Mrs. OJIE DEBORAH VOKE
Publication Title A Framework for Feature Selection using Data Value Metric and Genetic Algorithm
Publication Type journal
Publisher International Journal of Computer Applications
Publication Authors Ojie Deborah Voke , Akazue Maureen, Imianvan Anthony
Year Published 1-04
Abstract Most organizations analyse input data to develop an accurate description or model using the features present in the data. There have been huge amount of generated data in the big data ecosystem which demand better and efficient ways to distil high utility or value from it so as to compliment decision makers in making recommendations and decisions. Before applying classification algorithm, relevant features are selected by a suitable feature selection algorithm. Data Value Metric (DVM) is an information theoretic measure based on the notion of mutual information which has been shown to be a good metric to validate the quality and utility of data in a big data ecosystem and in traditional data. Data Value Metric (DVM) suffers from local minima and loss of diversity in the population since it is using forward selection search strategy, however, hybridizing it with Genetic Algorithm is hoped to overcome the problem of local minima as there would be a blend of evolutionary search to ensure a balance between exploration and exploitation of the search space. This paper proposed the hybrid model of Genetic Algorithm and Data Value Metric (DVM) as an information theoretic metric for quantifying the quality and utility for feature selection which can be applied to traditional data.
Publication Title WEB-BASED ACADEMIC ADVISING SYSTEM FOR NIGERIAN UNIVERSITIES
Publication Type journal
Publisher Global Scientific Journal
Paper Link www.globalscientificjournal.com
Publication Authors Ogala, Justin Onyarin & Ojie, Deborah V.
Year Published 2-02
Abstract Web-based academic advising system was designed to facilitate more accurate advising sessions
on campus, as well as provide a complete history of past advising sessions. Advisors may select
which courses they wish a student to register in, up to several semesters in to the future, as well as
leave comments for the student and other campus staff. The system was designed and developed
using Relational Data Model (RDM) and Data Flow Diagram (DFD) and was implemented using
PHP and MySQL programming languages. The researchers have developed an interactive webbased
information system that can help Nigerian universities to facilitate more accurate advising
sessions on campus and make important decisions. The developed System can handle errors,
updates and modification of data more efficiently and can be accessed anywhere and anytime than
the manual methods of academic advising system. This paper describes an Advisement System
designed to mitigate the issues of an out- of-the-box implementation in Nigerian university to help
improve retention and graduation. A successful implementation of this research study would
enable the main objective of this system to assist Nigerian universities orientation camp in solving
the problems associated with the manual method of academic advising system.
Publication Title THE BORDERLESS WORLD-INFORMATION AND COMMUNICATION TECHNOLOGY (GREEN); BRIDGING DIGITAL GAP IN EDUCATION.
Publication Type conference
Publisher Association for Digital Education and Communications Technology Conference Proceedings
Publication Authors AGHWARE F. O (PHD); MALASOWE B. O (PHD); AND OJIE D. V
Year Published 1-03
Abstract A colossal causatum of the COVID-19 sudden happening is the radical global embrace of Information and Communication Technology (ICT) in all spheres of the education sector especially in developed economies regardless the preparedness. Going by the new normal kind of, irrespective of the imminent challenges of its prior ubiquitous adoption, there is now a swift resultant ICT inclusion in which the economy is wholly driven by ICT. Notably in education, the COVID -19 disruption scaled up ICT as an instantaneous apparatus to subsist the teaching and learning sector during the universal lockdown which ravaged the whole world between 2019 through 2020 of which the impact still evident. Again, the out break of the Pandemic revealed to many world leaders in many developing countries that they had no choice than to embrace an ICT instrument propelling the development of national knowledge-base. Regardless the superficial hitches in ICT integration in teaching and learning, the effects of the COVID-19 pandemic fast tracked ICT penetration hence today, teachers and students in Nigeria and in deed worldwide had no choice than to work online notwithstanding their preparedness in terms of knowledge, skills and resources for the implemetation ICT in teaching and learning. In as much as ICT has come to stay in bridging the gaps in the education sector to in today bortherless world, the place of Green Information Technology must be acknowledged. This research paper addresed how ICT instantaneously bridged the educational gaps in a pandemic inclusive lockdown; and addressing Green IT as it affects our ecosystem. The research has provided the necessary information and details why there should be compulsory implementation of ICT in education to truely bridge the digital gap that existed in the education sector in our today botherless world thus proffering how best to deploy the ICT tools in securing the ecosystem.
Publication Title A Framework for Smart City Model Enabled by Internet of Things (IoT)
Publication Type journal
Publisher International Journal of Computer Applications
Publication Authors Ihama E.I. , Akazue M.I. Omede Edith, Ojie Deborah
Year Published 2023-05-05
Abstract The advancement in wireless telecommunication network has
increase the accessibility of more users to wireless
connectivity. With the advent of the fifth-generation (5G)
wireless network, a seamless connectivity is available for
internet users globally. A smart city is a metropolis that utilizes
information and communication technologies (ICT) to grow its
functionality effectively to disseminate information among the
public and to develop the quality of government facilities and
the welfare of the citizen. The Internet of Things (IoT) refer to
the interconnection of several systems, devices or physical
objects/things which are driven by sensors, software, and other
equipment in order to interconnect and interchange data with
other devices and systems through the internet. The Internet of
things (IoT), is a revolutionary method that allows a diverse
number of applications to be interconnected in order to create a
single communication architecture. Urbanization has resulted
in the increase in population, hence there is need to develop a
smart traffic light system to help in managing the problem of
urbanization; traffic congestion. The Internet of Things (IoT) a
key features necessary for employing a large-scale in IoTS are
low-cost sensors, high-speed and error-tolerant data
communications, smart computations, and numerous
applications which helps in solving these challenges associated
with traffic congestion. It enables a smart environment, smart
energy, smart transportation system. In this paper, we shall
discuss IoT technology, review some literatures on application
area of Internet of Things (IoT), and challenges of IoT. And
also discuss the applications of IoT, in smart city development,
and traffic congestion management in smart city design, and
how it proffers solution to urbanization problem.
Publication Title Theoretical Utility of Data Value Metric and Genetic Algorithms for Variable Clustering in an Unsupervised Learning Environmen
Publication Type journal
Publisher Caliphate Journal of Science & Technology (CaJoST)
Paper Link https://dx.doi.org/10.4314/cajost.v6i1.13
Publication Authors Okpako A. Ejaita1 and Ojie D. Voke2
Year Published 2024-01-01
Abstract Cluster analysis is regarded as one of the most important unsupervised
learning tasks, with its natural application in dividing data into meaningful
groups, also known as clusters, based on the information in the data by
describing the objects in terms of their relationships and capturing the data's
natural structure. Many traditional performance evaluation metrics for
clustering algorithms abound in the literature, treating various attributes or
variables equally when measuring similarity; however, different attributes or
variables may contribute differently due to the amount of information they
contain, which can vary greatly. Data Value Metric (DVM) is an information
theoretic measure based on the concept of mutual information that has been
shown to be a good metric for validating data quality and utility in a big data
ecosystem and in traditional data. Because it uses a forward selection
search strategy, Data Value Metric (DVM) suffers from local minima and
loss of diversity in the population; however, hybridizing it with Genetic
Algorithm will overcome the problem of local minima because there will be a
blend of evolutionary search to ensure a balance between exploration and
exploitation of the search space. This paper proposed a hybrid model of the
Genetic Algorithm and the Data Value Metric (DVM) as an information theoretic metric for quantifying the quality and utility of variable clustering selection that can be applied to traditional data.