Browsing by Author "Chandrasekaran, K."

Now showing 1 - 20 of 364

A bio-inspired model to provide data security in cloud storage
(Institute of Electrical and Electronics Engineers Inc., 2017) Hitaswi, N.; Chandrasekaran, K.
The demand for cloud computing is increasing rapidly because of the advantages it provides to the customers like, pay as you use, self-serving, elastic, sharing of resources, ease of use, and accessibility. Due to the increase in the usage of the technology, there exists a high chance of compromising the security of the data being stored on the cloud. The major hindrance in the usage of the technology is the security concerns which accompany it. This increases the demand for a robust security mechanism to protect the data on the cloud. So as to overcome this drawback of cloud computing, encrypting the data to be stored on the cloud is one of the solutions. As part of this paper, a security mechanism to improve the security of data in cloud storage is suggested. The security mechanism used is inspired by the bio-inspired genetic algorithm. The inspiration behind the proposed security model is an amalgamation of genetic algorithm and attribute based encryption. As per the methodology proposed the data need to be encrypted before being stored on the cloud. This way the cloud service provider is unaware of the data being stored and even if the data is compromised to some third party, there is no information leakage. Â© 2016 IEEE.
A client-side anti-pharming (CSAP) approach
(Institute of Electrical and Electronics Engineers Inc., 2016) Arya, B.; Chandrasekaran, K.
Pharming is a type of social engineering attack wherein an attacker wants to steal sensitive information of internet users. Pharming is advanced technique than Phishing attack. In phishing, attacker's URL is different from targeted legitimate website URL but in case of pharming, attacker's URL is same to legitimate URL. Pharming attacks can be conducted by exploiting vulnerabilities in DNS server, which is more advanced type of attack than phishing. It's a special attack because the attacker doesn't have to target individual user. When attacker performs pharming on a Domain Name System (DNS) server, all users who are using DNS service through that server will fall victim of pharming attack. Various techniques are proposed for avoiding pharming attack. We present an approach which uses multiple DNS servers. Â© 2016 IEEE.
A comparison of linear discriminant analysis and ridge classifier on Twitter data
(Institute of Electrical and Electronics Engineers Inc., 2017) Singh, A.; Prakash, B.S.; Chandrasekaran, K.
This document is about the accuracy analysis of two of the most prominent classifiers present in today's academic arena. Classifiers are being used extensively in machine learning applications today and need to present a high rate of success to be considered useful. Tikhonov regularization incorporated within the Ridge Classifier is the basis for its classification. It utilises the LevenbergMarquardt algorithm for non-linear least-squares problems to classify objects. Linear Discriminant Analysis, on the other hand, utilises aspects of ANOVA[2,3] and regression analysis. LDA works by getting explicit information from the user. It needs the definition of the variables - both dependent and independent. It doesn't use any implicit assumptions in its modelling. There is no interconnection between the two variables initially. Using these two classifiers we compare their effectiveness at mapping a set of data scraped in real-time from Twitter to its corresponding generalised hashtag, and suggest why the differences, if any, arise. Â© 2016 IEEE.
A Framework To Study Heuristic TSP Algorithms With Google Maps API
(Institute of Electrical and Electronics Engineers Inc., 2019) Ajumal, P.A.; Ananthakrishnan, S.; Jain, A.; Athreya, H.N.; Chandrasekaran, K.
Millions of people depend on the navigation facilities available in smart-phones and web browsers for their daily commutes, planning long trips ahead of time, looking up places etc. Integration of GPS and compass made navigating anywhere in the world a trivial task. Today, there are several applications available that fit the purpose of navigation such as Waze, HereWeGo (previously known as Here Maps by Nokia), Google Maps, etc. When Google Maps was used to embark on a tour that will take us to chosen places by covering the least distance possible, it is observed that none of the aforementioned applications provide such a feature. In this paper, a framework is developed with Google Maps APIs to create such a feature. This problem is mapped to the Traveling salesman problem and tried to solve it using algorithms known for approximating TSP such as Artificial Bee Colony Algorithm, Particle Swarm Optimization and Two-opt Algorithm. The framework is tested with these algorithms and found that, Particle Swarm Optimization gives the best possible route. Â© 2019 IEEE.
A game theoretic approach to a self managing MOOC based distributed system
(Institute of Electrical and Electronics Engineers Inc., 2014) Sharath, N.; Parikh, S.S.; Chandrasekaran, K.
The need to introduce an e learning platform in a campus such as ours is significant. In order to cater to the needs of nearly 7000 active users within the campus, a distributed system that is formulated. This system is required to to be as efficient as possible. This paper gives a topology for the system that is required and introduces self-managing properties that will add to the increased performance of the system in terms of speed, accuracy and security. With the aid of software agents continuously monitoring the progress of the entities in the system, we are able to introduce several self managing properties that govern the performance of the system as a whole. The software agents are modeled to be rational thinkers since every entity has a motive of performing its best. A game is simulated between two non cooperative agents as a case study and it is shown that the decision to move towards Nash Equilibrium serves better than any other random strategy. Â© 2014 IEEE.
A generic approach to security evaluation for multimedia data
(Association for Computing Machinery acmhelp@acm.org, 2015) Saha, G.; Bhat, T.; Chandrasekaran, K.
Beginning with a critical analysis of existing multimedia metrics, this paper builds upon their drawbacks in streaming media by the introduction of alternate metrics, backed by analytical correctness proofs of accuracy and comparative simulation with earlier metrics to justify the improvements made in security judgement techniques.
A grasshopper optimization algorithm-based movie recommender system
(Springer, 2024) Ambikesh, G.; Rao, S.S.; Chandrasekaran, K.
A movie recommendation system functions as a specialized information system, providing users with personalized suggestions aligned with their movie preferences. Employing advanced algorithms and data analysis methods, these systems scrutinize variables such as users' viewing history and preferences to formulate personalized recommendations. Our proposed methodology, termed GOA-k-means, amalgamates the Grasshopper Optimization Algorithm (GOA) with k-means clustering to navigate the dynamic nature of user preferences. Facilitating real-time calibration, GOA-k-means yields recommendations that adapt to users' shifting interests. We developed our model utilizing a dataset of one million records from Movielens, pre-processed via z-score normalization and subjected to Principal Component Analysis (PCA) for feature extraction. In comparison to conventional techniques, GOA-k-means demonstrated superior performance in metrics such as precision, recall, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), establishing itself as a valuable tool for augmenting user engagement in the entertainment industry. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
A green greedy process scheduler for cloud data centers
(Institute of Electrical and Electronics Engineers Inc., 2014) Karthik, C.; Gupta, A.; Chandrasekaran, K.
In this paper we have addressed a major problem in current day data centers- power consumption. Power consumption in data centers has become a major problem these days, both from economic and environmental perspective. Various factors affect the power consumption, one of them being the scheduling of tasks on the data center servers. Basically we achieved a real-time simulation of two cloud scheduling algorithms and compared the power efficiency of the two algorithms in terms of two main temperature parameters of the servers-idle temperature and critical temperature. We assumed that we were given all the task parameters such as running time etc. and then we calculated a final temperature that a system will reach on running that particular task. Then we decided which system could accommodate that task based on that systems critical temperature and chose the best system among those based on a score proposed in the paper. Â© 2014 IEEE.
A Green Mechanism Design Approach to Automate Resource Procurement in Cloud
(Elsevier, 2015) Ketankumar, D.C.; Verma, G.; Chandrasekaran, K.
Cloud computing paradigm is emerging as the solution to all the infrastructure setup problems of IT industry. But the thriving demand of cloud infrastructure has increased the energy consumption of the data centers drastically. As the energy consumption of the data center rises, it leads us to high carbon emissions which are dangerous for the environment. In this paper, we propose a green cloud broker for resource procurement problem by considering the metrics of energy efficiency and environmental friendly operations of the cloud service provider. We use mechanism design methods to decide the allocation and payment for the submitted job dynamically. We perform experiments and show the results of comparisons of energy consumption and emission of greenhouse gases between the allocation decided by the proposed green cloud broker and a without taking the green metric into consideration. Â© 2015 The Authors.
A Heuristic Algorithm to Find a Path to be Blocked by Minimizing Traffic Disruption
(Institute of Electrical and Electronics Engineers Inc., 2020) Das, M.; Ambati, S.S.; Chandrasekaran, K.
This paper discusses the problem of finding a path to be blocked from the source to the destination for a vehicle to pass by in such a way that the traffic disruption caused is minimum. The traffic disruption caused by blocking a path is measured by estimating the number of vehicles that would have crossed any of the vertices in the path if the path had not been blocked. It also presents a heuristic algorithm 'Aggregate Traffic Minimization' (ATM) to solve the above problem. The traffic disruption caused by the path chosen by the ATM algorithm was compared with that of a popular baseline algorithm and was found that ATM outperforms the baseline alzorithm in most cases. Â© 2020 IEEE.
A hierarchical blockchain architecture for secure data sharing for vehicular networks
(Springer Science and Business Media B.V., 2023) Srinivasan, K.S.; Divakarla, U.; Chandrasekaran, K.; Reddy, K.H.K.
Data sharing is common phenomenon between the stakeholders within an organization and it is vital to sustain in the context of application. Internet of Things (IoT) is an umbrella of all applications’ online services like smart city, smart agriculture, smart grid and smart vehicles. In case of autonomous vehicular network (AVN), the data generated by vehicles, sensing units and road side units (RSU) is sensitive in nature so, secure data sharing (SDS) in AVN is the prime importance. In the area of SDS, Blockchain is gaining popularity which is an immutable distributed ledger technology and emerged as one of the prime solutions towards secure data sharing. As an innovative contribution, we proposedBlockchain based hierarchical secure data sharing model for sharing within vehicular network (VN). The proposed architecture is able to share road traffic related information e.g., road conditions, traffic congestion with the nearby vehicles and other stakeholders in the vehicular network. The performance of the proposed model is analyzed by using a simulation study and the efficacy of the simulated results outperforms than that of existing models. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.
A Machine Learning Approach for Daily Temperature Prediction Using Big Data
(Springer Science and Business Media Deutschland GmbH, 2022) Divakarla, U.; Chandrasekaran, K.; Hemant Kumar Reddy, K.H.K.; Reddy, R.V.; Rao, M.
Due to global warming, weather forecasting becomes complex problem which is affected by a lot of factors like temperature, wind speed, humidity, year, month, day, etc. weather prediction depends on historical data and computational power to analyze. Weather prediction helps us in many ways like in astronomy, agriculture, predicting tsunamis, drought, etc. this helps us to be prepared in advance for any kinds disasters. With rapid development in computational power of high end machines and availability of enormous data weather prediction becomes more and more popular. But handling such huge data becomes an issue for real time prediction. In this paper, we introduced the machine learning-based prediction approach in Hadoop clusters. The extensive use of map-reduce function helps us distribute the big data into different clusters as it is designed to scale up from single servers to thousands of machines, each offering local computation and storage. An ensemble distributed machine learning algorithms are employed to predict the daily temperature. The experimental results of proposed model outperform than the techniques available in literature. Â© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
A Machine Learning Approach for Load Balancing in a Multi-cloud Environment
(Springer Science and Business Media Deutschland GmbH, 2022) Divakarla, D.; Chandrasekaran, K.
A multi-cloud environment makes use of two or more cloud computing services from different cloud vendors. A typical multi-cloud environment can consist of either only private clouds or only public clouds or a combination of both. Load balancing mechanism is essential in such a computing environment to distribute user requests or network load efficiently across multiple servers or virtual machines, ensuring high availability and reliability. Scalability is also achieved by sending requests only to those servers that are healthy and available to take up the computing workload and thus providing the flexibility to scale up and scale down to satisfy QoS requirements as well, in order to save costs. In our proposed model, a time series-based approach as well as predictive load balancing has been experimented and the results are presented. Â© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
A modified secure version of the Telegram protocol (MTProto)
(Institute of Electrical and Electronics Engineers Inc., 2016) Job, J.; Naresh, V.; Chandrasekaran, K.
The advent of mobile phones and the spread of the internet have caused a substantial increase in the utilization of these technologies for personal communication. A wide range of mobile applications exist, most of which use their own proprietary protocol. Reports of snooping attacks have prompted the parent organizations and users to guarantee that the encrypted data sent over a public network is decrypted only by the intended recipient. Smart phone operating systems provide GPS data to these applications so that users can tag photos with this information. As these applications mostly run a daemon or service in the background to automatically receive messages, an unattended switched on location service coupled with a weak protocol leaves the user highly vulnerable of being tracked by eavesdroppers. These applications are known to, by observing their behaviour, upload the user's contact list to the server so as identify those contacts using the same application. These are but just two important data that need to be protected by tough security measures during transit. Any loop hole in security protocols will leave the user vulnerable to attacks, even outside the digital world. Online chat protocols such as the Telegram protocol ensure end-to-end security of data. Although the protocol itself has been explained in much detail by the designers, this protocol is disfavored because of its performance drawbacks and its susceptibility to man-in-the-middle attacks. In this paper, we modify the Telegram protocol in an attempt to make it more efficient and secure. Â© 2015 IEEE.
A novel approach for evaluating trust of resources in cloud environment
(Institute of Electrical and Electronics Engineers Inc., 2017) Divakarla, U.; Chandrasekaran, K.
Trust is a significant facet in decision making of any distributed network. Cloud computing is a new computing model that provides computing resources to consumers. Due to outsourcing. there is always an uncertainty about the reliability and quality of the services. Though service providers assure of quality and secure services, these assurances do not satisfy the trustworthiness of the service providers for the consumers. In this paper, we have proposed a model that develops a strong trust relationship between consumer and resources of the service provider in cloud environment. This trust relation strengthens the security of the resources as well as the authentication of the consumer. The implementation proved that trust model developed is more efficient in terms of compute time and process time. Â© 2016 IEEE.
A Novel Approach towards Windows Malware Detection System Using Deep Neural Networks
(Elsevier B.V., 2022) Divakarla, U.; Reddy, K.H.K.; Chandrasekaran, K.
Now-a-day's malicious software is increasing in numbers and at present becomes more harmful for any digital equipment like mobile, tablet, and computers. Traditional techniques like static and dynamic analysis, signature-based detection methods are become absolute and not effective at all. The advanced techniques like code encryption and code packing techniques can be used to hide detection; polymorphic malware is a new class of malware that changes their code structure from time to time to avoid detection, so there is a need for an intelligent system which can efficiently analyze the features of a new, unknown executable file and classify it correctly. There have been learning-based malware detection systems proposed in the literature, but most of those proposed approaches present a high accuracy over a small dataset, whereas the performance is very poor over industry-standard datasets. Operating system like windows is always in prime malware target because of the sheer high number of users. This paper proposes a simple, deep learning-based detection approachthat classifies a specified executable into benign or harmful. It has been trained using EMBER, an industry-level Windows malware dataset and tests with an accuracy of 87.76%. Â© 2023 The Authors. Published by Elsevier B.V.
A novel family genetic approach for virtual machine allocation
(Elsevier B.V., 2015) Joseph, C.T.; Chandrasekaran, K.; Cyriac, R.
The concept of virtualization forms the heart of systems like the Cloud and Grid. Efficiency of systems that employ virtualization greatly depends on the efficiency of the technique used to allocate the virtual machines to suitable hosts. The literature contains many evolutionary approaches to solve the virtual machine allocation problem, a broad category of which employ Genetic Algorithm. This paper proposes a novel technique to allocate virtual machines using the Family Gene approach. Experimental analysis proves that the proposed approach reduces energy consumption and the rate of migrations, and hence offers much scope for future research. Â© 2015 Published by Elsevier B.V.
A Novel Machine Learning Approach for Bug Prediction
(Elsevier B.V., 2016) Puranik, S.; Deshpande, P.; Chandrasekaran, K.
With the growing complexities of the software, the number of potential bugs is also increasing rapidly. These bugs hinder the rapid software development cycle. Bugs, if left unresolved, might cause problems in the long run. Also, without any prior knowledge about the location and the number of bugs, managers may not be able to allocate resources in an efficient way. In order to overcome this problem, researchers have devised numerous bug prediction approaches so far. The problem with the existing models is that the researchers have not been able to arrive at an optimized set of metrics. So, in this paper, we make an attempt to select the minimal number of best performing metrics, thereby keeping the model both simple and accurate at the same time. Most of the bug prediction models use regression for prediction and since regression is a technique to best approximate the training data set, the approximations don't always fit well with the test data set. Keeping this in mind, we propose an algorithm to predict the bug proneness index using marginal R square values. Though regressions are performed as intermediary steps in this algorithm, the underlying logic is different in nature when compared with the models using regressions alone. Â© 2016 The Authors. Published by Elsevier B.V.
A parallel dynamic programming approach for data analysis
(Institute of Electrical and Electronics Engineers Inc., 2016) Deepak, A.; Shravya, K.S.; Chandrasekaran, K.
In spite of presence of many classical and modified data analysis techniques, data analysis in the field of software engineering still remains a challenge because of the presence of large number of both continuous and discreet explanatory variables judging the outcome of one and more than one dependant variables. Requirement for an efficient multivariate data analysis technique which fulfils the constraints associated with software data led to the design of OSR (optimized set reduction) which uses a greedy algorithm for data analysis using both the principles of machine learning and conventional statistics. With the incoming of big data and other increasing dimensions of data set, we, through this paper, try to propose a new algorithm, based on the similar lines of optimised set reduction, using its strength to extract subsets. As the current trend of programming demands an algorithm to execute in parallel, we also propose a modification to our algorithm for it to run in a multicore platform with good efficiency. Â© 2015 IEEE.
A perspective study of virtual machine migration
(Institute of Electrical and Electronics Engineers Inc., 2014) Joseph, C.T.; Chandrasekaran, K.; Cyriac, R.
Cloud Computing is one of the leading technologies. As a solution to many of the challenges faced by Cloud providers, virtualization is employed in Cloud. Virtual machine migration is a tool to utilize virtualization well. This paper gives an overview of the different works in literature that consider virtual machine migration. The different works related to virtual migration are classified into different categories. Some of the works that consider less explored areas of virtual machine migration are discussed in detail. Â© 2014 IEEE.