Informatics Publishing Limited

V. Subha ¹, D. Murugan ¹

Affiliations
1 Department of Computer Science & Engineering, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, IN

Abstract

In recent days, it has been found that vast amount of data is available in medical field that aid the doctors in disease diagnosis. Data mining techniques have been applied to extract knowledge from these medical data so that disease prediction becomes easy. In this paper, cardiotocogram (CTG) data is classified using support vector machine (SVM). An optimised feature subset is produced using Firefly Algorithm (FFA) with SVM evaluation. The results show that the performance of classification is improved with the optimal reduced feature set than with full feature set.

Keywords

SVM Classifier, Cardiotocography, Firefly Algorithm, Feature Selection.

Full Text

     

S. Venkatasan ¹, D. Murugan ¹

Affiliations
1 Department of Economics, Annamalai University, Annamalai Nagar, Tamil Nadu, IN

Abstract

Green revolution has resulted in over application of inorganic inputs such as fertilizer and plant protection chemicals. The post green revolution period has threatened the sustainability of Indian agriculture and raised a serious concern about receding groundwater level, loss of soil fertility, low diversity of production system and increasing cost of production. In view of these concerns, the modern-day agriculture gave birth to organic farming. The present study makes a comparative economic analysis of organic farming and inorganic farming under different sizes of land holdings in Pondicherry Union Territory. Since the organic manure consumption in agriculture results in increase in agriculture production, all the farms in the study region may use organic manure which may lead to reduction in the cost of production, and the same may be disseminated to the farmers through NGOs and other extension activities.

Keywords

Agricultural Production, Organic and Inorganic, Manure, Organic Farming, Economic Analysis.

Full Text

   

T. Vignesh ¹, K. K. Thyagharajan ², D. Murugan ³, M. Sakthivel ⁴, S. Pushparaj ⁴

Affiliations
1 Department of Computer Science and Engineering, S. A. Engineering College, Chennai - 600077, Tamil Nadu, IN
2 R. M. D Engineering College, Kavaraipettai - 601206, IN
3 Department of Computer Science and Engineering, M. S. University, Tirunelveli - 627012,Tamil Nadu, IN
4 Department of Geography, University of Madras, Chennai - 600005, Tamil Nadu, IN

Abstract

Objectives: To classify the satellite images into different land use/land cover classes such as water, building, cropland, forest, etc, to monitor the environmental impacts. Method: In this paper, images are grouped into various clusters using a novel SVD trace function clustering algorithm. The clustered samples are used as a training set in a novel unsupervised Ensemble Minimization Learning algorithm (EML) for classification. The main aim of using EML is to classify the forest, vegetative land patterns, build up area in rural and urban areas with the use of best accuracy rate. Finding: Our proposed methods provides 90.56% classification rate with low error rate. This EML applies multinomial probit model and ensembles simulated data set and improves the learning of nonlinear relationships between the classified attributes. Multinomial probit model is used to bring all the related possible segmented values to fall into one single category, thus increasing the classification accuracy. Our proposed methods experimented with three different real data sets. The experimental results indicate that our proposed unsupervised model outperforms than the previous techniques. Application: It could be using for land use/land cover change detection, under water object identification, coastal area monitoring, etc. Improvement: In future it could be apply in video data and could be improve the classification accuracy also.

Keywords

Ensemble Minimization Learning algorithm, Land use/Land Cover Classification, Multinominal Probit Model, SVD Trace Function, Unsupervised Algorithm.

Full Text

   

R. Rejani ¹, D. Murugan ¹, Deepu V. Krishnan ²

Affiliations
1 Department of Computer Science and Engineering, Manonmaniam Sundaranar University, IN
2 Infosys Limited, IN

Abstract

One of the drawback of most of the existing steganography methods is that it alters the bits used for storing color information. Some of the examples include LSB or MSB based steganography. There are also various existing methods like Dynamic RGB Intensity Based Steganography Scheme, Secure RGB Image Steganography from Pixel Indicator to Triple Algorithm etc that can be used to find out the steganography method used and break it. Another drawback of the existing methods is that it adds noise to the image which makes the image look dull or grainy making it suspicious for a person about existence of a hidden message within the image. To overcome these shortcomings we have come up with a pixel pattern based steganography which involved hiding the message within in image by using the existing RGB values whenever possible at pixel level or with minimum changes. Along with the image a key will also be used to decrypt the message stored at pixel levels. For further protection, both the message stored as well as the key file will be in encrypted format which can have same or different keys or decryption. Hence we call it as a RGB pixel pattern based steganography.

Keywords

Data Protection, Steganography, Stegoimage, Cover Image, LSB, MSB, RGB.

Full Text

     

R. Rejani ¹, D. Murugan ¹, Deepu V. Krishnan ²

Affiliations
1 Department of Computer Science and Engineering, Manonmanium Sundarnar University, IN
2 Infosys Limited, Technopark Campus, IN

Abstract

The safety of data and communications for both organizations and personal purposes which at the same time is easy to maintain and having less overhead on system resources is a very important issue. This paper presents a new/alternate secure Database system based on steganography for data hiding. The system provides integrity more confidentiality, and authentication during access or editing of confidential data. The proposed DB system uses steganography technique to store a database of records. The system allows a user to create basic tables and records which are hidden from others inside an image. In this paper propose an architecture which can be used by application developers to retrieve data from the created database in an easy manner. The proposed method is highly useful for use as an embedded DB also in mobile computing as it can store small amount of data easily.

Keywords

Data Protection, Secure Database, Steganography, StegoDB.

Full Text

     

D. Murugan ¹, S. Arumugam ², K. RajalakshmiDepartment of CSE, Francis Xavier Engineering College ³, T. I. Manish ¹

Affiliations
1 Department of CSE, Manonmaniam Sundaranar University, IN
2 Nandha College of Engineering and Technology, Erode, IN
3 Department of CSE, Francis Xavier Engineering College, IN

Abstract

The face recognition problem is made difficult by the great variability in head rotation and tilt, lighting intensity and angle, facial expression, aging, partial occlusion (e.g. Wearing Hats, scarves, glasses etc.), etc. The Eigenfaces algorithm has long been a mainstay in the field of face recognition and the face space has high dimension. Principal components from the face space are used for face recognition to reduce dimensionality. A multiscale representation for face recognition is done to preserve the discriminant information prior to dimensionality reduction. In this paper, three multiscale representation techniques Gabor filter; Log Gabor filter and Discrete Wavelet Transform are applied prior to dimensionality reduction. PCA is then applied on the above techniques to find the face recognition accuracy rate and to compare the results of the three methods with PCA method. The approximation coefficients in discrete wavelet transform is extracted and it is used to compute the face recognition accuracy instead of using all the coefficients.

Keywords

Eigenfaces, Face Space, Gabor Filter, Principal Components, Multiscale, Log Gabor Filter.

Full Text

   

R. Rejani ¹, D. Murugan ¹, Deepu V. Krishnan ²

Affiliations
1 Department of Computer Science and Engineering, Manonmanium Sundarnar University, Tirunelveli, IN
2 Infosys Limited, Technopark, Karyavattom Campus, IN

Abstract

Steganography is an important area of research in information security. It is the technique of disclosing information into the cover image via. text, video, and image without causing statistically significant modification to the cover image. Secure communication of data through internet has become a main issue due to several passive and active attacks. The purpose of stegnography is to hide the existence of the message so that it becomes difficult for attacker to detect it. Different steganography techniques are implemented to hide the information effectively also researchers contributed various algorithms in each technique to improve the technique's efficiency. In this paper we do a brief analysis of different spatial domain image stegnography techniques and their comparison. The modern secure image steganography presents a challenging task of transferring the embedded information to the destination without being detected.

Keywords

Cover Image, Embedding, LSB, MSB, RGB, Steganography, Stego-Image.

Full Text

   

A. Ramya ¹, D. Murugan ¹, T. I. Manish ²

Affiliations
1 Department of Computer Science & Engineering, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, IN
2 Department of Computer Science & Engineering, Adi Shankara Institute of Engineering & Technology, Ernakulam, Kerala, IN

Abstract

Noise removing in the medical image is still a challenging task in the research field especially for the imaging devices like mammogram and ultra-sound. Even though advance scanning technology has been invented, these conventional devices play a vital role in scanning the mammogram breast cancer and fetus images. During the image acquisition itself, these images will get corrupted by the physical interference which appears as a noise in an image and affects its visual quality. In this paper we have applied the various traditional and conventional mean based noise removal techniques for the impulse noise corrupted mammogram breast image and standard benchmark. From this comparative analysis we have found that alpha-trimmed mean filters gives the better result than the other filters in terms of PSNR, SSIM and visual quality.

Keywords

Impulse Noise, Wiener Filter, Noise Reduction, Arithmetic Mean Filter, Medical Image.

Full Text

     

R. Rejani ¹, D. Murugan ¹

Affiliations
1 Department of Computer Science and Engineering, Manonmaniam Sundaranar University, IN

Abstract

Piracy has been a huge problem to the entire IT industry. In the recent years there has been an increase in the usage of mobile based applications and many a times these applications have been illegally copied and used a lot. Apart from applications, piracy also affects video, audio producers, digital book etc. This results in huge revenue loss to the application developers and also in many cases causes the spread of viruses and backdoor programs causing hijacking of personal data. The most commonly pirated mobile apps are games and utility apps. In this paper we are proposing a new method of protecting mobile apps using steganography which will help in protecting the mobile apps against piracy.

Keywords

Data Protection, Steganography, Stego Image, Cover Image, LSB, MSB, RGB.

Full Text

     

D. Murugan ¹, S. Selva Rathna ¹

Affiliations
1 Department of Computer Science, Manonmaniam Sundaranar University, IN

Abstract

The aim of this paper is to identify the impact of the fuzzy based privacy preserving method in clustering which is one of the important data mining process. Fuzzy member ship functions like Bell shape, S- Shape and PI shape membership functions are applied on standard database to generate sanitised database. Further, various clustering algorithms are applied on the sanitised database and the results are compared. WEKA tool is used for testing K-Means clustering algorithm on privacy preserved database generated using various fuzzy member ship function. This analysis will help to develop new Fuzzy Based privacy preserving clustering techniques and also lead future researches in Privacy preserved data mining.

Keywords

Clustering, Fuzzy Membership Function, Privacy Preserving Data Mining, WEKA Tool.

Full Text