Time filter

Source Type

Rajarajeswari P.L.,Sri Krishna College of Engineering And Technology | Karthikeyan N.K.,Karpagam College of Engineering
Journal of Intelligent and Fuzzy Systems | Year: 2017

The lifetime of a Wireless Sensor Network (WSN) depends on the efficiency of the Cluster Head (CH) selection techniques that address most of the significant issues related to network management. The existing energy based CH selection mechanisms consider that all the participating sensors are trustworthy. Conversely, the trust-based CH selection schemes assume that the sensor nodes are energy efficient. But, these assumptions of energy factor or trust assessment made by the CH selection mechanisms may not be true and the Residual Energy (RE) of the sensors may not be the sole factor to identify an effective CH in a WSN. Hence, this paper presents hybrid integrated energy and trust assessment based forecasting model known as Hyper-geometric Energy Factor based Semi-Markov Prediction Mechanism (HEFSPM) for effective CH election so as to improve the lifetime of the network. From the simulation results, it is inferred that HEFSPM is superior in improving the lifetime of the network to a maximum extent of 22 than the existing CH election mechanisms considered for investigation. © 2017-IOS Press and the authors. All rights reserved.

Sreelaja N.K.,Sri Krishna College of Engineering And Technology | Vijayalakshmi Pai G.A.,PSG College of Technology
Applied Soft Computing Journal | Year: 2012

Encryption of binary images is essential since it is vulnerable to eavesdropping in wired and wireless networks. The security of data becomes important since the communications over open network occur frequently. This paper focuses on encryption of binary image using a stream cipher method. In this paper we propose an Ant Colony Optimization (ACO) based approach of generating keys for encryption. The binary image is represented in a text form and encrypted using a stream cipher method. A novel technique termed Ant Colony Optimization Key Generation Binary Image Encryption (AKGBE) algorithm employs a character code table for encoding the keys and the plain text representing the binary image. The main advantage of this approach is that it reduces the number of keys to be stored and distributed. Experimental results demonstrating AKGBE's encrypting binary images of different sizes and the comparison of its performance with other stream cipher methods are presented. © 2012 Elsevier B.V. All rights reserved.

Sreeja N.K.,Sri Krishna College of Engineering And Technology | Sankar A.,PSG College of Technology
Swarm and Evolutionary Computation | Year: 2016

Most data mining algorithms aim at discovering customer models and classification of customer profiles. Application of these data mining techniques to industrial problems such as customer relationship management helps in classification of customers with respect to their status. The mined information does not suggest any action that would result in reclassification of customer profile. Such actions would be useful to maximize the objective function, for instance, the net profit or minimizing the cost. These actions provide hints to a business user regarding the attributes that have to be changed to reclassify the customers from an undesirable class (e.g. disloyal) to the desired class (e.g. loyal). This paper proposes a novel algorithm called Hierarchical Heterogeneous Ant Colony Optimization based Action Rule Mining (HHACOARM) algorithm to generate action rules. The algorithm has been developed considering the resource constraints. The algorithm has ant agents at different levels in the hierarchy to identify the flexible attributes whose values need to be changed to mine action rules. The advantage of HHACOARM algorithm is that it generates optimal number of minimal cost action rules. HHACOARM algorithm does not generate invalid rules. Also, the computational complexity of HHACOARM algorithm is less compared to the existing action rule mining methods. © 2016 Elsevier B.V.

Sreeja N.K.,Sri Krishna College of Engineering And Technology | Sankar A.,PSG College of Technology
Applied Soft Computing Journal | Year: 2015

Abstract Classification is a method of accurately predicting the target class for an unlabelled sample by learning from instances described by a set of attributes and a class label. Instance based classifiers are attractive due to their simplicity and performance. However, many of these are susceptible to noise and become unsuitable for real world problems. This paper proposes a novel instance based classification algorithm called Pattern Matching based Classification (PMC). The underlying principle of PMC is that it classifies unlabelled samples by matching for patterns in the training dataset. The advantage of PMC in comparison with other instance based methods is its simple classification procedure together with high performance. To improve the classification accuracy of PMC, an Ant Colony Optimization based Feature Selection algorithm based on the idea of PMC has been proposed. The classifier is evaluated on 35 datasets. Experimental results demonstrate that PMC is competent with many instance based classifiers. The results are also validated using nonparametric statistical tests. Also, the evaluation time of PMC is less when compared to the gravitation based methods used for classification. © 2015 Elsevier B.V. All rights reserved.

Vidya Banu R.,Sri Krishna College of Engineering And Technology | Nagaveni N.,Coimbatore Institute of Technology
Information Sciences | Year: 2013

Data processing techniques and the growth of the internet have resulted in a data explosion. The data that are now available may contain sensitive information that could, if misused, jeopardise the privacy of individuals. In today's web world, the privacy of personal and personal business information is a growing concern for individuals, corporate entities and governments. Preserving personal and sensitive information is critical to the success of today's data mining techniques. Preserving the privacy of data is even more crucial in critical sectors such as defence, health care and finance. Privacy Preserving Data Mining (PPDM) addresses such issues by balancing the preservation of privacy and the utilisation of data. Traditionally, Geometrical Data Transformation Methods (GDTMs) have been widely used for privacy preserving clustering. The drawback of these methods is that geometric transformation functions are invertible, which results in a lower level of privacy protection. In this work, a Principal Component Analysis (PCA)-based technique that preserves the privacy of sensitive information in a multi-party clustering scenario is proposed. The performance of this technique is evaluated further by applying a classical K-means clustering algorithm, as well as a machine learning-based clustering method on synthetic and real world datasets. The accuracy of clustering is computed before and after privacy-preserving transformation. The proposed PCA-based transformation method resulted in superior privacy protection and better performance when compared to the traditional GDTMs. © 2013 Elsevier Inc. All rights reserved.

Jawahar N.,Thiagarajar College of Engineering | Balaji N.,Sri Krishna College of Engineering And Technology
Applied Soft Computing Journal | Year: 2012

This paper proposes a genetic algorithm (GA) based heuristic to the multi-period fixed charge distribution problem associated with backorder and inventories. The objective is to determine the size of the shipments, backorder and inventories at each period, so that, the total cost incurred during the entire period towards transportation, backorder and inventories is minimum. The model is formulated as pure integer nonlinear programming and 0-1 mixed integer linear programming problems, and proposes a GA based heuristic to provide solution to the above problem. The proposed GA based heuristic is evaluated by comparing their solutions with lower bound, LINGO solver and approximate solutions. The comparisons reveal that the GA generates better solutions than the approximate solutions, and is capable of providing solutions equal to LINGO solutions and closer to the lower bound value of the problems. © 2011 Elsevier B.V. All rights reserved.

Natarajan A.,Anna University | Subramanian S.,Sri Krishna College of Engineering And Technology | Premalatha K.,Bannari Amman Institute of Technology
International Journal of Bio-Inspired Computation | Year: 2012

Bloom filter (BF) is a simple but powerful data structure that can check membership to a static set. The trade-off to use Bloom filter is a certain configurable risk of false positives. The odds of a false positive can be made very low if the hash bitmap is sufficiently large. Spam is an irrelevant or inappropriate message sent on the internet to a large number of newsgroups or users. A spam word is a list of well-known words that often appear in spam mails. The proposed system of bin Bloom filter (BBF) groups the words into number of bins with different false positive rates based on the weights of the spam words. Cuckoo search (CS) and bat algorithm are bio-inspired algorithms that imitate the way cuckoo breeding and microbat foraging behaviours respectively. This paper demonstrates the CS and bat algorithm for minimising the total membership invalidation cost of the BBFs by finding the optimal false positive rates and number of elements stored in every bin. The experimental results demonstrate the application of CS and bat algorithm for various numbers of bins and strings. Copyright © 2012 Inderscience Enterprises Ltd.

Kotteeswaran R.,St. Joseph's College | Sivakumar L.,Sri Krishna College of Engineering And Technology
Journal of Process Control | Year: 2014

Coal gasifier, an essential part of Integrated Gasification Combined Cycle (IGCC) converts coal into synthesis gas (syngas or producer gas) under certain pressure and temperature. The quality of syngas is highly influenced by quality of coal (calorific value) and hence greatly affects the power generation. Gasifier control seems to be highly difficult since it involves many variables and inherent nonlinearity. The baseline PI controller provided with ALSTOM benchmark challenge II (benchmark model of coal gasifier) fails to satisfy the constraints at 0% load for sinusoidal pressure disturbance and coal quality variations (±18%). This paper evaluates the tuning parameters of ALSTOM benchmark challenge II using Multi-Objective Particle Swarm Optimisation (MOPSO) algorithm. Robustness of the optimal PI controller is tested under sinusoidal and step pressure disturbance tests at 100%, 50% and 0% load conditions with decreased and increased coal quality variations. Test results show that the optimal PI controller meets all the constraints comfortably at all load conditions and provides better results for coal quality variations. © 2013 Elsevier Ltd. All rights reserved.

Gowtham R.,Amrita University | Krishnamurthi I.,Sri Krishna College of Engineering And Technology
Computers and Security | Year: 2014

Phishing is a web-based criminal act. Phishing sites lure sensitive information from naive online users by camouflaging themselves as trustworthy entities. Phishing is considered an annoying threat in the field of electronic commerce. Due to the short lifespan of phishing webpages and the rapid advancement of phishing techniques, maintaining blacklists, white-lists or employing solely heuristics-based approaches are not particularly effective. The impact of phishing can be largely mitigated by adopting a suitable combination of all these techniques. In this study, the characteristics of legitimate and phishing webpages were investigated in depth, and based on this analysis, we proposed heuristics to extract 15 features from such webpages. These heuristic results were fed as an input to a trained machine learning algorithm to detect phishing sites. Before applying heuristics to the webpages, we used two preliminary screening modules in this system. The first module, the preapproved site identifier, checks webpages against a private white-list maintained by the user, and the second module, the Login Form Finder, classifies webpages as legitimate when there are no login forms present. These modules help to reduce superfluous computation in the system and in addition reducing the rate of false positives without compromising on the false negatives. By using all of these modules, we are able to classify webpages with 99.8% precision and a 0.4% of false positive rate. The experimental results indicate that this method is efficient for protecting users from online identity attacks. © 2013 Elsevier Ltd. All rights reserved.

Viswanathan V.,Sri Krishna College of Engineering And Technology | Ilango K.,Sri Krishna College of Engineering And Technology
Information Sciences | Year: 2012

Semantic relationship deals with complex relationship between two entities in a knowledge base. In the process of finding the relationship, multiple paths connecting entities could be explored. Each path has a different meaning depending on the type of relation. Some of them may be relevant while others may be irrelevant depending on users' perspective with varying results for the same query. Hence, ranking these paths according to the user's need is imperative. In this paper, we adopt personalization approach to rank the semantic relationship paths. Here, user's interest level in various domains can be captured through their web browsing history and it is incorporated in calculating the context weights of the paths during the ranking process. The effectiveness of the ranking method is demonstrated through Spearman's foot rule correlation and precision rate. The experimental results prove that our proposed method is more efficient for ranking semantic relationship paths. © 2012 Elsevier Inc. All rights reserved.

Loading Sri Krishna College of Engineering And Technology collaborators
Loading Sri Krishna College of Engineering And Technology collaborators