Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
Search Results
Item A novel overlapping community detection using parallel CFM and sequential nash equilibrium(Institute of Electrical and Electronics Engineers Inc., 2018) Sarswat, A.; Guddeti, R.M.Detecting Overlapping Community in Social Networks is one of the challenging and complex problem. Several approaches based on heuristic, modularity & modularity density, graph partitioning and game theory are available for community detection. However getting an optimum and stable solution with less computation cost for large datasets is not possible using these existing approaches. Hence, in this work, we propose a novel overlapping community detection algorithm based on parallel community forest model and sequential Nash Equilibrium for large datasets. In this paper, community forest model (CFM) is implemented in parallel using Spark framework to get the initial community structure and then a Nash Equilibrium is computed to find a stable overlapping community structure. We conducted experiments on the benchmark LFR dataset with different sizes like 500, 1000, 2000 upto 10,000 nodes to evaluate the proposed method. Our experimental results clearly demonstrate that the proposed approach outperforms the existing works in terms of quality, scalability, stability and less computation time. © 2018 IEEE.Item Energy efficient quality of service aware virtual machine migration in cloud computing(Institute of Electrical and Electronics Engineers Inc., 2018) Sharma, N.; Sharma, P.; Guddeti, R.M.This paper deals with mulit-objective (network aware, energy efficient, and Service Level Agreement (SLA) aware) Virtual Machines (VMs) migration at the cloud data center. The proposed VMs migration technique migrate the VMs from the underutilized PMs to the energy efficient Physical Machines (PMs) at the cloud data center. Further, the multi-objective VMs migration technique not only reduces the power consumption of PMs and switches but also guarantees the quality of service by maintaining the SLA at the cloud data center. Our proposed VMs migration approach can find the good balance between three conflict objectives as compared to other algorithms. Further, the cloudsim based experimental results demonstrate the superiority of our proposed multi-objective VMs migration technique in terms of energy efficiency and also reduces the SLA violation over state-of-the-art VMs migration techniques such as Interquartile Range (IQR), and Random VMs migration techniques at the cloud data center. © 2018 IEEE.Item Heuristic-based iot application modules placement in the fog-cloud computing environment(Institute of Electrical and Electronics Engineers Inc., 2018) Natesha, B.V.; Guddeti, R.M.Nowadays many Smart City applications make use of Internet of Things (IoT) devices for monitoring the environment. The increase in use of IoT for smart city applications causes exponential increase in the volume of data. Using centralised cloud for time sensitive IoT applications is not feasible due to more delay because of the network congestion. Hence, fog computing is used for processing the data near to the edge of the network, where processing is done by distributed network nodes. But, there is a challenge to select the fog nodes which can host and process the application modules. The placement of application module on these fog devices is known as NP-hard problem. Hence, we need better placement strategies to decide placement of application modules in fog infrastructure to minimize the application latency. In this paper, we design a First-Fit Decreasing (FFD) heuristic based approach for placing IoT application modules on Fog-Cloud and carried out the experiment using iFogsim simulator. The simulation results demonstrate that the proposed method shows significant decrease in both the application latency and energy consumption of Fog-Cloud as compared to the benchmark method. © 2018 IEEE.Item GWOTS: Grey Wolf Optimization Based Task Scheduling at the Green Cloud Data Center(Institute of Electrical and Electronics Engineers Inc., 2018) Natesha, B.V.; Sharma, N.; Domanal, S.; Guddeti, R.M.Task Scheduling is a key challenging issue of Infrastructure as a Service (IaaS) based cloud data center and it is well-known NP-complete problem. As the number of users' requests increases then the load on the cloud data center will also increase gradually. To manage the heavy load on the cloud data center, in this paper, we propose multiobjective Grey Wolf Optimization (GWO) technique for task scheduling. The main objective of our proposed GWO based scheduling algorithm is to achieve optimum utilization of cloud resources for reducing both the energy consumption of the data center and total makespan of the scheduler for the given list of tasks while providing the services as requested by the users. Our proposed scheduling algorithm is compared with non meta-heuristic algorithms (First-Come-First-Serve (FCFS) and Modified Throttle (MT)), and meta-heuristic algorithms (Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Cat Swarm Optimization (CSO)). Experimental results demonstrate that the proposed GWO based scheduler outperforms all algorithms considered for performance evaluation in terms of makespan for the list of tasks, resource utilization and energy consumption. © 2018 IEEE.Item Unobtrusive students' engagement analysis in computer science laboratory using deep learning techniques(Institute of Electrical and Electronics Engineers Inc., 2018) Ashwin, T.S.; Guddeti, R.M.Nowadays, analysing the students' engagement using non-verbal cues is very popular and effective. There are several web camera based applications for predicting the students' engagement in an e-learning environment. But there are very limited works on analyzing the students' engagement using the video surveillance cameras in a teaching laboratory. In this paper, we propose a Convolutional Neural Networks based methodology for analysing the students' engagement using video surveillance cameras in a teaching laboratory. The proposed system is tested on five different courses of computer science and information technology with 243 students of NITK Surathkal, Mangalore, India. The experimental results demonstrate that there is a positive correlation between the students' engagement and learning, thus the proposed system outperforms the existing systems. © 2018 IEEE.Item Resource Provisioning Framework for IoT Applications in Fog Computing Environment(IEEE Computer Society help@computer.org, 2018) Rakshith, G.; Rahul, M.V.; Sanjay, G.S.; Natesha, B.V.; Guddeti, R.M.The increasing utility of ubiquitous computing and dramatic shifts in the domain of Internet of Things (IoT) have generated the need to devise methods to enable the efficient storage and retrieval of data. Fog computing is the de facto paradigm most suitable to make efficient use of the edge devices and thus shifting the impetus from a centralized cloud environment to a decentralized computing paradigm. By utilizing fog resources near to the edge of the network, we can reduce the latency and the overheads involved in the processing of the data by deploying the required services on them. In this paper, we present resource provisioning framework which provisions the resources and also manages the registered services in a dynamic topology of the fog architecture. The results demonstrate that using fog computing for deploying services reduces the total service time. © 2018 IEEE.Item A reinforcement learning and recurrent neural network based dynamic user modeling system(Institute of Electrical and Electronics Engineers Inc., 2018) Tripathi, A.; Ashwin, T.S.; Guddeti, R.M.With the exponential growth in areas of machine intelligence, the world has witnessed promising solutions to the personalized content recommendation. The ability of interactive learning agents to take optimal decisions in dynamic environments has been very well conceptualized and proven by Reinforcement Learning (RL). The learning characteristics of Deep-Bidirectional Recurrent Neural Networks (DBRNN) in both positive and negative time directions has shown exceptional performance as generative models to generate sequential data in supervised learning tasks. In this paper, we harness the potential of the said two techniques and strive to create personalized video recommendation through emotional intelligence by presenting a novel context-Aware collaborative filtering approach where intensity of users' spontaneous non-verbal emotional response towards recommended video is captured through system-interactions and facial expression analysis for decision-making and video corpus evolution with real-Time data streams. We take into account a user's dynamic nature in the formulation of optimal policies, by framing up an RL-scenario with an off-policy (Q-Learning) algorithm for temporal-difference learning, which is used to train DBRNN to learn contextual patterns and generate new video sequences for the recommendation. Evaluation of our system with real users for a month shows that our approach outperforms state-of-The-Art methods and models a user's emotional preferences very well with stable convergence. © 2018 IEEE.Item CVUCAMS: Computer vision based unobtrusive classroom attendance management system(Institute of Electrical and Electronics Engineers Inc., 2018) Gupta, S.K.; Ashwin, T.S.; Guddeti, R.M.One of the major challenges in a smart classroom environment is to develop a computer vision based unobtrusive classroom attendance management system. Traditional classroom environment follows a manual attendance marking system either by calling the student's names or by forwarding an attendance sheet; both interrupts the teaching-learning process and also consume a lot of time. Further, it can be erroneous due to factors such as students' proxy etc. In this paper, we propose an unobtrusive face recognition based smart classroom attendance management system using the high definition rotating camera for capturing the faces of students. The proposed system uses Max-Margin Face Detection (MMFD) technique for the face detection and the model is trained using the Inception-V3 CNN technique for the students' identification. The proposed smart classroom system was tested for a classroom with 20 students at National Institute of Technology Karnataka Surathkal, Mangalore, India and we got the experimental results demonstrate the train and test accuracy of 97.67% and 96.66%, respectively. © 2018 IEEE.