Papers by Ashalatha Nayak
Parallel Implementation of DNA Cryptography Encryption Scheme using MPI and CUDA
Construction and evaluation of metaontology using databases
2015 Annual IEEE India Conference (INDICON), 2015
Ontologies perform the cumbersome task of translating data on the web into a form suitable for ma... more Ontologies perform the cumbersome task of translating data on the web into a form suitable for manipulation by machines. The discovery of concepts and relationships from unstructured text is a crucial and challenging task in constructing ontology (s). A pragmatic solution is offered by a metaontology as it supplements the ontology with related concept pairs and relationships. An ideal approach to construct a metaontology is to employ databases as they save on the time required to store, retrieve and update data. The relationships in the database are augmented by converting them into a graph to determine transitive relationships. Accuracy is ensured by integrating only those relationships with the ontology which have a high degree of certainty. This is affirmed by the evaluation and the results obtained using the ontology constructed along the lines of the metaontology.
Interdisciplinary Journal of Information, Knowledge, and Management, 2017
NC 4.0) This article is licensed it to you under a Creative Commons Attribution-NonCommercial 4.0... more NC 4.0) This article is licensed it to you under a Creative Commons Attribution-NonCommercial 4.0 International License. When you copy and redistribute this paper in full or in part, you need to provide proper attribution to it to ensure that others can later locate this work (and to ensure that others do not accuse you of plagiarism). You may (and we encourage you to) adapt, remix, transform, and build upon the material for any non-commercial purposes. This license does not permit you to use this material for commercial purposes.
Document Preparation For Engineering Education :A Case Study using LaTeX
Education demands creating, editing and presenting topics using document preparation software. Vi... more Education demands creating, editing and presenting topics using document preparation software. Visual design editors and logical design editors are the two broad classes of document preparation systems. Example for Visual design editor include Microsoft word, Powerpoint etc. Example for logical design editor include TEX,LATEX. Proprietary software and open source software are the two broad classes of document typesetting software. In this paper logical design using open source free LATEXsoftware is discussed. The application of LATEXin various formats and in various Engineering subjects is also discussed.
A Neural Attention Model for Automatic Question Generation Using Dual Encoders
Advances in Intelligent Systems and Computing, 2021
A novel approach to generate distractors for Multiple Choice Questions
Expert Systems with Applications
RandomCoCo.txt
Input file comprising of randomly selected compound and complex sentences for simplification.
RandomCoCo_output.txt
Dataset comprises of randomly selected complex as well as compound sentences which are transforme... more Dataset comprises of randomly selected complex as well as compound sentences which are transformed into simple sentences
International Journal of Web Engineering and Technology, 2017
Tacit knowledge externalisation (TKE) is a vital business process used in decision-making, busine... more Tacit knowledge externalisation (TKE) is a vital business process used in decision-making, business innovation and problem-solving activities within an enterprise. The paper proposes a Web 2.0-based internal crowdsourcing workflow that provides a generic and flexible structure for the process of externalisation. The workflow comprises crowd creation, crowd opinion, crowd voting, crowd wisdom and crowd learning phases, which encompass knowledge elicitation, sharing and utilisation activities that occur during the externalisation process. The workflow is implemented as an ASP.NET web application titled TKApp, measured using the certainty-factor model and demonstrated for a decision-making scenario in a start-up company. Additionally, the core logic of the workflow is developed as a SOAP-based web service and deployed publicly, thus empowering any enterprise to reuse the service for externalisation purposes.
Machine learning models to predict the dropouts in Massive Open Online Courses
2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), 2018
Massive Open Online Courses have emerged as an alternative to the traditional educational system ... more Massive Open Online Courses have emerged as an alternative to the traditional educational system because of the flexibility in timings and also it overcomes the economic and geographical barriers for the users. MOOCs also help learners from diverse background to communicate and exchange knowledge in MOOCs forums. The number of learners enrolling for such courses is very high, despite the unrestricted accessibility the completion rate is very low. Various factors affect the completion of the course by the students such as interest in the subject, purpose of enrolling in the subject, whether the lecturer is able to convey his knowledge to the students or not. EDM (Educational Data Mining) and LA (Learning Analytics) are the fields in which data of students learning activity is analyzed to obtain certain vital information or can be used in prediction using EDM tools and techniques. Data analysis shows that there is a strong relationship between the number of events such as click event, video watched forum post and the successful learner's outcome. Machine Learning algorithms are applied and the result shows that Decision Tree gives an optimum result with the highest performance.
Information Extraction using Rule based software agents in Knowledge grid
For the successful information processing and handling of document collections, effective informa... more For the successful information processing and handling of document collections, effective information extraction methods are necessary. A distributed team work environment requires team knowledge management. A knowledge flow exists in team work processes and this knowledge flow reflects the knowledge level cooperation in team work, which in turn defines the effectiveness of team work. Distributed software development team focuses on work co-operation and resource sharing between members during software development life cycle and knowledge flow should reflect cognitive cooperation process dynamically. Hence each team member can use experience of predecessor accumulated during previous projects and avoid redundant work. With the advent of the networks, the system specification is done in one geographic area and the design in some other place. The entire software development process has distributed resources such as five generic up-level ontologies and a knowledge based [KB] issues and...
Different Machine Learning Models to Predict Dropouts in MOOCs
2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018
Massive Open Online Courses have emerged as an alternative to the traditional educational system ... more Massive Open Online Courses have emerged as an alternative to the traditional educational system because of the flexibility in timings and also it overcomes the economic and geographical barriers for the users. MOOCs also help learners from diverse background to communicate and exchange knowledge in MOOCs forums. The number of learners enrolling in such courses is very high. Despite the unrestricted accessibility, the completion rate is very low. Various factors affect the completion of the course by the students such as interest in the subject, the purpose of enrolling in the subject, whether the lecturer is able to convey his knowledge to the students or not. EDM (Educational Data Mining) and LA (Learning Analytics) are the fields in which data of students learning activity is analyzed to obtain certain vital information or can be used in prediction using EDM tools and techniques. Data analysis shows that there is a strong relationship between the number of events such as click event, video watched, forum post and the successful learner's outcome. Machine Learning algorithms are applied on the dataset from HarvardX and the result shows that Random Forest gives an optimum result with the highest performance.
Information Discovery and Delivery, 2020
Purpose The purpose of this study is to develop an efficient prediction model using vital signs a... more Purpose The purpose of this study is to develop an efficient prediction model using vital signs and standard medical score systems, which predicts the clinical severity level of the patient in advance based on the quick sequential organ failure assessment (qSOFA) medical score method. Design/methodology/approach To predict the clinical severity level of the patient in advance, the authors have formulated a training dataset that is constructed based on the qSOFA medical score method. Further, along with the multiple vital signs, different standard medical scores and their correlation features are used to build and improve the accuracy of the prediction model. It is made sure that the constructed training set is suitable for the severity level prediction because the formulated dataset has different clusters each corresponding to different severity levels according to qSOFA score. Findings From the experimental result, it is found that the inclusion of the standard medical scores and t...
Modeling data races using UML/MARTE profile
2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2014
Unified Modeling Language(UML) is a standard language for modeling in the domain of Object Orient... more Unified Modeling Language(UML) is a standard language for modeling in the domain of Object Oriented Software Development. However, it lacks the modeling construct for real time systems. The UML profile for Modeling and Analysis of Real Time Embedded Systems (MARTE) has been recently standardized by Object Management Group (OMG) to provide the necessary constructs. It provides support for Model Driven Engineering (MDE) of real time systems. The goal of this paper is to present the UML/MARTE profile in identifying a concurrency issue known as data race. The proposed approach leads to a supporting tool for automated detection of data races in which UML Sequence diagram is used to specify the temporal ordering of messages.
International Journal of Artificial Intelligence in Education
Multiple Choice Questions (MCQs) are a popular assessment method because they enable automated ev... more Multiple Choice Questions (MCQs) are a popular assessment method because they enable automated evaluation, flexible administration and use with huge groups. Despite these benefits, the manual construction of MCQs is challenging, time-consuming and error-prone. This is because each MCQ is comprised of a question called the "stem", a correct option called the "key" along with alternative options called "distractors" whose construction demands expertise from the MCQ developers. In addition, there are different kinds of MCQs such as Wh-type, Fill-in-the-blank, Odd one out, and many more needed to assess understanding at different cognitive levels. Automatic Question Generation (AQG) for developing heterogeneous MCQ stems has generally followed two approaches: semantics-based and machine-learning-based. Questions generated via AQG techniques can be utilized only if they are grammatically correct. Semantics-based techniques have been able to generate a range ...
Cornell University - arXiv, Aug 26, 2021
Autonomous exploration of unknown environments is a vital function for robots and has application... more Autonomous exploration of unknown environments is a vital function for robots and has applications in a wide variety of scenarios. Our focus primarily lies in its application for the task of efficient coverage of unknown environments. Various methods have been proposed for this task and frontier based methods are an efficient category in this class of methods. Efficiency is of utmost importance in exploration and heuristics play a critical role in guiding our search. In this work we demonstrate the ability of heuristics that are learnt by imitating clairvoyant oracles. These learnt heuristics can be used to predict the expected future return from selected states without building search trees, which are inefficient and limited by on-board compute. We also propose an additional filter-based heuristic which results in an enhancement in the performance of the frontier-based planner with respect to certain tasks such as coverage planning.
NS-2 extension for interface assignment in AODV routing protocol
2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)
Network Simulator(NS-2) is an open source discrete event simulator, widely used by the networking... more Network Simulator(NS-2) is an open source discrete event simulator, widely used by the networking research community. NS-2 provides flexibility for the researcher to extend the simulator functionality for any new area of research in networks. The primary objective of the paper is to investigate the development and simulation of the interface assignment in multi-interface multi-channel wireless adhoc network in NS-2. Accordingly, existing ad hoc on-demand distance vector(AODV) routing protocol which was designed for single interface single channel (S-AODV) was studied and modified to support multi-interface multi-channel (M-AODV)configuration. Simulation results show better performance of M-AODV over S-AODV.
IEEE Access
Controlling the mortality rate at the Mass Casualty Incident presents an increasingly important c... more Controlling the mortality rate at the Mass Casualty Incident presents an increasingly important challenge for Emergency service organizations. Preparation is required by any healthcare system to minimize the loss of life and maximize casualty recovery. The literature conjectures that casualty rates can be decreased by integrating technology with the emergency service management system. To develop a superior mortality rate-controlling plan it is critical to anticipate the clinical condition deterioration of the casualties and effectively serve a large number of casualties with an optimal number of medical resources. Thus, this research proposes a multi methodology approach that integrates a prediction model to forecast the worsening of the casualties' clinical conditions with an optimization model to detect the number of medical resources needed to treat the casualties. The method incorporates the Gravitational Search based Back Propagation Neural Network-based prediction model together with the qSOFA medical score to produce an accurate casualty' clinical condition prediction. The findings of the prediction model are then combined with methods to identify in advance the optimum number of medical resources needed to control the rate of incoming casualties. The proposed multi-methodological approach experimented on the MIMIC-II dataset results show that clinical condition prediction and allocation of the optimal number of medical resources supports reduction in mortality length. The prediction model has the Accuracy, Sensitivity, and Specificity values 91.9%, 94.7%, and 83.9% respectively. Further, the optimization model is compared with the literature work and the result shows the better performance with regard to mortality length and Queue length performance parameters. The proposed work involving the prediction model of clinical conditions and the optimization model of medical resources facilitates clinicians to serve the casualties with better health treatment, thus reducing the mortality length.
A Statistical approach to evaluate the efficiency and effectiveness of the Machine Learning algorithms analyzing Sentiments
2019 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)
In the process of analyzing sentiments for a given dataset various machine learning techniques ar... more In the process of analyzing sentiments for a given dataset various machine learning techniques are used. The models using these learning algorithms help in determining the sentiments across the textual documents. There is a need to evaluate the effectiveness of the models in terms of analyzing and predicting sentiments. This paper provides a statistical approach to measure the effectiveness of the models and also evaluates their effectiveness with respect to the data representations. Here an experimental research is carried out with an inductive mode to measure and evaluate the models. The models are built using Decision Tree, Naive Bayes and Support Vector Machines. Data has been represented using features of Term Frequency and Inverse Document Frequency and Bag-of-words. Statistical tools used for measuring the models are Chi-square test and Analysis of Variance.
Translation Techies @DravidianLangTech-ACL2022-Machine Translation in Dravidian Languages
Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
Uploads
Papers by Ashalatha Nayak