Taiwo Kolajo - Academia.edu (original) (raw)

Papers by Taiwo Kolajo

Research paper thumbnail of Legal Frameworks Regulating Computational Models in Wireless Communication Systems

CRC Press eBooks, Jul 1, 2024

Research paper thumbnail of Speech Emotion Recognition Model Using Deep Learning

OSISA journal, Jan 13, 2024

Research paper thumbnail of Government regulatory policies on telehealth data protection using artificial intelligence and blockchain technology

Research paper thumbnail of A Survey on Recommendation System Techniques

UMYU Scientifica, Jun 29, 2023

Research paper thumbnail of A Framework for Predictive - Diagnosis of Prevalent Illness among University Students

Journal of Applied Artificial Intelligence

The issue of identifying the prevalence of sickness that is linked to the population of a nation,... more The issue of identifying the prevalence of sickness that is linked to the population of a nation, state, neighborhood, organization, or school has not been taken into consideration by the majority of prior studies on the prediction of illness among populations. They frequently merely choose any sickness based on assumption, while those that determined the prevalence of the condition before developing their framework utilized survey data or data from web repositories, which removes idiosyncrasies from those data. In order to increase performance, this research suggests an enhanced data analytics framework for the predictive diagnosis of common illnesses affecting university students. In order to do this, exploratory data analysis (EDA) using a multivariate analytic technique was conducted using a high-level model methodology using CRISP-DM stages. When the suggested strategy was evaluated on support vector machines, ensemble gradient boosting, random forest, decision tree, K-neighbor...

Research paper thumbnail of Real-time event detection in social media streams through semantic analysis of noisy terms

Journal of Big Data

Interactions via social media platforms have made it possible for anyone, irrespective of physica... more Interactions via social media platforms have made it possible for anyone, irrespective of physical location, to gain access to quick information on events taking place all over the globe. However, the semantic processing of social media data is complicated due to challenges such as language complexity, unstructured data, and ambiguity. In this paper, we proposed the Social Media Analysis Framework for Event Detection (SMAFED). SMAFED aims to facilitate improved semantic analysis of noisy terms in social media streams, improved representation/embedding of social media stream content, and improved summarization of event clusters in social media streams. For this, we employed key concepts such as integrated knowledge base, resolving ambiguity, semantic representation of social media streams, and Semantic Histogram-based Incremental Clustering based on semantic relatedness. Two evaluation experiments were conducted to validate the approach. First, we evaluated the impact of the data enr...

Research paper thumbnail of Leveraging big data to combat terrorism in developing countries

2017 Conference on Information Communication Technology and Society (ICTAS), 2017

Terrorism is a matter of great concern in many nations because of its impact on sustainable devel... more Terrorism is a matter of great concern in many nations because of its impact on sustainable development, which is critical for developing countries. Efforts on the part of security agencies need to stay a step ahead of threats of terrorism to effectively prevent their occurrence. Many research efforts that sought to combat terrorism using big data have been reported in the literature. However, most of them have targeted data from only one type of social media per time. This paper proposes a model that harnesses data from multiple social media sources in order to detect terrorist activities by using Apache Spark technology for implementation. This paper describes the Social Media Analysis for Combating Terrorism (SMACT) model as a plausible approach that leverages Big Data analytics to address terrorism problems in developing nations. SMACT is further illustrated by a practical use case from the Nigerian context in order to depict its viability as a potential panacea for handling terrorism threats.

Research paper thumbnail of Streaming Data and Data Streams

Wiley StatsRef: Statistics Reference Online, 2021

Research paper thumbnail of SMAFED: Real-Time Event Detection in Social Media Streams

Interactions via social media platforms have made it possible for anyone, irrespective of physica... more Interactions via social media platforms have made it possible for anyone, irrespective of physical location, to gain access to quick information on events taking place all over the globe. However, the semantic processing of social media data is complicated due to challenges such as language complexity, unstructured data, and ambiguity. In this paper, we proposed the Social Media Analysis Framework for Event Detection (SMAFED). SMAFED aims to facilitate improved semantic analysis of noisy terms in social media streams, improved representation/embedding of social media stream content, and improved summarisation of event clusters in social media streams. For this, we employed key concepts such as integrated knowledge base, resolving ambiguity, semantic representation of social media streams, and Semantic Histogram-based Incremental Clustering based on semantic relatedness. Two evaluation experiments were conducted to validate the approach. First, we evaluated the impact of the data enr...

Research paper thumbnail of A Trace of Historical Linkage of Computer Connectivity Frameworks : From Computer Networks to the Cloud of Things

A lot of advancements have taken place and still taking place in computing. Gone are the days tha... more A lot of advancements have taken place and still taking place in computing. Gone are the days that people had to rely on inevitable standalone computer to meet their needs. With advancement in technology, computing is turning the world to a better place. Even physical objects are now connected to the internet with the help of wireless sensor networks. This paper traces the historical linkage of different computing frameworks from computer networks to cloud of things with a view to helping researchers and organisations understand the various evolution phases of computer networks. The progression of ideas from the advent of computer networks to six (6) different computer connectivity frameworks like distributed computing, cluster computing, grid computing, cloud computing, internet of things and the cloud of things was examined making all the developments that have taken place to be easily seen in a single medium. The emergence of each framework as well as the strengths, weaknesses an...

Research paper thumbnail of Sentiment Analysis on Twitter Health News

Microblogging has become a generally accepted way of expressing opinions and sentiments about pro... more Microblogging has become a generally accepted way of expressing opinions and sentiments about products, services, media, institutions to mention but few. A lot of research has focused on analyzing Twitter health news for topic modelling using various clustering approaches, but few have reported it for sentiment analysis. The fact that such data contains potential information for revealing the opinion of people about health services and behaviours make it an interesting study. In this paper, general sentiments about Twitter health news was investigated. Natural language processing and text mining tool, AYLIEN API was used to extract sentiments subjectivities and polarities from a previously uncategorized dataset. The result shows that most of the tweets in Twitter health news are objective, that is, expressing facts with an average of 64% objective while 34% are personal views or opinions (subjective) with subjectivity confidence of 0.9. Sentiment polarity reveals 9% positive, 19% ne...

Research paper thumbnail of Data Mining Technique for Predicting Telecommunications Industry Customer Churn Using both Descriptive and Predictive Algorithms

As markets have become increasingly saturated, companies have acknowledged that their business st... more As markets have become increasingly saturated, companies have acknowledged that their business strategies need to focuson identifying those customers who are most likely to churn. It is becoming common knowledge in business, that retainingexisting customers is the best core marketing strategy to survive in industry. In this research, both descriptive and predictivedata mining techniques were used to determine the calling behaviour of subscribers and to recognise subscribers with highprobability of churn in a telecommunications company subscriber database. First a data model for the input data variablesobtained from the subscriber database was developed. Then Simple K-Means and Expected Maximization (EM) clusteringalgorithms were used for the clustering stage, while Decision Stump, M5P and RepTree Decision Tree algorithms were usedfor the classification stage. The best algorithms in both the clustering and classification stages were used for the predictionprocess where customers that...

Research paper thumbnail of Employing both descriptive and predictive algorithms toward improving prediction accuracy

The research describes the use of both descriptive and predictive algorithms for better accurate ... more The research describes the use of both descriptive and predictive algorithms for better accurate prediction. The current research has focused on the use of either descriptive or predictive algorithm for prediction, but this research work employed the two algorithms. Clustering technique was used in the descriptive stage while classification technique was used in the predictive stage. K-Means and Expected Maximization (EM) were used for clustering while models from three classifiers (Decision Stump, M5P and RepTree) were used for classification. The result of using each of the two algorithms individually was presented as well as the result of combination of both algorithms. It was discovered that utilizing both algorithms for prediction provided more accurate result. Keywords : Data Mining, Clustering, Classification, Expected Maximization, M5P

Research paper thumbnail of Career Guidance through Admission Procedures in Nigerian Universities Using Artificial Neural Networks

The study describes the application of Artificial Neural Network model in guiding students for su... more The study describes the application of Artificial Neural Network model in guiding students for suitable career through admission procedures in Nigerian universities. Before a candidate can be admitted to any of the Nigerian universities, he/she must be appraised based on some factors. The researchers looked into and identified various factors that may likely influence the performance of a student. These factors include ordinary level subjects' scores and subjects' combination, universal tertiary matriculation examination scores, post-universal tertiary matriculation examination scores, age on admission, parental background, types and location of secondary school attended, gender, number of sitting for Senior Secondary Certificate Examination, among others. These factors then served as input variables for the Artificial Neural Network model. A model based on the Multilayer Perceptron Topology was deployed and trained using final year students' data from faculty of Science...

Research paper thumbnail of A framework for pre-processing of social media feeds based on integrated local knowledge base

Information Processing & Management, 2020

Research paper thumbnail of Sentiment Analysis on Naija-Tweets

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2019

Research paper thumbnail of Big data stream analysis: a systematic literature review

Journal of Big Data, 2019

Research paper thumbnail of Internet Capabilities for Effective Learning and Research

The Internet has continued to span great geographical space and generality interests. It has prov... more The Internet has continued to span great geographical space and generality interests. It has provided enough space for social interaction and information exchange. It is hard to imagine a world without the internet. Like other fields of human endeavours, the internet is no doubt revolutionising the act of researching, especially in the sciences. Regardless of any viewpoint, research outlines formal, methodical and rigorous processes, specifically the application of scientific methods of problem recognition, definition, solution development, data collection, analysis and conclusions. Expectedly, the introduction of the Internet heralded the upswing of the new soft form of learning; with the aim of achieving speedy and cost effective diffusion of knowledge. Secondly, the internet has also helped in aggregating with ease such knowledge which can be shared amongst geographically-detached partners. So, whether it involves fundamental/pure or basic distributed research, action, applied re...

Research paper thumbnail of Human-centric and Semantics-based Explainable Event Detection: A Survey

In recent years, there has been a surge in interest in artificial intelligent systems that can pr... more In recent years, there has been a surge in interest in artificial intelligent systems that can provide human-centric explanations for decisions or predictions. No matter how good and efficient a model is, users or practitioners find it difficult to trust such model if they cannot understand the model or its behaviours. Incorporating explainability that is human-centric in event detection systems is significant for building a decision-making process that is more trustworthy and sustainable. Human-centric and semantics-based explainable event detection will achieve trustworthiness, explainability, and reliability, which are currently lacking in AI systems. This paper provides a survey on the human-centric explainable AI, explainable event detection, and semantics-based explainable event detection by answering some research questions that bother on the characteristics of human-centric explanations, the state of explainable AI, methods for human-centric explanations, the essence of huma...

Research paper thumbnail of Legal Frameworks Regulating Computational Models in Wireless Communication Systems

CRC Press eBooks, Jul 1, 2024

Research paper thumbnail of Speech Emotion Recognition Model Using Deep Learning

OSISA journal, Jan 13, 2024

Research paper thumbnail of Government regulatory policies on telehealth data protection using artificial intelligence and blockchain technology

Research paper thumbnail of A Survey on Recommendation System Techniques

UMYU Scientifica, Jun 29, 2023

Research paper thumbnail of A Framework for Predictive - Diagnosis of Prevalent Illness among University Students

Journal of Applied Artificial Intelligence

The issue of identifying the prevalence of sickness that is linked to the population of a nation,... more The issue of identifying the prevalence of sickness that is linked to the population of a nation, state, neighborhood, organization, or school has not been taken into consideration by the majority of prior studies on the prediction of illness among populations. They frequently merely choose any sickness based on assumption, while those that determined the prevalence of the condition before developing their framework utilized survey data or data from web repositories, which removes idiosyncrasies from those data. In order to increase performance, this research suggests an enhanced data analytics framework for the predictive diagnosis of common illnesses affecting university students. In order to do this, exploratory data analysis (EDA) using a multivariate analytic technique was conducted using a high-level model methodology using CRISP-DM stages. When the suggested strategy was evaluated on support vector machines, ensemble gradient boosting, random forest, decision tree, K-neighbor...

Research paper thumbnail of Real-time event detection in social media streams through semantic analysis of noisy terms

Journal of Big Data

Interactions via social media platforms have made it possible for anyone, irrespective of physica... more Interactions via social media platforms have made it possible for anyone, irrespective of physical location, to gain access to quick information on events taking place all over the globe. However, the semantic processing of social media data is complicated due to challenges such as language complexity, unstructured data, and ambiguity. In this paper, we proposed the Social Media Analysis Framework for Event Detection (SMAFED). SMAFED aims to facilitate improved semantic analysis of noisy terms in social media streams, improved representation/embedding of social media stream content, and improved summarization of event clusters in social media streams. For this, we employed key concepts such as integrated knowledge base, resolving ambiguity, semantic representation of social media streams, and Semantic Histogram-based Incremental Clustering based on semantic relatedness. Two evaluation experiments were conducted to validate the approach. First, we evaluated the impact of the data enr...

Research paper thumbnail of Leveraging big data to combat terrorism in developing countries

2017 Conference on Information Communication Technology and Society (ICTAS), 2017

Terrorism is a matter of great concern in many nations because of its impact on sustainable devel... more Terrorism is a matter of great concern in many nations because of its impact on sustainable development, which is critical for developing countries. Efforts on the part of security agencies need to stay a step ahead of threats of terrorism to effectively prevent their occurrence. Many research efforts that sought to combat terrorism using big data have been reported in the literature. However, most of them have targeted data from only one type of social media per time. This paper proposes a model that harnesses data from multiple social media sources in order to detect terrorist activities by using Apache Spark technology for implementation. This paper describes the Social Media Analysis for Combating Terrorism (SMACT) model as a plausible approach that leverages Big Data analytics to address terrorism problems in developing nations. SMACT is further illustrated by a practical use case from the Nigerian context in order to depict its viability as a potential panacea for handling terrorism threats.

Research paper thumbnail of Streaming Data and Data Streams

Wiley StatsRef: Statistics Reference Online, 2021

Research paper thumbnail of SMAFED: Real-Time Event Detection in Social Media Streams

Interactions via social media platforms have made it possible for anyone, irrespective of physica... more Interactions via social media platforms have made it possible for anyone, irrespective of physical location, to gain access to quick information on events taking place all over the globe. However, the semantic processing of social media data is complicated due to challenges such as language complexity, unstructured data, and ambiguity. In this paper, we proposed the Social Media Analysis Framework for Event Detection (SMAFED). SMAFED aims to facilitate improved semantic analysis of noisy terms in social media streams, improved representation/embedding of social media stream content, and improved summarisation of event clusters in social media streams. For this, we employed key concepts such as integrated knowledge base, resolving ambiguity, semantic representation of social media streams, and Semantic Histogram-based Incremental Clustering based on semantic relatedness. Two evaluation experiments were conducted to validate the approach. First, we evaluated the impact of the data enr...

Research paper thumbnail of A Trace of Historical Linkage of Computer Connectivity Frameworks : From Computer Networks to the Cloud of Things

A lot of advancements have taken place and still taking place in computing. Gone are the days tha... more A lot of advancements have taken place and still taking place in computing. Gone are the days that people had to rely on inevitable standalone computer to meet their needs. With advancement in technology, computing is turning the world to a better place. Even physical objects are now connected to the internet with the help of wireless sensor networks. This paper traces the historical linkage of different computing frameworks from computer networks to cloud of things with a view to helping researchers and organisations understand the various evolution phases of computer networks. The progression of ideas from the advent of computer networks to six (6) different computer connectivity frameworks like distributed computing, cluster computing, grid computing, cloud computing, internet of things and the cloud of things was examined making all the developments that have taken place to be easily seen in a single medium. The emergence of each framework as well as the strengths, weaknesses an...

Research paper thumbnail of Sentiment Analysis on Twitter Health News

Microblogging has become a generally accepted way of expressing opinions and sentiments about pro... more Microblogging has become a generally accepted way of expressing opinions and sentiments about products, services, media, institutions to mention but few. A lot of research has focused on analyzing Twitter health news for topic modelling using various clustering approaches, but few have reported it for sentiment analysis. The fact that such data contains potential information for revealing the opinion of people about health services and behaviours make it an interesting study. In this paper, general sentiments about Twitter health news was investigated. Natural language processing and text mining tool, AYLIEN API was used to extract sentiments subjectivities and polarities from a previously uncategorized dataset. The result shows that most of the tweets in Twitter health news are objective, that is, expressing facts with an average of 64% objective while 34% are personal views or opinions (subjective) with subjectivity confidence of 0.9. Sentiment polarity reveals 9% positive, 19% ne...

Research paper thumbnail of Data Mining Technique for Predicting Telecommunications Industry Customer Churn Using both Descriptive and Predictive Algorithms

As markets have become increasingly saturated, companies have acknowledged that their business st... more As markets have become increasingly saturated, companies have acknowledged that their business strategies need to focuson identifying those customers who are most likely to churn. It is becoming common knowledge in business, that retainingexisting customers is the best core marketing strategy to survive in industry. In this research, both descriptive and predictivedata mining techniques were used to determine the calling behaviour of subscribers and to recognise subscribers with highprobability of churn in a telecommunications company subscriber database. First a data model for the input data variablesobtained from the subscriber database was developed. Then Simple K-Means and Expected Maximization (EM) clusteringalgorithms were used for the clustering stage, while Decision Stump, M5P and RepTree Decision Tree algorithms were usedfor the classification stage. The best algorithms in both the clustering and classification stages were used for the predictionprocess where customers that...

Research paper thumbnail of Employing both descriptive and predictive algorithms toward improving prediction accuracy

The research describes the use of both descriptive and predictive algorithms for better accurate ... more The research describes the use of both descriptive and predictive algorithms for better accurate prediction. The current research has focused on the use of either descriptive or predictive algorithm for prediction, but this research work employed the two algorithms. Clustering technique was used in the descriptive stage while classification technique was used in the predictive stage. K-Means and Expected Maximization (EM) were used for clustering while models from three classifiers (Decision Stump, M5P and RepTree) were used for classification. The result of using each of the two algorithms individually was presented as well as the result of combination of both algorithms. It was discovered that utilizing both algorithms for prediction provided more accurate result. Keywords : Data Mining, Clustering, Classification, Expected Maximization, M5P

Research paper thumbnail of Career Guidance through Admission Procedures in Nigerian Universities Using Artificial Neural Networks

The study describes the application of Artificial Neural Network model in guiding students for su... more The study describes the application of Artificial Neural Network model in guiding students for suitable career through admission procedures in Nigerian universities. Before a candidate can be admitted to any of the Nigerian universities, he/she must be appraised based on some factors. The researchers looked into and identified various factors that may likely influence the performance of a student. These factors include ordinary level subjects' scores and subjects' combination, universal tertiary matriculation examination scores, post-universal tertiary matriculation examination scores, age on admission, parental background, types and location of secondary school attended, gender, number of sitting for Senior Secondary Certificate Examination, among others. These factors then served as input variables for the Artificial Neural Network model. A model based on the Multilayer Perceptron Topology was deployed and trained using final year students' data from faculty of Science...

Research paper thumbnail of A framework for pre-processing of social media feeds based on integrated local knowledge base

Information Processing & Management, 2020

Research paper thumbnail of Sentiment Analysis on Naija-Tweets

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, 2019

Research paper thumbnail of Big data stream analysis: a systematic literature review

Journal of Big Data, 2019

Research paper thumbnail of Internet Capabilities for Effective Learning and Research

The Internet has continued to span great geographical space and generality interests. It has prov... more The Internet has continued to span great geographical space and generality interests. It has provided enough space for social interaction and information exchange. It is hard to imagine a world without the internet. Like other fields of human endeavours, the internet is no doubt revolutionising the act of researching, especially in the sciences. Regardless of any viewpoint, research outlines formal, methodical and rigorous processes, specifically the application of scientific methods of problem recognition, definition, solution development, data collection, analysis and conclusions. Expectedly, the introduction of the Internet heralded the upswing of the new soft form of learning; with the aim of achieving speedy and cost effective diffusion of knowledge. Secondly, the internet has also helped in aggregating with ease such knowledge which can be shared amongst geographically-detached partners. So, whether it involves fundamental/pure or basic distributed research, action, applied re...

Research paper thumbnail of Human-centric and Semantics-based Explainable Event Detection: A Survey

In recent years, there has been a surge in interest in artificial intelligent systems that can pr... more In recent years, there has been a surge in interest in artificial intelligent systems that can provide human-centric explanations for decisions or predictions. No matter how good and efficient a model is, users or practitioners find it difficult to trust such model if they cannot understand the model or its behaviours. Incorporating explainability that is human-centric in event detection systems is significant for building a decision-making process that is more trustworthy and sustainable. Human-centric and semantics-based explainable event detection will achieve trustworthiness, explainability, and reliability, which are currently lacking in AI systems. This paper provides a survey on the human-centric explainable AI, explainable event detection, and semantics-based explainable event detection by answering some research questions that bother on the characteristics of human-centric explanations, the state of explainable AI, methods for human-centric explanations, the essence of huma...