George Okereke - Academia.edu (original) (raw)

Papers by George Okereke

Research paper thumbnail of Sentiment Analysis - An optimized Weighted Horizontal Ensemble approach

International journal of advanced trends in computer science and engineering, Apr 10, 2024

Sentiment Analysis has gained authority as one of the primary means of analyzing feedbacks and op... more Sentiment Analysis has gained authority as one of the primary means of analyzing feedbacks and opinion by individuals, organizations and governments. The result of sentiment analysis informs an organization on areas to improve and how best to manage customers. While sentiment analysis may be misleading as no algorithm has been considered 100% efficient, the choice of algorithms can optimize the result based on the dataset in question. This paper aims at studying various algorithms and implementing a weighted horizontal ensemble algorithm as a panacea to low confidence level in the results of sentiment analysis. We designed a system that implements the original Naive Bayes algorithm, Multinomial Naïve Bayes algorithm, Bernoulli Native Bayes algorithm, Logistic Regression algorithm, Linear Support Vector Classifier algorithm and the Stochastic Gradient Descent algorithm. Our dataset was sourced from the Stanford University. It contains fifty thousand (50,000) movie reviews. Dataset from the Nigerian movie review was used to test the models. The reviews were encoded as a sequence of word indices. An accuracy of over 91% was achieved. The Ensemble technique delivered an F1-measure of 90%. Ensemble technique provides a more reliable confidence level on sentiment analysis. The researchers also discovered that change in writing style can affect the performance of sentiment analysis.

Research paper thumbnail of Clustering Nigeria’s IDP Camps for Effective Budgeting and Re-Settlement Policies Using an Optimized K-Means Approach

African Conflict and Peacebuilding Review, Aug 31, 2023

Research paper thumbnail of Towards an improved internet of things sensors data quality for a smart aquaponics system yield prediction

Research paper thumbnail of A Mobile Application Based Optimized Out-Patient Emergency Request Model

International journal of advanced trends in computer science and engineering, Apr 10, 2024

This paper developed a mobile APP called Health Emergency Request APP (HER-APP). The App sends ou... more This paper developed a mobile APP called Health Emergency Request APP (HER-APP). The App sends out-patients' emergency request to any closest health personnel within a particular location and matches a patient to a particular health personnel for immediate attention. We observed that the process of responding to out-of-hospital emergencies after a crisis have faced a lot of communication challenges between patients and the nearest healthcare personnel especially in Nigeria. There is also a problem of assigning a patient to the most qualified health personal for better care. This has resulted in increased mortality even when such emergency could better be handled. It becomes compelling to develop a mobile APP that allows a seamless communication between patient under emergency and the nearest medical expert with medical facility to save lives prior to the full engagement of the attention of a medical doctor or ambulance. This emergency request service-oriented mobile application helps patients contact any closest health personnel within a particular location using a location tracking service. The mobile application implements a matching algorithm between patients and responders, and assists people in emergency to get quick pre-clinical treatment. It uses an optimized service-oriented architecture which reduces the communication process between a patient in an emergency and the doctor or responder using a Google global positioning system as a location tracking service to helps track a patient requesting for assistance as well as all available responders. The APP uses location factor to determine a model to enhance the system on a large scale basis to provide a dispatch method to allocate patients to responders. This paper enhanced the Hungarian model and determines the best patient-responder match. The mobile APP is available at www.github.com/magnifikuc.

Research paper thumbnail of A Deception Based Intelligent Intrusion Detection System for Detecting Threats of Exploits in Cloud Based Environments

Proceedings of the 28th iSTEAMS Multidisciplinary & Inter-tertiary Research Conference, 2021

Despite its numerous advantages, cloud computing faces major security threats with constantly evo... more Despite its numerous advantages, cloud computing faces major security threats with constantly evolving digital prints and attack-like patterns. Unfortunately, due to the share size and complexity of cloud computing, traditional approaches to Intrusion Detection Systems (IDS) have been shown to be rather defective in adapting to, identifying and mitigating threat in cloud based environment. While, anomaly-based IDS are plagued with misidentifying legitimate network activities or sometimes permitting sophisticated malicious traffic patterns, signature-based IDS on the other hand are less adaptive and practically ineffective against sophisticated attacks and advanced persistent threat (APT). This paper presents a unique design approach for deception-based intelligent Intrusion Detection Systems, which are better suited for operations in cloud based environments. Modelling and simulation was conducted using Application Characterization Engine and Flow Modelling Engine within OPNET modul...

Research paper thumbnail of A Metric Model for Ranking the Security Strength of a Web Page

It is common knowledge that any system or process that cannot be measured cannot be managed. This... more It is common knowledge that any system or process that cannot be measured cannot be managed. This wisdom also applies to security as well. As much as the expansion of use of Information Technology (IT) in various processes is increasing, the question of security readily comes to mind often. Today we see various new ICT products and applications appearing in the market daily via web sites. Again, cases of Web security breaching are also on the increase since the Internet is accessible from any where. We see reports in the national dailies about the terms like hacking or other security breaching very common words. The concept of Computer Security in general is being heavily researched and this perfectly makes sense in a world where ecommerce and e-governance are becoming the standard. Security metrics are assuming tremendous importance as they are vital for assessing the current security status, to develop operational best practices and for guiding future security research. Security m...

Research paper thumbnail of A Comparative Analysis of Electronic Transfer Systems

This paper carries out an in depth survey of five electronic transfer systems (ETSs), explains th... more This paper carries out an in depth survey of five electronic transfer systems (ETSs), explains the transfers mechanisms for each case, establishes the merits and demerits of each type of electronic transfer system and finally performs a comparative analysis and ranking of the five common electronic transfer systems using named criteria. Electronic transfer systems being systems that transfer digital data or digital information from one computer or device to another over communication networks. The result obtained showed that GSM (Mobile phone) had the highest ranking. ATM was ranked second and Email, Interbank Transfer and E-commerce were ranked third, fourth and fifth respectively. The paper provided justification for the ranking.

Research paper thumbnail of Exploratory Data Analysis and Feature Selection for Social Media Hackers Prediction Problem

Computer Science & Engineering: An International Journal

In machine learning, the intelligence of a developed model is greatly influenced by the dataset u... more In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the target domain on which the developed model will be deployed. Social media platform has experienced more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two possible ways. The first is to use the activities of the user while the second is to use the supplied details the user registered the account with. To adequately identify a social media user as hacker proactively, there are relevant user details called features that can be used to determine whether a social media user is a hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features that can be used by a predictive model to proactively identify hackers on the social media platform. A web crawler was developed to mine the user dataset on which exploratory data analysis was carried out to select the best features for the dataset ...

Research paper thumbnail of An automated guide to COVID-19 and future pandemic prevention and management

Journal of Electrical Systems and Information Technology

In this paper, we present CoFighter, a mobile application for prevention and management of COVID-... more In this paper, we present CoFighter, a mobile application for prevention and management of COVID-19 and other related pandemics in the globalized world. We took advantage of the proliferation of mobile smart devices in every home to design and implement an Android application for COVID-19 and similar pandemics. Since the outbreak of COVID-19 pandemic in 2019, there has been even more serious pressures on governments and health institutions on the best way to provide appropriate and reliable guide to individuals on how to contain the virus and similar pandemics in the future. Citizens have not been adequately informed of the various provisions and guides by their governments and the wide usage of social media had led to the spread of fake news, misinformation and conspiracy theories. It therefore becomes very necessary to develop a dynamic information repository in the form of a mobile application to help combat the spread of any pandemic whenever the need arises. The application pro...

Research paper thumbnail of A Conceptual Framework of a Detective Model for Social Bot Classification

International journal of ambient systems and applications, Dec 30, 2022

Social media platform has greatly enhanced human interactive activities in the virtual community.... more Social media platform has greatly enhanced human interactive activities in the virtual community. Virtual socialization has positively influenced social bonding among social media users irrespective of one's location in the connected global village. Human user and social bot user are the two types of social media users. While human users personally operate their social media accounts, social bot users are developed software that manages a social media account for the human user called the botmaster. This botmaster in most cases are hackers with bad intention of attacking social media users through various attacking mode using social bots. The aim of this research work is to design an intelligent framework that will prevent attacks through social bots on social media network platforms.

Research paper thumbnail of K-means clustering of electricity consumers using time-domain features from smart meter data

Journal of Electrical Systems and Information Technology

Smart meter stores electricity consumption data of every consumer in the smart grid system. A bet... more Smart meter stores electricity consumption data of every consumer in the smart grid system. A better understanding of consumption behaviors and an effective consumer classification based on the similarity of these behaviors can be helpful for flexible demand management and effective energy control. In this paper, we propose an implementation of unsupervised classification for categorizing consumers based on the similarity of their typical electricity consumption behaviors. The main goal is to group similar observations together in order to easily look at the dataset. Hence, we go through pattern identification in households’ consumption with the K-means clustering algorithm. K-means clusters consumption behaviors based on extracted temporal features into k groups. The result from the algorithm helps power suppliers to understand power consumers’ better and helps them make better informed decision based on the information available to them. The dataset used in this paper is a real da...

Research paper thumbnail of An Evaluation of Topic Models for the Estimation of Unobserved Variables in Structured and Unstructured Documents

For effective data collection, researchers are often faced with three challenges of where, what a... more For effective data collection, researchers are often faced with three challenges of where, what and how? Where to find researchable data, with what tools and methodologies to scrape websites for such data, and how to perform the required analytics and extract insightful knowledge. This study examines the possibility and the extent user tweets could influence the direction of research, especially in the field of machine learning and artificial intelligence. In this paper, we use the Latent Dirichlet Allocation (LDA) topic modelling technique to discover machine learning research topics popularity in 35,860 unorganized datasets (tweets) from 20 Artificial Intelligence and machine learning related handles, while using 7,241 articles from 42 years’ Neural Information Processing Systems (NIPS) conference papers dataset, an organized document as a control. The Latent Semantic Index (LSI) and the Hierarchical Dirichlet Process (HDP) are used to compare the performance of the LDA. Embedding...

Research paper thumbnail of Algorithms for the Development of Deep Learning Models for Classification and Prediction of Learner Behaviour in MOOCs

Artificial Intelligence for Data Science in Theory and Practice

Research paper thumbnail of Supervised Shallow Multi-task Learning: Analysis of Methods

Neural Processing Letters, 2022

Research paper thumbnail of Algorithms for the Development of Deep Learning Models for Classification and Prediction of Behaviour in MOOCS

2020 IEEE Learning With MOOCS (LWMOOCS), 2020

MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the intern... more MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the international agenda about inclusive and equitable education and lifelong learning opportunities for all (SDG4) [1]. A great deal universities and institutions offer valuable free courses to their numerous students and to people around the word through MOOC platforms. However, because of huge number of learners and data generated, learner’s behaviour in those platforms remain a kind of black box for learners themselves and for courses instructors who are supposed to tutor or monitor learners in the learning process. Therefore, learner do not receive sufficient support from instructors and from their peers, during the learning process [2]. This is one the main reasons that lead to high dropout, low completion and success rate observed in the MOOCs. Many research work have suggested descriptive, predictive and prescriptive models to address this issue, but most of these models focus on predicting dropout, completion and/or success, and do not generally pay enough attention to one of the key step (learner behaviour), that comes before, and can explain dropping out and failure. Our research aims to develop a deep learning model to predict learner behaviour (learner interactions) in the learning process, in order to equip learners and course instructors with insight understanding of the learner behaviour in the learning process. This specific paper will focus on analysing relevant algorithms to develop such model. For this analysis, we used data from UNESCO-IICBA (International Institute for Capacity Building in Africa) MOOC platform, designed for teacher training in Africa, and then we examine many types of features: geographical, social behavioural and learning behavioural features. Learner’s behaviour being a time series Big data, we built the predictive model using Deep Learning algorithms for better performance and accuracy (Thanks to the power of deep learning) compared to baseline Machine learning algorithms. Time series data is best handled by recurrent neural networks (RNN) [3], so, we choose RNN and implemented/tested the three main architectures of RNN: Simple RNNs, GRU (Gated Recurrent Unit) RNNs and LSTM (Long short-term memory) RNNs. The models were trained using L2 Regularization, based on the predictions results, we unexpectedly found model with simple RNNs produced the best performance and accuracy on the dataset used than the other RNN architectures. We had couple of observations, example: we saw a correlation between video viewing and quiz behaviour and the participation of the learner to the learning process. This observation could allow teachers to provide meaningful support and guidance to at risk or less active students. We also observed that, the shorter the video or the quiz, the more the viewer. We conclude that we could use learner video or quiz viewing behaviour to predict his behaviour concerning other MOOC contents. These results suggest the need of deeper research on educational video and educational quiz designing for MOOCs.

Research paper thumbnail of An Automated Age prediction model for Human Resource Development

Age falsification in labour is a global challenge which adversely affects Civil Service productiv... more Age falsification in labour is a global challenge which adversely affects Civil Service productivity especially in third world countries. The Nigerian labour force for instance is filled with senile and over aged employees due to falsified age. This continues to affect production adversely in our institutions, establishments and businesses. This paper presents a model for solving the menace of age falsification in Nigerian Civil service. The model predicts employees’ age using the dates on the employee’s certificates. The duration period from primary to tertiary is used to predict the actual age taking into cognizance the waiting/delay periods between transition points. The model is based on the Nigerian system of education 6-3-3-4. A data set of student applicants was created for the purpose of the research. An inferential research was carried out on the data set using Mann-Whitney test statistic to show that there is indeed a diaprity between the quoted age of employees and their ...

Research paper thumbnail of Cutting Edge Trends in Deception Based Intrusion Detection Systems—A Survey

Journal of Information Security, 2021

Cyber criminals have become a formidable treat in today's world. This present reality has placed ... more Cyber criminals have become a formidable treat in today's world. This present reality has placed cloud computing platforms under constant treats of cyber-attacks at all levels, with an ever-evolving treat landscape. It has been observed that the number of threats faced in cloud computing is rising exponentially mainly due to its widespread adoption, rapid expansion and a vast attack surface. One of the front-line tools employed in defense against cyber-attacks is the Intrusion Detection Systems (IDSs). In recent times, an increasing number of researchers and cyber security practitioners alike have advocated the use of deception-based techniques in IDS and other cyber security defenses as against the use of traditional methods. This paper presents an extensive overview of the deception technology environment, as well as a review of current trends and implementation models in deception-based Intrusion Detection Systems. Issues mitigating the implementation of deception based cyber security defenses are also investigated.

Research paper thumbnail of Mining and visualising contradictory data

Journal of Big Data, 2017

A noisy dataset can contain contradictory data. Contradictory data is synonymous to incorrect dat... more A noisy dataset can contain contradictory data. Contradictory data is synonymous to incorrect data and it is important that such data be investigated and evaluated when analysing a noisy dataset. Different approaches to dealing with contradictory data have been proposed by different researchers. For example [1, 2] proposed methods for identifying and removing contradictory data in noisy datasets. However, the removal of contradictory data from a noisy dataset will increase the incompleteness in the dataset thereby reducing the soundness of any information from such set of data. It is therefore important to identify and evaluate contradictory instances when analysing a large and noisy dataset. This will improve the soundness of the analysis from such a dataset. Evidently, the analysis of big data is identified as the next frontier for innovation and advancement of technology [3, 4]. There is therefore the need to identify appropriate approaches to dealing with contradictions in a large and noisy dataset. There are different forms of contradictions. For example, there are contradictions from the use of modal words, structural, subtle lexical contrasts, as well as world knowledge

Research paper thumbnail of Visual Identification of Inconsistency in Pattern

Pattern Recognition [Working Title], 2021

The visual identification of inconsistencies in patterns is an area in computing that has been un... more The visual identification of inconsistencies in patterns is an area in computing that has been understudied. While pattern visualisation exposes the relationships among identified regularities, it is still very important to identify inconsistencies (irregularities) in identified patterns. The significance of identifying inconsistencies for example in the growth pattern of children of a particular age will enhance early intervention such as dietary modifications for stunted children. It is described in this chapter, the need to have a system that identifies inconsistencies in identified pattern of a dataset. Also, techniques that enable the visual identification of inconsistencies in patterns such as fault tolerance and colour coding are described. Two approaches are presented in this chapter for visualising inconsistencies in patterns namely; visualising inconsistencies in objects with many attribute values and visual comparison of an investigated dataset with a case control dataset...

Research paper thumbnail of Sentiment Analysis - An optimized Weighted Horizontal Ensemble approach

International journal of advanced trends in computer science and engineering, Apr 10, 2024

Sentiment Analysis has gained authority as one of the primary means of analyzing feedbacks and op... more Sentiment Analysis has gained authority as one of the primary means of analyzing feedbacks and opinion by individuals, organizations and governments. The result of sentiment analysis informs an organization on areas to improve and how best to manage customers. While sentiment analysis may be misleading as no algorithm has been considered 100% efficient, the choice of algorithms can optimize the result based on the dataset in question. This paper aims at studying various algorithms and implementing a weighted horizontal ensemble algorithm as a panacea to low confidence level in the results of sentiment analysis. We designed a system that implements the original Naive Bayes algorithm, Multinomial Naïve Bayes algorithm, Bernoulli Native Bayes algorithm, Logistic Regression algorithm, Linear Support Vector Classifier algorithm and the Stochastic Gradient Descent algorithm. Our dataset was sourced from the Stanford University. It contains fifty thousand (50,000) movie reviews. Dataset from the Nigerian movie review was used to test the models. The reviews were encoded as a sequence of word indices. An accuracy of over 91% was achieved. The Ensemble technique delivered an F1-measure of 90%. Ensemble technique provides a more reliable confidence level on sentiment analysis. The researchers also discovered that change in writing style can affect the performance of sentiment analysis.

Research paper thumbnail of Clustering Nigeria’s IDP Camps for Effective Budgeting and Re-Settlement Policies Using an Optimized K-Means Approach

African Conflict and Peacebuilding Review, Aug 31, 2023

Research paper thumbnail of Towards an improved internet of things sensors data quality for a smart aquaponics system yield prediction

Research paper thumbnail of A Mobile Application Based Optimized Out-Patient Emergency Request Model

International journal of advanced trends in computer science and engineering, Apr 10, 2024

This paper developed a mobile APP called Health Emergency Request APP (HER-APP). The App sends ou... more This paper developed a mobile APP called Health Emergency Request APP (HER-APP). The App sends out-patients' emergency request to any closest health personnel within a particular location and matches a patient to a particular health personnel for immediate attention. We observed that the process of responding to out-of-hospital emergencies after a crisis have faced a lot of communication challenges between patients and the nearest healthcare personnel especially in Nigeria. There is also a problem of assigning a patient to the most qualified health personal for better care. This has resulted in increased mortality even when such emergency could better be handled. It becomes compelling to develop a mobile APP that allows a seamless communication between patient under emergency and the nearest medical expert with medical facility to save lives prior to the full engagement of the attention of a medical doctor or ambulance. This emergency request service-oriented mobile application helps patients contact any closest health personnel within a particular location using a location tracking service. The mobile application implements a matching algorithm between patients and responders, and assists people in emergency to get quick pre-clinical treatment. It uses an optimized service-oriented architecture which reduces the communication process between a patient in an emergency and the doctor or responder using a Google global positioning system as a location tracking service to helps track a patient requesting for assistance as well as all available responders. The APP uses location factor to determine a model to enhance the system on a large scale basis to provide a dispatch method to allocate patients to responders. This paper enhanced the Hungarian model and determines the best patient-responder match. The mobile APP is available at www.github.com/magnifikuc.

Research paper thumbnail of A Deception Based Intelligent Intrusion Detection System for Detecting Threats of Exploits in Cloud Based Environments

Proceedings of the 28th iSTEAMS Multidisciplinary & Inter-tertiary Research Conference, 2021

Despite its numerous advantages, cloud computing faces major security threats with constantly evo... more Despite its numerous advantages, cloud computing faces major security threats with constantly evolving digital prints and attack-like patterns. Unfortunately, due to the share size and complexity of cloud computing, traditional approaches to Intrusion Detection Systems (IDS) have been shown to be rather defective in adapting to, identifying and mitigating threat in cloud based environment. While, anomaly-based IDS are plagued with misidentifying legitimate network activities or sometimes permitting sophisticated malicious traffic patterns, signature-based IDS on the other hand are less adaptive and practically ineffective against sophisticated attacks and advanced persistent threat (APT). This paper presents a unique design approach for deception-based intelligent Intrusion Detection Systems, which are better suited for operations in cloud based environments. Modelling and simulation was conducted using Application Characterization Engine and Flow Modelling Engine within OPNET modul...

Research paper thumbnail of A Metric Model for Ranking the Security Strength of a Web Page

It is common knowledge that any system or process that cannot be measured cannot be managed. This... more It is common knowledge that any system or process that cannot be measured cannot be managed. This wisdom also applies to security as well. As much as the expansion of use of Information Technology (IT) in various processes is increasing, the question of security readily comes to mind often. Today we see various new ICT products and applications appearing in the market daily via web sites. Again, cases of Web security breaching are also on the increase since the Internet is accessible from any where. We see reports in the national dailies about the terms like hacking or other security breaching very common words. The concept of Computer Security in general is being heavily researched and this perfectly makes sense in a world where ecommerce and e-governance are becoming the standard. Security metrics are assuming tremendous importance as they are vital for assessing the current security status, to develop operational best practices and for guiding future security research. Security m...

Research paper thumbnail of A Comparative Analysis of Electronic Transfer Systems

This paper carries out an in depth survey of five electronic transfer systems (ETSs), explains th... more This paper carries out an in depth survey of five electronic transfer systems (ETSs), explains the transfers mechanisms for each case, establishes the merits and demerits of each type of electronic transfer system and finally performs a comparative analysis and ranking of the five common electronic transfer systems using named criteria. Electronic transfer systems being systems that transfer digital data or digital information from one computer or device to another over communication networks. The result obtained showed that GSM (Mobile phone) had the highest ranking. ATM was ranked second and Email, Interbank Transfer and E-commerce were ranked third, fourth and fifth respectively. The paper provided justification for the ranking.

Research paper thumbnail of Exploratory Data Analysis and Feature Selection for Social Media Hackers Prediction Problem

Computer Science & Engineering: An International Journal

In machine learning, the intelligence of a developed model is greatly influenced by the dataset u... more In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the target domain on which the developed model will be deployed. Social media platform has experienced more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two possible ways. The first is to use the activities of the user while the second is to use the supplied details the user registered the account with. To adequately identify a social media user as hacker proactively, there are relevant user details called features that can be used to determine whether a social media user is a hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features that can be used by a predictive model to proactively identify hackers on the social media platform. A web crawler was developed to mine the user dataset on which exploratory data analysis was carried out to select the best features for the dataset ...

Research paper thumbnail of An automated guide to COVID-19 and future pandemic prevention and management

Journal of Electrical Systems and Information Technology

In this paper, we present CoFighter, a mobile application for prevention and management of COVID-... more In this paper, we present CoFighter, a mobile application for prevention and management of COVID-19 and other related pandemics in the globalized world. We took advantage of the proliferation of mobile smart devices in every home to design and implement an Android application for COVID-19 and similar pandemics. Since the outbreak of COVID-19 pandemic in 2019, there has been even more serious pressures on governments and health institutions on the best way to provide appropriate and reliable guide to individuals on how to contain the virus and similar pandemics in the future. Citizens have not been adequately informed of the various provisions and guides by their governments and the wide usage of social media had led to the spread of fake news, misinformation and conspiracy theories. It therefore becomes very necessary to develop a dynamic information repository in the form of a mobile application to help combat the spread of any pandemic whenever the need arises. The application pro...

Research paper thumbnail of A Conceptual Framework of a Detective Model for Social Bot Classification

International journal of ambient systems and applications, Dec 30, 2022

Social media platform has greatly enhanced human interactive activities in the virtual community.... more Social media platform has greatly enhanced human interactive activities in the virtual community. Virtual socialization has positively influenced social bonding among social media users irrespective of one's location in the connected global village. Human user and social bot user are the two types of social media users. While human users personally operate their social media accounts, social bot users are developed software that manages a social media account for the human user called the botmaster. This botmaster in most cases are hackers with bad intention of attacking social media users through various attacking mode using social bots. The aim of this research work is to design an intelligent framework that will prevent attacks through social bots on social media network platforms.

Research paper thumbnail of K-means clustering of electricity consumers using time-domain features from smart meter data

Journal of Electrical Systems and Information Technology

Smart meter stores electricity consumption data of every consumer in the smart grid system. A bet... more Smart meter stores electricity consumption data of every consumer in the smart grid system. A better understanding of consumption behaviors and an effective consumer classification based on the similarity of these behaviors can be helpful for flexible demand management and effective energy control. In this paper, we propose an implementation of unsupervised classification for categorizing consumers based on the similarity of their typical electricity consumption behaviors. The main goal is to group similar observations together in order to easily look at the dataset. Hence, we go through pattern identification in households’ consumption with the K-means clustering algorithm. K-means clusters consumption behaviors based on extracted temporal features into k groups. The result from the algorithm helps power suppliers to understand power consumers’ better and helps them make better informed decision based on the information available to them. The dataset used in this paper is a real da...

Research paper thumbnail of An Evaluation of Topic Models for the Estimation of Unobserved Variables in Structured and Unstructured Documents

For effective data collection, researchers are often faced with three challenges of where, what a... more For effective data collection, researchers are often faced with three challenges of where, what and how? Where to find researchable data, with what tools and methodologies to scrape websites for such data, and how to perform the required analytics and extract insightful knowledge. This study examines the possibility and the extent user tweets could influence the direction of research, especially in the field of machine learning and artificial intelligence. In this paper, we use the Latent Dirichlet Allocation (LDA) topic modelling technique to discover machine learning research topics popularity in 35,860 unorganized datasets (tweets) from 20 Artificial Intelligence and machine learning related handles, while using 7,241 articles from 42 years’ Neural Information Processing Systems (NIPS) conference papers dataset, an organized document as a control. The Latent Semantic Index (LSI) and the Hierarchical Dirichlet Process (HDP) are used to compare the performance of the LDA. Embedding...

Research paper thumbnail of Algorithms for the Development of Deep Learning Models for Classification and Prediction of Learner Behaviour in MOOCs

Artificial Intelligence for Data Science in Theory and Practice

Research paper thumbnail of Supervised Shallow Multi-task Learning: Analysis of Methods

Neural Processing Letters, 2022

Research paper thumbnail of Algorithms for the Development of Deep Learning Models for Classification and Prediction of Behaviour in MOOCS

2020 IEEE Learning With MOOCS (LWMOOCS), 2020

MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the intern... more MOOCs (Massive Open Online Courses) are definitely one of the best approach to support the international agenda about inclusive and equitable education and lifelong learning opportunities for all (SDG4) [1]. A great deal universities and institutions offer valuable free courses to their numerous students and to people around the word through MOOC platforms. However, because of huge number of learners and data generated, learner’s behaviour in those platforms remain a kind of black box for learners themselves and for courses instructors who are supposed to tutor or monitor learners in the learning process. Therefore, learner do not receive sufficient support from instructors and from their peers, during the learning process [2]. This is one the main reasons that lead to high dropout, low completion and success rate observed in the MOOCs. Many research work have suggested descriptive, predictive and prescriptive models to address this issue, but most of these models focus on predicting dropout, completion and/or success, and do not generally pay enough attention to one of the key step (learner behaviour), that comes before, and can explain dropping out and failure. Our research aims to develop a deep learning model to predict learner behaviour (learner interactions) in the learning process, in order to equip learners and course instructors with insight understanding of the learner behaviour in the learning process. This specific paper will focus on analysing relevant algorithms to develop such model. For this analysis, we used data from UNESCO-IICBA (International Institute for Capacity Building in Africa) MOOC platform, designed for teacher training in Africa, and then we examine many types of features: geographical, social behavioural and learning behavioural features. Learner’s behaviour being a time series Big data, we built the predictive model using Deep Learning algorithms for better performance and accuracy (Thanks to the power of deep learning) compared to baseline Machine learning algorithms. Time series data is best handled by recurrent neural networks (RNN) [3], so, we choose RNN and implemented/tested the three main architectures of RNN: Simple RNNs, GRU (Gated Recurrent Unit) RNNs and LSTM (Long short-term memory) RNNs. The models were trained using L2 Regularization, based on the predictions results, we unexpectedly found model with simple RNNs produced the best performance and accuracy on the dataset used than the other RNN architectures. We had couple of observations, example: we saw a correlation between video viewing and quiz behaviour and the participation of the learner to the learning process. This observation could allow teachers to provide meaningful support and guidance to at risk or less active students. We also observed that, the shorter the video or the quiz, the more the viewer. We conclude that we could use learner video or quiz viewing behaviour to predict his behaviour concerning other MOOC contents. These results suggest the need of deeper research on educational video and educational quiz designing for MOOCs.

Research paper thumbnail of An Automated Age prediction model for Human Resource Development

Age falsification in labour is a global challenge which adversely affects Civil Service productiv... more Age falsification in labour is a global challenge which adversely affects Civil Service productivity especially in third world countries. The Nigerian labour force for instance is filled with senile and over aged employees due to falsified age. This continues to affect production adversely in our institutions, establishments and businesses. This paper presents a model for solving the menace of age falsification in Nigerian Civil service. The model predicts employees’ age using the dates on the employee’s certificates. The duration period from primary to tertiary is used to predict the actual age taking into cognizance the waiting/delay periods between transition points. The model is based on the Nigerian system of education 6-3-3-4. A data set of student applicants was created for the purpose of the research. An inferential research was carried out on the data set using Mann-Whitney test statistic to show that there is indeed a diaprity between the quoted age of employees and their ...

Research paper thumbnail of Cutting Edge Trends in Deception Based Intrusion Detection Systems—A Survey

Journal of Information Security, 2021

Cyber criminals have become a formidable treat in today's world. This present reality has placed ... more Cyber criminals have become a formidable treat in today's world. This present reality has placed cloud computing platforms under constant treats of cyber-attacks at all levels, with an ever-evolving treat landscape. It has been observed that the number of threats faced in cloud computing is rising exponentially mainly due to its widespread adoption, rapid expansion and a vast attack surface. One of the front-line tools employed in defense against cyber-attacks is the Intrusion Detection Systems (IDSs). In recent times, an increasing number of researchers and cyber security practitioners alike have advocated the use of deception-based techniques in IDS and other cyber security defenses as against the use of traditional methods. This paper presents an extensive overview of the deception technology environment, as well as a review of current trends and implementation models in deception-based Intrusion Detection Systems. Issues mitigating the implementation of deception based cyber security defenses are also investigated.

Research paper thumbnail of Mining and visualising contradictory data

Journal of Big Data, 2017

A noisy dataset can contain contradictory data. Contradictory data is synonymous to incorrect dat... more A noisy dataset can contain contradictory data. Contradictory data is synonymous to incorrect data and it is important that such data be investigated and evaluated when analysing a noisy dataset. Different approaches to dealing with contradictory data have been proposed by different researchers. For example [1, 2] proposed methods for identifying and removing contradictory data in noisy datasets. However, the removal of contradictory data from a noisy dataset will increase the incompleteness in the dataset thereby reducing the soundness of any information from such set of data. It is therefore important to identify and evaluate contradictory instances when analysing a large and noisy dataset. This will improve the soundness of the analysis from such a dataset. Evidently, the analysis of big data is identified as the next frontier for innovation and advancement of technology [3, 4]. There is therefore the need to identify appropriate approaches to dealing with contradictions in a large and noisy dataset. There are different forms of contradictions. For example, there are contradictions from the use of modal words, structural, subtle lexical contrasts, as well as world knowledge

Research paper thumbnail of Visual Identification of Inconsistency in Pattern

Pattern Recognition [Working Title], 2021

The visual identification of inconsistencies in patterns is an area in computing that has been un... more The visual identification of inconsistencies in patterns is an area in computing that has been understudied. While pattern visualisation exposes the relationships among identified regularities, it is still very important to identify inconsistencies (irregularities) in identified patterns. The significance of identifying inconsistencies for example in the growth pattern of children of a particular age will enhance early intervention such as dietary modifications for stunted children. It is described in this chapter, the need to have a system that identifies inconsistencies in identified pattern of a dataset. Also, techniques that enable the visual identification of inconsistencies in patterns such as fault tolerance and colour coding are described. Two approaches are presented in this chapter for visualising inconsistencies in patterns namely; visualising inconsistencies in objects with many attribute values and visual comparison of an investigated dataset with a case control dataset...