University of Ibadan Journals
Not a member yet
794 research outputs found
Sort by
A Proposed Framework for Optimum Feature Selection using Improved Chicken Swarm Optimization Algorithm for Face Recognition system
Get PDFFeature selection is a significant assignment in data mining and pattern detection as it lessens the largeness of the data sets and at the same time preserves the classification exploit. Standard Chicken Swarm Optimization (CSO) has been universally employed for feature selection considering its efficacy. The standard CSO algorithm, however, experiences the challenges of falling at local optima and high computational cost due mainly to the large search space. The study proposed a framework to increase the accuracy of a face recognition system. The Improved Chicken Swarm Optimization technique will be formulated from standard CSO and chaotic map by introducing chaotic gauss map and chaotic tent map equations into the rooster and hens update equations of CSO respectively and will be employed for feature selection. Local binary pattern (LBP) will be used for feature extraction. Finally, the classification of individual images based on input images will be recognized using a Support Vector Machine (SVM) classifier. The evaluation will be done by comparing the combination of the ICSO-LBP technique with the combination of CSO-LBP technique based on recognition accuracy and will serve as our performance metrics. Based on the proposed evaluation, this study believed that the ICSO-LBP technique would have a high recognition accuracy than the CSO-LBP and would also avoid being trapped at the local optimum and improve the convergence speed of the algorithm
A Review of Telecommunication Network Survivability Models
Get PDFTelecom networks are employed in numerous critical aspects of our society, such as business, financial services, and life-saving services. Natural disasters, misconfigurations, software upgrades, latent failures, and deliberate attacks can all cause several correlated failures in communication systems' physical infrastructures. These events may result in the long-term deterioration of telecommunications services. For this reason, research has to be carried out to know various methods used in designing survivability models used in resolving failures. A lot of research has been done on the review of telecom network failures, however, not sufficient work has been accomplished on the review of telecommunication network survivability. This paper presents a review and learning structure for telecommunication network survivability models to reveal hidden topics, which are less investigated. The survey comprises 119 accredited journal articles that have been published between 2001 and 2019 in 36 selected journals, which are suitable sources for telecommunication network failure survivability topics. The results reveal that there is a progressive volume of telecommunication network survivability models that have been carried out for various ranges of learning categories. The results reveal hidden telecommunication network survivability topics, which have received lesser attention. The findings can hopefully be used as a learning reference guide to understanding telecommunication network survivability models, as well as a source for researchers interested in telecommunication network survivability research to stimulate their further interests
A Model for Identifying Deceptive Acts from Non-Verbal Cues In Visual Video Using Bidirectional Long Short Term Memory (BiLSTM) With Convolutional Neural Network (CNN) Features
Get PDFAbstractAutomatic identification of deception is crucial in so many areas like security, police investigations, court trials, political debates, relationships, and workplace and so on. Techniques for deception detection range from detecting deception through verbal, nonverbal and vocal clues. Existing works have been thoroughly dependent on combining different modalities of videos like audio and text for identifying deceptive behaviours These approaches have improved the overall accuracy of deception detection systems but there are exceptions where videos do not have accompanying audio and text. The aim of this research is to develop a model that can identify deceptive behaviours through non-verbal cues gotten from the visual modality of videos. The Real Life Deception Dataset created by Perez et al. (2015) was used for the purpose of this research. It contained labelled videos of deceptive and truthful court cases. Image frames were extracted from each video and pre-processed. A Convolutional Neural Network (CNN) was used to learn the different behavioural gestures and cues exhibited in these image frames before passing these learned features to the Bidirectional Long Short Term Memory (BiLSTM) algorithm which then classifies as either deceptive or truthful. Training and testing was also done using BiLSTM and evaluated with existing works. The model performed well in identifying deception from visual videos using CNN features learned from image frames. It gave an accuracy of 61% with a loss of 0.2 after running for three epochs. Sourcing local data from surveillance cameras and security feeds can be further explored tovalidate this wor
Knowledge Management in Software Testing
Get PDFAbstractSoftware testing aids in the assessment and improvement of software quality. Software testers employ a variety of techniques to uncover more defects with the least amount of labour even though the testing necessitates a lot of knowledge. Since adherence to Knowledge Management concepts can assist software testing professionals in their advancement of knowledge reuse, sharing, and testing process, this study is therefore aimed at identifying the Knowledge Management practices in software development organizationsas well as to ascertain whether Knowledge Management has benefitted the organizations. To realise this goal, a survey was conducted among fifteen software developers from fifteen software development organizations. Descriptive and inferential statistics were employed using simple descriptive statistics and crosstabs. This study found out that the software developers are familiar with the Knowledge Management concepts and six Knowledge Management. These are knowledge acquisition, creation, sharing, storage, organization and application. The study also shows that Knowledge Management has made organizations developing software improve in their software testing processes by saving time and avoiding the need to reinvent the wheel as well as increased their level of productivity
A Framework for Facial Expression Recognition Based Feedback Tracking in Online Educational Platforms
Get PDFDuring times of worldwide pandemic, online teaching platforms are becoming increasingly popular as an alternative to traditional learning environment. However, while many online platforms have been reported in the literature, many of them lack a reliable feedback tracking mechanism through which the emotional state of students or users can be determined for effective teaching and learning. This has necessitated the need to design and simulate an online feedback system. Sample facial images were obtained from FER-2013 Dataset, and preprocessed. Principal Component Analysis (PCA) was used in extracting the facial features in the sample images. A total of 31,885 images with six different emotional classifications which are happy, sad, fear, neutral, angry, disgust were considered. The images were then split into training and test images with train consisting of 75% of the whole dataset while test had 25%. Ensemble of Support Vector Machine, Random Forest and k-nearest neighbour were used in classifying the images. The results of classification serve as inputs to the feedback tracking mechanism of the proposed model, which was formulated as an algorithm. The performance of the proposed ensemble model was compared with its based classifiers using metrics such as Precision, Recall, F1- score, and Accuracy. The simulation results during training showed that ensemble (SVM +RF+KNN) had accuracy 98.92%, RF had accuracy 92.94%, SVM had accuracy 95.57%., and KNN had accuracy 85.42%. Likewise in test dataset, Ensemble (SVM +RF+KNN) had accuracy 93.92%, RF had accuracy 90.94%, SVM had accuracy 91.57%, and KNN had accuracy 83.42%. Other performance metrics such as Precision, F1-Score, and Recall were also measured during simulation. The study designed a system for obtaining feedback based on facial expression of online participants for an improved online educational platform usage and acceptance. The developed online feedback framework could be integrated into the existing online educational platforms for improved usage and acceptance
SOLVIZ: A Document Visualization System Based On Topic Modelling
Get PDFAbstractThe digital age has led to a voracious appetite for data as the world is gradually becoming a global village. Technology giants, businesses, schools and organization harness data in order to run their daily activities and beat competitors. Data has now become the crude oil of this global village. However, data could be structured, semistructured or unstructured. Understanding contents and features in the stack of data and getting hidden information stack could be very tedious and time consuming. Fortunately, a lot of information visualization techniques have been implemented to bring out meaning from the various forms of data. Meaningful information can be derivedfrom data with the applications of these techniques. However, the application of some of these techniques pose some level of difficulties for the users. The presentation provided by some of these visualization techniques has rendered little help while leaving the user confused on getting around the information needed. This paper presents an information visualization abstraction for document visualization using the solar system. The abstraction led to the development of a document visualization tool tagged Solviz that provides an effective and powerful discovery of information in documents using topic modelling for extracting thematic elements from documents. It enablesa user to explore hidden information in documents using a three dimensional space. Users can drill down into the document from topics to keywords to paragraphs in the document. The implementation also provides a data format which would allow anyone make use of this system efficiently
POST COVID – 19 PANDEMIC AND ITS EFFECT ON EFFECTIVE SPACE RE – ALLOCATION IN PLANNING
Get PDFBefore the outbreak of the COVID -19 Pandemic, space allocation for different land uses in planning have been in line with stipulated standard, which allowed easy accessibility within and among the public spaces in our cities. However, the recent outbreak of the COVID – 19 Pandemic has placed restrictions on the use of public spaces and also introduced the issue of physical distancing. These recent restrictions have become major policy measures to reduce and curtail the spread and likely transmission of the COVID – 19 virus and more importantly, to protect the health of the general public. The public spaces are now experiencing low patronage as a result of the “stay at home” and “lockdown restrictions’’. This paper assessed the post COVID-19 Pandemic and its effect on effective space reallocation in planning. The COVID-19 Pandemic will fundamentally and perhaps permanently change the stipulated standards used in the allocation of space for various land uses which will eventually alter the city designs in our various countries. There is therefore the need to assess these changes in order to inform the planners, the architects and landscape designers on recent urban planning design and space allocation in a post COVID-19 world
KNOWLEDGE, ATTITUDE AND PRACTICE OF GOOD ORAL HYGIENE AMONG SECONDARY SCHOOL STUDENTS OF YABA LOCAL COUNCIL DEVELOPMENT AREA OF LAGOS STATE
Get PDFSecondary school students in Nigeria face challenges regarding their oral health because of the daily high consumption of sugary foods and drinks, which predisposes them to dental caries and periodontal disease. This study investigates the Knowledge, Attitude and Practice of Good Oral Hygiene among Secondary School Students of Yaba local council development area of Lagos State. Descriptive survey research design was employed by this study. The population of this research comprised of 3,216 secondary school students in Yaba local council area, a self-developed questionnaire was used to elicit information, frequency count and sample percentages were used for data analysis and presentation. A multistage sampling technique was used in this study. The findings revealed that 65.5% of the school students have good knowledge of oral hygiene. It was revealed that 64.0% of school students in the study area have positive attitude towards dental health, in addition, the practice of good oral hygiene is well above average as 70.5% among respondents. It was also revealed that level of education does not significantly determine the practice of good oral hygiene among secondary school students. It was recommended that enlightenment programme and public awareness on good oral hygiene by the government and non-governmental organizations should be done regularly. Regular radio and online programme on good oral hygiene should be made available to Adolescent
ATTITUDE OF TEACHERS TOWARDS INCLUSIVE EDUCATION: IMPLICATION FOR EDUCATION FOR ALL
Get PDFThe study was carried out to determine the attitude of teachers towards inclusive education and its implication to education for all. Descriptive survey design was adopted. The population of the study was 1,183 teachers while the sample was 472 respondents. Proportionate random sampling technique was used to select 94 respondents from 31 public junior secondary schools and 378 respondents’ from124 public primary schools. In order to ensure fairness, 50% was further employed on proportionate basis to ensure equal gender representation. The questionnaire tagged ‘Attitude of Teachers towards Inclusive Education Assessment Scale (TIEAS) was used for date collection. The instrument was validated by experts while the reliability was determined by the administration of the instrument to a smaller group of respondents numbering twenty (20) in a trial test conducted in Ikwo Local Government Area of Ebonyi State. The reliability index was computed using Cronbach Alpha approach which yielded a reliability coefficient of 0.76. The services of three (3) research assistants were employed for the administration and collection of the instruments, whereas, simple percentage counts were used to answer four (4) research questions that guided the study. Four (4) null hypotheses were formulated and analyzed with t-test at 0. 05 probability level. The result indicates that 74% of teachers are negatively disposed to inclusive education. Also, the result of null hypothesis 1 was rejected; indicating that the attitude of teachers towards special education need students is significant whereas, hypothesis 2 affirms that age and experience of teachers are of great factors. It further revealed that female teachers are more friendly and accommodating to disabled students more than their male counterparts. It is therefore recommended that teachers should be made to undergo specialized and professional training regularly to cope with inclusive education situations in integrated and mainstream school environment amongst other things
Analytical Perspective: Failures in Telecommunication Networks in Africa and Deployment of Ant Colony System (ACS) Survivability Technology
Get PDFAbstractA failure in a telecommunications network, such as the loss of a link or a node, can occur for a variety of reasons. Accidental cable cuts, hardware malfunctions, software errors, natural disasters (e.g., fire), and operator mistakes are common causes of failures in Africa (e.g., incorrect maintenance). Because many of the causes of failure are outside the control of developing-country telecom operators, there is growing interest in the design of survivable networks. With the telecommunications network gaining traction, it is critical that telecommunications networkrelated issues such as node-to-node failures be resolved as soon as possible in order tAbstracto maximize network resource utilization while minimizing failure rate. Many researches have been done on single failure points in telecommunications network, but very little on multiple network failures. This study suggests an Ant Colony System (ACS) survivability model based on capacity effectiveness and quick restoration to quickly resolve multiple node failure problems to improve service quality. The swarm model's resilience was tested using a nodeto-node failure at the network's edges. Along with its working path, each communication flow seeks a survival path in order to protect multiple intermediate node-to-node failures. The survival solution path from this scenario demonstrates that the proposed swarm technology is feasible for current business applications in Africa thatrequire high speed/broadband network