An academic, holds B.Sc. Computer Science from Benue State University, Makurdi, and M.Sc. and Ph.D. Computer Science from Obafemi Awolowo University, Ile-Ife. A lecturer with University of Agriculture, Makurdi, Nigeria. I have interest in data science and engineering, software engineering and information systems. Supervisors: Prof. H. A. Soriyan Address: Nigeria
Background and Purpose: The need for better and faster decision-making based on data is stronger ... more Background and Purpose: The need for better and faster decision-making based on data is stronger than ever; and being able to use massive amounts of data is a necessary competitive advantage. This has necessitated the urgent need for a sophisticated data analytics model for the effective transformation of data into actionable information to enhance quality decision-making. For instance, the healthcare domain is faced with unnecessary delays in the processing of the data submitted to the National Health Insurance Scheme (NHIS). Methods: To address this, a data analytics model based on deep learning was designed in this research using unified modelling language. Results: This model is intended to be implemented using Apache Hadoop and MySQL. When implemented, the model will make it easier to consolidate, cleanse, analyse, and publish data, so that all stakeholders will get information that they can act on, in the format they need. Conclusion: Thus, the stakeholders will access the inf...
AN IMPLEMENTATION OF A REPOSITORY FOR HEALTHCARE INSURANCE USING MONGODB, 2020
The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Niger... more The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Nigeria has given rise to the lack of an appropriate data storage mechanism to house data in the Scheme. This paper x-rayed these data storage challenges with a view to implementing a storage mechanism that can handled large volume and different formats of data in the Scheme. The NHIS is currently using the paper-based, file and cabinet data storage system with some of the data stored in the form of PDF, Excel and image files on the computer system. This has led to serious challenges ranging from the loss of data, lack of appropriate data storage facilities to accommodate the data to the delay in the administration of quality care to beneficiaries of the Scheme. Also, the diversity of data with the ever-growing datasets which is also generated at very high rate has also constituted a major challenge for NHIS. This research therefore developed a computer-based data storage system using MongoDB...
This study aimed at developing a system using support vector machine (SVM) that will forecast sal... more This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period
World Academy of Science, Engineering and Technology, International Journal of Computer and Information Engineering, 2015
This paper studied steganography and designed a simplistic approach to a steganographic tool for ... more This paper studied steganography and designed a simplistic approach to a steganographic tool for hiding information in image files with the view of addressing the security challenges with data by hiding data from unauthorized users to improve its security. The Structured Systems Analysis and Design Method (SSADM) was used in this work. The system was developed using Java Development Kit (JDK) 1.7.0_10 and MySQL Server as its backend. The system was tested with some hypothetical health records which proved the possibility of protecting data from unauthorized users by making it secret so that its existence cannot be easily recognized by fraudulent users. It further strengthens the confidentiality of patient records kept by medica l practitioners in the health setting. In conclusion, this work was able to produce a user friendly steganography software that is very fast to install and easy to operate to ensure privacy and secrecy of sensitive data. It also produced an exact copy of the original image and the one carrying the secret message when compared with each other.
A common problem associated with hospitals especially the nontertiary hospitals (primary and seco... more A common problem associated with hospitals especially the nontertiary hospitals (primary and secondary hospitals) is long queue. Attempts have been made to address this using the ticket approach, however, this does not minimize crowd in and around hospitals. In the wake of the consciousness of the need to avoid crowd with the emergence of the Corona Virus (COVID-19), it has become important to note that some diseases are transmissible when people clinch close within a vicinity especially in the hospital environment. It is therefore imperative to devise a means to reduce the usual crowd witnessed at the different units/sections in the hospital, precisely by outpatients. In this study, a centralized queue control system was developed that can be used in the different sections of hospitals. The system applied Poisson Distribution, Haversine Model, Little’s Law and Kendall Notation. It is a web-based system, designed to run on the Internet as it focused on the outpatients and the fact t...
Road traffic accidents are a very rampant issue causing injury, loss of lives and property worldw... more Road traffic accidents are a very rampant issue causing injury, loss of lives and property worldwide. In this research, a system for determining the severity of motorcycle accidents in Lokoja Metropolis of Central Nigeria was developed. The research considered different areas that are highly prone to accidents in Lokoja. Although accidents cannot be totally avoided, through scientific analysis, their frequency and severity can be reduced. The methodology used in this research is Knowledge Discovery in Databases with the Decision Tree Algorithm as the soft computing technique used for analysis. Python programming language was used for the implementation. The dataset used was gotten from the Federal Road Safety Corps (FRSC) in Lokoja. After the training and testing of the dataset, we achieved an accuracy of 90.5%. The motorcycle accident severity prediction system developed could serve as a tool that can be used to cub the enormous challenges faced by FRSC in curtailing motorcycle acc...
TOWARDS FOOD SECURITY: THE PREDICTION OF CLIMATIC FACTORS IN NIGERIA USING RANDOM FOREST APPROACH, Oct 31, 2021
With the explosive growth in the world‘s population which has little or no corresponding rise in ... more With the explosive growth in the world‘s population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented ...
The application of data mining has been utilized in different fields ranging from agriculture, fi... more The application of data mining has been utilized in different fields ranging from agriculture, finance, education, security, medicine, research etc. Data mining derives useful information from careful examination of data. In Nigeria, Agriculture plays a critical role in the economy as it provides high level of employment for many people. It is typical of farmers in Nigeria to plant crops without paying considerate attention to the soil and crop requirements as most farmers inherit the lands used for farming from their fathers and just continue in the pattern of farming they had always known. This is not favorable in the level of productivity they can actually attain as the effect can be seen in same level of crop yield year after year if not even worse. Modern farming techniques make use of data mining from previous data considering soil types, and other factors like weather and climatic conditions. This study built a model that enables possible prediction of crop yield from the his...
A Mathematical Approach to Healthcare Insurance Data Analytics, 2020
The emergence of big data analytics as a way of deriving insights from data brought excitement to... more The emergence of big data analytics as a way of deriving insights from data brought excitement to mathematicians, statisticians, computer scientists and other professionals. However, the absence of a mathematical foundation for analytics has become a real challenge amidst the flock of big data marketing activities, especially in healthcare insurance. This paper developed a mathematical model for the analytics of healthcare insurance data using set theory. We implemented a prototype of the model using Java Programming Language, MapReduce Framework, Association Rule Mining and MongoDB. Also, we tested the model accuracy using data from the National Health Insurance Scheme in Nigeria to reduce delay. The result showed that the accuracy level was 97.14% on average, which depicts a higher performance for the model. This result implies that delays affecting the processing of data submitted by the providers and enrollees to the HMOs reduced drastically leading to the improvement in the eas...
Point-of-care data capture is an important part of a clinical information system. Unfortunately, ... more Point-of-care data capture is an important part of a clinical information system. Unfortunately, health care providers find it time consuming and repetitive to perform data entry via computers. In this paper, we designed a user-friendly interface for the entry of patient information which gives the health care provider an easy to use interface for patient data entry. This system uses portable terminals and supports the entire loop of daily nursing work. This system was developed with the aim to make nursing work more efficient, by reducing the time needed for indirect work (patent information documentation, conferring with other healthcare providers, etc.), while increasing the time expended in direct patient care. The proposed system has three main functional parts: 1) Data Browsing which provides patient information such as a brief history, assessments and vital-sign charts; 2) Schedule Planning helps nurses organize doctors' instructions and make To-do lists for the day; and ...
With the explosive growth in the world's population which has little or no corresponding rise in ... more With the explosive growth in the world's population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented random forest algorithm using Python programming language to predict the aforementioned climate parameters. The data used was gotten from the Nigerian Meteorological (NiMet) Agency, Lokoja, Kogi State between 1988 and 2018. The result shows that random forest algorithm is effective in climate prediction as the accuracy from the model based on the climatic factors considered was 94.64%. With this, farmers would be able to plan ahead to prevent the impact of the fluctuations in these climatic factors; thus, the yield of crops would be increased. This would dwarf the negative impact of food insecurity to the populace.
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.
AN IMPLEMENTATION OF A REPOSITORY FOR HEALTHCARE INSURANCE USING MONGODB, 2020
The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Niger... more The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Nigeria has given rise to the lack of an appropriate data storage mechanism to house data in the Scheme. This paper x-rayed these data storage challenges with a view to implementing a storage mechanism that can handled large volume and different formats of data in the Scheme. The NHIS is currently using the paper-based, file and cabinet data storage system with some of the data stored in the form of PDF, Excel and image files on the computer system. This has led to serious challenges ranging from the loss of data, lack of appropriate data storage facilities to accommodate the data to the delay in the administration of quality care to beneficiaries of the Scheme. Also, the diversity of data with the ever-growing datasets which is also generated at very high rate has also constituted a major challenge for NHIS. This research therefore developed a computer-based data storage system using MongoDB which has full index support, replication, high availability and auto-sharding. The design was done with Enterprise Application Diagrams and implemented using Java Programming Language, MapReduce Framework and MongoDB. The study shows that there are inequities in the delivery of services within the NHIS in Nigeria due to lack of proper storage medium. This is responsible for the ineffectiveness and inefficiency of healthcare services received through the Scheme. In conclusion, this research has provided the stakeholders with access to information more easily, which will enable them to plan, evaluate, and collaborate more effectively.
Queue Management in Non-Tertiary Hospitals for Improved Healthcare Service Delivery to Outpatients, 2020
A common problem associated with hospitals especially the non-tertiary hospitals (primary and sec... more A common problem associated with hospitals especially the non-tertiary hospitals (primary and secondary hospitals) is long queue. Attempts have been made to address this using the ticket approach, however, this does not minimize crowd in and around hospitals. In the wake of the consciousness of the need to avoid crowd with the emergence of the Corona Virus (COVID-19), it has become important to note that some diseases are transmissible when people clinch close within a vicinity especially in the hospital environment. It is therefore imperative to devise a means to reduce the usual crowd witnessed at the different units/sections in the hospital, precisely by outpatients. In this study, a centralized queue control system was developed that can be used in the different sections of hospitals. The system applied Poisson Distribution, Haversine Model, Little's Law and Kendall Notation. It is a web-based system, designed to run on the Internet as it focused on the outpatients and the fact that different sections of most non-tertiary hospitals could also be situated in different buildings or geographical area. The system was implemented using ASP.NET and Microsoft SQL. It was evaluated using data collected from non-tertiary hospitals in Benue State, Nigeria. The result showed reduced number of patients in the hospital per time and a little variation between the arrival and expected time of some patients. The system saves time for the patients, the hospital is more organized and crowds are avoided. Also, the pressure on the facilities of the hospitals at a time is also reduced significantly. Service delivery is improved and a healthier environment is assured for both patients and health workers.
This paper developed a distributed algorithm for Big Data Analytics to address the delay in the p... more This paper developed a distributed algorithm for Big Data Analytics to address the delay in the processing of big data. In order to achieve the aim of this research, an inspection of organizational documents, direct observation and collection of existing data from the National Health Insurance Scheme (NHIS) in Nigeria. The algorithm was formulated using Apriori Association Rule Mining and was specified using the enterprise application diagram. The implementation of the prototype for the algorithm was using MongoDB as the big data storage mechanism for the input. Comma Separated Values (CSV) files was used as the storage facility for the intermediate results generated during processing, and MySQL was used as the storage mechanism for the final output. Finally, Apache MapReduce as the big data multi-nodal processing platform and Java programming language as the implementation technology. This prototype was able to analyze different formats of data (i.e., pdf, excel, csv and images) with high volume and velocity. The result showed that the response time was 0.25 seconds, and the throughput was 8865.29 records per second. The stability of the prototype was also evaluated using the confidence of the rules generated. In conclusion, this research has shown that unnecessary delays in the processing of big data were due to the lack of appropriate data analytics tool to enhance the process. This study eliminated these irregularities which paved the way for quicker disbursement of funds to providers and other stakeholders, as well as, a quicker response to requests on enrollment, update and referral.
The application of data mining has been utilized in different fields ranging from agriculture, fi... more The application of data mining has been utilized in different fields ranging from agriculture, finance, education, security, medicine, research etc. Data mining derives useful information from careful examination of data. In Nigeria, Agriculture plays a critical role in the economy as it provides high level of employment for many people. It is typical of farmers in Nigeria to plant crops without paying considerate attention to the soil and crop requirements as most farmers inherit the lands used for farming from their fathers and just continue in the pattern of farming they had always known. This is not favorable in the level of productivity they can actually attain as the effect can be seen in same level of crop yield year after year if not even worse. Modern farming techniques make use of data mining from previous data considering soil types, and other factors like weather and climatic conditions. This study built a model that enables possible prediction of crop yield from the historic data collected and offers suggestions to farmers on the right soil nutrients requirements that would enhance crop yield. This will enable early prediction of crop yield and prior idea to improve on the soil to increase productivity. The research used XGBoost algorithm for the crop yield prediction and the Support Vector Machine algorithm for the recommendation of appropriate improvement of soil nutrient requirements. The accuracy obtained for the prediction with XGBoost was 95.28%, while that obtained for the recommendation of fertilizer using SVM was 97.86%.
This study aimed at developing a system using support vector machine (SVM) that will forecast sal... more This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period
Background and Purpose: The need for better and faster decision-making based on data is stronger ... more Background and Purpose: The need for better and faster decision-making based on data is stronger than ever; and being able to use massive amounts of data is a necessary competitive advantage. This has necessitated the urgent need for a sophisticated data analytics model for the effective transformation of data into actionable information to enhance quality decision-making. For instance, the healthcare domain is faced with unnecessary delays in the processing of the data submitted to the National Health Insurance Scheme (NHIS). Methods: To address this, a data analytics model based on deep learning was designed in this research using unified modelling language. Results: This model is intended to be implemented using Apache Hadoop and MySQL. When implemented, the model will make it easier to consolidate, cleanse, analyse, and publish data, so that all stakeholders will get information that they can act on, in the format they need. Conclusion: Thus, the stakeholders will access the inf...
AN IMPLEMENTATION OF A REPOSITORY FOR HEALTHCARE INSURANCE USING MONGODB, 2020
The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Niger... more The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Nigeria has given rise to the lack of an appropriate data storage mechanism to house data in the Scheme. This paper x-rayed these data storage challenges with a view to implementing a storage mechanism that can handled large volume and different formats of data in the Scheme. The NHIS is currently using the paper-based, file and cabinet data storage system with some of the data stored in the form of PDF, Excel and image files on the computer system. This has led to serious challenges ranging from the loss of data, lack of appropriate data storage facilities to accommodate the data to the delay in the administration of quality care to beneficiaries of the Scheme. Also, the diversity of data with the ever-growing datasets which is also generated at very high rate has also constituted a major challenge for NHIS. This research therefore developed a computer-based data storage system using MongoDB...
This study aimed at developing a system using support vector machine (SVM) that will forecast sal... more This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period
World Academy of Science, Engineering and Technology, International Journal of Computer and Information Engineering, 2015
This paper studied steganography and designed a simplistic approach to a steganographic tool for ... more This paper studied steganography and designed a simplistic approach to a steganographic tool for hiding information in image files with the view of addressing the security challenges with data by hiding data from unauthorized users to improve its security. The Structured Systems Analysis and Design Method (SSADM) was used in this work. The system was developed using Java Development Kit (JDK) 1.7.0_10 and MySQL Server as its backend. The system was tested with some hypothetical health records which proved the possibility of protecting data from unauthorized users by making it secret so that its existence cannot be easily recognized by fraudulent users. It further strengthens the confidentiality of patient records kept by medica l practitioners in the health setting. In conclusion, this work was able to produce a user friendly steganography software that is very fast to install and easy to operate to ensure privacy and secrecy of sensitive data. It also produced an exact copy of the original image and the one carrying the secret message when compared with each other.
A common problem associated with hospitals especially the nontertiary hospitals (primary and seco... more A common problem associated with hospitals especially the nontertiary hospitals (primary and secondary hospitals) is long queue. Attempts have been made to address this using the ticket approach, however, this does not minimize crowd in and around hospitals. In the wake of the consciousness of the need to avoid crowd with the emergence of the Corona Virus (COVID-19), it has become important to note that some diseases are transmissible when people clinch close within a vicinity especially in the hospital environment. It is therefore imperative to devise a means to reduce the usual crowd witnessed at the different units/sections in the hospital, precisely by outpatients. In this study, a centralized queue control system was developed that can be used in the different sections of hospitals. The system applied Poisson Distribution, Haversine Model, Little’s Law and Kendall Notation. It is a web-based system, designed to run on the Internet as it focused on the outpatients and the fact t...
Road traffic accidents are a very rampant issue causing injury, loss of lives and property worldw... more Road traffic accidents are a very rampant issue causing injury, loss of lives and property worldwide. In this research, a system for determining the severity of motorcycle accidents in Lokoja Metropolis of Central Nigeria was developed. The research considered different areas that are highly prone to accidents in Lokoja. Although accidents cannot be totally avoided, through scientific analysis, their frequency and severity can be reduced. The methodology used in this research is Knowledge Discovery in Databases with the Decision Tree Algorithm as the soft computing technique used for analysis. Python programming language was used for the implementation. The dataset used was gotten from the Federal Road Safety Corps (FRSC) in Lokoja. After the training and testing of the dataset, we achieved an accuracy of 90.5%. The motorcycle accident severity prediction system developed could serve as a tool that can be used to cub the enormous challenges faced by FRSC in curtailing motorcycle acc...
TOWARDS FOOD SECURITY: THE PREDICTION OF CLIMATIC FACTORS IN NIGERIA USING RANDOM FOREST APPROACH, Oct 31, 2021
With the explosive growth in the world‘s population which has little or no corresponding rise in ... more With the explosive growth in the world‘s population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented ...
The application of data mining has been utilized in different fields ranging from agriculture, fi... more The application of data mining has been utilized in different fields ranging from agriculture, finance, education, security, medicine, research etc. Data mining derives useful information from careful examination of data. In Nigeria, Agriculture plays a critical role in the economy as it provides high level of employment for many people. It is typical of farmers in Nigeria to plant crops without paying considerate attention to the soil and crop requirements as most farmers inherit the lands used for farming from their fathers and just continue in the pattern of farming they had always known. This is not favorable in the level of productivity they can actually attain as the effect can be seen in same level of crop yield year after year if not even worse. Modern farming techniques make use of data mining from previous data considering soil types, and other factors like weather and climatic conditions. This study built a model that enables possible prediction of crop yield from the his...
A Mathematical Approach to Healthcare Insurance Data Analytics, 2020
The emergence of big data analytics as a way of deriving insights from data brought excitement to... more The emergence of big data analytics as a way of deriving insights from data brought excitement to mathematicians, statisticians, computer scientists and other professionals. However, the absence of a mathematical foundation for analytics has become a real challenge amidst the flock of big data marketing activities, especially in healthcare insurance. This paper developed a mathematical model for the analytics of healthcare insurance data using set theory. We implemented a prototype of the model using Java Programming Language, MapReduce Framework, Association Rule Mining and MongoDB. Also, we tested the model accuracy using data from the National Health Insurance Scheme in Nigeria to reduce delay. The result showed that the accuracy level was 97.14% on average, which depicts a higher performance for the model. This result implies that delays affecting the processing of data submitted by the providers and enrollees to the HMOs reduced drastically leading to the improvement in the eas...
Point-of-care data capture is an important part of a clinical information system. Unfortunately, ... more Point-of-care data capture is an important part of a clinical information system. Unfortunately, health care providers find it time consuming and repetitive to perform data entry via computers. In this paper, we designed a user-friendly interface for the entry of patient information which gives the health care provider an easy to use interface for patient data entry. This system uses portable terminals and supports the entire loop of daily nursing work. This system was developed with the aim to make nursing work more efficient, by reducing the time needed for indirect work (patent information documentation, conferring with other healthcare providers, etc.), while increasing the time expended in direct patient care. The proposed system has three main functional parts: 1) Data Browsing which provides patient information such as a brief history, assessments and vital-sign charts; 2) Schedule Planning helps nurses organize doctors' instructions and make To-do lists for the day; and ...
With the explosive growth in the world's population which has little or no corresponding rise in ... more With the explosive growth in the world's population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented random forest algorithm using Python programming language to predict the aforementioned climate parameters. The data used was gotten from the Nigerian Meteorological (NiMet) Agency, Lokoja, Kogi State between 1988 and 2018. The result shows that random forest algorithm is effective in climate prediction as the accuracy from the model based on the climatic factors considered was 94.64%. With this, farmers would be able to plan ahead to prevent the impact of the fluctuations in these climatic factors; thus, the yield of crops would be increased. This would dwarf the negative impact of food insecurity to the populace.
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.
AN IMPLEMENTATION OF A REPOSITORY FOR HEALTHCARE INSURANCE USING MONGODB, 2020
The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Niger... more The explosive growth of unstructured data in the National Health Insurance Scheme (NHIS) in Nigeria has given rise to the lack of an appropriate data storage mechanism to house data in the Scheme. This paper x-rayed these data storage challenges with a view to implementing a storage mechanism that can handled large volume and different formats of data in the Scheme. The NHIS is currently using the paper-based, file and cabinet data storage system with some of the data stored in the form of PDF, Excel and image files on the computer system. This has led to serious challenges ranging from the loss of data, lack of appropriate data storage facilities to accommodate the data to the delay in the administration of quality care to beneficiaries of the Scheme. Also, the diversity of data with the ever-growing datasets which is also generated at very high rate has also constituted a major challenge for NHIS. This research therefore developed a computer-based data storage system using MongoDB which has full index support, replication, high availability and auto-sharding. The design was done with Enterprise Application Diagrams and implemented using Java Programming Language, MapReduce Framework and MongoDB. The study shows that there are inequities in the delivery of services within the NHIS in Nigeria due to lack of proper storage medium. This is responsible for the ineffectiveness and inefficiency of healthcare services received through the Scheme. In conclusion, this research has provided the stakeholders with access to information more easily, which will enable them to plan, evaluate, and collaborate more effectively.
Queue Management in Non-Tertiary Hospitals for Improved Healthcare Service Delivery to Outpatients, 2020
A common problem associated with hospitals especially the non-tertiary hospitals (primary and sec... more A common problem associated with hospitals especially the non-tertiary hospitals (primary and secondary hospitals) is long queue. Attempts have been made to address this using the ticket approach, however, this does not minimize crowd in and around hospitals. In the wake of the consciousness of the need to avoid crowd with the emergence of the Corona Virus (COVID-19), it has become important to note that some diseases are transmissible when people clinch close within a vicinity especially in the hospital environment. It is therefore imperative to devise a means to reduce the usual crowd witnessed at the different units/sections in the hospital, precisely by outpatients. In this study, a centralized queue control system was developed that can be used in the different sections of hospitals. The system applied Poisson Distribution, Haversine Model, Little's Law and Kendall Notation. It is a web-based system, designed to run on the Internet as it focused on the outpatients and the fact that different sections of most non-tertiary hospitals could also be situated in different buildings or geographical area. The system was implemented using ASP.NET and Microsoft SQL. It was evaluated using data collected from non-tertiary hospitals in Benue State, Nigeria. The result showed reduced number of patients in the hospital per time and a little variation between the arrival and expected time of some patients. The system saves time for the patients, the hospital is more organized and crowds are avoided. Also, the pressure on the facilities of the hospitals at a time is also reduced significantly. Service delivery is improved and a healthier environment is assured for both patients and health workers.
This paper developed a distributed algorithm for Big Data Analytics to address the delay in the p... more This paper developed a distributed algorithm for Big Data Analytics to address the delay in the processing of big data. In order to achieve the aim of this research, an inspection of organizational documents, direct observation and collection of existing data from the National Health Insurance Scheme (NHIS) in Nigeria. The algorithm was formulated using Apriori Association Rule Mining and was specified using the enterprise application diagram. The implementation of the prototype for the algorithm was using MongoDB as the big data storage mechanism for the input. Comma Separated Values (CSV) files was used as the storage facility for the intermediate results generated during processing, and MySQL was used as the storage mechanism for the final output. Finally, Apache MapReduce as the big data multi-nodal processing platform and Java programming language as the implementation technology. This prototype was able to analyze different formats of data (i.e., pdf, excel, csv and images) with high volume and velocity. The result showed that the response time was 0.25 seconds, and the throughput was 8865.29 records per second. The stability of the prototype was also evaluated using the confidence of the rules generated. In conclusion, this research has shown that unnecessary delays in the processing of big data were due to the lack of appropriate data analytics tool to enhance the process. This study eliminated these irregularities which paved the way for quicker disbursement of funds to providers and other stakeholders, as well as, a quicker response to requests on enrollment, update and referral.
The application of data mining has been utilized in different fields ranging from agriculture, fi... more The application of data mining has been utilized in different fields ranging from agriculture, finance, education, security, medicine, research etc. Data mining derives useful information from careful examination of data. In Nigeria, Agriculture plays a critical role in the economy as it provides high level of employment for many people. It is typical of farmers in Nigeria to plant crops without paying considerate attention to the soil and crop requirements as most farmers inherit the lands used for farming from their fathers and just continue in the pattern of farming they had always known. This is not favorable in the level of productivity they can actually attain as the effect can be seen in same level of crop yield year after year if not even worse. Modern farming techniques make use of data mining from previous data considering soil types, and other factors like weather and climatic conditions. This study built a model that enables possible prediction of crop yield from the historic data collected and offers suggestions to farmers on the right soil nutrients requirements that would enhance crop yield. This will enable early prediction of crop yield and prior idea to improve on the soil to increase productivity. The research used XGBoost algorithm for the crop yield prediction and the Support Vector Machine algorithm for the recommendation of appropriate improvement of soil nutrient requirements. The accuracy obtained for the prediction with XGBoost was 95.28%, while that obtained for the recommendation of fertilizer using SVM was 97.86%.
This study aimed at developing a system using support vector machine (SVM) that will forecast sal... more This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period
A Mathematical Approach to Healthcare Insurance Data Analytics, 2020
The emergence of big data analytics as a way of deriving insights from data brought excitement to... more The emergence of big data analytics as a way of deriving insights from data brought excitement to mathematicians, statisticians, computer scientists and other professionals. However, the absence of a mathematical foundation for analytics has become a real challenge amidst the flock of big data marketing activities, especially in healthcare insurance. This paper developed a mathematical model for the analytics of healthcare insurance data using set theory. We implemented a prototype of the model using Java Programming Language, MapReduce Framework, Association Rule Mining and MongoDB. Also, we tested the model accuracy using data from the National Health Insurance Scheme in Nigeria to reduce delay. The result showed that the accuracy level was 97.14% on average, which depicts a higher performance for the model. This result implies that delays affecting the processing of data submitted by the providers and enrollees to the HMOs reduced drastically leading to the improvement in the easy flow of resources.
TOWARDS FOOD SECURITY: THE PREDICTION OF CLIMATIC FACTORS IN NIGERIA USING RANDOM FOREST APPROACH, Oct 31, 2021
With the explosive growth in the world‘s population which has little or no corresponding rise in ... more With the explosive growth in the world‘s population which has little or no corresponding rise in the food production, food insecurity has become eminent, and hence, the need to seek for opportunities to increase food production in order to cater for this population is paramount. The second goal of the Sustainable Development Goals (SDGs) (i.e., ending hunger, achieving food security and improved nutrition, and promoting sustainable agriculture) set by the United Nations (UN) for the year 2030 clearly acknowledged this fact. Improving food production cannot be achieved using the obsolete conventional methods of agriculture by our farmers; hence, this study focuses on developing a model for predicting climatic conditions with a view to reducing their negative impact, and boosting the yield of crop. Temperature, wind, humidity and rainfall were considered as the effect of these factors is more devastating in Nigeria as compared to sun light which is always in abundance. We implemented random forest algorithm using Python programming language to predict the aforementioned climate parameters. The data used was gotten from the Nigerian Meteorological (NiMet) Agency, Lokoja, Kogi State between 1988 and 2018. The result shows that random forest algorithm is effective in climate prediction as the accuracy from the model based on the climatic factors considered was 94.64%. With this, farmers would be able to plan ahead to prevent the impact of the fluctuations in these climatic factors; thus, the yield of crops would be increased. This would dwarf the negative impact of food insecurity to the populace.
Uploads
implemented random forest algorithm using Python programming language to predict the aforementioned climate parameters. The data used was gotten from the Nigerian Meteorological (NiMet) Agency, Lokoja, Kogi State between 1988 and 2018. The result shows that random forest algorithm is effective in climate prediction as the accuracy from the model based on the climatic factors considered was 94.64%. With this, farmers would be able to plan ahead to prevent the impact of the fluctuations in these climatic factors; thus, the yield of crops would be increased. This would dwarf the negative impact of food insecurity to the populace.