Papers by mehrotra deepti
Interdisciplinary Journal of e-Skills and Lifelong Learning, 2014
Today Learning Management Systems (LMS) have become an integral part of learning mechanism of bot... more Today Learning Management Systems (LMS) have become an integral part of learning mechanism of both learning institutes and industry. A Learning Object (LO) can be one of the atomic components of LMS. A large amount of research is conducted into identifying benchmarks for creating Learning Objects. Some of the major concerns associated with LO are size, learning outcomes, pedagogical relevance, and amount of information it delivers to learners. With the advent of knowledge enriched learning, there is a need to create Knowledge Objects (KO) as well and combine these with LOs to create Learning Knowledge Objects (LKO), which can be delivered through an LMS, so that a more holistic knowledge bank is provided to the learners. For an effective LMS, creating a high quality LKO using an algorithm that ensures the delivery of appropriate learning material to the learners is the key issue. Smaller and relevant objects can be delivered to the student using data mining approaches, thereby helping advanced learners to improve their higher order thinking skills. Use of hierarchical clustering techniques for identifying LOs based on user needs is already established. In this paper the Shared Density Approach (SDA) is used to get cohesive clusters and handle cluster of different densities. Finding similar learning objects through clustering technique reduces the domain of search. SDA not only helps with delivery of Learning Objects from a relevant cluster, but also helps in finding objects that are closer to one another but belong to a different class. Objects can be delivered based on user learning approaches, thereby have a wider usage and thus improve re-accessibility.
Electronic Journal of Health Informatics, Dec 16, 2014
Sharing of health data between independent organizations, each using customized Electronic Health... more Sharing of health data between independent organizations, each using customized Electronic Health Records (EHR) management systems or Healthcare Information System (HIS) encompasses major concerns. It requires an integrated interoperable environment or interface commonly understood by end-users of healthcare domain. The sheer number of systems, standards, procedures and system developers seriously hinders interoperability. Developers need to adhere to the standards while designing such system. Developing standardized interfaces would enable seamless communication and transfer of required EHR between disparate systems. The paper after giving a detailed overview of interoperability identifies the challenges to Health Informatics data-exchange in interoperable environment and recommends some viable solutions in this direction. This paper provides a glance at different approaches of designing interoperable models and illustrates the healthcare models designed on such approaches. The study also includes available set of vocabularies, formats and standards specifically designed for the purpose. Considering the Health environment, protecting the confidentiality and illegal disclosure during transfer of EHR between organizations, is a serious concern. Vendors incorporate customized and vendor-dependent security attributes while designing the application, resulting in major challenge of securely sharing of data. The paper includes available security controls and gaps accruing due to interoperability and recommends the need of robust security control improving accessibility and availability of EHR at the required place by the authorized user.
International Journal of Software Engineering and Its Applications, 2015
Software designers are motivated to utilize off-the-shelf software components for rapid applicati... more Software designers are motivated to utilize off-the-shelf software components for rapid application development. Such applications are expected to have high reliability as a result of deploying trusted components. This paper introduces Halstead's software science to predict the fault before testing phase for component based system. Halstead's software science is used to predict the faults for individual component and based on this faults reliability of different component is measured so that only reliable component will be reused.
With the increase in the complexity of software systems, the fault rate increases, which results ... more With the increase in the complexity of software systems, the fault rate increases, which results in an exponential increase of errors and leads to decrease of reliability of the system. For predicting the reliability of any system all errors are recorded in the error logs. This is because predictable and frequently occurring errors which are of crucial interest from the huge error log, is of utmost important. In this paper it is attempt to show how error logs are being analyzed to predict reliability, using the A-priori algorithm
This research emphasizes the need to find out the faults from software system to evaluate it for ... more This research emphasizes the need to find out the faults from software system to evaluate it for its quality. Software metrics can be used to collect information regarding structural properties of a software design which can be further statistically analyzed, interpreted and linked to its quality. Metrics information can be collected from internal design like logic & algorithmic details as well as from the external design i.e. interfaces of software. There are various software metrics exists which can measure the faults from the software system, in this paper various faults prediction and classification techniques has been studied to find out the faults from the software system. This research identifies a set of metrics to measure and classify the faults from the software systems.
Procedia Computer Science, 2015
With the advent of K-economy, all leading business organizations are incorporating knowledge mana... more With the advent of K-economy, all leading business organizations are incorporating knowledge management as an integral part of their functioning. Education sector, though a non-profit domain has also witnessed increase in the implementation of business intelligence and knowledge centric processes over the years. The paper exemplifies the importance of knowledge evaluation in higher education organizations, through measures developed using data mining techniques. Applying these knowledge measures or indicator in the education domain eventually help the higher education organizations to establish themselves as knowledge centric higher education organizations (KCHEO).
Effective Curriculum Development through Rule Induction in Knowledge Centric Higher Education Organization
Confluence 2013: The Next Generation Information Technology Summit (4th International Conference), 2013
ABSTRACT The whole shift of the business domain from product based economy to knowledge based eco... more ABSTRACT The whole shift of the business domain from product based economy to knowledge based economy has created a stir in the working environment of various organizations. They now take substantial steps to increase their knowledge base which can help them to sustain in longer run. With the advent of privatization in education and cut throat competition among educational institutions, the same is applicable to this not-for-profit domain also. This paper substantiates the role of data mining technique of rule induction in knowledge acquisition for the knowledge base of a knowledge centric higher education organization.
Applied Soft Computing, 2014
This paper surveys strategies applied to avoid premature convergence in Genetic Algorithms (GAs).... more This paper surveys strategies applied to avoid premature convergence in Genetic Algorithms (GAs). Genetic Algorithm belongs to the set of nature inspired algorithms. The applications of GA cover wide domains such as optimization, pattern recognition, learning, scheduling, economics, bioinformatics, etc. Fitness function is the measure of GA, distributed randomly in the population. Typically, the particular value for each gene start dominating as the search evolves. During the evolutionary search, fitness decreases as the population converges, this leads to the problems of the premature convergence and slow finishing. In this paper, a detailed and comprehensive survey of different approaches implemented to prevent premature convergence with their strengths and weaknesses is presented. This paper also discusses the details about GA, factors affecting the performance during the search for global optima and brief details about the theoretical framework of Genetic algorithm. The surveyed research is organized in a systematic order. A detailed summary and analysis of reviewed literature are given for the quick review. A comparison of reviewed literature has been made based on different parameters. The underlying motivation for this paper is to identify methods that allow the development of new strategies to prevent premature convergence and the effective utilization of genetic algorithms in the different area of research.
Journal of Information Technology and Application in Education, 2014
E-learning today shows an exponential growth and there is a need to develop more flexible deliver... more E-learning today shows an exponential growth and there is a need to develop more flexible delivery processes, which will add value to the learning experiences of a student during his/her learning process. The atomic unit of any e-learning environment is a Learning Object, a reusable digital entity. These Learning Objects are stored in repositories and managed by Learning Management Systems in order to provide a better coverage of concepts to the learner. A close relative of Learning Object is the Knowledge Object which is an essential unit of a Knowledge Management System. In this research paper, a way is proposed to converge these objects together and most similar Learning Knowledge Objects delivered to a student using hierarchical clustering techniques. The learning experience is more valuable for a student especially for those with higher order thinking skills.
2012 Third International Conference on Computer and Communication Technology, 2012
Research and Academic Institutions own and archive a great number of documents like lesson plan, ... more Research and Academic Institutions own and archive a great number of documents like lesson plan, study material and research related resources, which are needed to be stored and used over for a longer period of time by lecturers and researchers. In order to achieve this it is required to convert these educational resources into Learning Objects and store them in structured & meaningful way via a learning management system (LMS) thus enriching classical teaching. Also with enhancement of e-learning environment there is a great need of managing the LMS repositories by storing information resources as Learning object, a digital entity which can be used in electronic learning environment. These learning objects are stored in repositories and are managed by Learning Management Systems. It aids teaching and learning process and helps in communications between users. Many designs of LMS are non user-centric and has limited capabilities in delivering user preferred learning material. Searching through keywords or metadata of learning material will result in display of huge quantity of information. Thus there is an earnest need to identify the techniques that can provide more efficient mechanism for information retrieval. Recommendation techniques have shown to be successful in many domains (e.g. movies, books, music, etc.). Thus there is a need to deploy a recommending system in the E-Learning domain to extend the functionality of standardbased learning management systems with providing the user based retrieval. In this paper a model is being proposed that can enhance the search and delivery of a relevant learning object based on his/her preferences and further ranking & clustering of learning objects are done through K-Mean and Self Organising Maps for a personalised learning environment.
The most important dimension of learning is the content, and a Learning Management System (LMS) s... more The most important dimension of learning is the content, and a Learning Management System (LMS) suffices this to a certain extent. The present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a user centric approach. These features can suffice the need of all learners, when they have different learning requirements. For a true learning, knowledge should also be delivered along with the domain information. There is a need to design an architecture for user centric Knowledge Driven Learning Management System (KDLM). Thus, for holistic learning, knowledge enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched learning ca...
International Journal of Information Engineering and Electronic Business, 2015
With the advent of dynamic website usually all business processes of a business organization are ... more With the advent of dynamic website usually all business processes of a business organization are linked with the website of the organization. This is resulted in designing of a complex and gigantic website which may result in slow download and unfriendly navigation. Satisfying the end user need is one of the key principles of designing an effective website. As there are different users for given website, hence there are different criteria on which user wants to get satisfied, hence evaluating a website is a multi-criteria decision making problem. In order to incorporate uncertainties and vagueness in decision making Fuzzy Analytic Hierarchy (FAHP) approach is extended with Fuzzy TOPSIS approach, where different decision makers (DM's) opinion was considered for ranking the website.
Applying CHAID algorithm to investigate critical attributes of secured interoperable health data exchange
With enhanced interoperability in healthcare environment the
exchange of electronic health record... more With enhanced interoperability in healthcare environment the
exchange of electronic health records (EHRs), both intra and inter
organisations, has increased manifold. Sharing of the EHR creates room for
illegal disclosures and confidentiality breaches. Interoperable healthcare is a
complex system with many independent components. To design a secured
framework for such a system, one need to understand the most important
security attributes and predict various dependencies among them. The security
attributes selected for statistical analysis are taken from the real-time study of
patient-doctor relationship existing in any hospital or clinic. Hospitals with
functional EHR-systems are the prerequisite of this study. The dependencies in
the obtained data are generated through classification technique, chi-squared
automatic interaction detection (CHAID). The decision tree obtained is
analysed and verified using regression. The paper enabled the identification of
the salient feature controlling which would maximally reduce security threats
while sharing EHRs in interoperable healthcare environment.
This research emphasizes the need to find out the faults from software system to evaluate it for ... more This research emphasizes the need to find out the faults from software system to evaluate it for its
quality. Software metrics can be used to collect information regarding structural properties of a software design
which can be further statistically analyzed, interpreted and linked to its quality. Metrics information can be
collected from internal design like logic & algorithmic details as well as from the external design i.e. interfaces
of software. There are various software metrics exists which can measure the faults from the software system,
in this paper various faults prediction and classification techniques has been studied to find out the faults from
the software system. This research identifies a set of metrics to measure and classify the faults from the
software systems.
Software designers are motivated to utilize off-the-shelf software components for rapid applicati... more Software designers are motivated to utilize off-the-shelf software components for rapid application development. Such applications are expected to have high reliability as a result of deploying trusted components. This paper introduces Halstead’s software science to predict the fault before testing phase for component based system. Halstead’s software science is used to predict the faults for individual component and based on this faults reliability of different component is measured so that only reliable component will be reused.
With the advent of K-economy, all leading business organizations are incorporating knowledge mana... more With the advent of K-economy, all leading business organizations are incorporating knowledge management as an integral part of their functioning. Education sector, though a non-profit domain has also witnessed increase in the implementation of business intelligence and knowledge centric processes over the years. The paper exemplifies the importance of knowledge evaluation in higher education organizations, through measures developed using data mining techniques. Applying these knowledge measures or indicator in the education domain eventually help the higher education organizations to establish themselves as knowledge centric higher education organizations (KCHEO).
The most important dimension of learning is the content, and an LMS suffices this to a certain ex... more The most important dimension of learning is the content, and an LMS suffices this to a certain extent. The
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
The most important dimension of learning is the content, and an LMS suffices this to a certain ex... more The most important dimension of learning is the content, and an LMS suffices this to a certain extent. The
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
With the advent of dynamic website usually
all business processes of a business organization are
... more With the advent of dynamic website usually
all business processes of a business organization are
linked with the website of the organization. This is
resulted in designing of a complex and gigantic website
which may result in slow download and unfriendly
navigation. Satisfying the end user need is one of the key
principles of designing an effective website. As there are
different users for given website, hence there are different
criteria on which user wants to get satisfied, hence
evaluating a website is a multi-criteria decision making
problem. In order to incorporate uncertainties and
vagueness in decision making Fuzzy Analytic Hierarchy
(FAHP) approach is extended with Fuzzy TOPSIS
approach, where different decision makers (DM’s)
opinion was considered for ranking the website
Sharing of health data between independent organizations, each using customized Electronic Health... more Sharing of health data between independent organizations, each using customized Electronic Health Records (EHR) management systems or Healthcare Information System (HIS) encompasses major concerns. It requires an integrated interoperable environment or interface commonly understood by end-users of healthcare domain. The sheer number of systems, standards, procedures and system developers seriously hinders interoperability. Developers need to adhere to the standards while designing such system. Developing standardized interfaces would enable seamless communication and transfer of required EHR between disparate systems. The paper after giving a detailed overview of interoperability identifies the challenges to Health Informatics data-exchange in interoperable environment and recommends some viable solutions in this direction. This paper provides a glance at different approaches of designing interoperable models and illustrates the healthcare models designed on such approaches. The study also includes available set of vocabularies, formats and standards specifically designed for the purpose. Considering the Health environment, protecting the confidentiality and illegal disclosure during transfer of EHR between organizations, is a serious concern. Vendors incorporate customized and vendor-dependent security attributes while designing the application, resulting in major challenge of securely sharing of data. The paper includes available security controls and gaps accruing due to interoperability and recommends the need of robust security control improving accessibility and availability of EHR at the required place by the authorized user.
Uploads
Papers by mehrotra deepti
exchange of electronic health records (EHRs), both intra and inter
organisations, has increased manifold. Sharing of the EHR creates room for
illegal disclosures and confidentiality breaches. Interoperable healthcare is a
complex system with many independent components. To design a secured
framework for such a system, one need to understand the most important
security attributes and predict various dependencies among them. The security
attributes selected for statistical analysis are taken from the real-time study of
patient-doctor relationship existing in any hospital or clinic. Hospitals with
functional EHR-systems are the prerequisite of this study. The dependencies in
the obtained data are generated through classification technique, chi-squared
automatic interaction detection (CHAID). The decision tree obtained is
analysed and verified using regression. The paper enabled the identification of
the salient feature controlling which would maximally reduce security threats
while sharing EHRs in interoperable healthcare environment.
quality. Software metrics can be used to collect information regarding structural properties of a software design
which can be further statistically analyzed, interpreted and linked to its quality. Metrics information can be
collected from internal design like logic & algorithmic details as well as from the external design i.e. interfaces
of software. There are various software metrics exists which can measure the faults from the software system,
in this paper various faults prediction and classification techniques has been studied to find out the faults from
the software system. This research identifies a set of metrics to measure and classify the faults from the
software systems.
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
all business processes of a business organization are
linked with the website of the organization. This is
resulted in designing of a complex and gigantic website
which may result in slow download and unfriendly
navigation. Satisfying the end user need is one of the key
principles of designing an effective website. As there are
different users for given website, hence there are different
criteria on which user wants to get satisfied, hence
evaluating a website is a multi-criteria decision making
problem. In order to incorporate uncertainties and
vagueness in decision making Fuzzy Analytic Hierarchy
(FAHP) approach is extended with Fuzzy TOPSIS
approach, where different decision makers (DM’s)
opinion was considered for ranking the website
exchange of electronic health records (EHRs), both intra and inter
organisations, has increased manifold. Sharing of the EHR creates room for
illegal disclosures and confidentiality breaches. Interoperable healthcare is a
complex system with many independent components. To design a secured
framework for such a system, one need to understand the most important
security attributes and predict various dependencies among them. The security
attributes selected for statistical analysis are taken from the real-time study of
patient-doctor relationship existing in any hospital or clinic. Hospitals with
functional EHR-systems are the prerequisite of this study. The dependencies in
the obtained data are generated through classification technique, chi-squared
automatic interaction detection (CHAID). The decision tree obtained is
analysed and verified using regression. The paper enabled the identification of
the salient feature controlling which would maximally reduce security threats
while sharing EHRs in interoperable healthcare environment.
quality. Software metrics can be used to collect information regarding structural properties of a software design
which can be further statistically analyzed, interpreted and linked to its quality. Metrics information can be
collected from internal design like logic & algorithmic details as well as from the external design i.e. interfaces
of software. There are various software metrics exists which can measure the faults from the software system,
in this paper various faults prediction and classification techniques has been studied to find out the faults from
the software system. This research identifies a set of metrics to measure and classify the faults from the
software systems.
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
present day LMS are designed to primarily address issues like ease of use, search, content and performance. Many surveys
had been conducted to identify the essential features required for the improvement of LMS, which includes flexibility and a
user centric approach. These features can suffice the need of all learners, when they have different learning requirements.
For a true learning, knowledge should also be delivered along with the domain information. Thus, there is a need to design
an architecture for user centric Knowledge Driven Learning Management System. Thus for holistic learning, knowledge
enriched teaching skills are required, which can enhance and increase the thinking skills of the learner to a higher level. The
current LMS needs an improvement in the direction of knowledge discovery, exploration so that knowledge enriched
learning can be provided to the learner.. It can be based on knowledge engineering principles like ontology, semantic
relationship between objects, cognitive approach and data mining techniques. In this paper, we are proposing an idea of an
enhanced Learning Object (LO) called Knowledge Driven Learning Object, which can be delivered to the user for better
learning. We had used a data mining approach, classification to harness and exploit these objects and classify them
according to their metadata, thereby strengthening the content of objects delivered through the LMS.
all business processes of a business organization are
linked with the website of the organization. This is
resulted in designing of a complex and gigantic website
which may result in slow download and unfriendly
navigation. Satisfying the end user need is one of the key
principles of designing an effective website. As there are
different users for given website, hence there are different
criteria on which user wants to get satisfied, hence
evaluating a website is a multi-criteria decision making
problem. In order to incorporate uncertainties and
vagueness in decision making Fuzzy Analytic Hierarchy
(FAHP) approach is extended with Fuzzy TOPSIS
approach, where different decision makers (DM’s)
opinion was considered for ranking the website