FACULTY OF SCIENCE
Permanent URI for this communityhttps://repository.ui.edu.ng/handle/123456789/266
Browse
558 results
Search Results
Item Predictive analysis for journal abstracts using polynomial neural networks algorithm(2017-07) Ojo, A. K.Academic journals are an important outlet for dissemination of academic research. In this study, Neural Networks model was used in the prediction of abstracts from The Institute of Electrical and Electronics Engineers (IEEE) Transactions on Computers. Simulation of results was done using the Polynomial Neural Networks algorithm. This algorithm, which is based on Group Method of Data Handling (GMDH) method, utilizes a class of polynomials such as linear, quadratic and modified quadratic. The prediction was done for a period of twenty-four months using a predictive model of three layers and two coefficients. The performance measures used in this study were mean square errors, mean absolute error and root mean square error.Item Twitter data analysis of ministries, department and agencies in Nigeria(2019-10) Ojo, A. K.; Olanrewaju, A. B.The use of social media tools as a means of communication by various ministries, departments and agencies (MDAs) in Nigeria started very late compared with personal use or in the private or corporate sector. The social media tool of interest is Twitter which is a microblogging application and it is becoming a momentous element of the public sector social media agenda. The study revealed the interest of citizens in the activities of the various MDAs in the country, some MDAs are not known to be too active since their activities are not given the required coverage in the contemporary media or the sector seems not to be receiving adequate attention and patronage. This paper made an empirical and methodological contribution to this new body of knowledge by presenting an overview study of general Twitter accounts maintained by the various MDAs of the Nigerian government. Over 70,000 tweets were used from 64 officially available Twitter accounts. It was discovered that the gradual use of Twitter is really creating a more engaging opportunity for the citizens to have firsthand information about the activities of the government agencies. The study revealed that the trend progressed over the years, that is, there was an upward movement in the use of twitter as a means of government citizen engagement over a 10 years’ period. It was discovered that the use of twitter was very high during the office hours and more activities between Mondays and Fridays. The Nigerian Football Federation led the first five MDAs. Most of the devices used by MDAs to access are laptops or desktops, followed by smart phones. Android devices are more in use than iPhone devices. The remaining devices are not popular in the public services.Item Ako, A.(2019-09) Ojo, A. K.This study presents an approach to extracting data from amazon dataset and performing some preprocessing on it by combining the techniques of Bi-Directional Long Short-Term Memory and 1-Dimensional Convolution Neural Network to classify the opinions into targets. After parsing the dataset and identifying desired information, we did some data gathering and preprocessing tasks. The feature selection technique was developed to extract structural features which refer to the content of the review (Parts of Speech Tagging) along with extraction of behavioral features which refer to the meta-data of the review. Both behavioral and structural features of reviews and their targets were extracted. Based on extracted features, a vector was created for each entity which consists of those features. In evaluation phase, these feature vectors were used as inputs of classifier to identify whether they were fake or non-fake entities. It could be seen that the proposed solution has over 90% of the predictions when compared with other work which had 77%. This increase was as a result of the combination of the bidirectional long short-term memory and the convolutional neural network algorithms.Item Reduction in high rate of packet drop in reverse adhoc on-demand distance vector routing protocol under wormhole attack in mobile adhoc networks(2019-09) Ojo, A. K.; Akinnifesi, A. S.Over the years the advent of wireless communication has made Mobile Ad-hoc Networks (MANETs) become more accessible platforms for easier exchange of data especially where it is expensive or impossible to establish fixed network infrastructure. These networks can offer a life-saving communication in a disaster or an emergency situation under well-equipped routing protocol as the quality of service provided by MANET is dependent on its routing protocol. This dependency has led to the development of several Multi-path routing protocol which guard against drop of unicast Route Reply packet associated with Ad-hoc On-Demand Distance Vector (AODV) - a single-path routing protocol. However, the performance of Reverse-AODV (a Multi-path routing protocol) can be vulnerable to high rate of packet drop under the influence of wormhole attack as the shortest path is selected and maintained for a given expiration time or until path fails. In this paper, we proposed an improved Reverse-AODV routing protocol (iR-AODV) which adopts different path routing; as a way of reducing the impact of wormhole attack on packets during transmission. The study simulated Reverse-AODV routing protocol and the improved version (iR-AODV) under wormhole attack. Both protocols were evaluated by considering different performance metrics under the same parameters such as number of nodes and simulation time. The results showed that the proposed iR-AODV recorded a smaller number of packet drop and higher Packet Delivery Ratio under wormhole attack when compared with R-AODV routing protocol.Item Improved model for detecting fake profiles in online social network: a case study of twitter(2019) Ojo, A. K.Online Social Network (OSN) is like a virtual community where people build social networks and relations with one another. The open access to the Internet has increased the growth of OSN which has attracted intruders to exploit the weaknesses of the Internet and OSN to their own gain. The rise in the usage of OSN has posed security threats to OSN users as they share personal and sensitive information online which could be exploited by these intruders by creating profiles to carry out a series of malicious activities on the social network. In fact, it is no gain saying that the intent of creating fake accounts has adverse effect and the Internet has made it quite easy to concede one’s identity; and this makes it difficult to detect fake accounts as they try to imitate real accounts. In this study, a model that can accurately identify fake profiles in OSN which uses Natural Language Processing Technique to eliminate or reduce the size of the dataset thereby improving the overall performance of the model was proposed. Principal Component Analysis was used for appropriate feature selection. After extraction, six attributes/features that influenced the classifier were found. Support Vector Machine (SVM), Naïve Bayes and Improved Support Vector Machine (ISVM) were used as Classifiers. ISVM introduced a penalty parameter to the standard SVM objective function to reduce the inequality constraints between the slack variables. This gave a better result of 90% than the SVM and Naïve Bayes which gave 77.4% and 77.3% respectively.Item Knowledge discovery in medical database using machine learning techniques(2019-07) Ojo, A. K.; Olanrewaju, A.In this study, an attempt was made using machine learning techniques to discover knowledge that will assist policy makers in taking decisions that will ensure that the sustainable development goals on Health is met. Agglomerative Hierarchical clustering was used to cluster the states by personnel information (number of doctors, community health workers, nurses and midwives), this was visualized using a dendrogram. The Exploratory analysis revealed that it is only community health workers that are well distributed in all the states, the North West states have the least number of hospitals offering ante-natal services. Random Forest model was used to generate a feature importance to determine the important attributes that determined the availability of maternal health delivery services in a hospital, an important discovery was the fact that the availability of doctors does not in any way determine the availability of maternal health delivery services but rather community health workers, nurses and midwives are the major determinants. Random Forest algorithm was also used to classify hospitals offering maternal health delivery services and the result compared with Logistic Regression, Bagging and Boosting. The evaluation metrics used were accuracy, precision and recall. For accuracy and precision, Random Forest performed best while for recall it performed poorly compared to all the other algorithms.Item Offline accessible system for agricultural e-commerce using unstructured supplementary services data application(2018-11) Ojo, A. K.; Ogundare, M. A.E-commerce has a major impact in the agricultural sector. The way people go about purchasing agricultural products and the way the farmers sell them are important. Sometimes, buyers have to travel far distances to get agricultural products and getting the right quality is not guaranteed. Various market prices cannot be compared because buyers do not have all the time and resources to visit every agricultural farm. Hence, the need for an offline accessible means of trading electronically which would help farmers and other buyers, make their appropriate business transactions online. This study is concerned with the application of Unstructured Supplementary Services Data Application (USSD) and Short Messaging Service to connect farmers to an e-commerce platform. Entity relationship model use case diagram and Unified Modeling Language class diagram were used in the system design. The farmer accesses the offline service via a USSD short code (offline module) and they can then manage their crop inventory and other basic details. Their crop inventory is then synced to the online e-commerce platform for buyers to compare prices, view crop availability and order crops. The farmer can either accept or reject to do business with a buyer via SMS and the buyer will be notified in the All Orders section of the platform. The system helps to connect farmers that do not have smartphones and Internet access to an online marketplace thereby increasing their access to market.Item A predicting phishing websites using support vector machine and multi-class classification based on association rule techniques(2018-06) Woods, N. C.; Agada, V. E.; Ojo, A. K.Phishing is a semantic attack which targets the user rather than the computer. It is a new Internet crime in comparison with other forms such as virus and hacking. Considering the damage phishing websites has caused to various economies by collapsing organizations, stealing information and financial diversion, various researchers have embarked on different ways of detecting phishing websites but there has been no agreement about the best algorithm to be used for prediction. This study is interested in integrating the strengths of two algorithms, Support Vector Machines (SVM) and Multi-Class Classification Rules based on Association Rules (MCAR) to establish a strong and better means of predicting phishing websites. A total of 11,056 websites were used from both PhishTank and yahoo directory to verify the effectiveness of this approach. Feature extraction and rules generation were done by the MCAR technique; classification and prediction were done by SVM technique. The result showed that the technique achieved 98.30% classification accuracy with a computation time of 2205.33s with minimum error rate. It showed a total of 98% Area under the Curve (AUC) which showed the proportion of accuracy in classifying phishing websites. The model showed 82.84% variance in the prediction of phishing websites based on the coefficient of determination. The use of two techniques together in detecting phishing websites produced a more accurate result as it combined the strength of both techniques respectively. This research work centralized on this advantage by building a hybrid of two techniques to help produce a more accurate result.Item A predicting phishing websites using support vector machine and multi-class classification based on association rule techniques(2018-06) Woods, N. C.; Agada, V. E.; Ojo, A. K.Phishing is a semantic attack which targets the user rather than the computer. It is a new Internet crime in comparison with other forms such as virus and hacking. Considering the damage phishing websites has caused to various economies by collapsing organizations, stealing information and financial diversion, various researchers have embarked on different ways of detecting phishing websites but there has been no agreement about the best algorithm to be used for prediction. This study is interested in integrating the strengths of two algorithms, Support Vector Machines (SVM) and Multi-Class Classification Rules based on Association Rules (MCAR) to establish a strong and better means of predicting phishing websites. A total of 11,056 websites were used from both PhishTank and yahoo directory to verify the effectiveness of this approach. Feature extraction and rules generation were done by the MCAR technique; classification and prediction were done by SVM technique. The result showed that the technique achieved 98.30% classification accuracy with a computation time of 2205.33s with minimum error rate. It showed a total of 98% Area under the Curve (AUC) which showed the proportion of accuracy in classifying phishing websites. The model showed 82.84% variance in the prediction of phishing websites based on the coefficient of determination. The use of two techniques together in detecting phishing websites produced a more accurate result as it combined the strength of both techniques respectively. This research work centralized on this advantage by building a hybrid of two techniques to help produce a more accurate result.Item Self-disciplinary time-restricted smartphone addiction management system using (android) mobile technology(2018) Ojo, A. K.; Ohajinwa, R. S.The values of smartphone devices have increased tremendously over last few years, especially with the development of mobile applications which have been beneficial. According to Google, there are over a billion active users of mobile applications deployed on Android Playstore as at 2015. This means that there are over a billion users who actually spend time on their smartphones. However, despite the tremendous advantages of smartphones and the applications that can be installed on them, there are negative consequences that can come from spending countless number of hours on a smartphone and, applications that help in curbing these addictions are really scarce. There still exists a large inefficiency in the current systems that help to curb or manage smartphone addictions. In view of the above, this study sought to present a time-restricted smartphone addiction system that is effective, efficient and relevant. This study explored the use of mobile technology in the design and development of the system (the application), which enables a user to select the applications he or she wants to lock within a specified period of time and at the same time gives the user an overall view of how often he or she uses the applications installed on the device.