← Back to Archives
ICRTCC
ICRTCC
📖 Volume: .
Design Challenges and Comprehensive Study on Cluster Based Routing Protocol in Wireless Sensor Network
P K Poonguzhali, Dr N PAnanthamoorthy, S.Jeeva Jabakani
Integrating Discrimination Prevention and Privacy Preservation into Data Mining
Sujitha S, Sreejith S
Impact and Application of Sentiment Analysis using Twitter: a survey
Hema Krishnan, M. Sudheep Elayidom, T. Santhanakrishnan
Implementation of Correlation Techniques for the Equity Market in India
Cerene Mariam Abraham, M. Sudheep Elayidom
Leveraging Cloud for Large Scale Business Transactions – A Survey
Neethu Mohandas, M Sudheep Elayidom, Sasi Gopalan
Early Diagnosis and Detection of Cancer using Artificial Neural Network based Prediction Algorithm
Alavi Kunhu, Nisi K, Sadeena Sabnam, Majida. A
Hybrid DWT-DCT Video Watermarking Algorithm for Copyright Protection of Multimedia Color Videos
Alavi Kunhu, Nisi K, Sadeena Sabnam, Majida A
Survey on Data Preprocessing Techniques for Fuzzy Association Rule Mining
ViniVijayan, Dr. M. Sudheep Elayidom
A Third Eye Investigator Utilizing Vibration Energy Harvesting
Chithra .P, Adeeb Ahammed .P, Eldhose .P .Sim
A Study on Network Steganography Methods
Amritha Sekhar, Manoj Kumar G., Prof. (Dr.) M. Abdul Rahiman
Abstract
Design Challenges and Comprehensive Study on Cluster Based Routing Protocol in Wireless Sensor Network
P K Poonguzhali, Dr N PAnanthamoorthy, S.Jeeva Jabakani
Abstract:
Recent year�s extensive research has been conducted on routing protocols for Wireless Sensor Network because of its numerous applications. A wireless sensor network is a collection of sensor nodes prearranged into a collective network to monitor the remote and physical environment. These sensors nodes are capable with limited processing and computing resources. The design of these routing protocols is to minimize the energy consumption in the network during transmission of information. During radio transmission and reception these sensor nodes consumes lot of power, hence forth to maintain uninterrupted transmission energy efficiency should be analysed and it is considered as one of the critical parameter in wireless sensor network is the inherent limited battery power within the sensor nodes. In this paper, the focus is mainly driven towards the review of energy efficient routing protocol and its design issues. Different routing protocols pros and cons were analysed. Some standard cluster�based available routing protocols were compared with respect to their clustering attributes for wireless sensor network. This document gives formatting instructions for authors preparing papers for publication in the Proceedings of an International Journal. The authors must follow the instructions given in the document for the papers to be published. You can use this document as both an instruction set and as a template into which you can type your own text.
Keywords:
Wireless sensor network, network life span, cluster-based routing, distributed clustering, energy efficiency.
Abstract
Integrating Discrimination Prevention and Privacy Preservation into Data Mining
Sujitha S, Sreejith S
Abstract:
In information society, massive and automated data collection is required for different purposes in our daily life. There are mainly two threats for individuals whose information is published: privacy and discrimination. In data mining, decision models are mainly derived on the basis of records stored by means of various data mining methods. But there may be a risk that the extracted knowledge imposes discrimination. Many organizations collect a lot of data for decision making. The sensitive information of the individual whom the published data relate to, may be revealed, if the data owner publishes the data directly. Discrimination prevention and privacy preservation need to be ensured simultaneously in decision making process. In this paper, Discrimination Prevention Data Mining (DPDM) and Privacy Preservation Data Mining (PPDM) have been studied and their relationships have been explored. Different privacy models and its impact on the data have also been analysed.
Keywords:
Anti-discrimination, discriminatory attribute, classification rule, rule generalization, rule protection, k-anonymity.
Abstract
The Efficient Spatial Index for Spatial Information Retrieval
Eldhose Paul, Ierin Babu
Abstract:
Spatial queries, such as nearest neighbour retrieval and range search, include only conditions on geometric properties. A spatial database handles multidimensional objects and offers fast access to those objects based on different selection criteria. Many applications demand a novel form of queries to discover the objects that considering both a spatial predicate, and a predicate on their associated texts on now-a-days. For example, considering all the hotels, a user would request for the hotel that is the nearest among those whose menus contain the specified keywords all at the same time. Here deals with the new method called efficient inverted list that extends the conventional inverted index to handle with multidimensional data, and arises with algorithms that can response nearest neighbor queries with keywords in real time.
Keywords:
Spatial inverted list, spatial queries, IR2-tree, multidimensional data.
Abstract
Impact and Application of Sentiment Analysis using Twitter: a survey
Hema Krishnan, M. Sudheep Elayidom, T. Santhanakrishnan
Abstract:
The exponential growth of internet over the past decade has increased millions of web pages published on every subject. Internet provides only a medium for communication between the computer and for accessing online document over this network but not to organize this large amount of data. There are different subject based web directories like Open Directory Project�s (ODP) Directory Mozilla (DMOZ), Yahoo etc., these directories organize web pages in hierarchy. Due to the rapid growth of web pages the categorization demands the need of machine learning technique to automatically maintain the web page directory service. To assign a web page into a class the textual information in the page serves as a hint. Here we propose a method which uses an extended TDW scheme for feature representation and a na�ve Bayesian to build the classification model. The web page categorization provides a wide range of advantages that ranges from knowledgebase construction, to improve the quality of web results, web content filtering, focused crawling etc.
Keywords:
Categorization, Extended TDW Matrix, Naive Bayesian, Feature selection.
Abstract
Web Page Categorization with Extended TDW Scheme
Arun P R, Sumesh M S, Eldhose P Sim
Abstract:
The exponential growth of internet over the past decade has increased millions of web pages published on every subject. Internet provides only a medium for communication between the computer and for accessing online document over this network but not to organize this large amount of data. There are different subject based web directories like Open Directory Project�s (ODP) Directory Mozilla (DMOZ), Yahoo etc., these directories organize web pages in hierarchy. Due to the rapid growth of web pages the categorization demands the need of machine learning technique to automatically maintain the web page directory service. To assign a web page into a class the textual information in the page serves as a hint. Here we propose a method which uses an extended TDW scheme for feature representation and a na�ve Bayesian to build the classification model. The web page categorization provides a wide range of advantages that ranges from knowledgebase construction, to improve the quality of web results, web content filtering, focused crawling etc.
Keywords:
Categorization, Extended TDW Matrix, Naive Bayesian, Feature selection.
Abstract
Implementation of Correlation Techniques for the Equity Market in India
Cerene Mariam Abraham, M. Sudheep Elayidom
Abstract:
The equity market is the place where shares of listed companies can be managed by public and can be traded through exchanges. The shareholders can enjoy the financial benefits of the companies whose shares they hold. While the traditional theory tells that the factors that move stock prices are due to earnings per share, valuation multiple etc, technical factors like inflation, economic strength, substitutes etc. can also affect the rise and fall in stock market. This paper suggests three main parameters which is responsible for the up down trends in market and verifies the dependency of these three parameters by the means of correlation method in statistical analysis. Parameters like open interest, last traded price in derivatives and delivery volume in cash market are taken into account for the same. By the means of correlation function, the dependency of these three parameters with each other have been studied and observed to be correlated.
Keywords:
Financial Market, Derivatives, Earnings per Share, open interest, Last Traded Price, Exchange-Traded Funds.
Abstract
Leveraging Cloud for Large Scale Business Transactions – A Survey
Neethu Mohandas, M Sudheep Elayidom, Sasi Gopalan
Abstract:
Leveraging cloud for the benefit of today�s business world is a significant area to work on. This paper gives insight on some of the works done so far that involves migration of business applications to cloud and on the performance enhancement it brings compared to the previous on-premise business applications. Big Data analytics is a hot topic in this domain, and this paper surveys some works done so far on Big Data analytics using the cloud framework. A brief introduction about the Cloud and Big Data and their significance in today�s business world is given. Our main motive is to give a brief overview of the effect of �the Cloud� and �Big Data� on today�s business.
Keywords:
On-premise, Migration, Cloud, Big Data analytics.
Abstract
Early Diagnosis and Detection of Cancer using Artificial Neural Network based Prediction Algorithm
Alavi Kunhu, Nisi K, Sadeena Sabnam, Majida. A
Abstract:
Programmed cell death is called apoptosis and when this process breaks down, cancer begins to form. The chance of survival and successful treatment greatly increases with the early detection of cancer. So in this paper we are proposing an artificial neural network based prediction algorithm for the early detection of cancer. In our proposed work, we divide the available cancer data records into two group called train data records and test data records. Based on a prediction algorithm, we train three different artificial neural network models to predict the abnormalities in the patient data by employing sliding window method. Later on, we use this trained networks to test data records and the results are analyzed using various metrics parameters such as sensitivity, specificity, accuracy, precision and area under curve.
Keywords:
Artificial neural networks; Sensitivity; Specificity; Accuracy; Precision.
Abstract
Hybrid DWT-DCT Video Watermarking Algorithm for Copyright Protection of Multimedia Color Videos
Alavi Kunhu, Nisi K, Sadeena Sabnam, Majida A
Abstract:
In this paper, we propose a new blind video watermarking algorithm for the copyright protection of multimedia colour videos. The novelty in the presented approach consists in designing a hybrid Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) based digital video watermarking. The distortion caused by watermarking is assessed by using peak signal to noise ratio (PSNR) and similarity structure index measure (SSIM) and robustness against different types of attacks have been assessed using Stirmark. The proposed video watermarking algorithm provides better imperceptibility in harmony with the human visual system and offers higher robustness against signal processing attacks.
Keywords:
Video watermarking; Copyright protection; DWT; DCT; PSNR; SSIM.
Abstract
Video Coding using Separated Sign Coding and Motion Compensation
Mr.Nithin.S.S, Dr.L.Padma Suresh
Abstract:
Haar wavelet is the most important mathematical tool which has stimulated many developments, particularly in signal and image processing. The main advantage of Haar is the multi-resolution properties. The major challenge in this video coding is motion management using HWT. To reduce the cost of storage and the bandwidth transmission of video file, a new method is proposed in this paper. The new method is the sub-band coding approach that employs Haar Wavelet Transform (HWT) and is based on a separate sign coding (SSC) from wavelet coefficients amplitude. To avoid the problem created by the lack of invariance translation, we use the method motion compensation (MC) technique.Results shows that PSNR become good compared to other techniques.
Keywords:
Haar Wavelet transform (HWT), transform, video coding, Motion compensation, SSC.
Abstract
Survey on Data Preprocessing Techniques for Fuzzy Association Rule Mining
ViniVijayan, Dr. M. Sudheep Elayidom
Abstract:
Data mining is the technique to find previously unknown and useful knowledge from a large database. Many association rule mining algorithms are introduced for data mining process. If we integrate the interesting computational logic of fuzzy set with association rule mining, it is called as Fuzzy Association Rule Mining (FARM).FARM will provide a better result for association rule mining strategy. It needs some preprocessing of data set before apply it to FARM. �������The main data preprocessing task in data mining is the numerical attribute management. . Most of the algorithms require the discretization of numerical attributes by splitting the continuous range of values into intervals. The data preprocessing techniques classify the entire data set in to fuzzy clusters. In this paper, we are summarized a number of suggested techniques for data preprocessing. And sort out an algorithm which seems to be the optimal in the group.
Keywords:
Data mining, Apriori algorithm, association rule, fuzzy set, fuzzy rule mining.
Abstract
Efficient student learning analysis based on Q-learning approach
Dr.M.Balamurugan, S.Venkatesh
Abstract:
The main objective of our process is to identify the student learning capacity and based on the marks and how to provide the teaching mechanisms of schools in centum marks. Especially to analyze the student learning capacity of physics subject. Provide that the real time student physics marks information as input. Based on the marks of the students we are going to identify the student capacity and predict the teaching methodology to that particular student. To identify the best learning method is used for Q-Learning algorithm. Q-Learning algorithm is a model free Reinforcement learning algorithm. It is mainly to identify the optimized solution. The optimized solution is identified based on the marks taken by the students in the exams.
Keywords:
Cognitive styles, Q-Learning, questionnaire, heuristics, inferential, relational, Correlation Analysis.
Abstract
Bigdata: Hadoop Cluster Deployment on Arm Architecture
Vijaykumar S, Dr. M. Balamurugan, Ranjani K
Abstract:
This Research work is the initiation of provisioning low power intensity, clustered architecture to ensure the calibre Big Data Analytics Framework. As a part of work, we made a trial on ARM Architecture that prolonging with compact single board computer called Raspberry-pi which had extensive supporting architecture towards embedded systems. Hence we initiate this proposal to bring an approach for Fault tolerance and reliable process with the help of Hadoop framework. Primitive we delivers a successful implementation of single node cluster on ARM. As a result, we can make high level data management provisioning system with low cost value.
Keywords:
Include at least 4 keywords or phrases.
Abstract
A Third Eye Investigator Utilizing Vibration Energy Harvesting
Chithra .P, Adeeb Ahammed .P, Eldhose .P .Sim
Abstract:
Interest in through-wall imaging has been surging for about a decade. Earlier work in this domain focused on simulations and modeling. This paper explores the potential of using Wi-Fi signals and recent advances in MIMO communications to build a device that can capture the motion of humans behind a wall and in closed rooms. The objective of this paper is to enable a see-through-wall technology that is low-bandwidth, low-power, compact, and accessible to non-military entities. To this end, the paper introduces Wi-Vi, a see-through-wall device that employs Wi-Fi signals in the 2.4 GHz ISM band. Wi-Vi limits itself to a 20 MHz-wide Wi-Fi channel, and avoids ultra-wideband solutions used today to address the flash effect. It also disposes of the large antenna array, typical in past systems, and uses instead a smaller 3-antenna MIMO radio. More than a decade of research in the field of thermal, motion, vibration and electromagnetic radiation energy harvesting has yielded increasing power output and smaller embodiments. In this paper we have introduced Vibration Energy Harvesting (VEH).ie. The energy produced due to vibrations are converted into electricity.
Keywords:
Seeing Through Walls, Wireless, MIMO, Gesture Based User Interface, Electrostatic converters, VEH, Electrets.
Abstract
Mining Queries to find the Nearest Neighbors
Alma Mary Margret, Kishore Sebastian, Liz Maria Mathew
Abstract:
Mobile devices with Geo positioning capabilities can send location-dependent queries to Location Based Services (LBS). To protect privacy of user, the location must not be disclosed to the server. Existing solutions utilize a trusted anonymizer between the users and the LBS. But the users are not protected from correlation attacks. Private Information Retrieval protocol is used to provide privacy to user location. This approach is secure, but it is expensive in terms of computational overhead. This paper specifies the use of Voronoi diagrams to solve the problem of secure outsourced kNN queries. Itemset with high profits are mined from the database. The itemset will be the query to the service provider. As the data owners do not have the infrastructure to process the query, so the dataset is outsourced to a cloud service provider. Secure voronoi cell enclosure evaluation is done to find the nearest neighbour.
Keywords:
Location Based Service, Point of Interest, Anonymity, Private Information Retrieval, Voronoi Diagrams.
Abstract
A Study on Network Steganography Methods
Amritha Sekhar, Manoj Kumar G., Prof. (Dr.) M. Abdul Rahiman
Abstract:
Steganography is a technology used since years for the communication of messages secretly. These secret messages are put inside honest carriers. Carriers can be digital images, audio files, video files and so on. The limitation in sending concealed longer messages has been overcoming by the inclusion of video files as carriers. Popular internet services such as Skype, BitTorrent, Google Suggest, and WLANs are targets of information hiding techniques. Nowadays, plotters are not only using the carriers but also the protocols for communication that regulate the path of the carrier through the Internet. This technique is named Network Steganography.
Keywords:
Protocol Steganography, Network Steganography, Cryptography.
Abstract
Audio Steganography Scheme to Advance the Security of Data in Hybrid Cloud
Hasna Parveen O H
Abstract:
Steganography is the art of science dealing with the hiding of secret data inside an image, audio, video or text files. One of the foremost differences between the steganography and cryptography is that even as we using cryptography technique we can�t spot the original data but we discern that data are hiding as encrypted format. But despite the fact that we are using steganography we can�t sense the charisma of secret data. Hence it is healthier to use steganographic approach to hide data in hybrid cloud to guarantee the security. In our paper it is about how to develop the security of data in the hybrid cloud. A hybrid cloud consists in cooperation of public and private data. Here the public data can be honestly accessed by the normal users devoid of any corroboration. But in the turn of a private data, it is obscured using an audio file. This private data can only evident to the owner and the personage whom the owner wishes to share the data. Hybrid cloud furthermore consist a section called OTP generator which engender one time password. While the owner tries to retrieve the data then a password is send to him. After the verification he can disengage the secret data in a private browser. So when hackers try to attack the cloud or private data he will be able to see simply the audio file. He can�t be aware of the presence of data. This approach is mainly based on the property of HAS.
Keywords:
Steganography, OTP generator, Hybrid cloud, HAS.
Abstract
Overview of Image Retrieval Techniques
Girija O K, M.Sudheep Elayidom
Abstract:
As the tremendous growth in the volume of images as well as the widespread application in multiple fields, the requirements for development of image retrieval techniques are enhanced. The image retrieval is an interesting and rapidly growing methodology in all fields. It is an effective and well organized approach for retrieving the image. In the other end, image mining is the arising concept which can be used to extract potential information from the collection of images. Image mining is the process of searching and discovering valuable information and knowledge from large volumes of data. It is an extension of data mining techniques for images. It handles the hidden knowledge extraction, image data association and additional patterns which are not clearly accumulated in the images. In this paper we provide an overview of the fundamental theories and emerging techniques for Image Retrieval and image mining, as well as several extended work in these areas.
Keywords:
Image retrieval, Image features, Extraction, Color models, Texture, Shape, Content based image retrieval.
Abstract
Inviolable Data mining in Cloud using AES and Paillier Cryptosystem
Nahan Rahman M.K.
Abstract:
An enormous amount of composite and permeate digital data, frequently figured as big data has been multiplied at a exponential rate with the promotion in technology. To stem the big data with the typical storage systems are not possible and canvassing the big data by using the traditional study tools has become a dispute to the analyzers The apportion of the big data to the cloud-lets or hosts is carried out by cloud computing .cloud computing dissolves the trouble of handling, storing and inspecting big data. Even though cloud computing is the logical solution for the problem of big data interpretation and storage, there shows a immense liability to the security of big data storage in cloud computing, demands more consideration. Major concern in storing big data in cloud environment is data privacy. Intrusion based on data-mining is the major obstacle which is needed to be encountered very seriously. This paper recommends a inviolable data mining way such as k means algorithm and also describes a secure and efficient encryption technique AES. Upon these encrypted data homomorphic computations are performed by following paillier cryptosystem. This looks forward for an inviolable system as there is a chance for the intruder�s attempt for becoming failed.
Keywords:
Cloud computing, K-means, AES, homomorphic encryption.
Abstract
Non-expanded Share Generation Algorithm using RGVSS
Shyni T S, Anusree L
Abstract:
This paper presents a new algorithm for non-expanded share generation using RGVSS. In random grid visual cryptography scheme each pixel is treated as a grid. In probability based RGVSS the black appearing probability of each pixel with respect to cover image is used to generate non-expanded meaningful shares. The proposed method is modified form of probability based RGVSS. Here thresholding is applied to each of the blank shares to reveal its content. On overlapping blank shares the secret image is revealed. This will generate high contrast non-expanded shares which give almost perfect reconstruction of secret image.
Keywords:
High contrast shares, Non-expanded shares, Random grids, Visual cryptography.