Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
18 results
Search Results
Item Parallelized K-Means clustering algorithm for self aware mobile Ad-hoc networks(2011) Thomas, L.; Manjappa, K.; Annappa, B.; Guddeti, G.R.M.Providing Quality of Service (QoS) in Mobile Ad-hoc Network (MANET) in terms of bandwidth, delay, jitter, throughput etc., is critical and challenging issue because of node mobility and the shared medium. The work in this paper predicts the best effective cluster while taking QoS parameters into account. The proposed work uses K-Means clustering algorithm for automatically discovering clusters from large data repositories. Further, iterative K-Means clustering algorithm is parallelized using Map-Reduce technique in order to improve the computational efficiency and thereby predicting the best effective cluster. Hence, parallel K-Means algorithm is explored for finding the best effective cluster containing the hops which lies in the best cluster with the best throughput in self aware MANET. Copyright © 2011 ACM.Item Utilization of map-reduce for parallelization of resource scheduling using MPI: PRS(2011) Thomas, L.; Annappa, B.Scheduling for speculative parallelization is a problem that remained unsolved despite its importance [2]. In the previous work scheduling was done based on Fixed-Size Chunking (FSC) technique which needed several'dry-runs' before an acceptable finalized chunk size that will be scheduled to each processors is found. There are many other scheduling methods which were originally designed for loops with no dependences, but they were primarily focused in the problem of load balancing. In this work we address the problem of scheduling tasks with and without dependences for speculative execution. We have found that a complexity between minimizing the number of re-executions and reducing overheads can be found if the size of the scheduled block of iterations is calculated at runtime. We introduce here a scheduling method called Parallelization of Resource scheduling (PRS) in which we first analyze the processing speed of each worker based on that further division of the actual task will be done. The result shows a 5% to 10% speedup improvement in real applications with dependences with respect to a carefully tuned PRS strategy. Copyright © 2011 ACM.Item Application of parallel K-means clustering algorithm for prediction of optimal path in self aware mobile ad-hoc networks with link stability(2011) Thomas, L.; Annappa, B.Providing Quality of Service (QoS) in terms of bandwidth, delay, jitter, throughput etc., for Mobile Ad-hoc Network (MANET) which is the autonomous collection of nodes, is challenging issue because of node mobility and the shared medium. This work is to predict the Optimal link based on the link stability which is the number of contacts between 2 pair of nodes that can be effectively applied for prediction of optimal effective path while taking QoS parameters into account to reach the destination using the application of K-Means clustering algorithm for automatically discovering clusters from large data repositories which is parallelized using Map-Reduce technique in order to improve the computational efficiency and thereby predicting the optimal effective path from source to sink. The work optimizes the previous result by pre-assigning task for finding the best stable link in MANET and then work is explored only on that stable link hence, by doing so we are able to predict the optimal path in more time efficient way. © 2011 Springer-Verlag.Item Efficient process mining through critical path network analysis(IEEE Computer Society, 2014) Thomas, L.; Manoj Kumar, M.V.; Annappa, B.Process mining is emerging scientific research discipline, concentrates on discovering, monitoring and enhancing the operational processes using the operational traces of the process documented in log. Process mining enables the process centric analysis of the data and aims at bridging gap between data mining, business process modeling and analysis. This article analyses use of Critical Path Method used in project management, in the context of process mining in order to find critical paths in process model. This article aims in leveraging process mining practices with the application of CPM and study its feasibility. Critical path identifies the minimum time possible to finish the project. Extra care must be taken while executing activities on critical path. Delay in any of the activities on critical path would definitely delay the process completion time and collapse overall process plan. © 2014 IEEE.Item Phenomenon of concept drift from process mining insight(IEEE Computer Society, 2014) Manoj Kumar, M.V.; Thomas, L.; Annappa, B.Process mining is originated form the fact that the modern information systems systematically record and maintain history of the process which they monitor and support. Systematic study of the recorded information in process centric manner will help to understand the process in a better way. Process mining acts as enabling technology by facilitating process centric analysis of data, which other available data science like data mining etc. fails to provide. Process mining algorithms are able to provide excellent insights on the process which they analyze, but they fail to handle the change in the process. Concept drift is a phenomenon of change in the process while it is being analyzed and it is a non-stationary learning problem. As the process changes while it is being analyzed, end result of the analysis becomes obsolete. Process mining algorithms are static biased, they assume that process at the beginning of analysis period will remain as same at the end of analysis period. There is at most requirement to effectively deal with the change in process to conduct optimal analysis. The main focus of this paper is to identify different factors to be considered while designing the solution for the problem of concept drift and explain each of the identified factors briefly. As the phenomenon of concept drift is extensively under consideration for research in other scientific research disciplines, this article considers restricting the content strictly concerning to the context of process mining. © 2014 IEEE.Item An optimal process model for a real time process(CEUR-WS, 2015) Thomas, L.; Manoj Kumar, M.V.; Annappa, B.; Vishwanath, K.P.Recommending an optimal path of execution and a complete process model for a real time partial trace of large and complex organization is a challenge. The proposed AlfyMiner (αyMiner) does this recommendation in cross organization process mining technique by comparing the variants of same process encountered in different organization. αyMiner proposes two novel techniques Process Model Comparator (αyComp) and Resource Behaviour Analyser (RBAMiner). αyComp identifies Next Probable Activity of the partial trace along with the complete process model of the partial trace. RBAMineridentifies the resources preferable for performing Next Probable Activity and analyse their behaviour based on performance, load and queue. αyMiner does this analysis and recommend the best suitable resource for performing Next Probable Activity and process models for the real time partial trace. Experiments were conducted on process logs of CoSeLoG Project1 and 72% of accuracy is obtained in identifying and recommending NPA and the performance of resources were optimized by 59% by decreasing their load.Item Capturing the sudden concept drift in process mining(CEUR-WS, 2015) Manoj Kumar, M.V.; Thomas, L.; Annappa, B.Concept drift is the condition when the process changes during the course of execution. Current methods and analysis techniques existing in process mining are not proficient of analyzing the process which has experienced the concept drift. State-of-the-art process mining approaches consider the process as a static entity and assume that process remains same from beginning of its execution period to end. Emphasis of this paper is to propose the technique for localizing concept drift in control-flow perspective by making use of activity correlation strength feature extracted using process log. Concept drift in the process is localized by applying statistical hypothesis testing methods. The proposed method is verified and validated on few of the real-life and artificial process logs, results obtained are promising in the direction of efficiently localizing the sudden concept drifts in process-log.Item Discovery of optimal neurons and hidden layers in feed-forward Neural Network(Institute of Electrical and Electronics Engineers Inc., 2016) Thomas, L.; Manoj Kumar, M.V.; Annappa, B.Identifying the number of neurons in each hidden layers and number of hidden layers in a multi layered Artificial Neural Network (ANN) is a challenge based on the input data. A new hypothesis is proposed for organizing the synapse from x to y neuron. The synapse of number of neurons to fire between the hidden layer is identified. By the introduction of this hypothesis, an effective number of neurons in multilayered Artificial Neural Network can be identified and self organizing neural network model is developed which is referred as cognitron. The normal brain model has 3 layered perceptron; but the proposed model organizes the number of layers optimal for identifying an effective model. Our result proved that the proposed model constructs a neural model directly by identifying the optimal weights of each neurons and number of neurons in each dynamically identified hidden layers. This optimized model is self organized with different range of neurons on different layer of hidden layer, and by comparing the performance based on computational time and error at each iteration. An efficient number of neurons are organized using gradient decent. The proposed model thus train large model to perform the classification task by inserting optimal layers and neurons. © 2016 IEEE.Item Recommending an alternative path of execution using an online decision support system(Association for Computing Machinery acmhelp@acm.org, 2017) Thomas, L.; Manoj Kumar, M.V.; Annappa, B.Prediction of disease severity is highly essential for understanding the progression of disease and initiating an alternative path of execution, which is priceless in treatment planning. An online decision support system (ODeSS) is proposed here for stratification of the patients who may need Endoscopic Retrograde CholangioPancreatography (ERCP) and recommend an alternate path of execution. By this an immediate intervention can be avoided. In this study gallstone disease (GSD) whose prevalence is increasing in India is considered. ODeSS is a versatile non-linear information model which clustered the traces based on the duration of its completion. This is a Retrospective analyses of 575 traces. ODeSS applied the technique of longest common subsequence for identifying the sequence of an online execution and discovering to which cluster of variants it may belong. This discovery assist in taking appropriate clinical decision by recommending an alternative path of execution for such cases which may need emergency interventions. ODeSS performance was evaluated using area under receiver operating characteristic curve (area under ROC curve). This showed an accuracy of 0.9653 in prediction. The proposed model was validated using ROC curve in k-fold cross validation. Hence the proposed ODeSS can be used to conduct a non-linear statistical analysis since, the relationships between the predictive variables are not linear. It can be used as a clinical practice to recommend the path of execution. This would assist in better treatment planning, avoiding future complications. © 2017 ACM.Item Distilling lasagna from spaghetti processes(Association for Computing Machinery acmhelp@acm.org, 2017) Manoj Kumar, M.V.; Thomas, L.; Annappa, B.If the operational process is flexible, control flow discovery methods in process mining tend to produce Spaghetti (unstructured) models. Spaghetti models generally consist of large number of activities and paths. These models are unstructured, incomprehensible difficult to analyse, impossible to use during operational support and enhancement. Due The structural complexity of Spaghetti processes majority of techniques in process mining can not be applied on them. There is a at most necessity to design and develop methods for simplifying the structure of Spaghetti process to make them easily understandable and reusable. The methods proposed in this paper concentrates on offering the tools and techniques for analysing the Spaghetti process. The problems addressed in this paper are 1) converting the unstructured Spaghetti to structured and simplified Lasagna process, 2) identifying the list of possible, significant, and impossible paths of execution in Lasagna process. The proposed technique is verified and validated on real-life road traffic fine management event-log taken from standard repository. © 2017 ACM.