Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
23 results
Search Results
Item Foundations of healthcare informatics(Elsevier, 2021) Annappa, B.; Manoj Kumar, M.V.; Thomas, L.Health informatics fundamentally deals with the acquisition (recording), processing, interpreting, and using of healthcare (patient) data by domain experts. Healthcare informatics generally refers to the management of data/information in healthcare rather than the application of computers in it-which is centered on patient care. The sheer amount of data and imperfection in decision making imply the usage of information systems (particularly process-aware information systems, called PAIS) in managing the healthcare process. Health informatics mainly offers tools for controlling the healthcare process and facilitating the acquisition of medical knowledge (recording). It offers a reliable and fast communication path among the people involved in the healthcare process. © 2021 Elsevier Inc. All rights reserved.Item Deep Learning for COVID-19(Springer Science and Business Media Deutschland GmbH, 2022) Bs, B.S.; Manoj Kumar, M.V.; Thomas, L.; Ajay Kumar, M.A.; Wu, D.; Annappa, B.; Hebbar, A.; Vishnu Srinivasa Murthy, Y.V.S.Ever since the outbreak in Wuhan, China, a variant of Coronavirus named “COVID 19” has taken human lives in millions all around the world. The detection of the infection is quite tedious since it takes 3–14 days for the symptoms to surface in patients. Early detection of the infection and prohibiting it would limit the spread to only to Local Transmission. Deep learning techniques can be used to gain insights on the early detection of infection on the medical image data such as Computed Tomography (CT images), Magnetic resonance Imaging (MRI images), and X-Ray images collected from the infected patients provided by the Medical institution or from the publicly available databases. The same techniques can be applied to do the analysis of infection rates and do predictions for the coming days. A wide range of open-source pre-trained models that are trained for general classification or segmentation is available for the proposed study. Using these models with the concept of transfer learning, obtained resultant models when applied to the medical image datasets would draw much more insights into the COVID-19 detection and prediction process. Innumerable works have been done by researchers all over the world on the publicly available COVID-19 datasets and were successful in deriving good results. Visualizing the results and presenting the summarized data of prediction in a cleaner, unambiguous way to the doctors would also facilitate the early detection and prevention of COVID-19 Infection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Clinical decision support system for early disease detection and management: Statistics-based early disease detection(IGI Global, 2021) Thomas, L.; M V, M.K.; Annappa, B.Medical error is an adverse event of a failure in healthcare management, causing unintended injuries. Proper clinical care can be provided by employing a suitable clinical decision support system (CDSS) for healthcare management. CDSS assists the clinicians in identifying the severity of disease at the time of admission and predicting its progression. In this chapter, CDSS was developed with the help of statistical techniques. Modified cascade neural network (ModCNN) was built upon the architecture of cascade-correlation neural network (CCNN). ModCNN first identifies the independent factors associated with disease and using that factor; it predicts its progression. A case progressing towards severity can be given better care, avoiding later stage complications. Performance of ModCNN was evaluated and compared with artificial neural network (ANN) and CCNN. ModCNN showed better accuracy than other statistical techniques. Thus, CDSS developed in this chapter is aimed at providing better treatment planning by reducing medical error. © 2021, IGI Global.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.
- «
- 1 (current)
- 2
- 3
- »