Garuda - Garba Rujukan Digital

CLUSTER PREDICTION MODEL FOR MARKET BASKET ANALYSIS: QUEST FOR BETTER ALTERNATIVES TO ASSOCIATIVE RULE MINING APPROACH Ojugo, Arnold Adimabua; Eboka, Andrew Okonji
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 9, No 3: September 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v9.i3.pp%p

Market basket analysis seeks to apply association rule mining on the massive sales transaction data. It yields an outcome that either aims to suppress product stock-up unnecessarily and/or product being stock-out. Such decision support system seeks to avoid the unnecessary demurrage and help businesses to keep their customers via better decision and improved service. Market data are time-bound on supply-demand value chain. With customer behavior varying in time, we seek to predict purchase of commonly combined itemset for a next period ? so that businesses can better support their decisions via adequate provisions of the required inventory. We use 3-KDD dataset and Delta Mall dataset ? adapting a time-clustering algorithm that examines buying behavior of customers, their preferences and frequency with which goods are purchased in common as a basket. Model yields average 162-rules for four-dataset from dataset. Result shows that previous basket items by random customers allow the selection purchase of items of similar value as best combined due to its shelf-placement using the concept of feature drift.

An Empirical Evaluation On Comparative Machine Learning Techniques For Detection of The Distributed Denial of Service (DDoS) Attacks Ojugo, Arnold; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 2 No. 1 (2020)
Publisher : Yayasan Ahmar Cendekia Indonesia

The advent of the Internet that aided the efficient sharing of resources. Also, it has introduced adversaries whom are today restlessly in their continued efforts at an effective, non-detectable means to invade secure systems, either for fun or personal gains. They achieve these feats via the use of malware, which is both on the rise, wreaks havoc alongside causing loads of financial losses to users. With the upsurge to counter these escapades, users and businesses today seek means to detect these evolving behavior and pattern by these adversaries. It is also to worthy of note that adversaries have also evolved, changing their own structure to make signature detection somewhat unreliable and anomaly detection tedious to network administrators. Our study investigates the detection of the distributed denial of service (DDoS) attacks using machine learning techniques. Results shows that though evolutionary models have been successfully implemented in the detection DDoS, the search for optima is an inconclusive and continuous task. That no one method yields a better optima than hybrids. That with hybrids, users must adequately resolve the issues of data conflicts arising from the dataset to be used, conflict from the adapted statistical methods arising from data encoding, and conflicts in parameter selection to avoid model overtraining, over-fitting and over-parameterization.

An Empirical Evaluation On Comparative Machine Learning Techniques For Detection of The Distributed Denial of Service (DDoS) Attacks Ojugo, Arnold; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 2 No. 1 (2020)
Publisher : Yayasan Ahmar Cendekia Indonesia

The advent of the Internet that aided the efficient sharing of resources. Also, it has introduced adversaries whom are today restlessly in their continued efforts at an effective, non-detectable means to invade secure systems, either for fun or personal gains. They achieve these feats via the use of malware, which is both on the rise, wreaks havoc alongside causing loads of financial losses to users. With the upsurge to counter these escapades, users and businesses today seek means to detect these evolving behavior and pattern by these adversaries. It is also to worthy of note that adversaries have also evolved, changing their own structure to make signature detection somewhat unreliable and anomaly detection tedious to network administrators. Our study investigates the detection of the distributed denial of service (DDoS) attacks using machine learning techniques. Results shows that though evolutionary models have been successfully implemented in the detection DDoS, the search for optima is an inconclusive and continuous task. That no one method yields a better optima than hybrids. That with hybrids, users must adequately resolve the issues of data conflicts arising from the dataset to be used, conflict from the adapted statistical methods arising from data encoding, and conflicts in parameter selection to avoid model overtraining, over-fitting and over-parameterization.

Extending Campus Network Via Intranet and IP-Telephony For Better Performance and Service Delivery: Meeting Organizational Goals Ojugo, Arnold Adimabua; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 1 No. 2 (2019)
Publisher : Yayasan Ahmar Cendekia Indonesia

The adoption of information and communication technology (ICT) tools and medium in todayâ€™s business, is geared to advance data processing tasks, timely exchange of data, easy access to the Internet at increased speed, extended memory to house large volumes of data, and better communications, etc. Businesses grow in lieu of advancing the services they offer; But, they require as a matter of urgency, a corresponding need for effective communication to grow exponentially. The Intranet provides an option to advance such via its many features (not limited to) collaborative communication channel, ease in business processes, etc. We posit that many businesses lack a clear strategy to implement an effective Intranet design. This often leads to investment profit loss, loss of time, unproductivity, and complete failure in achieving its set goals. Extending Ojugo and Eboka (2020) via a multi-service intranet, the study outcomes an infrastructure that allows the effective integration of data solutions via an open-source protocol, application, hardware, and software. Three common issues observed therein includes: packet loss, jitters, and latency. Jitters and packet loss can be resolved via increased bandwidth allocation; while, latency is minimized via upgrade in the infrastructure. Thus, our proposed solution seeks to provide users with mobility, resilience, economy, flexibility, and productivity with improved service delivery and performance. The study recommends that to harness the full benefits of Intranet and improve communication within businesses and organizations today, there is the need for a constant knowledge update is imperative, which will in turn improve effective communication in the implemented infrastructure.

Extending Campus Network Via Intranet and IP-Telephony For Better Performance and Service Delivery: Meeting Organizational Goals Ojugo, Arnold Adimabua; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 1 No. 2 (2019)
Publisher : Yayasan Ahmar Cendekia Indonesia

The adoption of information and communication technology (ICT) tools and medium in todayâ€™s business, is geared to advance data processing tasks, timely exchange of data, easy access to the Internet at increased speed, extended memory to house large volumes of data, and better communications, etc. Businesses grow in lieu of advancing the services they offer; But, they require as a matter of urgency, a corresponding need for effective communication to grow exponentially. The Intranet provides an option to advance such via its many features (not limited to) collaborative communication channel, ease in business processes, etc. We posit that many businesses lack a clear strategy to implement an effective Intranet design. This often leads to investment profit loss, loss of time, unproductivity, and complete failure in achieving its set goals. Extending Ojugo and Eboka (2020) via a multi-service intranet, the study outcomes an infrastructure that allows the effective integration of data solutions via an open-source protocol, application, hardware, and software. Three common issues observed therein includes: packet loss, jitters, and latency. Jitters and packet loss can be resolved via increased bandwidth allocation; while, latency is minimized via upgrade in the infrastructure. Thus, our proposed solution seeks to provide users with mobility, resilience, economy, flexibility, and productivity with improved service delivery and performance. The study recommends that to harness the full benefits of Intranet and improve communication within businesses and organizations today, there is the need for a constant knowledge update is imperative, which will in turn improve effective communication in the implemented infrastructure.

Modeling Behavioural Evolution as Social Predictor for the Coronavirus Contagion and Immunization in Nigeria Ojugo, Arnold Adimabua; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 3 No. 2 (2021)
Publisher : Yayasan Ahmar Cendekia Indonesia

Since the outbreak of the novel coronavirus (covid-19) pandemic from China in 2019, it has left the world leaders in great confusing due to its fast-paced propagation and spread that has left infected a world population of over Eleven Million persons with over five hundred and thirty four thousand deaths and counting with the United States of America, Brazil, Russia, India and Peru in the lead on these death toll. The pandemic whose increased mortality rate is targeted at â€˜agedâ€™ citizens, patients with low immunology as well as patients with chronic diseases and underlying health conditions. Study models covid-19 pandemic via a susceptible-infect-remove actor-based graph, with covid-19 virus as the innovation diffused within the social graph. We measure the rich connective patterns of the actor-based graph, and explore personal feats as they influence other nodes to adopt or reject an innovation. Results shows current triggers (lifting of inter-intra state migration bans) and shocks (exposure to covid-19 by migrants) will lead to late widespread majority adoption of 23.8-percent. At this, the death toll will climb from between 4.43-to-5.61-percent to over 12%.

Modeling Behavioural Evolution as Social Predictor for the Coronavirus Contagion and Immunization in Nigeria Ojugo, Arnold Adimabua; Eboka, Andrew Okonji
Journal of Applied Science, Engineering, Technology, and Education Vol. 3 No. 2 (2021)
Publisher : Yayasan Ahmar Cendekia Indonesia

Since the outbreak of the novel coronavirus (covid-19) pandemic from China in 2019, it has left the world leaders in great confusing due to its fast-paced propagation and spread that has left infected a world population of over Eleven Million persons with over five hundred and thirty four thousand deaths and counting with the United States of America, Brazil, Russia, India and Peru in the lead on these death toll. The pandemic whose increased mortality rate is targeted at â€˜agedâ€™ citizens, patients with low immunology as well as patients with chronic diseases and underlying health conditions. Study models covid-19 pandemic via a susceptible-infect-remove actor-based graph, with covid-19 virus as the innovation diffused within the social graph. We measure the rich connective patterns of the actor-based graph, and explore personal feats as they influence other nodes to adopt or reject an innovation. Results shows current triggers (lifting of inter-intra state migration bans) and shocks (exposure to covid-19 by migrants) will lead to late widespread majority adoption of 23.8-percent. At this, the death toll will climb from between 4.43-to-5.61-percent to over 12%.

Empirical Evaluation for Intelligent Predictive Models in Prediction of Potential Cancer Problematic Cases In Nigeria Ojugo, Arnold Adimabua; Obruche, Chris Obaro; Eboka, Andrew Okonji
ARRUS Journal of Mathematics and Applied Science Vol. 1 No. 2 (2021)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience614

The rapid rate as well as the volume in amount of data churned out on daily basis has necessitated the need for data mining process. Advanced by the field of data science with machine learning approaches as new paradigm and platform, it has become imperative to provide beneficial support in constructing models that can effectively assist domain experts/practitioners â€“ to make comprehensive decisions regarding potential cases. The study uses deep learning prognosis to effectively respond to problematic cases of cancer in Nigeria. We use the fuzzy rule-based memetic model to predict potential problematic cases of cancer â€“ predicting results from data samples collected from the Epidemiology laboratory at Federal Medical Center Asaba, Nigeria. Dataset is split into training (85%) and testing (15%) to aid model validation. Results indicate that age, obesity, environmental conditions and family relations (to the first and second degree) are critical factors to be watched for benign and malignant cancer types. Constructed model result shows high predictive capability strength compared to other models presented on similar studies.

Quest For Convergence Solution Using Hybrid Genetic Algorithm Trained Neural Network Model For Metamorphic Malware Detection Ojugo, Arnold Adimabua; Obruche, Chris Obaro; Eboka, Andrew Okonji
ARRUS Journal of Engineering and Technology Vol. 2 No. 1 (2022)
Publisher : Lembaga Penelitian dan Pengembangan Teknologi dan Rekayasa, Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/jetech613

An unstable economy is rife with fraud. Perpetrated on customers, it ranges from employeesâ€™ internal abuse to large fraud via high-value contracts cum control breaches that impose serious consequences to biz. Loyal employees may not perpetrate fraud if not for societal pressures and economic recession with its rationalization that they have bills to pay and children to feed. Thus, the need for financial institutions to embark on effective measures via schemes that will aids both fraud prevention and detection. Study proposes genetic algorithm trained neural net model to accurately classify credit card transactions. Compared, model used a rule-based system to provide it with start-up solution and it has a fraud catching rate of 91% with a consequent, false alarm rate of 9%. Its convergence time is found to depend on how close the initial solution space is to the fitness function, and for recombination and mutation rates applied.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search