UZOARU GODSON - Academia.edu (original) (raw)
Papers by UZOARU GODSON
INTERNATIONAL JOURNAL OF EDUCATION, RESEARCH AND SCIENTIFIC DEVELOPMENT, 2024
A conversational agent, often known as a chatbot, is a sort of artificial intelligence (AI) softw... more A conversational agent, often known as a chatbot, is a sort of artificial intelligence (AI) software that can simulate a discussion (or chat) with a user in natural language via messaging programs, websites, mobile apps, or the phone. This work describes a conversational chat system that uses an attention mechanism to react to Dengue requests. The model utilizes the three scoring techniques of the Luong Attention Mechanism: They are dot, general, and concat attention mechanisms: The results demonstrate that the accuracy of the dot attention mechanism is maximum and is 87% when the test questions were taken directly from the database, as determined by an assessment of the results, compared to 38% when the attention mechanism is not used. Furthermore, when the questions are asked with natural changes, human confirmation reliability is 63% as opposed to 16% when the attention mechanism is not applied. According to the study, chatbots may be employed anywhere due to their accuracy and 24-hour availability.
Many lives are lost today around the whole world as a result of improper diagnosis of diseases an... more Many lives are lost today around the whole world as a result of improper diagnosis of diseases and more so confusable diseases that have commonly related symptoms. These diseases pose huge risks to human lives when it is not detected early or misdiagnosed for other diseases. Consequently, in the diagnosis of diseases using machine-learning algorithms, more of the algorithms are suitable for the diagnosis of diseases while some may not be appropriate. In this research paper, a more suitable machine-learning algorithm was proposed; which employs rules and inferences in the diagnosis and classification of diseases. The research paper employed rule induction algorithm for the diagnosis of commonly transmitted diseases of e-coli, staphylococcus, gonorrhea, syphilis and candidiasis based on 250 patient datasets collected from Federal Medical Center Owerri. The result obtained yielded a classification accuracy of 96% sensitivity of 96% and specificity of 71%.
In the universities, mostly in Nigerian, general study courses examination popularly known as GST... more In the universities, mostly in Nigerian, general study courses examination popularly known as GST are written using paper and pen. This approach takes longer time for the lecturers to assess the students and more so during the invigilation. This paper is geared towards creating a more friendly approach, security based, high response time to downloading of the questions and uploading to grading in the form of computer based test having graphic user interface to administer examinations to the students of higher learning institutions using lightweight directory active protocol which runs on apache web server. The application was developed with PHP and CSS with SQL database scheme at the back end to store data of the general study questions, the answers and then grades the students immediately after the examination. This approach in general study examination having computer based test proved effective in administering examinations to the students, more secured and ubiquitous as students can stay anywhere to write the examinations when permitted by the school authority and enables by the administrator. Consequently, this approach is different from other computer based test as it incorporates both objective questions and subjective questions.
Phishing websites or URLs differ from software flaws as they exploit human vulnerabilities rather... more Phishing websites or URLs differ from software flaws as they exploit human vulnerabilities rather than technical weaknesses. Various methods exist to undermine the security of an internet user, but the most prevalent approach is phishing. This sort of assault aims to acquire or exploit a user's personal data, including passwords, credit card details, identity, and account information. Phishers gather user information by pretending to be authentic websites that are visually indistinguishable. Users' confidential data can be potentially retrieved, exposing them to the possibility of financial detriment or identity fraud. Consequently, there is a pressing requirement to develop a system that efficiently identifies phishing websites. This research presents three discrete deep learning methodologies for identifying phishing websites, which involve the use of long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and ultimately an LSTM-CNNbased methodology. The experimental results confirm the precision of the proposed methods, specifically 99.2%, 97.6%, and 96.8% for CNN, LSTM-CNN, and LSTM, respectively. The CNNbased technology displayed a superior phishing detection mechanism.
In every town and city, the problems encountered by road users are seemingly how to manipulate th... more In every town and city, the problems encountered by road users are seemingly how to manipulate the traffic, especially in the rush hours of morning and evening. Many towns and cities have battled on how to solve traffic situations, hence the introduction of traffic lights, but traffic lights are not enough to control the huge traffic problems bordering that town or city because of poor feasibility study of the traffic situation in the allocation of time slot in vehicular movements. This research paper is designed to solve traffic-related problems by employing forward and backward chaining algorithms. A comparison is made between manual traffic control system, traffic light control system and forward and backward chaining traffic control system with distances of the cars from the traffic control center in adjoining roads mapped at 2, 4, 6, 8, 10, 12, 14, 16, 18 and 20 kilometers and the response time to traffic control on look ahead in vehicles on the queue and congestion clearance were measured. The backward chaining algorithm looks at the number of cars in all the directions and calculates the lane that has the largest traffic and gives them a pass to reduce the traffic in that lane and then quickly turns to the normal traffic light system using the forward chain algorithm and forward and backward chaining yielded enhanced results more than manual and traffic light controls. This is achievable by employing backward and forward algorithms embedded in CCTV system cameras. The implementation of the computer traffic simulation was done using C-Sharp Programming Language.
In contrast to software vulnerabilities, phishing websites or URLs are a type of internet securit... more In contrast to software vulnerabilities, phishing websites or URLs are a type of internet security problem that focuses on human vulnerabilities. There are many ways to compromise an internet user's security, but the most popular one is phishing, an attack that seeks to obtain or misuse a user's personal data, such as passwords, credit card information, identity, and account information. Phishers collect information about users by impersonating legitimate websites that are indistinguishable to the naked eye. Users' sensitive information may be accessed, putting them at risk of financial harm or identity theft. As a result, there is an urgent need to create a system that effectively detects phishing websites. This paper proposes three distinct deep learning-based techniques for detecting phishing websites, including long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and finally an LSTM-CNN-based approach. Experimental findings demonstrate the accuracy of the suggested techniques, i.e., 99.2%, 97.6%, and 96.8% for CNN, LSTM-CNN, and LSTM, respectively. The proposed phishing detection method demonstrated by the CNN-based system is superior.
This paper is aimed at determining the best system performance metrics that will quickly respond ... more This paper is aimed at determining the best system performance metrics that will quickly respond to changes in an agile computing environment. This paper designed an architectural model for determining the best performance metrics in an agile computing environment such as Integrated Data Services Limited. The research work was based on six (6) system performance metrics; execution time, QUIPS, SPECs, Clock rate, MFLOPS and MIPS. MATLAB as a mathematical tool was used in the analysis of the various performance metrics to determine the best metrics. The experiments performed showed that execution time is the best performance metrics having execution time of 0.95, 0.97 and 1.01 followed by QUIPS and SPEC that has values of 6, 3 and 1.2 seconds in completing processes in the three experimental servers, while MFLOPS, MIPS and Clock Rates were found to be of poor performance metrics in any agile computing environment.
Uzoaru Godson C
In the universities, mostly in Nigerian, general study courses examination popularly known as GST... more In the universities, mostly in Nigerian, general study courses examination popularly known as GST are written using paper and pen. This approach takes longer time for the lecturers to assess the students and more so during the invigilation. This paper is geared towards creating a more friendly approach, security based, high response time to downloading of the questions and uploading to grading in the form of computer based test having graphic user interface to administer examinations to the students of higher learning institutions using lightweight directory active protocol which runs on apache web server. The application was developed with PHP and CSS with SQL database scheme at the back end to store data of the general study questions, the answers and then grades the students immediately after the examination. This approach in general study examination having computer based test proved effective in administering examinations to the students, more secured and ubiquitous as students can stay anywhere to write the examinations when permitted by the school authority and enables by the administrator. Consequently, this approach is different from other computer based test as it incorporates both objective questions and subjective questions.
Forms of Church Polity
Uzoaru Godson Chetachi, 2014
Uzoaru Godson Chetachi, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
Uzoaru Godson Chetachi, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
UZOARU GODSON CHETACHI, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
Uzoaru Godson Chetachi, 2014
Church government or sometimes called church polity is that branch of ecclesiology or study of th... more Church government or sometimes called church polity is that branch of ecclesiology or study of the church that addresses the organizational structure and hierarchy of the church.
Issues of church governance appear in the first chapters of the Acts of the Apostles; the first act recorded after the ascension is the election of Matthias as one of the Twelve Apostles, replacing Judas Iscariot .
INTERNATIONAL JOURNAL OF EDUCATION, RESEARCH AND SCIENTIFIC DEVELOPMENT, 2024
A conversational agent, often known as a chatbot, is a sort of artificial intelligence (AI) softw... more A conversational agent, often known as a chatbot, is a sort of artificial intelligence (AI) software that can simulate a discussion (or chat) with a user in natural language via messaging programs, websites, mobile apps, or the phone. This work describes a conversational chat system that uses an attention mechanism to react to Dengue requests. The model utilizes the three scoring techniques of the Luong Attention Mechanism: They are dot, general, and concat attention mechanisms: The results demonstrate that the accuracy of the dot attention mechanism is maximum and is 87% when the test questions were taken directly from the database, as determined by an assessment of the results, compared to 38% when the attention mechanism is not used. Furthermore, when the questions are asked with natural changes, human confirmation reliability is 63% as opposed to 16% when the attention mechanism is not applied. According to the study, chatbots may be employed anywhere due to their accuracy and 24-hour availability.
Many lives are lost today around the whole world as a result of improper diagnosis of diseases an... more Many lives are lost today around the whole world as a result of improper diagnosis of diseases and more so confusable diseases that have commonly related symptoms. These diseases pose huge risks to human lives when it is not detected early or misdiagnosed for other diseases. Consequently, in the diagnosis of diseases using machine-learning algorithms, more of the algorithms are suitable for the diagnosis of diseases while some may not be appropriate. In this research paper, a more suitable machine-learning algorithm was proposed; which employs rules and inferences in the diagnosis and classification of diseases. The research paper employed rule induction algorithm for the diagnosis of commonly transmitted diseases of e-coli, staphylococcus, gonorrhea, syphilis and candidiasis based on 250 patient datasets collected from Federal Medical Center Owerri. The result obtained yielded a classification accuracy of 96% sensitivity of 96% and specificity of 71%.
In the universities, mostly in Nigerian, general study courses examination popularly known as GST... more In the universities, mostly in Nigerian, general study courses examination popularly known as GST are written using paper and pen. This approach takes longer time for the lecturers to assess the students and more so during the invigilation. This paper is geared towards creating a more friendly approach, security based, high response time to downloading of the questions and uploading to grading in the form of computer based test having graphic user interface to administer examinations to the students of higher learning institutions using lightweight directory active protocol which runs on apache web server. The application was developed with PHP and CSS with SQL database scheme at the back end to store data of the general study questions, the answers and then grades the students immediately after the examination. This approach in general study examination having computer based test proved effective in administering examinations to the students, more secured and ubiquitous as students can stay anywhere to write the examinations when permitted by the school authority and enables by the administrator. Consequently, this approach is different from other computer based test as it incorporates both objective questions and subjective questions.
Phishing websites or URLs differ from software flaws as they exploit human vulnerabilities rather... more Phishing websites or URLs differ from software flaws as they exploit human vulnerabilities rather than technical weaknesses. Various methods exist to undermine the security of an internet user, but the most prevalent approach is phishing. This sort of assault aims to acquire or exploit a user's personal data, including passwords, credit card details, identity, and account information. Phishers gather user information by pretending to be authentic websites that are visually indistinguishable. Users' confidential data can be potentially retrieved, exposing them to the possibility of financial detriment or identity fraud. Consequently, there is a pressing requirement to develop a system that efficiently identifies phishing websites. This research presents three discrete deep learning methodologies for identifying phishing websites, which involve the use of long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and ultimately an LSTM-CNNbased methodology. The experimental results confirm the precision of the proposed methods, specifically 99.2%, 97.6%, and 96.8% for CNN, LSTM-CNN, and LSTM, respectively. The CNNbased technology displayed a superior phishing detection mechanism.
In every town and city, the problems encountered by road users are seemingly how to manipulate th... more In every town and city, the problems encountered by road users are seemingly how to manipulate the traffic, especially in the rush hours of morning and evening. Many towns and cities have battled on how to solve traffic situations, hence the introduction of traffic lights, but traffic lights are not enough to control the huge traffic problems bordering that town or city because of poor feasibility study of the traffic situation in the allocation of time slot in vehicular movements. This research paper is designed to solve traffic-related problems by employing forward and backward chaining algorithms. A comparison is made between manual traffic control system, traffic light control system and forward and backward chaining traffic control system with distances of the cars from the traffic control center in adjoining roads mapped at 2, 4, 6, 8, 10, 12, 14, 16, 18 and 20 kilometers and the response time to traffic control on look ahead in vehicles on the queue and congestion clearance were measured. The backward chaining algorithm looks at the number of cars in all the directions and calculates the lane that has the largest traffic and gives them a pass to reduce the traffic in that lane and then quickly turns to the normal traffic light system using the forward chain algorithm and forward and backward chaining yielded enhanced results more than manual and traffic light controls. This is achievable by employing backward and forward algorithms embedded in CCTV system cameras. The implementation of the computer traffic simulation was done using C-Sharp Programming Language.
In contrast to software vulnerabilities, phishing websites or URLs are a type of internet securit... more In contrast to software vulnerabilities, phishing websites or URLs are a type of internet security problem that focuses on human vulnerabilities. There are many ways to compromise an internet user's security, but the most popular one is phishing, an attack that seeks to obtain or misuse a user's personal data, such as passwords, credit card information, identity, and account information. Phishers collect information about users by impersonating legitimate websites that are indistinguishable to the naked eye. Users' sensitive information may be accessed, putting them at risk of financial harm or identity theft. As a result, there is an urgent need to create a system that effectively detects phishing websites. This paper proposes three distinct deep learning-based techniques for detecting phishing websites, including long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and finally an LSTM-CNN-based approach. Experimental findings demonstrate the accuracy of the suggested techniques, i.e., 99.2%, 97.6%, and 96.8% for CNN, LSTM-CNN, and LSTM, respectively. The proposed phishing detection method demonstrated by the CNN-based system is superior.
This paper is aimed at determining the best system performance metrics that will quickly respond ... more This paper is aimed at determining the best system performance metrics that will quickly respond to changes in an agile computing environment. This paper designed an architectural model for determining the best performance metrics in an agile computing environment such as Integrated Data Services Limited. The research work was based on six (6) system performance metrics; execution time, QUIPS, SPECs, Clock rate, MFLOPS and MIPS. MATLAB as a mathematical tool was used in the analysis of the various performance metrics to determine the best metrics. The experiments performed showed that execution time is the best performance metrics having execution time of 0.95, 0.97 and 1.01 followed by QUIPS and SPEC that has values of 6, 3 and 1.2 seconds in completing processes in the three experimental servers, while MFLOPS, MIPS and Clock Rates were found to be of poor performance metrics in any agile computing environment.
Uzoaru Godson C
In the universities, mostly in Nigerian, general study courses examination popularly known as GST... more In the universities, mostly in Nigerian, general study courses examination popularly known as GST are written using paper and pen. This approach takes longer time for the lecturers to assess the students and more so during the invigilation. This paper is geared towards creating a more friendly approach, security based, high response time to downloading of the questions and uploading to grading in the form of computer based test having graphic user interface to administer examinations to the students of higher learning institutions using lightweight directory active protocol which runs on apache web server. The application was developed with PHP and CSS with SQL database scheme at the back end to store data of the general study questions, the answers and then grades the students immediately after the examination. This approach in general study examination having computer based test proved effective in administering examinations to the students, more secured and ubiquitous as students can stay anywhere to write the examinations when permitted by the school authority and enables by the administrator. Consequently, this approach is different from other computer based test as it incorporates both objective questions and subjective questions.
Forms of Church Polity
Uzoaru Godson Chetachi, 2014
Uzoaru Godson Chetachi, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
Uzoaru Godson Chetachi, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
UZOARU GODSON CHETACHI, 2021
Queries can accomplish or discharge many different functions in a database. But their most common... more Queries can accomplish or discharge many different functions in a database. But their most common task is to retrieve specific data from the tables. The data you want to view is usually spread across several tables in the Database, making use of queries will allow you to view it in a single datasheet. Also, when you don't want to see all the records at once, queries let you add criteria to "filter" the data down to the records you want.
This Seminar Paper explains Advanced Query Languages and how intelligent query processing is done.
Keywords: Advanced Query, Intelligent Query, Processing, Languages
Uzoaru Godson Chetachi, 2014
Church government or sometimes called church polity is that branch of ecclesiology or study of th... more Church government or sometimes called church polity is that branch of ecclesiology or study of the church that addresses the organizational structure and hierarchy of the church.
Issues of church governance appear in the first chapters of the Acts of the Apostles; the first act recorded after the ascension is the election of Matthias as one of the Twelve Apostles, replacing Judas Iscariot .