

   

Satyendra Nath Mandal ¹, Abhijit Mondal ¹, Nil Kamal Basak ¹, Souvik Naskar ¹, Subhadip Bhattacharya ¹

Affiliations
1 Department of IT, Kalyani Government Engineering College, IN

Abstract

The RSA cryptosystem, invented by Ron Rivest, Adi Shamir and Ten Adleman was first publicized in the August 1977 issue of Scientific American. The cryptosystem is most commonly used for providing privacy and ensuring authenticity of digital data. These days RSA is deployed in many commercial systems. It is used by web servers and browsers to secure web traffic, it is used to ensure privacy and authenticity of e-mail, it is used to secure remote login sessions, and it is at the heart of electronic credit-card payment systems. In short, RSA is frequently used in applications where security of digital data is a concern. Symmetric key distribution problem is solved by it.

Goal of this work is to derive a new prime generation method with the help of current system time. That is why the method generates a unique prime every time the program is executed.

Full Text

   

Surajit Biswas ¹, Satyendra Nath Mandal ²

Affiliations
1 Kalyani Government Engineering College, Kalyani, Nadia, West Bengal, IN
2 Dept. of I.T., Kalyani Government Engineering College, Kalyani, Nadia, West Bengal, IN

Abstract

Human eye have the ability to detect and recognize a character of some language, which they know, by the power of their brain as they are accustomed to that shape of the character font. But this thing is typically challenging for computers as it has no ability to read and learn automatically. All it needs to work is to provide it an artificial technique by human beings to make its artificial brain to read and understand from a character image, an optical character image. There are lots of algorithms available for the optical character recognition. Although no such technique yet exists, which can guarantee that its steps are 100%? In this paper, a new technique has been proposed to detect optical characters from digital images. Here the basic algorithm for character contour tracing algorithm using Fourier descriptors is used and then the proposed algorithm is used to recognize the optical character so that it can help the basic recognition technique more and more accurate.

Keywords

Digital Image, Character Recognition, Fourier Descriptors, Contour Tracing, Shape Representation, Shape Similarity Measure, Feature Extraction.

Full Text

   

Satyendra Nath Mandal ¹

Affiliations
1 Department of IT, Kalyani Government Engineering College, IN

Abstract

Cryptography is an art of science to secure the confidential data. In the present paper, a brief history of the development of cryptography and its recent trends are outlined.

Full Text

   

Satyendra Nath Mandal ¹, Arghya Ghosh ², Subhojit Roy ², J. Pal Choudhury ¹, S. R. Bhadra Chaudhuri ³

Affiliations
1 Dept. of I.T, Kalyani Govt. Engg College, Kalyani, Nadia(W.B), IN
2 Dept. of CSE, Kalyani Govt. Engg College, Kalyani, Nadia(W.B), IN
3 Dept. of ETC, BESU, Howrah ( W. B), IN

Abstract

The productivity of plant can be measured in terms of pod yields produce by that plant. The production of plant dependent on various parameters of the plant like shoot length, number of leaves, ischolar_main length , ischolar_main numbers etc. Some other factors like soil, crop and distance management are also taken care of to produce maximum amount of yield. It is not desirable to use the no of leaves of the tree to calculate the growth of the plant because when the plant is growing some leaves may be lost and some new leaves may appear. It is also very difficult to measure the number of ischolar_mains and length of growth of ischolar_main in several time instances as it grows underground. So, it is very convenient to measure the plant growth on the basis of shoot length. In this paper, an effort has been made to predict the shoot length of mustard plant by Tabu Search (TS). The average error has been calculated based on the actual shoot and predicted shoot length. A comparitive study has been made among the different methods applied on same data set and one method has been selected based on minimum average error. The shoot length at maturity has been predicted by applying least square method on predicted data set with minimum average error. Finally, pod yield at maturity has been predicted by shoot length at maturity.

Keywords

Tabu Search, Soft Computing, Prediction, Forecasting, Average Error, Pod Yield.

Full Text

   

Satyendra Nath Mandal ¹, Soumi Sadhu ²

Affiliations
1 Dept. of I.T, Kalyani Govt. Engg College, Kalyani, Nadia(W.B), IN
2 Dept. of CSE, Kalyani Govt. Engg College, Kalyani, Nadia(W.B), IN

Abstract

Harmony Search Algorithm originally came from the analogy between the music improvisation and optimization process. The harmony search algorithm is searching the optimal solution using the novel stochastic derivative equation. The equation is based on density information of multiple solution vectors, instead of calculus based gradient information of single solution vector. In other words, if a certain value frequently appears in multiple vectors, then the value has higher chance to be selected rather than the other candidate values. In this paper, an algorithm has been proposed to solve the Sudoku problem based on harmony search. A comparative study has been made with the proposed algorithm with the existing solution of Sudoku problem by harmony search. It has been proved that the proposed algorithm minimized the iterations to solve the Sudoku problem.

Full Text

   

Uttam Kr. Mondal ¹, Satyendra Nath Mandal ², J. Pal Choudhury ², J. K. Mandal ³

Affiliations
1 Dept. of CSE & IT, College of Engg. & Management, Kolaghat , Midnapur (W.B), IN
2 Dept. of IT, Kalyani Govt. Engg. College, Kalyani, Nadia (W.B), IN
3 Dept. of CSE, University of Kalyani, Nadia (W.B), IN

Abstract

There are huge numbers of algorithms available in symmetry key block cipher. All these algorithms have been used either complicated keys to produce cipher text from plain text or a complicated algorithms for it. The level of security of all algorithms is dependent on either number of iterations or length of keys. In this paper, a symmetry key block cipher algorithm has been proposed to encrypt plain text into cipher text or vice versa using a frame set. A comparative study have been made with RSA, DES, IDEA, BAM and other algorithms with Chi-square value, frequency distribution, bit ratio to check the security level of proposed algorithm. Finally, a comparison has been made for time complexity for encryption of plain text and decryption from cipher text with the well-known existing algorithms.

Keywords

Cryptography, Plain Text, Cipher Text, Symmetric Key Algorithm, Chi-Square and Frequency Distributions.

Full Text

   

Satyendra Nath Mandal ¹, Kumarjit Banerjee ², Biswajit Maiti ³, J. Palchaudhury ¹

Affiliations
1 Dept. of I.T, Kalyani Govt. Engg College, Kalyani, Nadia (W.B), IN
2 CSE, Kalyani Govt. Engg College, Kalyani, Nadia (W.B), IN
3 Dept. of Mathmatics, Kalyani Govt. Engg College, Kalyani, Nadia (W.B), IN

Abstract

The RSA cryptosystem, invented by Ron Rivest, Adi Shamir and Len Adleman was first published in the August 1978 issue of ACM. The cryptosystem is most commonly used for providing priva cy and ensuring authenticity of digital data. The security level of this algorithm depends on chooing two large prime numbers. But, to handle large prime in personal computer is huge time consuming. Further, each and every compiler has a maximum limit to integer handling capability. In this paper, an approach has been made to modify trial division technique for implementation of RSA algorithm for large numbers beyond the range of a compiler that has been used to implement it. The time complexity of this modified trial division method has been calculated using personal computer, at the end for large integer.

Keywords

RSA Cryptosystem, Prime Number, Trail Division, Time Complexity.

Full Text

   

Satyendra Nath Mandal ¹, Sanket Dan ¹, Pritam Ghosh ¹, Subhranil Mustafi ¹, Kunal Roy ¹, Kaushik Mukherjee ¹, Dilip Kumar Hajra ², Santanu Banik ³

Affiliations
1 Kalyani Government Engineering College, Kalyani, Nadia, West Bengal 741235, IN
2 Department of Agronomy, UBKV, Pundibari, Cooch Behar, West Bengal 736165, IN
3 ICAR-National Research Centre on Pig, Rani, Guwahati, Assam 781131, IN

Abstract

Diversity in domestic animals in most of the species is depicted in the form of breeds. Phenotypic and genotypic characterizations are the tools for breed identification of livestock species. Variation within breed or similar looking breeds make it difficult to confirm breed identity of individual animal. An experiment was conducted with the aim of identification of breed of an individual goat by the help of its image using Inception model v3; a convolutional neural network. More than 500 digital images of individual goat captured in restricted (to get similar image-background) and unrestricted (natural) environment without imposing stress to animals. Six different purebred goats (Blackbengal, Beetal, Jamunapari, Barbari, Jakhrana and Sirohi) which have been reared and maintained by reputed government research organizations in India were used for training and testing the model. 10% of the captured images were used for testing the trained model. Breed confirmation was made by seeing the value (probability) in output terminals corresponding to six different breeds under study which best described an input image. 56 images out of the 60 images used in the test were successfully interpreted for breed identity by the trained model and thus the model was 93.33% accurate. Output probability of more than or equal to 0.95 was taken as minimum confidence limit for determination of breed. Value less than 0.95 was considered as unsuccessful test. Upon testing with images from breeds for which the model was not trained on, the output values could not provide confirmatory result. Therefore, the technique has great potential to solve confusion on breed identity. It would also be useful in implementation of Global Plan ofAction for animal genetic resource (AnGR).

Keywords

Livestock, Goat Breed Identification, Deep Learning, Convolutional Neural Network, Confidence Level.

Full Text

   

Deepsubhra Sarkar ¹, Pushkal Guha Choudhur ¹, Abhisek Dutta ¹, Sourish Sarkar ¹, Satyendra Nath Mandal ¹

Affiliations
1 Department of Information Technology, Kalyani Government Engineering College, Kalyani- 741235, IN

Abstract

With the recent advancements in the field of Deep Learning, largely due to the increase in computational power, the long-standing problem of large-scale image classification has been solved up to a considerable threshold. Since the advent of AlexNet in 2012, there has been an increase in the research and development of various Convolutional Neural Network based model to solve problems in the field of Computer Vision. This may be primarily attributed to the success of AlexNet in successfully classifying 1000 class subset of ImageNet with considerable accuracy. Consequently, many more Convolutional Neural Networks were introduced including VGG Net, Inception Net, ResNet, DenseNet, etc. each with better performance than its predecessor. This paper serves as a brief guide to the architecture of ResNet and some of its predecessors. It will also discuss DenseNet and ResNeXt as improvements of ResNet architecture.

Keywords

Computer Vision, Convolutional Neural Network, Deep learning. Image classification, ResNet, AlexNet.

Full Text

   

Arnab Nanda Goswami ¹, Shubhajyoti Das ¹, Satyendra Nath Mandal ¹

Affiliations
1 Department of Information Technology, Kalyani Government Engineering College, Kalyani- 741235., IN

Abstract

Tomato grains are an essential significant, abundant product in the Indian market with high commercial value. Diseases are detrimental to the plant's health, affecting its growth. It is crucial to monitor the condition of the crop for a sustainable farming system. There are many types of tomato diseases that affect the leaves of the crop at an alarming rate. This paper slightly modifies the evolutionary neural network model called lnceptionV3 to detect and classify disease on tomato leaves. The main goal of the proposed work is to find solutions to the problem of tomato leaf disease detection using simple methods while using minimal computing resources to achieve results comparable to the latest technology. Neural network models employ automated feature extraction to classify the input image into the corresponding disease class. This proposed system has achieved an average accuracy of 94-95%, which indicates the feasibility of the neural network approach even in adverse conditions. 

Keywords

leaf disease detection, neural network, convolution, inceptionV3

Full Text