About admin

This author has not yet filled in any details.
So far admin has created 1072 blog entries.

ESTIMATION OF TROPHIC STATUS INDEX OF LAKES USING FEED FORWARD NEURAL NETWORK MODEL WITH TWO LEARNING ALGORITHMS

Tushar Anthwal1, Akanksha Chandola Anthwal2, M. P. Thapliyal3

1Deptartment of Computer Science,Bhagwant University, Ajmer,Rajasthan, India

2Uttarakhand State Council for Science & Technology, Dehradun, India

3Department of Computer Science, HNB Garhwal (Central) University ,Srinagar Garhwal, India

 

ABSTRACT: 

 

The health of water bodies across the globe is of high concern as the pollution is accelerating rigorously. With the interventions of simple technology, some significant changes could be bought up. Lakes are dying because of high Trophic Index Status which shows the eutrophication level of water bodies. Taking this into account, feed forward back propagation neural network model is used to estimate the Trophic Status Index (TSI) of lakes which could compute the value of TSI with the given parameters; pH, temperature, dissolved oxygen, Secchi disk transparency, chlorophyll and total phosphate. Two learning algorithms; Levenberg Marquardt (LM) and Broyden–Fletcher–Goldfarb–Shanno (BFGS) Quasi Newton were used to train the network, which belongs to different classes. The results were analyzed using mean square error function and further checked for the deviation from actual data. Among both the training algorithm; LM demonstrated better performance with 0.0007 average mean square error for best validation performance and BFGS Quasi Newton shows the average mean square error of 1.07. 

 

Keywords: Artificial neural network, Eutrophication, Trophic Status Index, Water quality, Feed Forward back propagation

 

pdf

By | 2018-01-20T17:20:13+00:00 January 20th, 2018|General, Publications, Volume XII, Issue I|0 Comments

TEMPLATE PROTECTION SCHEME FOR MULTIBIOMETRIC SYSTEM USING FUZZY VAULT BASED ON FEATURE LEVEL FUSION

1Sandip Kumar Singh Modak, 2Vijay Kumar Jha

Department of Computer Science & Engineering, Birla Institute of Technology, Mesra (Ranchi)-835215

1Research Scholar,2Associate Professor

 

ABSTRACT:

Security of multibiometric template is crucial as they contain information regarding multiple traits of the same user. Hence multibiometric template protection is the main focus of this work. Stored biometric template can be replaced by an imposter’s template to gain unauthorized access; a physical spoof can be created from the template to gain unauthorized access to the system and the stolen template can be replayed to the matcher to gain unauthorized access. Multibiometric based systems are more secure compare to the unimodal based system and this is one of the factors for its popularity. Fuzzy vault and fuzzy commitment are two well known schemes for template security. Fuzzy vault is a biometric cryptosystem that secure both the secret key and the biometric template by binding them within a cryptographic framework. In this paper we propose a template protection scheme based on feature level fusion using fuzzy vault .this work extracts feature points from two different biometric modalities namely fingerprint and iris. After the feature level fusion of these two modalities the feature sets are evaluated on a generated polynomial which is turn is derived from a randomly generated key. Finally some chaff points are added that do not lie on the polynomial to form a vault. Since the points lying on polynomial encode the complete information about the template and the secret key, concealing these points secure both the template and secret simultaneously. The main purpose of Embedding algorithm in the process of feature level fusion is to converting different biometric representation into a common representation space.

 

Keywords: Multibiometric, Fuzzy Vault, Feature level Fusion, Embedding Algorithm, Template Protection, Iris, Fingerprint.

 

pdf

By | 2018-01-19T17:38:00+00:00 January 19th, 2018|Conference Publications, Publications|0 Comments

A COMPREHENSIVE SURVEY ON BIG DATA ANALYTICS AND TOOLS

1 Dr. Sheikh Gouse, 2, 3 Raswitha Bandi, 4 Dr. P.Amrendar Reddy

1 Associate Professor, Dept. of IT, MLR Institute of Technology, Dundigal, Hyderabad, Telangana, India

2 Assistant Professor, Dept. of IT MLR Institute of Technology, Dundigal, Hyderabad, Telangana, India.

3 Research Scholar, Dept. of CSE, K L University, Vijayawada, Andhra Pradesh, India

4  Associate Professor, Dept. of IT MLR Institute of Technology, Dundigal, Hyderabad,

Telangana, India.

 

ABSTRACT:

 

Huge information is another innovation drifts these days. Enormous Data is a monstrous volume of both organized, semi organized and unstructured dataset of petabytes or Exabyte’s. Organized information comprise of database SQL, semi organized comprises of CSV, XML i.e. no SQL and unstructured is content and media is becoming speedier. Unstructured information is delivering 80% from both human and machine. Unstructured information produced by machine is satellite pictures, recordings and photography, logical and radar information. Organized information produced from human is content, social, portable and web content information. So regular delivering pettabytes of information from different sources, it is hard to process utilizing customary database and programming procedures. Its backings Look into, improvement, administration and expository administrations. It pushes different associations to enhance operations and make speedier, cleverer choices. Different types (i.e. structured, unstructured and semi structured) of data cannot be organized by traditional Storage system so to handle these types of data and as well as processing, Analyzing and managing of data which requires big data. In this paper, we studied the different characteristics, applications, vendors and Big Data analytics tools.

 

Keywords: Big data, Hadoop, Big data tools.

 

pdf

By | 2018-01-19T17:35:07+00:00 January 19th, 2018|Conference Publications, Publications|0 Comments

A RELIABLE AGNOSTIC DATA COMPRESSION MODEL BETWEEN EDGE AND CLOUD IOT PLATFORM

S. Balachandar and Dr. R. Chinnaiyan      

Application Delivery Lead

 Shell India Market Private Limited-  Bangalore

Professor , Department of Master of Computer Applications

New Horizon College of Engineering, Bangalore

ABSTRACT:

Due to rapidly adopting different IOT devices at edge layer which translates the data into various formats like JSON, GeoJSON,  XML, SenML,  etc.. Processing & real time transfer of data from edge to cloud is becoming a mammoth task. Many times data files contains a format which is not parsed by  the big data layer in cloud. It is essential to keep a data compressor and real-time migration agent which transfer the data from edge to cloud seamlessly in the defined compression formats (e.g. Avro, Parqueet, etc..). This paper deals with agnostic data compression between edge and cloud IoT platforms.

 

Keywords: IOT Devices, Data format, Edge, Big Data, Data compression, data migration

 

pdf

By | 2018-01-19T17:19:13+00:00 January 19th, 2018|General, Publications, Volume XII, Issue I|0 Comments

RESEARCH TRENDS IN SEMANTIC BASED INTEGRATED TOURISM MANAGEMENT: A SURVEY

            1M.Thangaraj ,  2K.S.Gomathi

1Department of Computer science, Madurai Kamaraj University,Madurai,

Tamil Nadu, India

2 Department, Madurai Kamaraj University, Madurai,

 

ABSTRACT: 

 

The growth in the use of internet has transferred the web users to use the internet to gather travel related information. Although the information is plenty, it is difficult to get accurate and specific information. In order to solve these problems, the concept of semantic web comes into existence to have communication between human and computer. Travel and tourism are information intensive domains where in online information places a crucial role for the whole lifecycle of the journey. The backbone of semantic web is formed by ontology. Ontologies can assist organizational, browsing, parametric search and more intelligent access to online information. There are numerous applications operating towards semantic web and the fascinating among them is tourism that promotes the countries’ economy. This paper focuses on the survey that shows   how semantic web along with Ontology help in providing right information and discusses various issues that are related to tourism management.

 

Keywords: Tourism, Semantic Web, Ontology, Personalized Recommendation Systems, Route Recommendation

 

pdf

By | 2018-01-19T17:11:20+00:00 January 19th, 2018|General, Publications, Volume XII, Issue I|0 Comments

DENGUE DISEASE PREDICTION IN INDIA USING MACHINE LEARNING APPROACHES

Dr.N.Kannathasa

Department of Computer Science

Kanchi Mamunivar Centre for Post Graduate Studies Puducherry-605 008

Union Territory of Puducherry, India

 

ABSTRACT: 

 

Mosquito-borne diseases on upswing in India. The increase in cases of these diseases was due to the harsh weather and severe drought in several parts of the state which offered a fertile breeding ground for several of these species. The monsoon rain and water logging increased the likelihood of eggs surviving, especially for dengue-causes/Aedes aegypti mosquitoes. The research objectives of this study are assess whether online data, epidemiological and meteorological data, from Google Trends are a viable data source for monitoring dengue epidemics. The use of social network data can help researchers estimate the number of such dengue incidences ahead of official reports, which always take time depending on the laboratory process. The results of this kind of study can help researchers make a good prediction of the number of dengue cases at near real-time even though the people who tweeted did not go to hospitals or get diagnosed. This study will illustrates the effectiveness of applying machine learning techniques in the field of public health. Artificial Intelligence based applications could improve health outcomes and the quality of life for millions of people in the coming years.

        

Keywords: Mosquito-borne, Dengue, Google Trends, Epidemics, Machine Learning, Prediction, Artificial Intelligence.

 

pdf

By | 2018-01-18T16:44:37+00:00 January 18th, 2018|General, Publications, Volume XII, Issue I|0 Comments

GENERATE RADIOLOGY REPORT USING SVM CLASSIFICATION

Poonam Kasbe1, Sharmishta Chavan 2, Madhuri Pawar³, Payal Bharat, Sarita Patil5

 1,2,3,4 Department of Computer Engineering, GHRCEM, Wagholi, Pune, India.

5 Professor, Department of Computer Engineering, GHRCEM, Wagholi, Pune, India.

 

ABSTRACT:

 

In bio-medical field, radiology reports are generated day by day in huge amount. Processing of radiology reports is the part of clinical fields. In this paper describes to recognizing and take out the disease from the patient’s radiology reports. Methodology includes pre-processing of image, segmentation of image, feature extraction of image and classification by using support vector machine. For image Segmentation using clustering algorithm i.e. k-means clustering and it is used for classification of image with similar features.

 

Keywords: Radiology reports, feature extraction, JAVA, laptop, hard disc.

 

pdf

By | 2018-01-18T16:40:31+00:00 January 18th, 2018|General, Publications, Volume XII, Issue I|0 Comments

IMAGE COMPRESSION BASED ON VECTOR QUANTIZATION USING NOVEL GENETIC ALGORITHM FOR COMPRESSING MEDICAL IMAGES

M.Mary Shanthi Rani 1, P.Chitra 2 and R. Vijayalakshmi 3

 1Department of Computer Science and Applications, The Gandhigram Rural Institution -DU, Gandhigram, Tamil Nadu, India

 

ABSTRACT: 

 

This paper presents a novel techniques of vector quantization using genetic algorithm to compressing medical test images. Genetic Algorithms (GAs) are adaptive heuristic search algorithm depends on the evolutionary ideas of natural selection and genetics. The main aim of this proposed method is to develop an effective algorithm which could produce a high compression ratio without any degradation in image. Vector quantization is a smart tool in lossy image compression technique which creates an efficient codebook. In this proposed work focuses on optimized result using novel genetic algorithm for compressing medical images. Experimental results shows that the proposed work reveals good compression ratio and higher PSNR value than the other existing methods.

 

Keywords: Image Compression, Genetic Algorithm, Computational Methods, Optimization Technique, Vector Quantization

 

pdf

By | 2018-01-17T16:31:17+00:00 January 17th, 2018|General, Publications, Volume XII, Issue I|0 Comments

A SURVEY ON NETWORK STORAGE TECHNOLOGY OF DIRECT ATTACHED STORAGE, STORAGE AREA NETWORK, NETWORK ATTACHED STORAGE

Bohar Singh

 Computer Science and Application, Govt College Sri Muktsar sahib, Punjab

 

ABSTRACT:

 

                As the growing trend of internet, large network storage repositories have become important for large data storage. Every year vast amount of new data is generated by humans and applications which use data in various format including texts, video, audio and images. Traditional database storage model (DAS) consists of disk drives physically attached to a database server system using SCSI or other interface but it include lack of scalability, distance restrictions, performance, and limited multiple host storage sharing Which can be improved with the help of network storage system that should be high capacity, scalability, availability and performance. With the help of SAN and NAS, storage can be efficiently utilized and it mitigates pitfalls of direct attached storage to aid more flexible storage access. SAN and NAS use open industry-standard network protocols to provide storage facility. This paper provides the basics and survey on new storage technologies of these protocols and an easy-to-understand comparison of the storage attachment alternatives you can select from to build the infrastructure to access your most important digital asset such as your data

 

Keywords: DAS (Direct Attached Storage), NAS (Network Attached Storage), SAN (Storage Attached Network)

 

pdf

By | 2018-01-17T16:24:23+00:00 January 17th, 2018|General, Publications, Volume XI Issue XII|0 Comments

ANALYSIS AND ANALYTICS OF BIG DATA

Prabhjot Kaur

 Department of Computer Engineering in Big Data

Chandigarh University, Gharuan, Mohali

 

ABSTRACT: 

 

Looking into the field of big-data a picture appears in mind and our perception directly points to the huge size, generation of data with large speed and different formats in which the data is found. As for as the data is concerned it is useless until proper information and knowledge is extracted from it, and this can be done only with the help of Analysis. Analysis is the only way to gain the accurate and deep understanding of the historic view of data, what has happened?  In the past and after gathering this much of information we are able to predict what would happen?  Based on our critical thinking and logical ability. There is a need for self-sustained analysis, modeling and planning. Thus Analysis and Analytics act as bow-arrow and Target in Big-data, Analysis as bow-arrow because it is a prerequisite, and Analytics is target because it is based on our prediction.

 

Keywords: Big Data, Analysation, Analytics

 

pdf

By | 2018-01-16T16:16:15+00:00 January 16th, 2018|General, Publications, Volume XII, Issue I|0 Comments

VIRTUAL SHOPPING MALL AN APPLICATION OF VR

Prof. Shiv Sutar 1, Pritam Rikame2, Neeraj Upadhyay3, Mayuresh Kakade4, Yash Tatkondawar  5

 1Department of Computer Engineering

 2Department of Computer Engineering MIT College of Engineering, Pune, India

 

ABSTRACT

 

The tremendous development of technological wave, in particular to virtual technology, has brought shopping activities into a new generation. The customers are turning their faith on purchasing their product on online web based platform. But the real visualization and product reliability can’t be seen in on online web based platform. Hence this project deals with a virtualization of the road and shops where the person can directly go search shop and purchase it in the real time and also customer can directly buy the product in the retail shop and also it gains the navigation of the information. Using a 3D virtual environment and adding a shopping idea to it is considered as very interesting, especially if it reflects the real world in a virtual reality that makes its users attached to it. This research examines the effects of using 3D virtual shopping malls and how the user interaction and experience in this type of virtual environments.

 

Keywords: Virtual Reality, 3d Graphics, Simulation, Graphical environments, Apriori Algorithm

 

pdf

By | 2018-01-14T16:08:29+00:00 January 14th, 2018|General, Publications, Volume XII, Issue I|0 Comments

PERFORMANCE ASSESSMENT OF FACULTY FOR INSTITUTE GRADATION USING DATA MINING TECHNIQUES

[1] Renuka Agrawal, [2] S. M. Ghosh, [3] Jyoti Singh

 1  Research Scholar,Department of Computer Engineering , Dr. C.V. Raman University (C.G.)

 2  Professor Department of Computer Engineering, Dr. C.V. Raman University(C.G.)

Joint Controller, VYAPM,(C.G.), India

 

ABSTRACT:

 

The spectrum of applications of Educational Data Mining to industrial and commercial problems is so wide as to defy easy characterization. In this paper a holistic framework is proposed based on the psychological conceptions of human competence and performance in the workplace. We explain the application of Data Mining that can be used in an institute to systematically assess existing and future competencies required. Using this approach, Educational Institute will be able to more effectively use their resources to reap more benefits from their investments in both people and technology. The objective of this research is to develop a prototype of a system that can be used by academic advisors in their academic planning. Performance appraisal of employee is important in managing the human resource of an organization. With the change towards knowledge-based capitalism, maintaining talented knowledgeable workers is critical. The appraisal process describes a human resource methodology that is frequently used for both employee appraisal and employee development. The appraisal may further be utilized for assessing the department in which a faculty is associated with and can also be used for the institute gradation. The appraisal is a comprehensive method where in the feedback about the employee comes from all the sources that come into contact with the employee on his/her job. The respondents for an employee can be her/his peers, subordinates team members, students, seniors and others. The proposed system is an attempt to implement the feedback based appraisal system in academics especially engineering colleges.

 

Keywords: Performance appraisal system, Institute gradation, Educational Institute, Formative Assessment, Summative Assessment

 

pdf

By | 2018-01-13T16:48:05+00:00 January 13th, 2018|General, Publications, Volume XII, Issue I|0 Comments

EVALUATION BASED SECURE SOFTWARE ARCHITECTURE AND DESIGN FRAMEWORK

Mubashirah Majeed1, S.M.K Quadri2

                                   Department of Computer Sciences University of Kashmir, Srinagar, India                                  

Department of Computer Sciences, Jamia Milia Islamia, New Delhi,   India

 

ABSTRACT

In this paper we are proposing a hybrid secure software development lifecycle (H-SSDLC).The proposed H-SSDLC provides the early indications for the software developer to think about the security at the very early stage of software development lifecycle. An empirical evaluation based on the most important security attributes like dependency, availability, confidentiality and integrity is carried on a system to determine the security level of the components. The calculated security (severity) levels provide the early indications for the developer to take the necessary counter measures to mitigate the security flaws early in the software development process. Our proposed framework uses the best of the techniques at each level of development to achieve the more secure system.

Keywords:  vulnerabilities, Confidentiality, secure software, Security Requirements, Component Based Design

 

pdf

By | 2018-01-13T16:45:24+00:00 January 13th, 2018|General, Publications, Volume XII, Issue I|0 Comments

INTRODUCTION TO QUERY PROCESSING AND OPTIMIZATION IN DISTRIBUTED DATABASE SYSTEM

Anjali Saini1

1 Department of Computer Science and Engineering, Ph..D Scholar, Singhania University, India

 

ABSTRACT:

 

 Query processing is a technique for achieving information from the database in an effective and convenient  way. The performance of the database system rely on the techniques of query processing that we used in various database systems.The query optimizer is a remarkable component or element in today’s relational database management system(RDBMS). This element is creditable for translating or converting a user-submitted query  which is generally written in a non-procedural language into an reliable query evaluation program that can be implemented  against the database. This research paper describe and give an overview of query processing and optimization steps in distributed database system .  The study in this research paper will give the guidelines to the scholars ,researchers and practitioners of computer science and engineering in their field .

 

Keywords-  Query Processing, Distributed Database System and Query Optimization

 

pdf

By | 2018-01-13T16:42:02+00:00 January 13th, 2018|General, Publications, Volume XII, Issue I|0 Comments

REVIEW ON THE VIDEO SEGMENTATION TECHNIQUES

Piyush Bisht

Dept. of Computer Science & Engineering,Amity School of Engineering and Technology,

Amity University Uttar Pradesh, Noida,India

 

ABSTRACT:

 

From the fast few years video summarization has become the active area of research. With the increasing load of the multimedia content on the internet, it has become significantly important. To extract desired content from video various techniques have being introduced for the video segmentation as it is the integral part of the video summarization like color histogram differences[25][27], edge change ratio[27], standard deviation of pixel intensities[27] etc. One video segmentation technique is not good for all the types of videos. Some techniques give better result in one case and some in the other case. Another issue encountered in segmenting the video into shots are their space and time complexity.

 

Keywords:  Color Histogram, Frames, Shot Segmentation, Thresholding, Video Summarization

 

pdf

By | 2018-01-13T16:39:15+00:00 January 13th, 2018|General, Publications, Volume XII, Issue I|0 Comments

ALL EASY ACCESS EDUCATIONAL WEB PORTAL

Ritu Tiwari 1, Shital Biradar 2,Prashant Maskar3,Riyaz Kazi4

 1,2,3,4Department of Computer Engineering  GHRCEM Pune India

 

ABSTRACT:   

 

This web application is an educational portal dedicated to provide free information on education, educational institution, courses, and other educational services in Ethiopia. The website consists of free online directory that contains very useful information on all schools, colleges & universities. The web portal also consists of helpful resources such as past examination question papers for schools, colleges and universities. This educational portal will help to communicate different state students with similar courses, so they can share their knowledge and other educational information interactively.

 

Keywords: Educational web portal, free information, interactive online chat, Students, easy web access, search module.

 

pdf

By | 2018-01-12T16:33:29+00:00 January 12th, 2018|General, Publications, Volume XII, Issue I|0 Comments

A REVIEW ON BIG DATA ANALYTICS IN MEDICAL IMAGING

Sanjukta Mishra

 Assistant Professor, Department of Computer Science, Brainware University,Kolkata, India 

 

 ABSTRACT: 

 

Big data analytics in the application of medical image processing plays a vital role .For better healthcare it is necessary for automatic analysis which helps in early diagnosis of diseases. This paper describes the overview of Big Data, the benefits, challenges and models of big data analytics for analyzing the medical images from a large dataset in a distributed environment. This paper also proposed a Spark with Yarn framework for medical imaging.

 

Keywords: Big Data, Hadoop, Spark, Yarn, Medical imaging

 

pdf

By | 2018-01-11T16:48:51+00:00 January 11th, 2018|General, Publications, Volume XII, Issue I|0 Comments

FURNISHING CERTAINTY TO SKIPCLOUD BY DEPLOYING VISUAL CRYPTOGRAPHY TACTICS

 Y Venkata Narayana1, T Krishnamachari 2, K Vinaya Sree Bai 3

1,2,3 Department of Computer Science & Engineering

  DVR & Dr HS MIC College of Technology, Kanchikacherla, Andhra Pradesh-521180, India

 

ABSTRACT: 

 

Now a day’s authentication plays a prominent mantle in each and every cloud services. As a part of security, it is not safe to be contingent on text watchwords and incisive image watchwords. And also services provided systems must to be further secure and should be reliable, as each and every task is performed, which is related to user’s data. Particularly authentication and validation of user access is the major task. Text watchwords and incisive image watchwords are not secure, because there is a chance of surfing difficulty. The SkipCloud used, is provided with just login credentials which is a very simple technique where possibility of hacking is more. So, in order to overcome this problem we implemented an proficient algorithm for secured authentication services. The algorithm mainly deals with Images and Visual Cryptography. As a solution to the problem, in this paper, at the time of first registration, the user is provided an email id and then an image of the user’s selection.

 

Keywords: Mantle, Watchwords, Visual Cryptography, Incisive, Tactic, Pertinent

 

pdf

By | 2018-01-11T16:44:42+00:00 January 11th, 2018|General, Publications, Volume XII, Issue I|0 Comments

SECURE PASSWORD AUTHENTICATION SCHEME WITH DIGITAL INTERFACE

                   Poonam Pandey1   Prof. Rajesh Kumar Tyagi2   Dr. Alok  Gahlot3

1 P .hD scholar Department of Computer Engineering  College of Engineering T.M.U Moradabad U.P

                                        2 Director MSI C-4Janakpuri,New Delhi110058  New Delhi India   

          3 Asst.Professsor Department of Computer Engineering  College of Engineering T.M.U Moradabad U.P India

 

ABSTRACT:

Password security is the primary concern for any authentication system.The main aim of the password is to protect the system from unauthorized user.The emerging growth of the internet and other technology the password is the main key to secure the data over internet.using password.       There are many way to provide security over the internet .In this paper we describe an efficient security by using randomly generated single integer input value. For each and every string our scheme will provide unique digit for creating password.We provide systematic approach for authentication of password at application layer.

 

Keywords:- Security ,Authentication ,Random number.,Password, Cryptography.

 

pdf

By | 2018-01-10T15:43:15+00:00 January 10th, 2018|General, Publications, Volume XII, Issue I|0 Comments

SECURING TEXT DATA BY HIDING IN AN IMAGE USING AES CRYPTOGRAPHY AND LSB STEGANOGRAPHY RESULTING LOSSLESS FORMAT IMAGE

1Jayati Bhadra , 2M.K. Banga , 3M. Vinayaka Murthy

1Research Scholar, School Of Computer Science, Reva university, Rukmini Knowledge Park, Kattigenahalli, Yelahanka, Bengaluru, Karnataka 560064, India

2 Professor, School Of Computer Science, Dayananda Sagar University Shavige Malleshwara Hills,Kumaraswamy Layout,Bangalore 560078, Karnataka, India

3Professor,  School Of Computer Science, Reva university, Rukmini Knowledge Park, Kattigenahalli, Yelahanka, Bengaluru, Karnataka 560064, India

 

ABSTRACT:

In the field of computer network, cryptography and steganography are the well-known features of security. Both the techniques, if used single handedly has feebleness. So, providing acceptable level of security is essential for data transmission. The paper proposes a hybrid mechanism that employs Advanced Encryption Standard scheme to encrypt data and an LSB Steganography algorithm to embed the data in a gray scale image and gives lossless compression form of the resultant image. Python is used to implement the proposed hybrid algorithm to create lossless image format. MATLAB is used to simulation results which show that it has good embedding capacity and security with a little decrease in PSNR value.

 

Keywords: Advanced Encryption Standard Cryptography, Least Significant Bit Steganography, lossless compression

 

pdf

By | 2018-01-10T15:36:29+00:00 January 10th, 2018|General, Publications, Volume XII, Issue I|0 Comments

RESTORATION OF DEGRADED NON-UNIFORMALLY ILLUMINATED HISTORICAL KANNADA HANDWRITTEN DOCUMENT IMAGES

Parashuram Bannigidad 1, Chandrashekar Gudada 2

 1, 2 Department of Computer Science

Rani Channamma University, Belagavi-591156, Karnataka, India

 

ABSTRACT:

 

The digital image processing has got much attention of the researchers towards development of automatic optical character recognition system. The document image analysis mainly focused on printed and handwritten document images. In printed document image analysis, the input image is that of machine printed document, where as in handwritten document image analysis, it is of document written by different persons on a paper using pen or pencil. Presently, most of the research work addresses issues related to handwritten document images and the Kannada script. The printed script recognition system is much easier than handwritten script recognition system. In printed documents, font style and size of the characters are standardized, whereas handwritten characters vary in size and style of font from person to person and time to time, which is a very tedious job for recognition. In this paper, a new novel approach is proposed for restoration of degraded historical Kannada handwritten documents using the combination of special local and global binarization techniques, by eliminating of non – uniformly illuminated background. The performance evaluation of the proposed method is tested with ground truth images by extracting geometric feature values of Precision, Recall, F-Measure, MSE and PSNR. It observed that, from the experimentation of results, the average value of PSNR, Precision and F-Measure are 10.07, 0.648 and 77.194 and MSE, Recall are 0.102 and 0.97, respectively. The above said comparison performance evaluation approaches; i.e. the values of PSNR, Precision and F-Measure is higher and the MSE, Recall are lesser comparatively other methods i.e. Souvala and Niblack, which indicates the quality of reconstruction of degreded historical handwritten document images. These results are also compared with manual results visualized by the Epigraphists, language experts, and thus, demonstrate the efficacy of the proposed method. Restoration of degraded Kannada handwritten documents plays an important role in age identification, Kannada character recognition and classification for the Kannada handwritten documents. The proposed algorithm is also implemented with other datasets, namely, H-DIBCO-2016 series and Bickley diary datasets, these datasets contains the documents written on a paper using English language; which proves the exhaustiveness of the proposed algorithm.

 

Keywords: Hastaprati, Image enhancement, degraded document, Kannada script, Image restoration, Local otsu, Sobel filter, Local standard deviation.

 

pdf

By | 2018-01-10T15:30:55+00:00 January 10th, 2018|General, Publications, Volume XII, Issue I|0 Comments

AN IMAGE PRE-PROCESSING TECHNIQUE FOR DETECTING FIRE AUTOMATICALLY IN FLAME IMAGES

R. Vijayalakshmi 1 *, S.Muruganand 2

Department of Electronics and Instrumentation, Bharathiar University,

Coimbatore-641046, Tamilnadu, India

 

ABSTRACT

 

Edge detection techniques is the pre-processing step in image process analysis. Digital image processing play vital role in flame images for monitoring and detecting fire automatically. Some unique features of flame are used to find its edges. The brightness of the flame is much higher than the other objects in the image. The expected edge output of flame image should be clear and undisturbed. To find this, several known edge detection methods are tested to the image. The new proposed method consists of combining available best methods to detect edges in flame images in the fire monitoring and detecting system.  This method identifies edges correctly and clearly by removing all the noise. The results of this method proved the edges are robust, clarity, continuity and effective than other existing techniques.

 

Keywords:- Edge detection, flame image analysis, fire monitoring, digital image processing.

 

pdf

By | 2018-01-10T10:14:19+00:00 January 10th, 2018|General, Publications, Volume XI Issue XII|0 Comments

BEYOND LIGHTNING: A SYSTEMATIC REVIEW OF INFORMATION SECURITY IN THE AGE OF CLOUD COMPUTING USING KEY MANAGEMENT

Sakshi Chhabra 1, Ashutosh Kumar Singh2

1Department of Computer Applications NIT Kurukshetra, Haryana, India

 2Department of Computer Applications NIT Kurukshetra, Haryana, India

 

ABSTRACT: 

 

Cloud Computing is a completely new-paradigm because of its low-cost, tremendous performance, on-demand access, authorization with many other wide range of luxurious features. The prosperity of cloud fetches not only opportunities to organizations, but also composed more convenience for people’s daily life. Based on a systematic literature review, this paper introduces the detailed analysis of cloud security issues and put forward the best-security key management approaches. We have identified many models of security, but in particular, we briefly present the most popular one techniques of Security by Key Management. In this paper, we aim at classifying and evaluating the security challenges, techniques and various algorithms used for cloud security. Our work provides initial experimental data of cloud attacks against a key network and shows that the network performance degrades dramatically only when several attack intensity approaches to the maximum. We have developed the evaluation of the techniques that have been applied to conserve the security of the existing data. Moreover, we then qualitatively analyze an internal comparison of an individual approach separately. To develop suitable security solutions for such environment, this paper give a comprehensive functionality-wise comparison study and key-mechanism based security-reachable methods from the outlook of the completion of security requirements.

 

Keywords: Cloud Computing, Data Security, Key Management, Cloud Security Architecture, Cloud Challenges and Threats

 

pdf

By | 2018-01-10T10:04:19+00:00 January 10th, 2018|General, Publications, Volume XI Issue XII|0 Comments

SPEECH-ENABLED IVR USING ARTIFICIAL BANDWIDTH EXTENSION TECHNIQUE

Mohan Dholvan1, Dr. Anitha Sheela Kancharla2

 1Department of Electronics and Computer Engineering, SNIST, Hyderabad, Telangana, India

 2Department of Electronics & Communication Engineering JNTU, Hyderabad, India

 

ABSTRACT: 

 

In modern world, Speech Enabled Interactive Voice Response (SEIVR) Systems are slowly replacing the existing IVRs but the recognition accuracy is not up to the mark, the reason is public telephone systems transmit speech across a limited frequency range, about 300–3400 Hz, called narrowband (NB) which results in a significant reduction of quality and intelligibility of speech. Also, a comparative analysis has been done for various NB and WB speech codecs as to how a phoneme is recognized. This analysis helped us to find out the root cause for degradation in performances of SEIVR systems. Main objective of ABWE with side information is to extract WB spectral components from WB input speech and to embed these derived spectral components into coded NB speech signal and finally transmit them onto a NB channel. Reverse procedure can be carried out at receiver to artificially produce WB speech. Here, it is to be noted that transmission channel is NB whereas end terminals are made WB compatible so this method provides alternative solution to coexisting state of the art WB coders (which require WB channels) while offering comparable speech quality and giving natural sounding in terms of intelligibility and naturalness. In the light of the experimental results achieved, it can be concluded that the implementation of artificial bandwidth technique (ABWE) will drastically improve the recognition accuracy, which further results in enormous improvement in the performance of SEIVR systems.

 

Keywords: SEIVR, ABWE, NB Speech codec, WB Speech Codec, Wideband Spectral components

 

pdf

By | 2018-01-10T09:57:28+00:00 January 10th, 2018|General, Publications, Volume XI Issue XII|0 Comments

ASSESSMENT ON IMPROVISING FREQUENT ITEMSET MINING IN HUGE VOLUME OF DATASET

Dr. K. Kavitha

Assistant Professor in Computer Science

Mother Teresa Women’s University, Kodaikanal

 

ABSTRACT

Map Reduce programming model is focused for distributed large scale data processing with some constraints and properties.  It is frequently used as a classification or clustering method in machine learning or data mining. Distributed data processing framework called Map Reduce proposed to simplify the parallel processing using a distributed computing platform which typically uses client/server communication model.  In this process, uses a Parallel Frequent Item Sets mining algorithm for predicting the large amount of datasets using the Map reduce technique. Map reduce model is a vital research area in recent years. The previous research work in this background and the basic concept of the system requirement for this thesis is considered in this paper.  This gives an objective, critical summary of published research literature relevant to this research and also summarised the concept of FiDoop. Many Fidoop incorporates the frequent items ultra-metric tree or FIU-tree achieving compressed storage and avoiding the necessity to build conditional pattern bases.

 

KEYWORDS:  Fi-Doop, Itemset, Map reduce, Frequent item, Parallel Mining, Hadoop

 

pdf

By | 2018-01-09T12:57:45+00:00 January 9th, 2018|General, Publications, Volume XI Issue XII|0 Comments

SYNTHESIS OF TRAINING DATASET FOR ARTIFICIAL NEURAL NETWORK FOR DIAGNOSING SCHIZOPHRENIA

Moumita Paul1, Dr. Monisha Chakraborty2

 1School of Bioscience and Engineering, Jadavpur Univerisity, Kolkata, India

2Associate Professor, School of Bioscience and Engineering, Jadavpur Univerisity, Kolkata, India

 

ABSTRACT: 

 

Artificial neural networks have been deployed in order to diagnose various diseases. This paper deals with the diagnosis of schizophrenia which is a serious mental disorder, on the basis of the ratings obtained by the subject on a psychometric test. A neural network may be deployed to accept the subject’s ratings and return an output. If the output is closer to zero than to one then the subject is not schizophrenic, and if the output is closer to one than to zero, then the subject is schizophrenic. However because of the difficulty of obtaining an adequate number and variety of samples from real subjects, the training data has been synthesized with the help of a fuzzy expert system that diagnoses schizophrenia from the psychometric test ratings. The synthetic data so obtained may be used to train neural networks designed to diagnose subjects based on the results of psychometric tests.

 

Keywords: artificial neural network, schizophrenia, psychometric test, training data, synthetic generation

 

pdf

By | 2018-01-05T00:40:34+00:00 January 5th, 2018|General, Publications, Volume XI Issue XII|0 Comments

A REVIEW OF SPATIAL ANALYSIS OF MULTIDIMENSIONAL TOPOGRAPHIC DATA

Rajesh K. Maurya1, Sushil T. Kulkarni2

 1Department of Computer Science (UDCS), University of Mumbai, Maharashtra-400098, India

 2Department of Mathematics, Jai Hind College, Mumbai, Maharashtra- 400020, India

 

ABSTRACT: 

 

Spatial analysis has evolved and found unprecedented growth in last two decade. Higher dimensional spatial analysis including those in three dimensions has exhibited potentially limitless opportunity for knowledge discovery and generating information used in object reconstruction, topographic understanding and creating spatial databases. This paper studies and highlights the state of the art development and applications done so far in spatial analysis especially suitable for higher dimensional topographic datasets. A comparison of spatial analysis problems and a possible approach for solving them are also presented. Importance and relevance of geo-statistical modeling and machine learning approaches are highlighted and thereby suggest pointers to further research opportunities.

 

Keywords: Spatial Analysis, Multidimensional Data, Spatial Data Mining, Topographic surface, LiDAR

 

pdf

By | 2018-01-04T23:57:49+00:00 January 4th, 2018|General, Publications, Volume XI Issue XII|0 Comments

3D RECONSTRUCTION OF HILLS OF SANJAY GANDHI NATIONAL PARK REGION FROM DIGITAL RASTER ELEVATION DATA

Swati R Maurya1, Ganesh M Magar2

 1Department of Computer Science, S. K. Somaiya College of ASC, Vidyavihar(E), Mumbai, Maharashtra, India, 400077

 2P.G. Department of Computer Science, S. N. D. T Women’s University, Santacruz (E), Mumbai, Maharashtra, India, 400049

 

ABSTRACT:

 

Reconstruction and modeling of large geospatial features such as terrain and mountains are vital in study and planning of ecological infrastructure. This includes wild animal habitat, urban and civic planning. Identifying zone of influence of natural infrastructures such as forest, hills, and mountains has the valuable contribution. Wildlife safety and tracking activities can be better monitored and executed if visualization and simulation of the affected region are available. This paper presents a geostatistical approach for reconstructing and visualization of hills of the region around Sanjay Gandhi National Park, Borivali, India from raster data and identifies the zone of immediate influence of wildlife to adjacent urban regions. Reconstruction of 3D geospatial hills and mountains has been achieved from raster image data of 30m resolution obtained from satellite imagery. Contour list of the lower reach of wildlife over these mountains is identified, extracted, georeferenced and finally integrated together with the constructed 3D hills. Additionally, hydrological sources in the nearby area are also identified and saved for virtual modeling and visualization purpose. It is shown that bilinear and cubic convolution based interpolation is more suitable than nearest neighbor estimates for raster data of test region. The results are physically verified with known ground truth values and also validated with google maps in a georeferenced environment. The accuracy of around 97.13% has been obtained for the reconstructed hill region.

 

Keywords: 3D Reconstruction, Visualization, Geostatistical Modelling, Digital Elevation Model

 

pdf

By | 2018-01-04T23:51:38+00:00 January 4th, 2018|General, Publications, Volume XI Issue XII|0 Comments

ANALYSIS OF IOT IN AUTOMOTIVE INDUSTRY USED IN SMART CITIES

Jincy John1, Kruthika G2,Aishah Farah A J3,Anagha C4,Sowmya Naik5

1Department of Information Science Engineering, CEC, Bangalore, India

2Department of Information Science Engineering, CEC, Bangalore, India

3Department of Information Science Engineering, CEC, Bangalore, India

4Department of Information Science Engineering, CEC, Bangalore, India

5Assisstant professor, Department of Computer Science Engineering, CEC, Bangalore, India

 

ABSTRACT: 

 

This paper analyzes the benefits of big data for smart cities in automotive industries and the potential of the knowledge discovery from sensed data. Big data enables real-time systems monitoring, management, optimization and anticipation. In this work we present some examples of applications of big data analysis in a scenario of smart city. It describes the services provided in the Smart Campus of the University of Murcia. With the recent advancement in technologies such as embedded system, wireless distributed sensor, smart cognitive radio networks, cloud computing, intelligent converter, the production of smarter, safer and energy efficient is possible in near future. The results obtained after applying the most appropriate big data techniques in this scenario show how it is possible to provide efficiently services like the management of the energy consumption and comfort in buildings, and the transport congestion in the context of smart cities. This paper will discuss the impacts of IoT and Big Data and other emerging technologies mentioned above to the automotive industry.

 

Keywords: Internet of Things, Big Data, Automotive Industry, Cloud Computing, Smart City.

 

pdf

By | 2018-01-04T00:41:16+00:00 January 4th, 2018|General, Publications, Volume XI Issue XII|0 Comments

A DYNAMIC PREDICTION MODEL AND IMPACT-BASED WEATHER FORECAST WARNING SERVICES ON MULTI-HAZARD FOR SOUTH DISTRICTS IN INDIA

Dr. N. Priya

Assitant Professor, Dept. of Computer Science

SDNB Vaishnav College for Women, Chromepet, Chennai-600 044, Tamilnadu, India

 

ABSTRACT:

 

Each year the impact of severe hydro meteorological events around the globe give rise to multiple casualties and significant damage on property and infrastructure in human life. The reasons for these fatalities lie in the gap between forecast prediction and the impact warnings of multi-hazard events by the authorities of emergency management and by the population at large. This paper aims at providing a clearer prediction and interpretation on north east monsoon rainfall data for south districts in India. A dynamic prediction model using data mining has been implemented and the results are summarized according to various types of hazards. Finally a framework has been proposed for building an impact-based warning service. The study has special focus on south districts such as Tamil Nadu and Puducherry in India in terms of absolute number of the loss of human life and the infrastructure in the last 3 years.

 

Keywords : Multi-hazard, Dynamic Prediction Model, Impact-based warning service.

 

pdf

By | 2018-01-04T00:27:15+00:00 January 4th, 2018|General, Publications, Volume XI Issue XII|0 Comments
Load More Posts