Faculty Publications

Search Results

Now showing 1 - 4 of 4

Using genetic algorithm for process migration in multicore kernels
(Springer Verlag service@springer.de, 2017) Shravya, K.S.; Deepak, A.; Chandrasekaran, K.
Process migration is used in multicore operating systems to improve their performance. The implementation of the migration event contributes largely to the performance of the scheduling algorithm and hence decides how effective a multicore kernel is. There have been several effective algorithms which decide how a process can be migrated from one core to another in a multicore operating system. This paper looks further into the mechanism of process migration in multicore operating systems. The main aim of this paper is not to answer how the process migration should take place but it aims to answer when process migration should take place and to decide the site of process migration. For this, an artificial intelligence concept called genetic algorithm is used. Genetic algorithm works on the theory of survival of the fittest to find an optimally good solution during decision making phase. Â© Springer Nature Singapore Pte Ltd. 2017.
Membrane-based models for service selection in cloud
(Elsevier Inc., 2021) Raghavan, S.; Chandrasekaran, K.
Cloud service selection is one of the prime areas of research within the ambit of cloud computing, which has gained wide attention in the recent past. The service selection algorithm primarily involves selecting the best service from a set of available services, based on Quality of Service (QoS) attributes. The QoS attributes are the parameters which allow the users to ascertain the actual quality of the service, often quantitatively. Over the years, there have been several methods designed for service selection in the cloud that are primarily sequential, with many being sensitive to changes. Thus, the aim is to propose multiple robust and parallel models for cloud service selection. The proposed models are designed using Membrane Computing paradigm, which is an inherently parallel computing model, combined with the Improved Technique for Order of Preference by Similarity to Ideal Solution (ITOPSIS), a popular Multi-Criteria Decision Making Method. Two methods based on a tactical amalgamation of ITOPSIS and Enzymatic Numerical P System (A membrane computing device variant) structure are proposed here. The proposed parallel models are implemented, tested, and the obtained results are analyzed. The results indicate one model to be robust (less sensitive) and the other to be moderately sensitive. © 2020 Elsevier Inc.
ENPS-IPROMETHEE: Enzymatic Numerical P System-based Improved Preference Ranking Organization Method for Enrichment Evaluation
(Springer, 2022) Raghavan, S.; Chandrasekaran, K.
Membrane Computing is a natural computing paradigm inspired by the structure and activity of a biological cell. Membrane-based models can be realized using P System and these models have multiple applications. Here, it is applied to solve a Multi-criteria Decision-Making (MCDM) problem. MCDM is one of the important area in Decision-Making. It involves ranking items from a given set of items based on multiple criteria and it has several applications in different broad arenas which include Economics, Engineering and Management. MCDM includes several clusters of techniques that have been divided based on its modes of operation. All the techniques available till now consider sequential computing paradigm as the base for computation but in this work a parallel technique is used. Here, Enzymatic Numerical P System (ENPS)-based MCDM technique is designed. ENPS is a variant of P System used specifically for numerical problems. The proposed model, ENPS-IPROMETHEE is based on Improved Preference Ranking Organization Method for Enrichment Evaluation (IPROMETHEE), a popular outranking-based MCDM method. The designed model is verified and tested using PeP and GPUPeP simulators which are used for simulating ENPS models. A membrane file generator tool called as P-Generator is developed for automatic membrane generation. Two standard, existing datasets are considered and the model is studied for its sensitivity. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
Forecasting Land-Use and Land-Cover Change Using Hybrid CNN-LSTM Model
(Institute of Electrical and Electronics Engineers Inc., 2024) Varma, B.; Naik, N.; Chandrasekaran, K.; Venkatesan, M.; Rajan, J.
Land-use and land-cover (LULC) information helps analyze future trends and is essential for environmental management and sustainable planning. Time-series satellite images are employed in this study to forecast changes in LULC. Deep-learning (DL) frameworks have been widely used for modeling dynamic LULC changes at the regional level. However, improving the accuracy of the existing prediction models is necessary. This letter proposes an integrated convolutional neural network (CNN) and long short-term memory network (LSTM) known as a hybrid CNN-LSTM model to address the fine-scale LULC prediction requirement. The efficiency of the proposed approach was examined using LULC data for the Dakshina Kannada District of Karnataka State, India. The proposed model achieved an overall accuracy of 95.11% and a kappa coefficient of 0.92, based on the ground-truth data for 2014. The model's predictions for 2035, based on data from 2005 to 2014, revealed the following trends: Urbanization exhibited a pattern of rapid expansion and increased growth. The integrated CNN-LSTM model extracted spatial and temporal features for effectively predicting LULC changes. Infrastructure development, population density, and enhanced economic activities were the major driving factors of changes in LULC for the study region. Robust LULC change forecasting will strengthen LULC evaluations, aid in understanding complex land-use systems, and empower decision-makers to formulate effective land management strategies in the coming years. © 2004-2012 IEEE.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results