Qualification: 
Ph.D, M.Tech, BE
sajeevgp@am.amrita.ac.in

Dr. Sajeev currently serves as Associate Professor at Department of Computer Science and Engineering, School of Engineering, Amritapuri Campus. He received his Ph. D. from the National Institute of Technology Calicut, India. His research interests include Open Systems, Web Cache Systems, P2P Networking, Traffic Measurement & Modeling and Web Server Acceleration, and has published many research papers in international journals and conferences. He is the reviewer of International Journal of Computers & Electrical Engineering, Elsevier and the TPC Member of IEEE organised  conferences. 

Publications

Publication Type: Conference Proceedings

Year of Publication Title

2018

K. D. Raj and Dr. Sajeev G. P., “A Community Based Web Summarization in Near Linear Time”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 962-968., 2018.[Abstract]


The rapid growth of web users searching for their topics of interest on web, pose challenges to the system, in particular to the search engines. Web content summarization is one crucial application which helps in leveraging the performance of search engines. However summarizing the totality of web content is a laborious task due to the massiveness of web data. Segmenting the web into communities and extracting only relevant pages from those communities for summarization could be a viable solution. This paper presents a novel technique for web summarization by extracting pages of the web according to their degree of authenticity. For this, a large collection of pages are crawled from the web and the communities are identified in linear time based on edge streaming in graph. Then, through link analysis, more authentic pages are identified for summarization. The proposed method is validated through experimentation using real and synthetic data. The results indicate that the proposed model is useful for building an optimized search engine.

More »»

2018

R. M. Chandran and Dr. Sajeev G. P., “A Novel Collaborative Caching Framework for Peer-to-Peer Networks”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 988-994., 2018.[Abstract]


Caching is a well accepted method for curtailing the Internet traffic generated by peer to peer (P2P) applications. In general, any form of caching suffers from cache pollution. The pollution is severe in P2P cache system especially when the caches act collaboratively. This paper proposes a new collaborative caching framework utilizing intelligent cache updating scheme, for controlling the cache pollution, without compromising in performance. We validate the proposed system through simulations using real world data, in comparison with other caching algorithms. Test results indicate that the proposed framework drastically reduces the cache pollution compared to existing schemes.

More »»

2018

J. Cheriyan and Dr. Sajeev G. P., “SpreadMax: A Scalable Cascading Model for Influence Maximization in Social Networks”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 1290-1296., 2018.[Abstract]


The rumor spreading and influence maximization are two important forms of social network communication. Many social network applications utilize influence maximization for finding the seed node. The most common approach for influence maximization is greedy, which delivers an optimal solution. However, the greedy approach has high computational overhead and offers a limited spreading capability. We address this problem by proposing a novel framework, SpreadMax, for maximizing the spreading process with reduced computational overhead. Our model consists of two phases. In the first phase, we identify seed nodes using hierarchical reachability approach and these designated seed nodes spread infection during the second phase. The proposed model is validated through experiments using real-world data, in comparison with existing methods. We observed that the SpreadMax technique performs better in maximizing the influence.

More »»

2018

K. K. Samhitha, Dr. Sajeev G. P., and Jayasree Narayanan, “A Novel Community Detection Method for Collaborative Networks”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 866-872., 2018.[Abstract]


Community structure prevails in network graphs like social networks, web graphs and collaborative networks. Clique percolation is one popular method used for unfolding the community structure in networks. However, clique percolation method is inefficient as the computational time is high for merging the identified cliques. This paper proposes a novel technique for detecting overlapping community structure by addressing the problem of clique merging. We reduce the overall time for community detection by applying edge streaming technique. The proposed method is validated through experiments using real and synthetic data in comparison with conventional clique percolation algorithm. The performance parameters such as execution time and goodness of the cluster are used for comparison and the results are promising. This model is suitable for community detection in collaborative network.

More »»

2018

T. R. K. Prasad, Jayakumar P., and Dr. Sajeev G. P., “A K-Clique Based Clustering Protocol for Resource Discovery in P2P Network”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 2475-2480, 2018.[Abstract]


Data transfer amongst peers in a network without a central authority to regulate traffic, is on the ascendancy in the recent years. In this paper, we propose a k-clique based overlay network formation using multi key-single value pair mapping mechanism within a peer to peer network. This clique based model aims to discover resources of the same metadata type within a cluster of subnet with a minimum of hops as possible subject to the nodes having certain properties. The discovery of a subset of resources sharing similar characteristics is essential in the context of requirements being dynamic, in fields related to Internet of Things and Cloud systems. The simulated experiment validates our approach as it discovers resources in very less number of hops.

More »»

2018

A. R. Kurup and Dr. Sajeev G. P., “Task Personalization for Inexpertise Workers in Incentive Based Crowdsourcing Platforms”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 286-292., 2018.[Abstract]


Crowdsourcing is an emerging technology which enables human workers to perform the task that cannot be done using automated tools. The crucial constituent of crowdsourcing platform is human workers. Since crowdsourcing platforms are overcrowded, workers find difficulty in selecting a suitable task for them. Employing task recommendation systems could improve this situation. However, task recommendation for new and inexpert workers is not explored well. We address this problem by designing a task recommendation model using skill taxonomy and participation probability of existing expert workers. The proposed model is validated through experimentation with both real and synthetic dataset

More »»

Publication Type: Conference Paper

Year of Publication Title

2017

A. R. Kurup and Dr. Sajeev G. P., “Task recommendation in reward-based crowdsourcing systems”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


Crowdsourcing systems are distributed problem solving platforms, where small tasks are channelled to a crowd in the form of open calls for solutions. Reward based crowdsourcing systems tries to attract the interested and capable workers to provide solutions in return for monetary rewards. We study the task recommendation problem in reward based crowdsourcing platforms, where we leverage both implicit and explicit features of the worker-reward and worker-task attributes. Given a set of workers, set of tasks, participation, winner attributes, we intend to recommend tasks to workers by exploiting interactions between tasks and workers. Two models based on worker-reward based features and worker task based features are presented. The proposed approach is compared with multiple related techniques using real world dataset.

More »»

2017

P. Das, Jisha R. C., and Dr. Sajeev G. P., “Adaptive web personalization system using splay tree”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


Web personalization helps in understanding the user interests and creating customized experiences for users. However the user preferences changes dynamically over a period. In order to adapt with the changing information needs of the user, we have developed a novel web personalization system that captures the user changing interest by analyzing the timing information. We use splay tree, which is a self-adaptive data structure, for tracking the changing trends of the users. The proposed web personalization model is validated by building a simulation model, with real and synthetic dataset, and the quality of results are promising.

More »»

2017

K. Pavani and Dr. Sajeev G. P., “A Novel Web Crawling Method for Vertical Search Engines”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


The main goal of focused web crawlers is to retrieve as many relevant pages as possible. However, most of the crawlers use page rank algorithm to lineup the pages in the crawler frontier. Since the page rank algorithm suffers from the drawback of “Richer get rich phenomenon”, focused crawlers often fail to retrieve the hidden relevant pages. This paper presents a novel approach for retrieving the hidden and relevant pages by combining rank and semantic similarity information. The model is validated by crawling the real web with different topics and the results are promising.

More »»

2017

P. Devika, Jisha R. C., and Dr. Sajeev G. P., “A novel approach for book recommendation systems”, in 2016 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2016, Chennai, India, 2017.[Abstract]


Recommendation systems are widely used in ecommerce applications. A recommendation system intends to recommend the items or products to a particular user, based on user's interests, other user's preferences, and their ratings. To provide a better recommendation system, it is necessary to generate associations among products. Since e-commerce and social networking sites generates massive data, traditional data mining approaches perform poorly. Also, the pattern mining algorithm such as the traditional Apriori suffers from high latency in scanning the large database for generating association rules. In this paper we propose a novel pattern mining algorithm called as Frequent Pattern Intersect algorithm (FPIntersect algorithm), which overcomes the drawback of Apriori. The proposed method is validated through simulations, and the results are promising.

More »»

2016

M. Annam and Dr. Sajeev G. P., “Entropy based informative content density approach for efficient web content extraction”, in Fourth International Symposium on Women in Computing and Informatics (WCI-2016), International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016.[Abstract]


Web content extraction is a popular technique for extracting the main content from web pages and discards the irrelevant content. Extracting only the relevant content is a challenging task since it is difficult to determine which part of the web page is relevant and which part is not. Among the existing web content extraction methods, density based content extraction is one popular method. However density based methods, suffer from poor efficiency, especially when the pages containing less information and long noise. We propose a web content extraction technique build on Entropy based Informative Content Density algorithm (EICD). The proposed EICD algorithm initially analyses higher text density content. Further, the entropy-based analysis is performed for selected features. The key idea of EICD is to utilize the information entropy for representing the knowledge that correlates to the amount of informative content in a page. The proposed method is validated through simulation and the results are promising. More »»

2016

Dr. Sajeev G. P. and Ramya, P. T., “Effective web personalization system based on time and semantic relatedness”, in Fourth International Symposium on Women in Computing and Informatics (WCI-2016), International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, India, 2016.[Abstract]


The key aspect in building a Web personalization system is the user's navigational pattern. However, the navigational pattern alone is insufficient to capture the user's interest and behavior. This paper proposes a novel web personalization system that accepts the timing information, semantic information along with the navigational pattern, and classifies the users according their interest and behavior on the site. The proposed model is validated by constructing a Web personalization model using the real and synthetic data and the results are promising. More »»

2016

TR. Krishnaprasad and Dr. Sajeev G. P., “A novel method for resource discovery from a range based request in a P2P network”, in Symposium on Emerging Topics in Computing and Communications (SETCAC'16), International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, India, 2016.[Abstract]


Peer to Peer (P2P) systems have increased the curiosity and pathways for people to discover and share the resources. While various methods have been proposed in the discovery of discrete value based resources, there is also a surging interest in discovering a range of resources for a given request. This work is a novel design of a P2P network that adheres to range requests and seeks to discover the resources sought for in the request. The proposed model seeks to find out the range of resource values from within a P2P network of nodes that are in a circular overlay structure. The validation of the design reaches the conclusion that the proposed model increases in efficiency as the number of hubs increases with respect to discovering a range of resources in the hubs.

More »»

2016

Dr. Sajeev G. P. and Nair, L. M., “LASER: A novel hybrid peer to peer network traffic classification technique”, in Fourth International Symposium on Women in Computing and Informatics (WCI-2016), International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016.[Abstract]


The popularity of Peer-to-peer (P2P) applications have shown a massive growth in recent times, and P2P traffic contributes considerably to the today's internet traffic. For efficient network traffic management and effective malware detection, P2P traffic classification is indispensable. This paper proposes LASER, Longest Common Subsequence (LCS)-based Application Signature ExtRaction technique, algorithm, a novel hybrid network traffic classification technique which classifies the P2P traffic into malicious P2P and non-malicious P2P traffic. The proposed classifier analyzes the header information for creating a communication module. Further, the signature is extracted from the payload information. We build the classifier by aggregating the information of header and the payload. The proposed hybrid classifier is analyzed for its performance and the results are promising. More »»

2015

Dr. Sajeev G. P. and M, R. Chandran, “Intelligent Pollution Controlling Mechanism for Peer to Peer Caches”, in Proceedings of the 2015 Seventh International Conference on Computational Intelligence, Modelling and Simulation (CIMSim2015), 2015.[Abstract]


This paper addresses the problem of cache pollution in P2P (Peer-to-peer) systems. P2P traffic has a significant impact on ISPs as it accounts for more than half of the all traffic. This will cause some negative impact on the Internet like network congestion, high latency. P2P caching is an efficient method for handling this problem. Most of the P2P cache systems suffer from Cache Pollution. This research proposes an intelligent cache updation algorithm, which helps in reducing the cache pollution by using the probabilistic approach. The proposed method is evaluated in comparison with Least Frequently Used and Least Recently Used algorithms. More »»

2015

L. M. Nair and Dr. Sajeev G. P., “Internet Traffic Classification by Aggregating Correlated Decision Tree Classifier”, in Proceedings of the 2015 Seventh International Conference on Computational Intelligence, Modelling and Simulation (CIMSim2015), 2015.[Abstract]


Peer-to-Peer (P2P) traffic shows a rapid growth in recent times. For efficient malware detection and network traffic management P2P network traffic classification is essential. The existing P2P traffic classification methods includes port-based, signature-based, pattern-based, and statistics based methods. However, none of these methods proved to be effective for the traffic classification in terms of the classification accuracy. This paper proposes a novel classification technique which classifies the internet traffic into P2P and non-P2P traffic with more accuracy and less computational overhead. The proposed classifier is the flow based classifier, that analyses the behavioural patterns utilizing the correlation metric algorithm. The proposed classifier is analyzed for its performance and the results are encouraging. More »»

2015

P. T. Ramya and Dr. Sajeev G. P., “Building Web Personalization System with Time-Driven Web Usage Mining”, in Proceedings of the Third International Symposium on Women in Computing and Informatics, New York, NY, USA, 2015.[Abstract]


Web personalization is a powerful tool used for personalizing the Websites. The personalization system aims at suggesting the Web pages to the users based on their navigational patterns. Use of attributes such as time, popularity of Web objects makes the model more efficient. This paper proposes a novel Web personalization model which utilizes time attributes, such as duration of visit, inter-visiting time, burst of visit, and the user's navigational pattern. Test results indicate that the proposed model explores the user's behaviour and their interest. More »»

2010

Dr. Sajeev G. P. and Sebastian, M. P., “A scheme for adaptive web caching based on multi level object classification”, in Intelligent and Advanced Systems (ICIAS), 2010 International Conference on, 2010.[Abstract]


Multi-level classification of web objects in caching is relatively an unexplored area. This paper proposes a novel caching scheme which utilizes a multi-level class information. A MLR (Multinomial Logistics Regression) based classifier is constructed using the information from web logs. Simulation results confirm that the model has good prediction capability and suggest that the proposed approach can improve the performance of the cache substantially. More »»

2010

Dr. Sajeev G. P. and Sebastian, M. P., “Building a semi intelligent web cache with light weight machine learning”, in Intelligent Systems (IS), 2010 5th IEEE International Conference, 2010.[Abstract]


This paper proposes a novel admission and replacement technique for web caching, which utilizes the multinomial logistic regression (MLR) as classifier. The MLR model is trained for classifying the web cache's object worthiness. The parameter object worthiness is a polytomous (discrete) variable which depends on the traffic and the object properties. Using worthiness as a key, an adaptive caching model is proposed. Trace driven simulations are used to evaluate the performance of the scheme. Test results show that a properly trained MLR model yields good cache performance in terms of hit ratios and disk space utilization, making the proposed scheme as a viable semi intelligent caching scheme. More »»

Publication Type: Journal Article

Year of Publication Title

2013

Dr. Sajeev G. P. and Sebastian, M. P., “Building semi-intelligent web cache systems with lightweight machine learning techniques”, Computers & Electrical Engineering, vol. 39, pp. 1174–1191, 2013.[Abstract]


This paper proposes a novel admission and replacement technique for web caching, which utilizes the multinomial logistic regression (MLR) as classifier. The MLR model is trained for classifying the web cache's object worthiness. The parameter object worthiness is a polytomous (discrete) variable which depends on the traffic and the object properties. Using worthiness as a key, an adaptive caching model is proposed. Trace driven simulations are used to evaluate the performance of the scheme. Test results show that a properly trained MLR model yields good cache performance in terms of hit ratios and disk space utilization, making the proposed scheme as a viable semi intelligent caching scheme.

More »»

2010

Dr. Sajeev G. P. and Sebastian, M. P., “A novel content classification scheme for web caches”, Evolving Systems, vol. 2, pp. 101–118, 2010.[Abstract]


Web caches are useful in reducing the user perceived latencies and web traffic congestion. Multi-level classification of web objects in caching is relatively an unexplored area. This paper proposes a novel classification scheme for web cache objects which utilizes a multinomial logistic regression (MLR) technique. The MLR model is trained to classify web objects using the information extracted from web logs. We introduce a novel grading parameter worthiness as a key for the object classification. Simulations are carried out with the datasets generated from real world trace files using the classifier in Least Recently Used-Class Based (LRU-C) and Least Recently Used-Multilevel Classes (LRU-M) cache models. Test results confirm that the proposed model has good online learning and prediction capability and suggest that the proposed approach is applicable to adaptive caching. More »»

2009

Dr. Sajeev G. P. and Sebastian, M. P., “Analyzing the Long Range Dependence and Object Popularity in Evaluating the Performance of Web Caching”, International Journal of Information Technology and Web Engineering (IJITWE), vol. 4, pp. 25–37, 2009.[Abstract]


Web cache systems enhance Web services by reducing the client side latency. To deploy an effective Web cache, analysis of the traffic characteristics is indispensable. Various reported results of traffic analysis show evidences of long range dependence (LRD) in the data stream and rank distribution of the documents in Web traffic. This article analyzes Web cache traffic properties like LRD and rank distribution based on the traces collected from NLANR (National Laboratory of Applied Network Research) cache servers. Traces are processed to investigate the performance of Web cache servers and traffic patterns. Statistical tools are utilized to measure the strengths of the LRD and popularity. The Hurst parameter, which is a measure of the LRD, is estimated using various statistical methods. It is observed that the presence of LRD in the traffic is feeble and does not influence the Web cache performance. More »»

Publication Type: Book Chapter

Year of Publication Title

2011

Dr. Sajeev G. P. and Sebastian, M. P., “Analyzing the Traffic Characteristics for Evaluating the Performance of Web Caching”, in Web Engineered Applications for Evolving Organizations: Emerging Knowledge, vol. 1, Information Science Reference, 2011, pp. 196–208.[Abstract]


Web cache systems enhance Web services by reducing the client side latency. To deploy an effective Web cache, study about traffic characteristics is indispensable. Various reported results show the evidences of long range dependence (LRD) in the data stream and rank distribution of the documents in Web traffic. This chapter analyzes Web cache traffic properties such as LRD and rank distribution based on the traces collected from NLANR (National Laboratory of Applied Network Research) cache servers. Traces are processed to investigate the performance of Web cache servers and traffic patterns. Statistical tools are utilized to measure the strengths of the LRD and popularity. The Hurst parameter, which is a measure of the LRD is estimated using various statistical methods. It is observed that presence of LRD in the trace is feeble and has practically no influence on the Web cache performance. More »»