G. Aghila

S. Shanmugapriyaa, K. S. Kuppusamy, G. Aghila

This paper focuses on building a blog search engine which doesn't focus only on keyword search but includes extended search capabilities. It also incorporates the blog-post concept clustering which is based on the category extracted from the blog post semantic content analysis. The proposed approach is titled as "BloSen (Blog Search Engine)". It involves in extracting the posts from blogs and parsing them to extract the blog elements and store them as fields in a document format. Inverted index is being built on the fields of the documents. Search is induced on the index and requested query is processed based on the documents so far made from blog posts. It currently focuses on Blogger and Wordpress hosted blogs since both these hosting services are the most popular ones in the blogosphere. The proposed BloSen model is experimented with a prototype implementation and the results of the experiments with the user's relevance cumulative metric value of 95.44% confirms the efficiency of the proposed model.

K. S. Kuppusamy, Leena Mary Francis, G. Aghila

With the prolific growth in usage of smartphones across the spectrum of people in the society it becomes mandatory to handle and configure these devices effectively to achieve optimum results from it. This paper proposes a context sensitive model termed COSMOS (COntext Sensitive MOdel for Smartphones) for configuring the smartphones using multifactor analysis with the help of decision trees. The COSMOS model proposed in this paper facilitates the configuration of various smartphone settings implicitly based on the user's current context, without interrupting the user for various inputs. The COSMOS model also proposes multiple context parameters like location, scheduler data, recent call log settings etc to decide the appropriate settings for the smartphones. The proposed model is validated by a prototype implementation in the Android platform. Various tests were conducted in the implementation and the settings relevancy metric value of 90.95% confirms the efficiency of the proposed model.

K. S. Kuppusamy, Leena Mary Francis, G. Aghila

The mammoth growth in the information technology sector in terms of both quantity and pervasiveness has opened up a Pandora's Box of issues which are relevant in technical and social aspects. This paper attempts to address one of the critical issues among them which is concerned with the proper utilization of computer systems and mobile devices by children and teens. This paper proposes a model termed "RePort (Remote Parental Control System using Smartphones)" which is aimed towards monitoring the access behaviour of computers and smartphones in general and internet to be specific, by teens and children in a private environment. The model is built such that the access behaviour shall be monitored from a remote location with the help of smartphone devices. The access- characteristics are modelled using various parameters in four different layers of the model.The proposed model is validated with a prototype implementation in the Android platform for smartphones and as a background service for computer systems. Various experiments were conducted on the prototype implementation and results of the experiments validate the efficiency of the proposed model with respect to user's relevancy metric which is computed as 93.46%.

K. S. Kuppusamy, G. Aghila

The evaluation of web pages against a query is the pivot around which the Information Retrieval domain revolves around. The context sensitive, semantic evaluation of web pages is a non-trivial problem which needs to be addressed immediately. This research work proposes a model to evaluate the web pages by cumulating the segment scores which are computed by multidimensional evaluation methodology. The model proposed is hybrid since it utilizes both the structural semantics and content semantics in the evaluation process. The score of the web page is computed in a bottom-up process by evaluating individual segment's score through a multi-dimensional approach. The model incorporates an approach for segment level annotation. The proposed model is prototyped for evaluation; experiments conducted on the prototype confirm the model's efficiency in semantic evaluation of pages.

P. Thiyagarajan, G. Aghila, V. Prasanna Venkatesan

Any Universal Steganalysis algorithm developed should be tested with various stego-images to prove its efficiency. This work is aimed to build the stego-image database which is obtained by implementing various RGB Least Significant Bit Steganographic algorithms. Though there are many stego-images sources available on the internet it lacks in the information such as how many rows has been infected by the steganography algorithms, how many bits have been modified and which channel has been affected. These parameters are important for Steganalysis algorithms and it helps to rate its efficiency. Images are chosen from board categories such as animals, nature, person to produce variety of Stego-Image.

P. Thiyagarajan, G. Aghila, V. Prasanna Venkatesan

Steganography is the art of hiding secret information in media such as image, audio and video. The purpose of steganography is to conceal the existence of the secret information in any given medium. This work aims at strengthening the security in steganography algorithm by generating dynamic pattern in selection of indicator sequence. In addition to this dynamicity is also encompassed in number of bits embedded in data channel. This technique has been implemented and the results have been compared and evaluated with existing similar techniques.

P. Thiyagarajan, G. Aghila, V. Prasanna Venkatesan

In spite of existence of many standard security mechanisms for ensuring secure e-Commerce business, users still fall prey for online attacks. One such simple but powerful attack is 'Phishing'. Phishing is the most alarming threat in the e-Commerce world and effective anti-phishing technique is the need of the hour. This paper focuses on a novel anti-phishing browser plug-in which uses information hiding technique - Steganography. A Robust Message based Image Steganography (RMIS) algorithm has been proposed. The same has been incorporated in the form of a browser plug-in (safari) called Pixastic. Pixastic is tested in an online banking scenario and it is compared with other well-known anti-phishing plug-in methods in practice. Various parameters such as robustness, usability and its behavior on various attacks have been analysed. From experimental results, it is evident that our method Pixastic performs well compared to other anti-phishing plug-ins.

P. Thiyagarajan, G. Aghila, V. Prasanna Venkatesan

The major threat in cyber crime for digital forensic examiner is to identify, analyze and interpret the concealed information inside digital medium such as image, audio and video. There are strong indications that hiding information inside digital medium has been used for planning criminal activities. In this way, it is important to develop a steganalysis technique which detects the existence of hidden messages inside digital medium. This paper focuses on universal image steganalysis method which uses RGB to HSI colour model conversion. Any Universal Steganalysis algorithm developed should be tested with various stego-images to prove its efficiency. The developed Universal Steganalysis algorithm is tested in stego-image database which is obtained by implementing various RGB Least Significant Bit Steganographic algorithms. Though there are many stego-image sources available on the internet it lacks in the information such as how many rows has been infected by the steganography algorithms, how many bits have been modified and which channel has been affected. These parameters are important for Steganalysis algorithms and it helps to rate its efficiency. Proposed Steganalysis using Colour Model has been tested with our Image Database and the results were affirmative.

K. S. Kuppusamy, Leena Mary Francis, G. Aghila

Though World Wide Web is the single largest source of information, it is ill-equipped to serve the people with vision related problems. With the prolific increase in the interest to make the web accessible to all sections of the society, solving this accessibility problem becomes mandatory. This paper presents a technique for making web pages accessible for people with low vision issues. A model for making web pages accessible, WILI (Web Interface for people with Low-vision Issues) has been proposed. The approach followed in this work is to automatically replace the existing display style of a web page with a new skin following the guidelines given by Clear Print Booklet provided by Royal National Institute of Blind. "Single Click Solution" is one of the primary advantages provided by WILI. A prototype using the WILI model is implemented and various experiments are conducted. The results of experiments conducted on WILI indicate 82% effective conversion rate.

K. S. Kuppusamy, G. Aghila

The World Wide Web caters to the needs of billions of users in heterogeneous groups. Each user accessing the World Wide Web might have his / her own specific interest and would expect the web to respond to the specific requirements. The process of making the web to react in a customized manner is achieved through personalization. This paper proposes a novel model for extracting keywords from a web page with personalization being incorporated into it. The keyword extraction problem is approached with the help of web page segmentation which facilitates in making the problem simpler and solving it effectively. The proposed model is implemented as a prototype and the experiments conducted on it empirically validate the model's efficiency.

K. S. Kuppusamy, G. Aghila

With the tremendous growth in the information communication sector, the mobile phones have become the prime information communication devices. The convergence of traditional telephony with the modern web enabled communication in the mobile devices has made the communication much effective and simpler. As mobile phones are becoming the crucial source of accessing the contents of the World Wide Web which was originally designed for personal computers, has opened up a new challenge of accommodating the web contents in to the smaller mobile devices. This paper proposes an approach towards building a model for rendering the web pages in mobile devices. The proposed model is based on a multi-dimensional web page segment evaluation model. The incorporation of personalization in the proposed model makes the rendering user-centric. The proposed model is validated with a prototype implementation.

K. S. Kuppusamy, Senthilraja. R, G. Aghila

The smartphone usage among people is increasing rapidly. With the phenomenal growth of smartphone use, smartphone theft is also increasing. This paper proposes a model to secure smartphones from theft as well as provides options to access a smartphone through other smartphone or a normal mobile via Short Message Service. This model provides option to track and secure the mobile by locking it. It also provides facilities to receive the incoming call and sms information to the remotely connected device and enables the remote user to control the mobile through SMS. The proposed model is validated by the prototype implementation in Android platform. Various tests are conducted in the implementation and the results are discussed.

K. S. Kuppusamy, G. Aghila

The web page usage mining plays a vital role in enriching the page's content and structure based on the feedbacks received from the user's interactions with the page. This paper proposes a model for micro-managing the tracking activities by fine-tuning the mining from the page level to the segment level. The proposed model enables the web-master to identify the segments which receives more focus from users comparing with others. The segment level analytics of user actions provides an important metric to analyse the factors which facilitate the increase in traffic for the page. The empirical validation of the model is performed through prototype implementation.

K. S. Kuppusamy, G. Aghila

With the phenomenal growth of content in the World Wide Web, the diversity of user supplied queries have become vivid. Searching for people on the web has become an important type of search activity in the web search engines. This paper proposes a model named "We.I.Pe" to identify people on the World Wide Web using e-mail Id as the primary input. The approach followed in this research work provides the collected information, based on the user supplied e-mail id, in an easier to navigate manner. The grouping of collected information based on various sources makes the result visualization process more effective. The proposed model is validated by a prototype implementation. Experiments conducted on the prototype implementation provide encouraging results

K. S. Kuppusamy, G. Aghila

The results rendered by the search engines are mostly a linear snippet list. With the prolific increase in the dynamism of web pages there is a need for enhanced result lists from search engines in order to cope-up with the expectations of the users. This paper proposes a model for dynamic construction of a resultant page from various results fetched by the search engine, based on the web page segmentation approach. With the incorporation of personalization through user profile during the candidate segment selection, the enriched resultant page is constructed. The benefits of this approach include instant, one-shot navigation to relevant portions from various result items, in contrast to a linear page-by-page visit approach. The experiments conducted on the prototype model with various levels of users, quantifies the improvements in terms of amount of relevant information fetched.

K. S. Kuppusamy, G. Aghila

The tremendous amount of increase in the quantity of information resources available on the web has made the total time that the user spends on a single page very minimal. Users revisiting the same page would be able to fetch the required information much faster if the information that they consumed during the previous visit(s) gets presented to them with a special style. This paper proposes a model which empowers the users to mark the content interesting to them, so that it can be identified easily during successive visits. In addition to the explicit marking by the users, the model facilitates implicit marking based on the user preferences. The prototype implementation based on proposed model validates the model's efficiency.

K. S. Kuppusamy, G. Aghila

The result listing from search engines includes a link and a snippet from the web page for each result item. The snippet in the result listing plays a vital role in assisting the user to click on it. This paper proposes a novel approach to construct the snippets based on a semantic evaluation of the segments in the page. The target segment(s) is/are identified by applying a model to evaluate segments present in the page and selecting the segments with top scores. The proposed model makes the user judgment to click on a result item easier since the snippet is constructed semantically after a critical evaluation based on multiple factors. A prototype implementation of the proposed model confirms the empirical validation.

K. S. Kuppusamy, G. Aghila

The evaluation of a web page with respect to a query is a vital task in the web information retrieval domain. This paper proposes the evaluation of a web page as a bottom-up process from the segment level to the page level. A model for evaluating the relevancy is proposed incorporating six different dimensions. An algorithm for evaluating the segments of a web page, using the above mentioned six dimensions is proposed. The benefits of fine-granining the evaluation process to the segment level instead of the page level are explored. The proposed model can be incorporated for various tasks like web page personalization, result re-ranking, mobile device page rendering etc.

K. S. Kuppusamy, G. Aghila

In the view of massive content explosion in World Wide Web through diverse sources, it has become mandatory to have content filtering tools. The filtering of contents of the web pages holds greater significance in cases of access by minor-age people. The traditional web page blocking systems goes by the Boolean methodology of either displaying the full page or blocking it completely. With the increased dynamism in the web pages, it has become a common phenomenon that different portions of the web page holds different types of content at different time instances. This paper proposes a model to block the contents at a fine-grained level i.e. instead of completely blocking the page it would be efficient to block only those segments which holds the contents to be blocked. The advantages of this method over the traditional methods are fine-graining level of blocking and automatic identification of portions of the page to be blocked. The experiments conducted on the proposed model indicate 88% of accuracy in filtering out the segments.