FACULTY OF SCIENCE
Permanent URI for this communityhttps://repository.ui.edu.ng/handle/123456789/266
Browse
698 results
Search Results
Item A model for conflicts’ prediction using deep neural network(2021-10) Olaide, O. B.; Ojo, A. K.Conflict is part of human social interaction, which may occur from a mere misunderstanding among groups of settlers. In recent times, advanced Machine Learning (ML) techniques have been applied to conflict prediction. Strategic frameworks for improving ML settings in conflict research are emerging and are being tested with new algorithm-based approaches. These developments have given rise to the need to develop a Deep Neural Network model that predicts conflicts. Hence, in this study, two Artificial Neural Network models were developed, the dataset which was extracted from https://www.data.worlduploaded by the Armed Conflict Location and Event Data Project (ACLED), in four separate CSV files (January 2015 to December 2018). The dataset for the year 2015 has 2697 instances and 28 features, for 2016 was 2233 with the same feature, for 2017 has 2669 instances with the same features, and 2018 has 1651 instances. After the development of the models: the baseline Artificial Neural Network achieved an accuracy of 95% and a loss of 5% on the training data and an accuracy of 90% and 10% loss on the test set. The Deep Neural Network Model achieved 98% accuracy and 2% loss on the training set, with 89% accuracy and 11% loss on the test set. It was concluded that to further improve the prediction of conflict, there is a need to address the issue of the dataset, in developing a better and more robust model.Item Predictive analysis in solar kiln drying of wood using recurrent neural networks(Foundation of Computer Science FCS, New York, USA, 2021-06) Ojo, A. K.; Amoo-Onidundu, C. E.Prediction in data mining, is a technique used in predicting results or outcomes of future occurrence in reference to existing information. Several predictive models have been developed for different fields of study. In solar kiln drying experiment, as a result of dependence on nature for its operation, outcomes of drying process is unstable and varies with weather variability. Although predictive models have been developed for wood drying experiments, there is very limited information on the use of Neural Networks for predicting outcomes in solar kiln drying of wood. In this work, Long Short-term Memory model, a special type of Recurrent Neural Network was adopted for prediction in solar kiln drying of wood. Data collected on external (atmospheric) and internal conditions of a solar kiln sited at from Forestry Research Institute of Nigeria was used for this study. Daily ambient and internal temperature and relative humidity were used as input data. The closeness of relationship between the experimental and predicted values (Mean Square Error, MSE = 0.97; 30.4) and (Squared Correlation, R2=0.68, 0.85) for Temperature and Relative Humidity respectively revealed that the model had a good agreement with data. The Equilibrium Moisture Content (EMC) of internal solar kiln environment which influences the outcome of drying was considered. The EMC of internal solar kiln environment was predicted for the next 730 days and suitability of the model for prediction was examined giving an MSE value of 0.2 and r2 value of 0.87. The findings of this study suggest a viable model for predicting drying outcomes under varying weather conditions.Item Improved model for facial expression classification for fear and sadness using local binary pattern histogram(2020) Ojo, A. K.; Idowu, T. O.In this study, a Local Binary Pattern Histogram model was proposed for Facial expression classification for fear and sadness. There have been a number of supervised machine models developed and used for facial recognition in past researches. The classifier requires human effort to perform feature extraction which has led to unknown changes in the expression of human face and incomplete feature extraction and low accuracy. This study proposed a model for improving the accuracies for fear and sadness and to extract features to distinguish between fear and sadness. Images of different people of varying ages were extracted from two datasets got from Japanese female facial expression (jaffe) dataset and Cohn cade got from Kaggle. In other to achieve an incremental development, classification was done using Linear Support Vector Machine (LSVM) and Random Forest Classifier (RFC). The accuracy rates for the LSVM models, LSVM1 and LSVM2 were 88% and 87% respectively while the RFC models, RFC1 and RFC2, were 81% and 82% respectively.Item Development of english to yoruba machine translator, using syntax-based model(2020-06) Ojo, A.; Obe, O.; Adebayo, A.; Oladunjoye, M.Machine translators are required to produce the best possible translation without human assistance. Every machine translator requires programs, automated dictionaries, and grammars to support translation. Studies have shown that the fluency of machine translators depends on the approach or model adopted for their respective developments. Machine translators do not simply involve substituting words in one language for another, but the application of complex linguistic knowledge to decode the contextual meaning of the source text in its entirety. Approaches to machine translators are divided into a single and hybrid approach. In the aim to improve on translation quality of existing English to Yoruba language translator systems, this paper adopts a syntax-based hybrid approach for translating sentences. The grammar for translation is designed and tested with Joshua (an open-source natural language toolkit). The procedure includes data collection, data preparation, data preprocessing, parsing, training of translation model, extract grammar rule, implement grammar, evaluate translations using bilingual evaluation understudy metrics. This paper discusses the translation quality of machine translators (precisely phrase-based and syntax-based) in both tabular and graphical representations. It was observed that a syntax-based translator seemly has higher translation quality than phrase-based.Item Long term evolution coexistence with wireless fidelity in unlicensed spectrum using modified blank subframe allocation technique(2020-05) Ojo, A. K.; Kolade, A. O.In recent times, there has been an exponential increase in the use of mobile wireless devices such as smartphones, tablets etc. This has in turn led to a matching increase in demand for mobile broadband data usage. Many technologies have been engaged in order to meet this enormous data need. Long Term Evolution (LTE) and Wireless Fidelity (Wi-Fi) are major technologies used in meeting this high data demand. However, LTE was designed to operate in the licensed spectrum as a schedule-based technology in which the Evolved Node B (eNodeB) allots time-slots to devices in its cell. The licensed spectrum is more expensive to maintain for service providers and with increase in mobile wireless devices that same licensed spectrum is more congested. Operation of LTE in Unlicensed spectrum has been proposed as a solution to this need. However, if LTE operates in the unlicensed spectrum in its native form, Wi-Fi and other legacy technologies operating in the unlicensed spectrum get deprived of channel access. In this paper, we proposed a modified Blank Subframe Allocation technique in combination with Listen before talk (LBT) Clear Channel Assessment (CCA) before allocating the spectrum to its users to give channel access opportunity to Wi-Fi devices. Simulation was conducted for both instances i.e. when LTE operates with only Blank Subframe Allocation (BSA) coexistence and when CCA is applied to the LTE node. Performances of both models were evaluated using performance matrices such as delay time and throughput. The results showed that the proposed model achieved a smaller delay time than the existing model.Item A mobile students’ industrial work experience scheme logbook application(Science and Education Publishing, 2020) Olojakpoke, D. M.; Ojo, A. K.Monitoring of students who are undergoing the Students’ Industrial Work Experience Scheme (SIWES) program by school-based supervisors is a difficult task because the current paper based logbook system currently employed is not adequate enough to determine how well students are undergoing the program. It is difficult for school-based supervisors to know whether students actually filled their logbooks daily, showing what they have done or whether they filled it all at the end of a long period of time which means that such entries are very likely to be fraudulent. Which is why school-supervisors try to visit students on the program to physically monitor such students, however due to distance and other logistical issues school-based supervisors are only able to visit such students once or at most twice or sometimes never. The application was developed following the incremental model. Node.Js was used for the backend, MongoDB was used as the database while React Native was used to create the front-end. This application helps school-based supervisors monitor students on the SIWES program more effectively and also makes grading and commenting on logbook entries a lot easier. It can therefore be deployed to tertiary institutions in Nigeria to assist them in the running of their respective SIWES programmes.Item Predicting customer churn in telecommunication industry using convolutional neural network model(2020-06) Amatare, S. A.; Ojo, A. K.In this study a Convolutional Neural Network (CNN) model was proposed for the prediction of customer churn in a telecommunication industry. Many supervised machine learning models have been built and used for predicting customer churn in past researches. However, in the building of these models, there is need for human intervention to carry out attribute selection which is very tedious, time-consuming, tailored to specific datasets and often result to attribute selection problems. This study proposed a convolutional neural network model for predicting customer churning behavior and to also get rid of human attribute selection and its problems. Two datasets were created from the fourteen thousand data instances that were gotten from one of the major cellular companies operating in Nigeria. Python programming language via the anaconda distribution was used for the development and implementation of our model. Jupyter notebook was our IDE choice. In other to achieve a like-for-like comparison, three other models were developed, which were two Multi-layer Perceptron (MLP) models and one other CNN model. The accuracy rates for the MLP models; MLP1 and MLP2, are 80% and 81% respectively while the CNN models, CNN1 and CNN2, are 81% and 89% respectively.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.